The following changes since commit 31ee895047bdcf7387e3570cbd2a473c6f744b08: Merge remote-tracking branch 'remotes/jasowang/tags/net-pull-request' into staging (2021-01-25 15:56:13 +0000) are available in the Git repository at: https://github.com/XanClic/qemu.git tags/pull-block-2021-01-26 for you to fetch changes up to bb24cdc5efee580e81f71c5ff0fd980f2cc179d0: iotests/178: Pass value to invalid option (2021-01-26 14:36:37 +0100) ---------------------------------------------------------------- Block patches: - Make backup block jobs use asynchronous requests with the block-copy module - Use COR filter node for stream block jobs - Make coroutine-sigaltstack’s qemu_coroutine_new() function thread-safe - Report error string when file locking fails with an unexpected errno - iotest fixes, additions, and some refactoring ---------------------------------------------------------------- Alberto Garcia (1): iotests: Add test for the regression fixed in c8bf9a9169 Andrey Shinkevich (10): copy-on-read: support preadv/pwritev_part functions block: add API function to insert a node copy-on-read: add filter drop function qapi: add filter-node-name to block-stream qapi: copy-on-read filter: add 'bottom' option iotests: add #310 to test bottom node in COR driver block: include supported_read_flags into BDS structure copy-on-read: skip non-guest reads if no copy needed stream: rework backing-file changing block: apply COR-filter to block-stream jobs David Edmondson (1): block: report errno when flock fcntl fails Max Reitz (14): iotests.py: Assume a couple of variables as given iotests/297: Rewrite in Python and extend reach iotests: Move try_remove to iotests.py iotests/129: Remove test images in tearDown() iotests/129: Do not check @busy iotests/129: Use throttle node iotests/129: Actually test a commit job iotests/129: Limit mirror job's buffer size iotests/129: Clean up pylint and mypy complaints iotests/300: Clean up pylint and mypy complaints coroutine-sigaltstack: Add SIGUSR2 mutex iotests/129: Limit backup's max-chunk/max-workers iotests/118: Drop 'change' test iotests/178: Pass value to invalid option Vladimir Sementsov-Ogievskiy (27): iotests: fix _check_o_direct qapi: block-stream: add "bottom" argument iotests: 30: prepare to COR filter insertion by stream job block/stream: add s->target_bs qapi: backup: add perf.use-copy-range parameter block/block-copy: More explicit call_state block/block-copy: implement block_copy_async block/block-copy: add max_chunk and max_workers parameters block/block-copy: add list of all call-states block/block-copy: add ratelimit to block-copy block/block-copy: add block_copy_cancel blockjob: add set_speed to BlockJobDriver job: call job_enter from job_pause qapi: backup: add max-chunk and max-workers to x-perf struct iotests: 56: prepare for backup over block-copy iotests: 185: prepare for backup over block-copy iotests: 219: prepare for backup over block-copy iotests: 257: prepare for backup over block-copy block/block-copy: make progress_bytes_callback optional block/backup: drop extra gotos from backup_run() backup: move to block-copy qapi: backup: disable copy_range by default block/block-copy: drop unused block_copy_set_progress_callback() block/block-copy: drop unused argument of block_copy() simplebench/bench_block_job: use correct shebang line with python3 simplebench: bench_block_job: add cmd_options argument simplebench: add bench-backup.py qapi/block-core.json | 66 +++++- block/backup-top.h | 1 + block/copy-on-read.h | 32 +++ include/block/block-copy.h | 61 ++++- include/block/block.h | 10 +- include/block/block_int.h | 15 +- include/block/blockjob_int.h | 2 + block.c | 25 ++ block/backup-top.c | 6 +- block/backup.c | 233 ++++++++++++------- block/block-copy.c | 227 +++++++++++++++--- block/copy-on-read.c | 184 ++++++++++++++- block/file-posix.c | 38 ++- block/io.c | 10 +- block/monitor/block-hmp-cmds.c | 7 +- block/replication.c | 2 + block/stream.c | 185 +++++++++------ blockdev.c | 83 +++++-- blockjob.c | 6 + job.c | 3 + util/coroutine-sigaltstack.c | 9 + scripts/simplebench/bench-backup.py | 167 ++++++++++++++ scripts/simplebench/bench-example.py | 2 +- scripts/simplebench/bench_block_job.py | 13 +- tests/qemu-iotests/030 | 12 +- tests/qemu-iotests/056 | 9 +- tests/qemu-iotests/109.out | 24 ++ tests/qemu-iotests/118 | 20 +- tests/qemu-iotests/118.out | 4 +- tests/qemu-iotests/124 | 8 +- tests/qemu-iotests/129 | 79 ++++--- tests/qemu-iotests/141.out | 2 +- tests/qemu-iotests/178 | 2 +- tests/qemu-iotests/178.out.qcow2 | 2 +- tests/qemu-iotests/178.out.raw | 2 +- tests/qemu-iotests/185 | 3 +- tests/qemu-iotests/185.out | 3 +- tests/qemu-iotests/219 | 13 +- tests/qemu-iotests/245 | 20 +- tests/qemu-iotests/257 | 1 + tests/qemu-iotests/257.out | 306 ++++++++++++------------- tests/qemu-iotests/297 | 112 +++++++-- tests/qemu-iotests/297.out | 5 +- tests/qemu-iotests/300 | 19 +- tests/qemu-iotests/310 | 117 ++++++++++ tests/qemu-iotests/310.out | 15 ++ tests/qemu-iotests/313 | 104 +++++++++ tests/qemu-iotests/313.out | 29 +++ tests/qemu-iotests/common.rc | 7 +- tests/qemu-iotests/group | 2 + tests/qemu-iotests/iotests.py | 37 +-- 51 files changed, 1797 insertions(+), 547 deletions(-) create mode 100644 block/copy-on-read.h create mode 100755 scripts/simplebench/bench-backup.py create mode 100755 tests/qemu-iotests/310 create mode 100644 tests/qemu-iotests/310.out create mode 100755 tests/qemu-iotests/313 create mode 100644 tests/qemu-iotests/313.out -- 2.29.2 From: Vladimir Sementsov-Ogievskiy <vsementsov@virtuozzo.com> Unfortunately commit "iotests: handle tmpfs" breaks running iotests with -nbd -nocache, as _check_o_direct tries to create $TEST_IMG.test_o_direct, but in case of nbd TEST_IMG is something like nbd+unix:///... , and test fails with message qemu-img: nbd+unix:///?socket[...]test_o_direct: Protocol driver 'nbd' does not support image creation, and opening the image failed: Failed to connect to '/tmp/tmp.[...]/nbd/test_o_direct': No such file or directory Use TEST_DIR instead. Fixes: cfdca2b9f9d4ca26bb2b2dfe8de3149092e39170 Signed-off-by: Vladimir Sementsov-Ogievskiy <vsementsov@virtuozzo.com> Message-Id: <20201218182012.47607-1-vsementsov@virtuozzo.com> Signed-off-by: Max Reitz <mreitz@redhat.com> --- tests/qemu-iotests/common.rc | 7 ++++--- 1 file changed, 4 insertions(+), 3 deletions(-) diff --git a/tests/qemu-iotests/common.rc b/tests/qemu-iotests/common.rc index XXXXXXX..XXXXXXX 100644 --- a/tests/qemu-iotests/common.rc +++ b/tests/qemu-iotests/common.rc @@ -XXX,XX +XXX,XX @@ _supported_cache_modes() # Check whether the filesystem supports O_DIRECT _check_o_direct() { - $QEMU_IMG create -f raw "$TEST_IMG".test_o_direct 1M > /dev/null - out=$($QEMU_IO -f raw -t none -c quit "$TEST_IMG".test_o_direct 2>&1) - rm -f "$TEST_IMG".test_o_direct + testfile="$TEST_DIR"/_check_o_direct + $QEMU_IMG create -f raw "$testfile" 1M > /dev/null + out=$($QEMU_IO -f raw -t none -c quit "$testfile" 2>&1) + rm -f "$testfile" [[ "$out" != *"O_DIRECT"* ]] } -- 2.29.2 From: Andrey Shinkevich <andrey.shinkevich@virtuozzo.com> Add support for the recently introduced functions bdrv_co_preadv_part() and bdrv_co_pwritev_part() to the COR-filter driver. Signed-off-by: Andrey Shinkevich <andrey.shinkevich@virtuozzo.com> Reviewed-by: Vladimir Sementsov-Ogievskiy <vsementsov@virtuozzo.com> Message-Id: <20201216061703.70908-2-vsementsov@virtuozzo.com> Signed-off-by: Max Reitz <mreitz@redhat.com> --- block/copy-on-read.c | 28 ++++++++++++++++------------ 1 file changed, 16 insertions(+), 12 deletions(-) diff --git a/block/copy-on-read.c b/block/copy-on-read.c index XXXXXXX..XXXXXXX 100644 --- a/block/copy-on-read.c +++ b/block/copy-on-read.c @@ -XXX,XX +XXX,XX @@ static int64_t cor_getlength(BlockDriverState *bs) } -static int coroutine_fn cor_co_preadv(BlockDriverState *bs, - uint64_t offset, uint64_t bytes, - QEMUIOVector *qiov, int flags) +static int coroutine_fn cor_co_preadv_part(BlockDriverState *bs, + uint64_t offset, uint64_t bytes, + QEMUIOVector *qiov, + size_t qiov_offset, + int flags) { - return bdrv_co_preadv(bs->file, offset, bytes, qiov, - flags | BDRV_REQ_COPY_ON_READ); + return bdrv_co_preadv_part(bs->file, offset, bytes, qiov, qiov_offset, + flags | BDRV_REQ_COPY_ON_READ); } -static int coroutine_fn cor_co_pwritev(BlockDriverState *bs, - uint64_t offset, uint64_t bytes, - QEMUIOVector *qiov, int flags) +static int coroutine_fn cor_co_pwritev_part(BlockDriverState *bs, + uint64_t offset, + uint64_t bytes, + QEMUIOVector *qiov, + size_t qiov_offset, int flags) { - - return bdrv_co_pwritev(bs->file, offset, bytes, qiov, flags); + return bdrv_co_pwritev_part(bs->file, offset, bytes, qiov, qiov_offset, + flags); } @@ -XXX,XX +XXX,XX @@ static BlockDriver bdrv_copy_on_read = { .bdrv_getlength = cor_getlength, - .bdrv_co_preadv = cor_co_preadv, - .bdrv_co_pwritev = cor_co_pwritev, + .bdrv_co_preadv_part = cor_co_preadv_part, + .bdrv_co_pwritev_part = cor_co_pwritev_part, .bdrv_co_pwrite_zeroes = cor_co_pwrite_zeroes, .bdrv_co_pdiscard = cor_co_pdiscard, .bdrv_co_pwritev_compressed = cor_co_pwritev_compressed, -- 2.29.2 From: Andrey Shinkevich <andrey.shinkevich@virtuozzo.com> Provide API for insertion a node to backing chain. Suggested-by: Max Reitz <mreitz@redhat.com> Signed-off-by: Andrey Shinkevich <andrey.shinkevich@virtuozzo.com> Reviewed-by: Vladimir Sementsov-Ogievskiy <vsementsov@virtuozzo.com> Reviewed-by: Max Reitz <mreitz@redhat.com> Message-Id: <20201216061703.70908-3-vsementsov@virtuozzo.com> Signed-off-by: Max Reitz <mreitz@redhat.com> --- include/block/block.h | 2 ++ block.c | 25 +++++++++++++++++++++++++ 2 files changed, 27 insertions(+) diff --git a/include/block/block.h b/include/block/block.h index XXXXXXX..XXXXXXX 100644 --- a/include/block/block.h +++ b/include/block/block.h @@ -XXX,XX +XXX,XX @@ void bdrv_append(BlockDriverState *bs_new, BlockDriverState *bs_top, Error **errp); void bdrv_replace_node(BlockDriverState *from, BlockDriverState *to, Error **errp); +BlockDriverState *bdrv_insert_node(BlockDriverState *bs, QDict *node_options, + int flags, Error **errp); int bdrv_parse_aio(const char *mode, int *flags); int bdrv_parse_cache_mode(const char *mode, int *flags, bool *writethrough); diff --git a/block.c b/block.c index XXXXXXX..XXXXXXX 100644 --- a/block.c +++ b/block.c @@ -XXX,XX +XXX,XX @@ static void bdrv_delete(BlockDriverState *bs) g_free(bs); } +BlockDriverState *bdrv_insert_node(BlockDriverState *bs, QDict *node_options, + int flags, Error **errp) +{ + BlockDriverState *new_node_bs; + Error *local_err = NULL; + + new_node_bs = bdrv_open(NULL, NULL, node_options, flags, errp); + if (new_node_bs == NULL) { + error_prepend(errp, "Could not create node: "); + return NULL; + } + + bdrv_drained_begin(bs); + bdrv_replace_node(bs, new_node_bs, &local_err); + bdrv_drained_end(bs); + + if (local_err) { + bdrv_unref(new_node_bs); + error_propagate(errp, local_err); + return NULL; + } + + return new_node_bs; +} + /* * Run consistency checks on an image * -- 2.29.2 From: Andrey Shinkevich <andrey.shinkevich@virtuozzo.com> Provide API for the COR-filter removal. Also, drop the filter child permissions for an inactive state when the filter node is being removed. To insert the filter, the block generic layer function bdrv_insert_node() can be used. The new function bdrv_cor_filter_drop() may be considered as an intermediate solution before the QEMU permission update system has overhauled. Then we are able to implement the API function bdrv_remove_node() on the block generic layer. Signed-off-by: Andrey Shinkevich <andrey.shinkevich@virtuozzo.com> Reviewed-by: Vladimir Sementsov-Ogievskiy <vsementsov@virtuozzo.com> Reviewed-by: Max Reitz <mreitz@redhat.com> Message-Id: <20201216061703.70908-4-vsementsov@virtuozzo.com> Signed-off-by: Max Reitz <mreitz@redhat.com> --- block/copy-on-read.h | 32 +++++++++++++++++++++++++ block/copy-on-read.c | 56 ++++++++++++++++++++++++++++++++++++++++++++ 2 files changed, 88 insertions(+) create mode 100644 block/copy-on-read.h diff --git a/block/copy-on-read.h b/block/copy-on-read.h new file mode 100644 index XXXXXXX..XXXXXXX --- /dev/null +++ b/block/copy-on-read.h @@ -XXX,XX +XXX,XX @@ +/* + * Copy-on-read filter block driver + * + * The filter driver performs Copy-On-Read (COR) operations + * + * Copyright (c) 2018-2020 Virtuozzo International GmbH. + * + * Author: + * Andrey Shinkevich <andrey.shinkevich@virtuozzo.com> + * + * This program is free software; you can redistribute it and/or modify + * it under the terms of the GNU General Public License as published by + * the Free Software Foundation; either version 2 of the License, or + * (at your option) any later version. + * + * This program is distributed in the hope that it will be useful, + * but WITHOUT ANY WARRANTY; without even the implied warranty of + * MERCHANTABILITY or FITNESS FOR A PARTICULAR PURPOSE. See the + * GNU General Public License for more details. + * + * You should have received a copy of the GNU General Public License + * along with this program. If not, see <http://www.gnu.org/licenses/>. + */ + +#ifndef BLOCK_COPY_ON_READ +#define BLOCK_COPY_ON_READ + +#include "block/block_int.h" + +void bdrv_cor_filter_drop(BlockDriverState *cor_filter_bs); + +#endif /* BLOCK_COPY_ON_READ */ diff --git a/block/copy-on-read.c b/block/copy-on-read.c index XXXXXXX..XXXXXXX 100644 --- a/block/copy-on-read.c +++ b/block/copy-on-read.c @@ -XXX,XX +XXX,XX @@ #include "qemu/osdep.h" #include "block/block_int.h" #include "qemu/module.h" +#include "qapi/error.h" +#include "block/copy-on-read.h" + + +typedef struct BDRVStateCOR { + bool active; +} BDRVStateCOR; static int cor_open(BlockDriverState *bs, QDict *options, int flags, Error **errp) { + BDRVStateCOR *state = bs->opaque; + bs->file = bdrv_open_child(NULL, options, "file", bs, &child_of_bds, BDRV_CHILD_FILTERED | BDRV_CHILD_PRIMARY, false, errp); @@ -XXX,XX +XXX,XX @@ static int cor_open(BlockDriverState *bs, QDict *options, int flags, ((BDRV_REQ_FUA | BDRV_REQ_MAY_UNMAP | BDRV_REQ_NO_FALLBACK) & bs->file->bs->supported_zero_flags); + state->active = true; + + /* + * We don't need to call bdrv_child_refresh_perms() now as the permissions + * will be updated later when the filter node gets its parent. + */ + return 0; } @@ -XXX,XX +XXX,XX @@ static void cor_child_perm(BlockDriverState *bs, BdrvChild *c, uint64_t perm, uint64_t shared, uint64_t *nperm, uint64_t *nshared) { + BDRVStateCOR *s = bs->opaque; + + if (!s->active) { + /* + * While the filter is being removed + */ + *nperm = 0; + *nshared = BLK_PERM_ALL; + return; + } + *nperm = perm & PERM_PASSTHROUGH; *nshared = (shared & PERM_PASSTHROUGH) | PERM_UNCHANGED; @@ -XXX,XX +XXX,XX @@ static void cor_lock_medium(BlockDriverState *bs, bool locked) static BlockDriver bdrv_copy_on_read = { .format_name = "copy-on-read", + .instance_size = sizeof(BDRVStateCOR), .bdrv_open = cor_open, .bdrv_child_perm = cor_child_perm, @@ -XXX,XX +XXX,XX @@ static BlockDriver bdrv_copy_on_read = { .is_filter = true, }; + +void bdrv_cor_filter_drop(BlockDriverState *cor_filter_bs) +{ + BdrvChild *child; + BlockDriverState *bs; + BDRVStateCOR *s = cor_filter_bs->opaque; + + child = bdrv_filter_child(cor_filter_bs); + if (!child) { + return; + } + bs = child->bs; + + /* Retain the BDS until we complete the graph change. */ + bdrv_ref(bs); + /* Hold a guest back from writing while permissions are being reset. */ + bdrv_drained_begin(bs); + /* Drop permissions before the graph change. */ + s->active = false; + bdrv_child_refresh_perms(cor_filter_bs, child, &error_abort); + bdrv_replace_node(cor_filter_bs, bs, &error_abort); + + bdrv_drained_end(bs); + bdrv_unref(bs); + bdrv_unref(cor_filter_bs); +} + + static void bdrv_copy_on_read_init(void) { bdrv_register(&bdrv_copy_on_read); -- 2.29.2 From: Andrey Shinkevich <andrey.shinkevich@virtuozzo.com> Provide the possibility to pass the 'filter-node-name' parameter to the block-stream job as it is done for the commit block job. Signed-off-by: Andrey Shinkevich <andrey.shinkevich@virtuozzo.com> Reviewed-by: Vladimir Sementsov-Ogievskiy <vsementsov@virtuozzo.com> [vsementsov: comment indentation, s/Since: 5.2/Since: 6.0/] Reviewed-by: Max Reitz <mreitz@redhat.com> Message-Id: <20201216061703.70908-5-vsementsov@virtuozzo.com> [mreitz: s/commit/stream/] Signed-off-by: Max Reitz <mreitz@redhat.com> --- qapi/block-core.json | 6 ++++++ include/block/block_int.h | 7 ++++++- block/monitor/block-hmp-cmds.c | 4 ++-- block/stream.c | 4 +++- blockdev.c | 4 +++- 5 files changed, 20 insertions(+), 5 deletions(-) diff --git a/qapi/block-core.json b/qapi/block-core.json index XXXXXXX..XXXXXXX 100644 --- a/qapi/block-core.json +++ b/qapi/block-core.json @@ -XXX,XX +XXX,XX @@ # 'stop' and 'enospc' can only be used if the block device # supports io-status (see BlockInfo). Since 1.3. # +# @filter-node-name: the node name that should be assigned to the +# filter driver that the stream job inserts into the graph +# above @device. If this option is not given, a node name is +# autogenerated. (Since: 6.0) +# # @auto-finalize: When false, this job will wait in a PENDING state after it has # finished its work, waiting for @block-job-finalize before # making any block graph changes. @@ -XXX,XX +XXX,XX @@ 'data': { '*job-id': 'str', 'device': 'str', '*base': 'str', '*base-node': 'str', '*backing-file': 'str', '*speed': 'int', '*on-error': 'BlockdevOnError', + '*filter-node-name': 'str', '*auto-finalize': 'bool', '*auto-dismiss': 'bool' } } ## diff --git a/include/block/block_int.h b/include/block/block_int.h index XXXXXXX..XXXXXXX 100644 --- a/include/block/block_int.h +++ b/include/block/block_int.h @@ -XXX,XX +XXX,XX @@ int is_windows_drive(const char *filename); * See @BlockJobCreateFlags * @speed: The maximum speed, in bytes per second, or 0 for unlimited. * @on_error: The action to take upon error. + * @filter_node_name: The node name that should be assigned to the filter + * driver that the stream job inserts into the graph above + * @bs. NULL means that a node name should be autogenerated. * @errp: Error object. * * Start a streaming operation on @bs. Clusters that are unallocated @@ -XXX,XX +XXX,XX @@ int is_windows_drive(const char *filename); void stream_start(const char *job_id, BlockDriverState *bs, BlockDriverState *base, const char *backing_file_str, int creation_flags, int64_t speed, - BlockdevOnError on_error, Error **errp); + BlockdevOnError on_error, + const char *filter_node_name, + Error **errp); /** * commit_start: diff --git a/block/monitor/block-hmp-cmds.c b/block/monitor/block-hmp-cmds.c index XXXXXXX..XXXXXXX 100644 --- a/block/monitor/block-hmp-cmds.c +++ b/block/monitor/block-hmp-cmds.c @@ -XXX,XX +XXX,XX @@ void hmp_block_stream(Monitor *mon, const QDict *qdict) qmp_block_stream(true, device, device, base != NULL, base, false, NULL, false, NULL, qdict_haskey(qdict, "speed"), speed, true, - BLOCKDEV_ON_ERROR_REPORT, false, false, false, false, - &error); + BLOCKDEV_ON_ERROR_REPORT, false, NULL, false, false, false, + false, &error); hmp_handle_error(mon, error); } diff --git a/block/stream.c b/block/stream.c index XXXXXXX..XXXXXXX 100644 --- a/block/stream.c +++ b/block/stream.c @@ -XXX,XX +XXX,XX @@ static const BlockJobDriver stream_job_driver = { void stream_start(const char *job_id, BlockDriverState *bs, BlockDriverState *base, const char *backing_file_str, int creation_flags, int64_t speed, - BlockdevOnError on_error, Error **errp) + BlockdevOnError on_error, + const char *filter_node_name, + Error **errp) { StreamBlockJob *s; BlockDriverState *iter; diff --git a/blockdev.c b/blockdev.c index XXXXXXX..XXXXXXX 100644 --- a/blockdev.c +++ b/blockdev.c @@ -XXX,XX +XXX,XX @@ void qmp_block_stream(bool has_job_id, const char *job_id, const char *device, bool has_backing_file, const char *backing_file, bool has_speed, int64_t speed, bool has_on_error, BlockdevOnError on_error, + bool has_filter_node_name, const char *filter_node_name, bool has_auto_finalize, bool auto_finalize, bool has_auto_dismiss, bool auto_dismiss, Error **errp) @@ -XXX,XX +XXX,XX @@ void qmp_block_stream(bool has_job_id, const char *job_id, const char *device, } stream_start(has_job_id ? job_id : NULL, bs, base_bs, base_name, - job_flags, has_speed ? speed : 0, on_error, &local_err); + job_flags, has_speed ? speed : 0, on_error, + filter_node_name, &local_err); if (local_err) { error_propagate(errp, local_err); goto out; -- 2.29.2 From: Andrey Shinkevich <andrey.shinkevich@virtuozzo.com> Add an option to limit copy-on-read operations to specified sub-chain of backing-chain, to make copy-on-read filter useful for block-stream job. Suggested-by: Max Reitz <mreitz@redhat.com> Suggested-by: Vladimir Sementsov-Ogievskiy <vsementsov@virtuozzo.com> Signed-off-by: Andrey Shinkevich <andrey.shinkevich@virtuozzo.com> Signed-off-by: Vladimir Sementsov-Ogievskiy <vsementsov@virtuozzo.com> [vsementsov: change subject, modified to freeze the chain, do some fixes] Message-Id: <20201216061703.70908-6-vsementsov@virtuozzo.com> Signed-off-by: Max Reitz <mreitz@redhat.com> --- qapi/block-core.json | 20 ++++++++- block/copy-on-read.c | 98 +++++++++++++++++++++++++++++++++++++++++++- 2 files changed, 115 insertions(+), 3 deletions(-) diff --git a/qapi/block-core.json b/qapi/block-core.json index XXXXXXX..XXXXXXX 100644 --- a/qapi/block-core.json +++ b/qapi/block-core.json @@ -XXX,XX +XXX,XX @@ 'data': { 'throttle-group': 'str', 'file' : 'BlockdevRef' } } + +## +# @BlockdevOptionsCor: +# +# Driver specific block device options for the copy-on-read driver. +# +# @bottom: The name of a non-filter node (allocation-bearing layer) that +# limits the COR operations in the backing chain (inclusive), so +# that no data below this node will be copied by this filter. +# If option is absent, the limit is not applied, so that data +# from all backing layers may be copied. +# +# Since: 6.0 +## +{ 'struct': 'BlockdevOptionsCor', + 'base': 'BlockdevOptionsGenericFormat', + 'data': { '*bottom': 'str' } } + ## # @BlockdevOptions: # @@ -XXX,XX +XXX,XX @@ 'bochs': 'BlockdevOptionsGenericFormat', 'cloop': 'BlockdevOptionsGenericFormat', 'compress': 'BlockdevOptionsGenericFormat', - 'copy-on-read':'BlockdevOptionsGenericFormat', + 'copy-on-read':'BlockdevOptionsCor', 'dmg': 'BlockdevOptionsGenericFormat', 'file': 'BlockdevOptionsFile', 'ftp': 'BlockdevOptionsCurlFtp', diff --git a/block/copy-on-read.c b/block/copy-on-read.c index XXXXXXX..XXXXXXX 100644 --- a/block/copy-on-read.c +++ b/block/copy-on-read.c @@ -XXX,XX +XXX,XX @@ #include "block/block_int.h" #include "qemu/module.h" #include "qapi/error.h" +#include "qapi/qmp/qdict.h" #include "block/copy-on-read.h" typedef struct BDRVStateCOR { bool active; + BlockDriverState *bottom_bs; + bool chain_frozen; } BDRVStateCOR; static int cor_open(BlockDriverState *bs, QDict *options, int flags, Error **errp) { + BlockDriverState *bottom_bs = NULL; BDRVStateCOR *state = bs->opaque; + /* Find a bottom node name, if any */ + const char *bottom_node = qdict_get_try_str(options, "bottom"); bs->file = bdrv_open_child(NULL, options, "file", bs, &child_of_bds, BDRV_CHILD_FILTERED | BDRV_CHILD_PRIMARY, @@ -XXX,XX +XXX,XX @@ static int cor_open(BlockDriverState *bs, QDict *options, int flags, ((BDRV_REQ_FUA | BDRV_REQ_MAY_UNMAP | BDRV_REQ_NO_FALLBACK) & bs->file->bs->supported_zero_flags); + if (bottom_node) { + bottom_bs = bdrv_find_node(bottom_node); + if (!bottom_bs) { + error_setg(errp, "Bottom node '%s' not found", bottom_node); + qdict_del(options, "bottom"); + return -EINVAL; + } + qdict_del(options, "bottom"); + + if (!bottom_bs->drv) { + error_setg(errp, "Bottom node '%s' not opened", bottom_node); + return -EINVAL; + } + + if (bottom_bs->drv->is_filter) { + error_setg(errp, "Bottom node '%s' is a filter", bottom_node); + return -EINVAL; + } + + if (bdrv_freeze_backing_chain(bs, bottom_bs, errp) < 0) { + return -EINVAL; + } + state->chain_frozen = true; + + /* + * We do freeze the chain, so it shouldn't be removed. Still, storing a + * pointer worth bdrv_ref(). + */ + bdrv_ref(bottom_bs); + } state->active = true; + state->bottom_bs = bottom_bs; /* * We don't need to call bdrv_child_refresh_perms() now as the permissions @@ -XXX,XX +XXX,XX @@ static int coroutine_fn cor_co_preadv_part(BlockDriverState *bs, size_t qiov_offset, int flags) { - return bdrv_co_preadv_part(bs->file, offset, bytes, qiov, qiov_offset, - flags | BDRV_REQ_COPY_ON_READ); + int64_t n; + int local_flags; + int ret; + BDRVStateCOR *state = bs->opaque; + + if (!state->bottom_bs) { + return bdrv_co_preadv_part(bs->file, offset, bytes, qiov, qiov_offset, + flags | BDRV_REQ_COPY_ON_READ); + } + + while (bytes) { + local_flags = flags; + + /* In case of failure, try to copy-on-read anyway */ + ret = bdrv_is_allocated(bs->file->bs, offset, bytes, &n); + if (ret <= 0) { + ret = bdrv_is_allocated_above(bdrv_backing_chain_next(bs->file->bs), + state->bottom_bs, true, offset, + n, &n); + if (ret > 0 || ret < 0) { + local_flags |= BDRV_REQ_COPY_ON_READ; + } + /* Finish earlier if the end of a backing file has been reached */ + if (n == 0) { + break; + } + } + + ret = bdrv_co_preadv_part(bs->file, offset, n, qiov, qiov_offset, + local_flags); + if (ret < 0) { + return ret; + } + + offset += n; + qiov_offset += n; + bytes -= n; + } + + return 0; } @@ -XXX,XX +XXX,XX @@ static void cor_lock_medium(BlockDriverState *bs, bool locked) } +static void cor_close(BlockDriverState *bs) +{ + BDRVStateCOR *s = bs->opaque; + + if (s->chain_frozen) { + s->chain_frozen = false; + bdrv_unfreeze_backing_chain(bs, s->bottom_bs); + } + + bdrv_unref(s->bottom_bs); +} + + static BlockDriver bdrv_copy_on_read = { .format_name = "copy-on-read", .instance_size = sizeof(BDRVStateCOR), .bdrv_open = cor_open, + .bdrv_close = cor_close, .bdrv_child_perm = cor_child_perm, .bdrv_getlength = cor_getlength, @@ -XXX,XX +XXX,XX @@ void bdrv_cor_filter_drop(BlockDriverState *cor_filter_bs) bdrv_drained_begin(bs); /* Drop permissions before the graph change. */ s->active = false; + /* unfreeze, as otherwise bdrv_replace_node() will fail */ + if (s->chain_frozen) { + s->chain_frozen = false; + bdrv_unfreeze_backing_chain(cor_filter_bs, s->bottom_bs); + } bdrv_child_refresh_perms(cor_filter_bs, child, &error_abort); bdrv_replace_node(cor_filter_bs, bs, &error_abort); -- 2.29.2 From: Andrey Shinkevich <andrey.shinkevich@virtuozzo.com> The test case #310 is similar to #216 by Max Reitz. The difference is that the test #310 involves a bottom node to the COR filter driver. Signed-off-by: Andrey Shinkevich <andrey.shinkevich@virtuozzo.com> Signed-off-by: Vladimir Sementsov-Ogievskiy <vsementsov@virtuozzo.com> [vsementsov: detach backing to test reads from top, limit to qcow2] Message-Id: <20201216061703.70908-7-vsementsov@virtuozzo.com> [mreitz: Add "# group:" line] Signed-off-by: Max Reitz <mreitz@redhat.com> --- tests/qemu-iotests/310 | 117 +++++++++++++++++++++++++++++++++++++ tests/qemu-iotests/310.out | 15 +++++ tests/qemu-iotests/group | 1 + 3 files changed, 133 insertions(+) create mode 100755 tests/qemu-iotests/310 create mode 100644 tests/qemu-iotests/310.out diff --git a/tests/qemu-iotests/310 b/tests/qemu-iotests/310 new file mode 100755 index XXXXXXX..XXXXXXX --- /dev/null +++ b/tests/qemu-iotests/310 @@ -XXX,XX +XXX,XX @@ +#!/usr/bin/env python3 +# group: rw quick +# +# Copy-on-read tests using a COR filter with a bottom node +# +# Copyright (C) 2018 Red Hat, Inc. +# Copyright (c) 2020 Virtuozzo International GmbH +# +# This program is free software; you can redistribute it and/or modify +# it under the terms of the GNU General Public License as published by +# the Free Software Foundation; either version 2 of the License, or +# (at your option) any later version. +# +# This program is distributed in the hope that it will be useful, +# but WITHOUT ANY WARRANTY; without even the implied warranty of +# MERCHANTABILITY or FITNESS FOR A PARTICULAR PURPOSE. See the +# GNU General Public License for more details. +# +# You should have received a copy of the GNU General Public License +# along with this program. If not, see <http://www.gnu.org/licenses/>. +# + +import iotests +from iotests import log, qemu_img, qemu_io_silent + +# Need backing file support +iotests.script_initialize(supported_fmts=['qcow2'], + supported_platforms=['linux']) + +log('') +log('=== Copy-on-read across nodes ===') +log('') + +# This test is similar to the 216 one by Max Reitz <mreitz@redhat.com> +# The difference is that this test case involves a bottom node to the +# COR filter driver. + +with iotests.FilePath('base.img') as base_img_path, \ + iotests.FilePath('mid.img') as mid_img_path, \ + iotests.FilePath('top.img') as top_img_path, \ + iotests.VM() as vm: + + log('--- Setting up images ---') + log('') + + assert qemu_img('create', '-f', iotests.imgfmt, base_img_path, '64M') == 0 + assert qemu_io_silent(base_img_path, '-c', 'write -P 1 0M 1M') == 0 + assert qemu_io_silent(base_img_path, '-c', 'write -P 1 3M 1M') == 0 + assert qemu_img('create', '-f', iotests.imgfmt, '-b', base_img_path, + '-F', iotests.imgfmt, mid_img_path) == 0 + assert qemu_io_silent(mid_img_path, '-c', 'write -P 3 2M 1M') == 0 + assert qemu_io_silent(mid_img_path, '-c', 'write -P 3 4M 1M') == 0 + assert qemu_img('create', '-f', iotests.imgfmt, '-b', mid_img_path, + '-F', iotests.imgfmt, top_img_path) == 0 + assert qemu_io_silent(top_img_path, '-c', 'write -P 2 1M 1M') == 0 + +# 0 1 2 3 4 +# top 2 +# mid 3 3 +# base 1 1 + + log('Done') + + log('') + log('--- Doing COR ---') + log('') + + vm.launch() + + log(vm.qmp('blockdev-add', + node_name='node0', + driver='copy-on-read', + bottom='node2', + file={ + 'driver': iotests.imgfmt, + 'file': { + 'driver': 'file', + 'filename': top_img_path + }, + 'backing': { + 'node-name': 'node2', + 'driver': iotests.imgfmt, + 'file': { + 'driver': 'file', + 'filename': mid_img_path + }, + 'backing': { + 'driver': iotests.imgfmt, + 'file': { + 'driver': 'file', + 'filename': base_img_path + } + }, + } + })) + + # Trigger COR + log(vm.qmp('human-monitor-command', + command_line='qemu-io node0 "read 0 5M"')) + + vm.shutdown() + + log('') + log('--- Checking COR result ---') + log('') + + # Detach backing to check that we can read the data from the top level now + assert qemu_img('rebase', '-u', '-b', '', '-f', iotests.imgfmt, + top_img_path) == 0 + + assert qemu_io_silent(top_img_path, '-c', 'read -P 0 0 1M') == 0 + assert qemu_io_silent(top_img_path, '-c', 'read -P 2 1M 1M') == 0 + assert qemu_io_silent(top_img_path, '-c', 'read -P 3 2M 1M') == 0 + assert qemu_io_silent(top_img_path, '-c', 'read -P 0 3M 1M') == 0 + assert qemu_io_silent(top_img_path, '-c', 'read -P 3 4M 1M') == 0 + + log('Done') diff --git a/tests/qemu-iotests/310.out b/tests/qemu-iotests/310.out new file mode 100644 index XXXXXXX..XXXXXXX --- /dev/null +++ b/tests/qemu-iotests/310.out @@ -XXX,XX +XXX,XX @@ + +=== Copy-on-read across nodes === + +--- Setting up images --- + +Done + +--- Doing COR --- + +{"return": {}} +{"return": ""} + +--- Checking COR result --- + +Done diff --git a/tests/qemu-iotests/group b/tests/qemu-iotests/group index XXXXXXX..XXXXXXX 100644 --- a/tests/qemu-iotests/group +++ b/tests/qemu-iotests/group @@ -XXX,XX +XXX,XX @@ 307 rw quick export 308 rw 309 rw auto quick +310 rw quick 312 rw quick -- 2.29.2 From: Andrey Shinkevich <andrey.shinkevich@virtuozzo.com> Add the new member supported_read_flags to the BlockDriverState structure. It will control the flags set for copy-on-read operations. Make the block generic layer evaluate supported read flags before they go to a block driver. Suggested-by: Vladimir Sementsov-Ogievskiy <vsementsov@virtuozzo.com> Signed-off-by: Andrey Shinkevich <andrey.shinkevich@virtuozzo.com> Signed-off-by: Vladimir Sementsov-Ogievskiy <vsementsov@virtuozzo.com> [vsementsov: use assert instead of abort] Reviewed-by: Max Reitz <mreitz@redhat.com> Message-Id: <20201216061703.70908-8-vsementsov@virtuozzo.com> Signed-off-by: Max Reitz <mreitz@redhat.com> --- include/block/block_int.h | 4 ++++ block/io.c | 10 ++++++++-- 2 files changed, 12 insertions(+), 2 deletions(-) diff --git a/include/block/block_int.h b/include/block/block_int.h index XXXXXXX..XXXXXXX 100644 --- a/include/block/block_int.h +++ b/include/block/block_int.h @@ -XXX,XX +XXX,XX @@ struct BlockDriverState { /* I/O Limits */ BlockLimits bl; + /* + * Flags honored during pread + */ + unsigned int supported_read_flags; /* Flags honored during pwrite (so far: BDRV_REQ_FUA, * BDRV_REQ_WRITE_UNCHANGED). * If a driver does not support BDRV_REQ_WRITE_UNCHANGED, those diff --git a/block/io.c b/block/io.c index XXXXXXX..XXXXXXX 100644 --- a/block/io.c +++ b/block/io.c @@ -XXX,XX +XXX,XX @@ static int coroutine_fn bdrv_aligned_preadv(BdrvChild *child, if (flags & BDRV_REQ_COPY_ON_READ) { int64_t pnum; + /* The flag BDRV_REQ_COPY_ON_READ has reached its addressee */ + flags &= ~BDRV_REQ_COPY_ON_READ; + ret = bdrv_is_allocated(bs, offset, bytes, &pnum); if (ret < 0) { goto out; @@ -XXX,XX +XXX,XX @@ static int coroutine_fn bdrv_aligned_preadv(BdrvChild *child, goto out; } + assert(!(flags & ~bs->supported_read_flags)); + max_bytes = ROUND_UP(MAX(0, total_bytes - offset), align); if (bytes <= max_bytes && bytes <= max_transfer) { - ret = bdrv_driver_preadv(bs, offset, bytes, qiov, qiov_offset, 0); + ret = bdrv_driver_preadv(bs, offset, bytes, qiov, qiov_offset, flags); goto out; } @@ -XXX,XX +XXX,XX @@ static int coroutine_fn bdrv_aligned_preadv(BdrvChild *child, ret = bdrv_driver_preadv(bs, offset + bytes - bytes_remaining, num, qiov, - qiov_offset + bytes - bytes_remaining, 0); + qiov_offset + bytes - bytes_remaining, + flags); max_bytes -= num; } else { num = bytes_remaining; -- 2.29.2 From: Andrey Shinkevich <andrey.shinkevich@virtuozzo.com> If the flag BDRV_REQ_PREFETCH was set, skip idling read/write operations in COR-driver. It can be taken into account for the COR-algorithms optimization. That check is being made during the block stream job by the moment. Add the BDRV_REQ_PREFETCH flag to the supported_read_flags of the COR-filter. block: Modify the comment for the flag BDRV_REQ_PREFETCH as we are going to use it alone and pass it to the COR-filter driver for further processing. Signed-off-by: Andrey Shinkevich <andrey.shinkevich@virtuozzo.com> Reviewed-by: Vladimir Sementsov-Ogievskiy <vsementsov@virtuozzo.com> Reviewed-by: Max Reitz <mreitz@redhat.com> Message-Id: <20201216061703.70908-9-vsementsov@virtuozzo.com> Signed-off-by: Max Reitz <mreitz@redhat.com> --- include/block/block.h | 8 +++++--- block/copy-on-read.c | 14 ++++++++++---- 2 files changed, 15 insertions(+), 7 deletions(-) diff --git a/include/block/block.h b/include/block/block.h index XXXXXXX..XXXXXXX 100644 --- a/include/block/block.h +++ b/include/block/block.h @@ -XXX,XX +XXX,XX @@ typedef enum { BDRV_REQ_NO_FALLBACK = 0x100, /* - * BDRV_REQ_PREFETCH may be used only together with BDRV_REQ_COPY_ON_READ - * on read request and means that caller doesn't really need data to be - * written to qiov parameter which may be NULL. + * BDRV_REQ_PREFETCH makes sense only in the context of copy-on-read + * (i.e., together with the BDRV_REQ_COPY_ON_READ flag or when a COR + * filter is involved), in which case it signals that the COR operation + * need not read the data into memory (qiov) but only ensure they are + * copied to the top layer (i.e., that COR operation is done). */ BDRV_REQ_PREFETCH = 0x200, diff --git a/block/copy-on-read.c b/block/copy-on-read.c index XXXXXXX..XXXXXXX 100644 --- a/block/copy-on-read.c +++ b/block/copy-on-read.c @@ -XXX,XX +XXX,XX @@ static int cor_open(BlockDriverState *bs, QDict *options, int flags, return -EINVAL; } + bs->supported_read_flags = BDRV_REQ_PREFETCH; + bs->supported_write_flags = BDRV_REQ_WRITE_UNCHANGED | (BDRV_REQ_FUA & bs->file->bs->supported_write_flags); @@ -XXX,XX +XXX,XX @@ static int coroutine_fn cor_co_preadv_part(BlockDriverState *bs, } } - ret = bdrv_co_preadv_part(bs->file, offset, n, qiov, qiov_offset, - local_flags); - if (ret < 0) { - return ret; + /* Skip if neither read nor write are needed */ + if ((local_flags & (BDRV_REQ_PREFETCH | BDRV_REQ_COPY_ON_READ)) != + BDRV_REQ_PREFETCH) { + ret = bdrv_co_preadv_part(bs->file, offset, n, qiov, qiov_offset, + local_flags); + if (ret < 0) { + return ret; + } } offset += n; -- 2.29.2 From: Andrey Shinkevich <andrey.shinkevich@virtuozzo.com> Stream in stream_prepare calls bdrv_change_backing_file() to change backing-file in the metadata of bs. It may use either backing-file parameter given by user or just take filename of base on job start. Backing file format is determined by base on job finish. There are some problems with this design, we solve only two by this patch: 1. Consider scenario with backing-file unset. Current concept of stream supports changing of the base during the job (we don't freeze link to the base). So, we should not save base filename at job start, - let's determine name of the base on job finish. 2. Using direct base to determine filename and format is not very good: base node may be a filter, so its filename may be JSON, and format_name is not good for storing into qcow2 metadata as backing file format. - let's use unfiltered_base Signed-off-by: Andrey Shinkevich <andrey.shinkevich@virtuozzo.com> Signed-off-by: Vladimir Sementsov-Ogievskiy <vsementsov@virtuozzo.com> [vsementsov: change commit subject, change logic in stream_prepare] Message-Id: <20201216061703.70908-10-vsementsov@virtuozzo.com> Reviewed-by: Max Reitz <mreitz@redhat.com> Signed-off-by: Max Reitz <mreitz@redhat.com> --- block/stream.c | 9 +++++---- blockdev.c | 8 +------- 2 files changed, 6 insertions(+), 11 deletions(-) diff --git a/block/stream.c b/block/stream.c index XXXXXXX..XXXXXXX 100644 --- a/block/stream.c +++ b/block/stream.c @@ -XXX,XX +XXX,XX @@ static int stream_prepare(Job *job) BlockDriverState *bs = blk_bs(bjob->blk); BlockDriverState *unfiltered_bs = bdrv_skip_filters(bs); BlockDriverState *base = bdrv_filter_or_cow_bs(s->above_base); + BlockDriverState *unfiltered_base = bdrv_skip_filters(base); Error *local_err = NULL; int ret = 0; @@ -XXX,XX +XXX,XX @@ static int stream_prepare(Job *job) if (bdrv_cow_child(unfiltered_bs)) { const char *base_id = NULL, *base_fmt = NULL; - if (base) { - base_id = s->backing_file_str; - if (base->drv) { - base_fmt = base->drv->format_name; + if (unfiltered_base) { + base_id = s->backing_file_str ?: unfiltered_base->filename; + if (unfiltered_base->drv) { + base_fmt = unfiltered_base->drv->format_name; } } bdrv_set_backing_hd(unfiltered_bs, base, &local_err); diff --git a/blockdev.c b/blockdev.c index XXXXXXX..XXXXXXX 100644 --- a/blockdev.c +++ b/blockdev.c @@ -XXX,XX +XXX,XX @@ void qmp_block_stream(bool has_job_id, const char *job_id, const char *device, BlockDriverState *base_bs = NULL; AioContext *aio_context; Error *local_err = NULL; - const char *base_name = NULL; int job_flags = JOB_DEFAULT; if (!has_on_error) { @@ -XXX,XX +XXX,XX @@ void qmp_block_stream(bool has_job_id, const char *job_id, const char *device, goto out; } assert(bdrv_get_aio_context(base_bs) == aio_context); - base_name = base; } if (has_base_node) { @@ -XXX,XX +XXX,XX @@ void qmp_block_stream(bool has_job_id, const char *job_id, const char *device, } assert(bdrv_get_aio_context(base_bs) == aio_context); bdrv_refresh_filename(base_bs); - base_name = base_bs->filename; } /* Check for op blockers in the whole chain between bs and base */ @@ -XXX,XX +XXX,XX @@ void qmp_block_stream(bool has_job_id, const char *job_id, const char *device, goto out; } - /* backing_file string overrides base bs filename */ - base_name = has_backing_file ? backing_file : base_name; - if (has_auto_finalize && !auto_finalize) { job_flags |= JOB_MANUAL_FINALIZE; } @@ -XXX,XX +XXX,XX @@ void qmp_block_stream(bool has_job_id, const char *job_id, const char *device, job_flags |= JOB_MANUAL_DISMISS; } - stream_start(has_job_id ? job_id : NULL, bs, base_bs, base_name, + stream_start(has_job_id ? job_id : NULL, bs, base_bs, backing_file, job_flags, has_speed ? speed : 0, on_error, filter_node_name, &local_err); if (local_err) { -- 2.29.2 From: Vladimir Sementsov-Ogievskiy <vsementsov@virtuozzo.com> The code already don't freeze base node and we try to make it prepared for the situation when base node is changed during the operation. In other words, block-stream doesn't own base node. Let's introduce a new interface which should replace the current one, which will in better relations with the code. Specifying bottom node instead of base, and requiring it to be non-filter gives us the following benefits: - drop difference between above_base and base_overlay, which will be renamed to just bottom, when old interface dropped - clean way to work with parallel streams/commits on the same backing chain, which otherwise become a problem when we introduce a filter for stream job - cleaner interface. Nobody will surprised the fact that base node may disappear during block-stream, when there is no word about "base" in the interface. Signed-off-by: Vladimir Sementsov-Ogievskiy <vsementsov@virtuozzo.com> Message-Id: <20201216061703.70908-11-vsementsov@virtuozzo.com> Reviewed-by: Max Reitz <mreitz@redhat.com> Signed-off-by: Max Reitz <mreitz@redhat.com> --- qapi/block-core.json | 12 ++++--- include/block/block_int.h | 1 + block/monitor/block-hmp-cmds.c | 3 +- block/stream.c | 50 +++++++++++++++++++--------- blockdev.c | 59 ++++++++++++++++++++++++++++------ 5 files changed, 94 insertions(+), 31 deletions(-) diff --git a/qapi/block-core.json b/qapi/block-core.json index XXXXXXX..XXXXXXX 100644 --- a/qapi/block-core.json +++ b/qapi/block-core.json @@ -XXX,XX +XXX,XX @@ # @device: the device or node name of the top image # # @base: the common backing file name. -# It cannot be set if @base-node is also set. +# It cannot be set if @base-node or @bottom is also set. # # @base-node: the node name of the backing file. -# It cannot be set if @base is also set. (Since 2.8) +# It cannot be set if @base or @bottom is also set. (Since 2.8) +# +# @bottom: the last node in the chain that should be streamed into +# top. It cannot be set if @base or @base-node is also set. +# It cannot be filter node. (Since 6.0) # # @backing-file: The backing file string to write into the top # image. This filename is not validated. @@ -XXX,XX +XXX,XX @@ ## { 'command': 'block-stream', 'data': { '*job-id': 'str', 'device': 'str', '*base': 'str', - '*base-node': 'str', '*backing-file': 'str', '*speed': 'int', - '*on-error': 'BlockdevOnError', + '*base-node': 'str', '*backing-file': 'str', '*bottom': 'str', + '*speed': 'int', '*on-error': 'BlockdevOnError', '*filter-node-name': 'str', '*auto-finalize': 'bool', '*auto-dismiss': 'bool' } } diff --git a/include/block/block_int.h b/include/block/block_int.h index XXXXXXX..XXXXXXX 100644 --- a/include/block/block_int.h +++ b/include/block/block_int.h @@ -XXX,XX +XXX,XX @@ int is_windows_drive(const char *filename); */ void stream_start(const char *job_id, BlockDriverState *bs, BlockDriverState *base, const char *backing_file_str, + BlockDriverState *bottom, int creation_flags, int64_t speed, BlockdevOnError on_error, const char *filter_node_name, diff --git a/block/monitor/block-hmp-cmds.c b/block/monitor/block-hmp-cmds.c index XXXXXXX..XXXXXXX 100644 --- a/block/monitor/block-hmp-cmds.c +++ b/block/monitor/block-hmp-cmds.c @@ -XXX,XX +XXX,XX @@ void hmp_block_stream(Monitor *mon, const QDict *qdict) int64_t speed = qdict_get_try_int(qdict, "speed", 0); qmp_block_stream(true, device, device, base != NULL, base, false, NULL, - false, NULL, qdict_haskey(qdict, "speed"), speed, true, + false, NULL, false, NULL, + qdict_haskey(qdict, "speed"), speed, true, BLOCKDEV_ON_ERROR_REPORT, false, NULL, false, false, false, false, &error); diff --git a/block/stream.c b/block/stream.c index XXXXXXX..XXXXXXX 100644 --- a/block/stream.c +++ b/block/stream.c @@ -XXX,XX +XXX,XX @@ static const BlockJobDriver stream_job_driver = { void stream_start(const char *job_id, BlockDriverState *bs, BlockDriverState *base, const char *backing_file_str, + BlockDriverState *bottom, int creation_flags, int64_t speed, BlockdevOnError on_error, const char *filter_node_name, @@ -XXX,XX +XXX,XX @@ void stream_start(const char *job_id, BlockDriverState *bs, BlockDriverState *iter; bool bs_read_only; int basic_flags = BLK_PERM_CONSISTENT_READ | BLK_PERM_WRITE_UNCHANGED; - BlockDriverState *base_overlay = bdrv_find_overlay(bs, base); + BlockDriverState *base_overlay; BlockDriverState *above_base; - if (!base_overlay) { - error_setg(errp, "'%s' is not in the backing chain of '%s'", - base->node_name, bs->node_name); - return; - } + assert(!(base && bottom)); + assert(!(backing_file_str && bottom)); + + if (bottom) { + /* + * New simple interface. The code is written in terms of old interface + * with @base parameter (still, it doesn't freeze link to base, so in + * this mean old code is correct for new interface). So, for now, just + * emulate base_overlay and above_base. Still, when old interface + * finally removed, we should refactor code to use only "bottom", but + * not "*base*" things. + */ + assert(!bottom->drv->is_filter); + base_overlay = above_base = bottom; + } else { + base_overlay = bdrv_find_overlay(bs, base); + if (!base_overlay) { + error_setg(errp, "'%s' is not in the backing chain of '%s'", + base->node_name, bs->node_name); + return; + } - /* - * Find the node directly above @base. @base_overlay is a COW overlay, so - * it must have a bdrv_cow_child(), but it is the immediate overlay of - * @base, so between the two there can only be filters. - */ - above_base = base_overlay; - if (bdrv_cow_bs(above_base) != base) { - above_base = bdrv_cow_bs(above_base); - while (bdrv_filter_bs(above_base) != base) { - above_base = bdrv_filter_bs(above_base); + /* + * Find the node directly above @base. @base_overlay is a COW overlay, + * so it must have a bdrv_cow_child(), but it is the immediate overlay + * of @base, so between the two there can only be filters. + */ + above_base = base_overlay; + if (bdrv_cow_bs(above_base) != base) { + above_base = bdrv_cow_bs(above_base); + while (bdrv_filter_bs(above_base) != base) { + above_base = bdrv_filter_bs(above_base); + } } } diff --git a/blockdev.c b/blockdev.c index XXXXXXX..XXXXXXX 100644 --- a/blockdev.c +++ b/blockdev.c @@ -XXX,XX +XXX,XX @@ void qmp_block_stream(bool has_job_id, const char *job_id, const char *device, bool has_base, const char *base, bool has_base_node, const char *base_node, bool has_backing_file, const char *backing_file, + bool has_bottom, const char *bottom, bool has_speed, int64_t speed, bool has_on_error, BlockdevOnError on_error, bool has_filter_node_name, const char *filter_node_name, @@ -XXX,XX +XXX,XX @@ void qmp_block_stream(bool has_job_id, const char *job_id, const char *device, bool has_auto_dismiss, bool auto_dismiss, Error **errp) { - BlockDriverState *bs, *iter; + BlockDriverState *bs, *iter, *iter_end; BlockDriverState *base_bs = NULL; + BlockDriverState *bottom_bs = NULL; AioContext *aio_context; Error *local_err = NULL; int job_flags = JOB_DEFAULT; + if (has_base && has_base_node) { + error_setg(errp, "'base' and 'base-node' cannot be specified " + "at the same time"); + return; + } + + if (has_base && has_bottom) { + error_setg(errp, "'base' and 'bottom' cannot be specified " + "at the same time"); + return; + } + + if (has_bottom && has_base_node) { + error_setg(errp, "'bottom' and 'base-node' cannot be specified " + "at the same time"); + return; + } + if (!has_on_error) { on_error = BLOCKDEV_ON_ERROR_REPORT; } @@ -XXX,XX +XXX,XX @@ void qmp_block_stream(bool has_job_id, const char *job_id, const char *device, aio_context = bdrv_get_aio_context(bs); aio_context_acquire(aio_context); - if (has_base && has_base_node) { - error_setg(errp, "'base' and 'base-node' cannot be specified " - "at the same time"); - goto out; - } - if (has_base) { base_bs = bdrv_find_backing_image(bs, base); if (base_bs == NULL) { @@ -XXX,XX +XXX,XX @@ void qmp_block_stream(bool has_job_id, const char *job_id, const char *device, bdrv_refresh_filename(base_bs); } - /* Check for op blockers in the whole chain between bs and base */ - for (iter = bs; iter && iter != base_bs; + if (has_bottom) { + bottom_bs = bdrv_lookup_bs(NULL, bottom, errp); + if (!bottom_bs) { + goto out; + } + if (!bottom_bs->drv) { + error_setg(errp, "Node '%s' is not open", bottom); + goto out; + } + if (bottom_bs->drv->is_filter) { + error_setg(errp, "Node '%s' is a filter, use a non-filter node " + "as 'bottom'", bottom); + goto out; + } + if (!bdrv_chain_contains(bs, bottom_bs)) { + error_setg(errp, "Node '%s' is not in a chain starting from '%s'", + bottom, device); + goto out; + } + assert(bdrv_get_aio_context(bottom_bs) == aio_context); + } + + /* + * Check for op blockers in the whole chain between bs and base (or bottom) + */ + iter_end = has_bottom ? bdrv_filter_or_cow_bs(bottom_bs) : base_bs; + for (iter = bs; iter && iter != iter_end; iter = bdrv_filter_or_cow_bs(iter)) { if (bdrv_op_is_blocked(iter, BLOCK_OP_TYPE_STREAM, errp)) { @@ -XXX,XX +XXX,XX @@ void qmp_block_stream(bool has_job_id, const char *job_id, const char *device, } stream_start(has_job_id ? job_id : NULL, bs, base_bs, backing_file, - job_flags, has_speed ? speed : 0, on_error, + bottom_bs, job_flags, has_speed ? speed : 0, on_error, filter_node_name, &local_err); if (local_err) { error_propagate(errp, local_err); -- 2.29.2 From: Vladimir Sementsov-Ogievskiy <vsementsov@virtuozzo.com> test_stream_parallel run parallel stream jobs, intersecting so that top of one is base of another. It's OK now, but it would be a problem if insert the filter, as one job will want to use another job's filter as above_base node. Correct thing to do is move to new interface: "bottom" argument instead of base. This guarantees that jobs don't intersect by their actions. Signed-off-by: Vladimir Sementsov-Ogievskiy <vsementsov@virtuozzo.com> Reviewed-by: Max Reitz <mreitz@redhat.com> Message-Id: <20201216061703.70908-12-vsementsov@virtuozzo.com> Signed-off-by: Max Reitz <mreitz@redhat.com> --- tests/qemu-iotests/030 | 4 +++- 1 file changed, 3 insertions(+), 1 deletion(-) diff --git a/tests/qemu-iotests/030 b/tests/qemu-iotests/030 index XXXXXXX..XXXXXXX 100755 --- a/tests/qemu-iotests/030 +++ b/tests/qemu-iotests/030 @@ -XXX,XX +XXX,XX @@ class TestParallelOps(iotests.QMPTestCase): node_name = 'node%d' % i job_id = 'stream-%s' % node_name pending_jobs.append(job_id) - result = self.vm.qmp('block-stream', device=node_name, job_id=job_id, base=self.imgs[i-2], speed=1024) + result = self.vm.qmp('block-stream', device=node_name, + job_id=job_id, bottom=f'node{i-1}', + speed=1024) self.assert_qmp(result, 'return', {}) for job in pending_jobs: -- 2.29.2 From: Vladimir Sementsov-Ogievskiy <vsementsov@virtuozzo.com> Add a direct link to target bs for convenience and to simplify following commit which will insert COR filter above target bs. This is a part of original commit written by Andrey. Signed-off-by: Vladimir Sementsov-Ogievskiy <vsementsov@virtuozzo.com> Reviewed-by: Max Reitz <mreitz@redhat.com> Message-Id: <20201216061703.70908-13-vsementsov@virtuozzo.com> Signed-off-by: Max Reitz <mreitz@redhat.com> --- block/stream.c | 23 ++++++++++------------- 1 file changed, 10 insertions(+), 13 deletions(-) diff --git a/block/stream.c b/block/stream.c index XXXXXXX..XXXXXXX 100644 --- a/block/stream.c +++ b/block/stream.c @@ -XXX,XX +XXX,XX @@ typedef struct StreamBlockJob { BlockJob common; BlockDriverState *base_overlay; /* COW overlay (stream from this) */ BlockDriverState *above_base; /* Node directly above the base */ + BlockDriverState *target_bs; BlockdevOnError on_error; char *backing_file_str; bool bs_read_only; @@ -XXX,XX +XXX,XX @@ static void stream_abort(Job *job) StreamBlockJob *s = container_of(job, StreamBlockJob, common.job); if (s->chain_frozen) { - BlockJob *bjob = &s->common; - bdrv_unfreeze_backing_chain(blk_bs(bjob->blk), s->above_base); + bdrv_unfreeze_backing_chain(s->target_bs, s->above_base); } } static int stream_prepare(Job *job) { StreamBlockJob *s = container_of(job, StreamBlockJob, common.job); - BlockJob *bjob = &s->common; - BlockDriverState *bs = blk_bs(bjob->blk); - BlockDriverState *unfiltered_bs = bdrv_skip_filters(bs); + BlockDriverState *unfiltered_bs = bdrv_skip_filters(s->target_bs); BlockDriverState *base = bdrv_filter_or_cow_bs(s->above_base); BlockDriverState *unfiltered_base = bdrv_skip_filters(base); Error *local_err = NULL; int ret = 0; - bdrv_unfreeze_backing_chain(bs, s->above_base); + bdrv_unfreeze_backing_chain(s->target_bs, s->above_base); s->chain_frozen = false; if (bdrv_cow_child(unfiltered_bs)) { @@ -XXX,XX +XXX,XX @@ static void stream_clean(Job *job) { StreamBlockJob *s = container_of(job, StreamBlockJob, common.job); BlockJob *bjob = &s->common; - BlockDriverState *bs = blk_bs(bjob->blk); /* Reopen the image back in read-only mode if necessary */ if (s->bs_read_only) { /* Give up write permissions before making it read-only */ blk_set_perm(bjob->blk, 0, BLK_PERM_ALL, &error_abort); - bdrv_reopen_set_read_only(bs, true, NULL); + bdrv_reopen_set_read_only(s->target_bs, true, NULL); } g_free(s->backing_file_str); @@ -XXX,XX +XXX,XX @@ static int coroutine_fn stream_run(Job *job, Error **errp) { StreamBlockJob *s = container_of(job, StreamBlockJob, common.job); BlockBackend *blk = s->common.blk; - BlockDriverState *bs = blk_bs(blk); - BlockDriverState *unfiltered_bs = bdrv_skip_filters(bs); + BlockDriverState *unfiltered_bs = bdrv_skip_filters(s->target_bs); bool enable_cor = !bdrv_cow_child(s->base_overlay); int64_t len; int64_t offset = 0; @@ -XXX,XX +XXX,XX @@ static int coroutine_fn stream_run(Job *job, Error **errp) return 0; } - len = bdrv_getlength(bs); + len = bdrv_getlength(s->target_bs); if (len < 0) { return len; } @@ -XXX,XX +XXX,XX @@ static int coroutine_fn stream_run(Job *job, Error **errp) * account. */ if (enable_cor) { - bdrv_enable_copy_on_read(bs); + bdrv_enable_copy_on_read(s->target_bs); } for ( ; offset < len; offset += n) { @@ -XXX,XX +XXX,XX @@ static int coroutine_fn stream_run(Job *job, Error **errp) } if (enable_cor) { - bdrv_disable_copy_on_read(bs); + bdrv_disable_copy_on_read(s->target_bs); } /* Do not remove the backing file if an error was there but ignored. */ @@ -XXX,XX +XXX,XX @@ void stream_start(const char *job_id, BlockDriverState *bs, s->base_overlay = base_overlay; s->above_base = above_base; s->backing_file_str = g_strdup(backing_file_str); + s->target_bs = bs; s->bs_read_only = bs_read_only; s->chain_frozen = true; -- 2.29.2 From: Andrey Shinkevich <andrey.shinkevich@virtuozzo.com> This patch completes the series with the COR-filter applied to block-stream operations. Adding the filter makes it possible in future implement discarding copied regions in backing files during the block-stream job, to reduce the disk overuse (we need control on permissions). Also, the filter now is smart enough to do copy-on-read with specified base, so we have benefit on guest reads even when doing block-stream of the part of the backing chain. Several iotests are slightly modified due to filter insertion. Signed-off-by: Andrey Shinkevich <andrey.shinkevich@virtuozzo.com> Signed-off-by: Vladimir Sementsov-Ogievskiy <vsementsov@virtuozzo.com> Message-Id: <20201216061703.70908-14-vsementsov@virtuozzo.com> Reviewed-by: Max Reitz <mreitz@redhat.com> Signed-off-by: Max Reitz <mreitz@redhat.com> --- block/stream.c | 105 ++++++++++++++++++++++--------------- tests/qemu-iotests/030 | 8 +-- tests/qemu-iotests/141.out | 2 +- tests/qemu-iotests/245 | 20 ++++--- 4 files changed, 80 insertions(+), 55 deletions(-) diff --git a/block/stream.c b/block/stream.c index XXXXXXX..XXXXXXX 100644 --- a/block/stream.c +++ b/block/stream.c @@ -XXX,XX +XXX,XX @@ #include "block/blockjob_int.h" #include "qapi/error.h" #include "qapi/qmp/qerror.h" +#include "qapi/qmp/qdict.h" #include "qemu/ratelimit.h" #include "sysemu/block-backend.h" +#include "block/copy-on-read.h" enum { /* @@ -XXX,XX +XXX,XX @@ typedef struct StreamBlockJob { BlockJob common; BlockDriverState *base_overlay; /* COW overlay (stream from this) */ BlockDriverState *above_base; /* Node directly above the base */ + BlockDriverState *cor_filter_bs; BlockDriverState *target_bs; BlockdevOnError on_error; char *backing_file_str; bool bs_read_only; - bool chain_frozen; } StreamBlockJob; static int coroutine_fn stream_populate(BlockBackend *blk, @@ -XXX,XX +XXX,XX @@ static int coroutine_fn stream_populate(BlockBackend *blk, { assert(bytes < SIZE_MAX); - return blk_co_preadv(blk, offset, bytes, NULL, - BDRV_REQ_COPY_ON_READ | BDRV_REQ_PREFETCH); -} - -static void stream_abort(Job *job) -{ - StreamBlockJob *s = container_of(job, StreamBlockJob, common.job); - - if (s->chain_frozen) { - bdrv_unfreeze_backing_chain(s->target_bs, s->above_base); - } + return blk_co_preadv(blk, offset, bytes, NULL, BDRV_REQ_PREFETCH); } static int stream_prepare(Job *job) @@ -XXX,XX +XXX,XX @@ static int stream_prepare(Job *job) Error *local_err = NULL; int ret = 0; - bdrv_unfreeze_backing_chain(s->target_bs, s->above_base); - s->chain_frozen = false; + /* We should drop filter at this point, as filter hold the backing chain */ + bdrv_cor_filter_drop(s->cor_filter_bs); + s->cor_filter_bs = NULL; if (bdrv_cow_child(unfiltered_bs)) { const char *base_id = NULL, *base_fmt = NULL; @@ -XXX,XX +XXX,XX @@ static void stream_clean(Job *job) StreamBlockJob *s = container_of(job, StreamBlockJob, common.job); BlockJob *bjob = &s->common; + if (s->cor_filter_bs) { + bdrv_cor_filter_drop(s->cor_filter_bs); + s->cor_filter_bs = NULL; + } + /* Reopen the image back in read-only mode if necessary */ if (s->bs_read_only) { /* Give up write permissions before making it read-only */ @@ -XXX,XX +XXX,XX @@ static int coroutine_fn stream_run(Job *job, Error **errp) StreamBlockJob *s = container_of(job, StreamBlockJob, common.job); BlockBackend *blk = s->common.blk; BlockDriverState *unfiltered_bs = bdrv_skip_filters(s->target_bs); - bool enable_cor = !bdrv_cow_child(s->base_overlay); int64_t len; int64_t offset = 0; uint64_t delay_ns = 0; @@ -XXX,XX +XXX,XX @@ static int coroutine_fn stream_run(Job *job, Error **errp) } job_progress_set_remaining(&s->common.job, len); - /* Turn on copy-on-read for the whole block device so that guest read - * requests help us make progress. Only do this when copying the entire - * backing chain since the copy-on-read operation does not take base into - * account. - */ - if (enable_cor) { - bdrv_enable_copy_on_read(s->target_bs); - } - for ( ; offset < len; offset += n) { bool copy; int ret; @@ -XXX,XX +XXX,XX @@ static int coroutine_fn stream_run(Job *job, Error **errp) } } - if (enable_cor) { - bdrv_disable_copy_on_read(s->target_bs); - } - /* Do not remove the backing file if an error was there but ignored. */ return error; } @@ -XXX,XX +XXX,XX @@ static const BlockJobDriver stream_job_driver = { .free = block_job_free, .run = stream_run, .prepare = stream_prepare, - .abort = stream_abort, .clean = stream_clean, .user_resume = block_job_user_resume, }, @@ -XXX,XX +XXX,XX @@ void stream_start(const char *job_id, BlockDriverState *bs, bool bs_read_only; int basic_flags = BLK_PERM_CONSISTENT_READ | BLK_PERM_WRITE_UNCHANGED; BlockDriverState *base_overlay; + BlockDriverState *cor_filter_bs = NULL; BlockDriverState *above_base; + QDict *opts; assert(!(base && bottom)); assert(!(backing_file_str && bottom)); @@ -XXX,XX +XXX,XX @@ void stream_start(const char *job_id, BlockDriverState *bs, } } - if (bdrv_freeze_backing_chain(bs, above_base, errp) < 0) { - return; - } - /* Make sure that the image is opened in read-write mode */ bs_read_only = bdrv_is_read_only(bs); if (bs_read_only) { - if (bdrv_reopen_set_read_only(bs, false, errp) != 0) { - bs_read_only = false; - goto fail; + int ret; + /* Hold the chain during reopen */ + if (bdrv_freeze_backing_chain(bs, above_base, errp) < 0) { + return; + } + + ret = bdrv_reopen_set_read_only(bs, false, errp); + + /* failure, or cor-filter will hold the chain */ + bdrv_unfreeze_backing_chain(bs, above_base); + + if (ret < 0) { + return; } } - /* Prevent concurrent jobs trying to modify the graph structure here, we - * already have our own plans. Also don't allow resize as the image size is - * queried only at the job start and then cached. */ - s = block_job_create(job_id, &stream_job_driver, NULL, bs, - basic_flags | BLK_PERM_GRAPH_MOD, + opts = qdict_new(); + + qdict_put_str(opts, "driver", "copy-on-read"); + qdict_put_str(opts, "file", bdrv_get_node_name(bs)); + /* Pass the base_overlay node name as 'bottom' to COR driver */ + qdict_put_str(opts, "bottom", base_overlay->node_name); + if (filter_node_name) { + qdict_put_str(opts, "node-name", filter_node_name); + } + + cor_filter_bs = bdrv_insert_node(bs, opts, BDRV_O_RDWR, errp); + if (!cor_filter_bs) { + goto fail; + } + + if (!filter_node_name) { + cor_filter_bs->implicit = true; + } + + s = block_job_create(job_id, &stream_job_driver, NULL, cor_filter_bs, + BLK_PERM_CONSISTENT_READ, basic_flags | BLK_PERM_WRITE, speed, creation_flags, NULL, NULL, errp); if (!s) { goto fail; } + /* + * Prevent concurrent jobs trying to modify the graph structure here, we + * already have our own plans. Also don't allow resize as the image size is + * queried only at the job start and then cached. + */ + if (block_job_add_bdrv(&s->common, "active node", bs, 0, + basic_flags | BLK_PERM_WRITE, &error_abort)) { + goto fail; + } + /* Block all intermediate nodes between bs and base, because they will * disappear from the chain after this operation. The streaming job reads * every block only once, assuming that it doesn't change, so forbid writes @@ -XXX,XX +XXX,XX @@ void stream_start(const char *job_id, BlockDriverState *bs, s->base_overlay = base_overlay; s->above_base = above_base; s->backing_file_str = g_strdup(backing_file_str); + s->cor_filter_bs = cor_filter_bs; s->target_bs = bs; s->bs_read_only = bs_read_only; - s->chain_frozen = true; s->on_error = on_error; trace_stream_start(bs, base, s); @@ -XXX,XX +XXX,XX @@ void stream_start(const char *job_id, BlockDriverState *bs, return; fail: + if (cor_filter_bs) { + bdrv_cor_filter_drop(cor_filter_bs); + } if (bs_read_only) { bdrv_reopen_set_read_only(bs, true, NULL); } - bdrv_unfreeze_backing_chain(bs, above_base); } diff --git a/tests/qemu-iotests/030 b/tests/qemu-iotests/030 index XXXXXXX..XXXXXXX 100755 --- a/tests/qemu-iotests/030 +++ b/tests/qemu-iotests/030 @@ -XXX,XX +XXX,XX @@ class TestParallelOps(iotests.QMPTestCase): self.assert_no_active_block_jobs() # Set a speed limit to make sure that this job blocks the rest - result = self.vm.qmp('block-stream', device='node4', job_id='stream-node4', base=self.imgs[1], speed=1024*1024) + result = self.vm.qmp('block-stream', device='node4', + job_id='stream-node4', base=self.imgs[1], + filter_node_name='stream-filter', speed=1024*1024) self.assert_qmp(result, 'return', {}) result = self.vm.qmp('block-stream', device='node5', job_id='stream-node5', base=self.imgs[2]) self.assert_qmp(result, 'error/desc', - "Node 'node4' is busy: block device is in use by block job: stream") + "Node 'stream-filter' is busy: block device is in use by block job: stream") result = self.vm.qmp('block-stream', device='node3', job_id='stream-node3', base=self.imgs[2]) self.assert_qmp(result, 'error/desc', @@ -XXX,XX +XXX,XX @@ class TestParallelOps(iotests.QMPTestCase): # block-commit should also fail if it touches nodes used by the stream job result = self.vm.qmp('block-commit', device='drive0', base=self.imgs[4], job_id='commit-node4') self.assert_qmp(result, 'error/desc', - "Node 'node4' is busy: block device is in use by block job: stream") + "Node 'stream-filter' is busy: block device is in use by block job: stream") result = self.vm.qmp('block-commit', device='drive0', base=self.imgs[1], top=self.imgs[3], job_id='commit-node1') self.assert_qmp(result, 'error/desc', diff --git a/tests/qemu-iotests/141.out b/tests/qemu-iotests/141.out index XXXXXXX..XXXXXXX 100644 --- a/tests/qemu-iotests/141.out +++ b/tests/qemu-iotests/141.out @@ -XXX,XX +XXX,XX @@ wrote 1048576/1048576 bytes at offset 0 {"timestamp": {"seconds": TIMESTAMP, "microseconds": TIMESTAMP}, "event": "JOB_STATUS_CHANGE", "data": {"status": "running", "id": "job0"}} {'execute': 'blockdev-del', 'arguments': {'node-name': 'drv0'}} -{"error": {"class": "GenericError", "desc": "Node drv0 is in use"}} +{"error": {"class": "GenericError", "desc": "Node 'drv0' is busy: block device is in use by block job: stream"}} {'execute': 'block-job-cancel', 'arguments': {'device': 'job0'}} {"return": {}} diff --git a/tests/qemu-iotests/245 b/tests/qemu-iotests/245 index XXXXXXX..XXXXXXX 100755 --- a/tests/qemu-iotests/245 +++ b/tests/qemu-iotests/245 @@ -XXX,XX +XXX,XX @@ class TestBlockdevReopen(iotests.QMPTestCase): # hd1 <- hd0 result = self.vm.qmp('block-stream', conv_keys = True, job_id = 'stream0', - device = 'hd1', auto_finalize = False) + device = 'hd1', filter_node_name='cor', + auto_finalize = False) self.assert_qmp(result, 'return', {}) - # We can't reopen with the original options because that would - # make hd1 read-only and block-stream requires it to be read-write - # (Which error message appears depends on whether the stream job is - # already done with copying at this point.) + # We can't reopen with the original options because there is a filter + # inserted by stream job above hd1. self.reopen(opts, {}, - ["Can't set node 'hd1' to r/o with copy-on-read enabled", - "Cannot make block node read-only, there is a writer on it"]) + "Cannot change the option 'backing.backing.file.node-name'") + + # We can't reopen hd1 to read-only, as block-stream requires it to be + # read-write + self.reopen(opts['backing'], {'read-only': True}, + "Cannot make block node read-only, there is a writer on it") # We can't remove hd2 while the stream job is ongoing opts['backing']['backing'] = None - self.reopen(opts, {'backing.read-only': False}, "Cannot change 'backing' link from 'hd1' to 'hd2'") + self.reopen(opts['backing'], {'read-only': False}, + "Cannot change 'backing' link from 'hd1' to 'hd2'") # We can detach hd1 from hd0 because it doesn't affect the stream job opts['backing'] = None -- 2.29.2 There are a couple of environment variables that we fetch with os.environ.get() without supplying a default. Clearly they are required and expected to be set by the ./check script (as evidenced by execute_setup_common(), which checks for test_dir and qemu_default_machine to be set, and aborts if they are not). Using .get() this way has the disadvantage of returning an Optional[str] type, which mypy will complain about when tests just assume these values to be str. Use [] instead, which raises a KeyError for environment variables that are not set. When this exception is raised, catch it and move the abort code from execute_setup_common() there. Drop the 'assert iotests.sock_dir is not None' from iotest 300, because that sort of thing is precisely what this patch wants to prevent. Signed-off-by: Max Reitz <mreitz@redhat.com> Reviewed-by: Vladimir Sementsov-Ogievskiy <vsementsov@virtuozzo.com> Reviewed-by: Willian Rampazzo <willianr@redhat.com> Message-Id: <20210118105720.14824-2-mreitz@redhat.com> --- tests/qemu-iotests/300 | 1 - tests/qemu-iotests/iotests.py | 26 +++++++++++++------------- 2 files changed, 13 insertions(+), 14 deletions(-) diff --git a/tests/qemu-iotests/300 b/tests/qemu-iotests/300 index XXXXXXX..XXXXXXX 100755 --- a/tests/qemu-iotests/300 +++ b/tests/qemu-iotests/300 @@ -XXX,XX +XXX,XX @@ import qemu BlockBitmapMapping = List[Dict[str, Union[str, List[Dict[str, str]]]]] -assert iotests.sock_dir is not None mig_sock = os.path.join(iotests.sock_dir, 'mig_sock') diff --git a/tests/qemu-iotests/iotests.py b/tests/qemu-iotests/iotests.py index XXXXXXX..XXXXXXX 100644 --- a/tests/qemu-iotests/iotests.py +++ b/tests/qemu-iotests/iotests.py @@ -XXX,XX +XXX,XX @@ qemu_opts = os.environ.get('QEMU_OPTIONS', '').strip().split(' ') imgfmt = os.environ.get('IMGFMT', 'raw') imgproto = os.environ.get('IMGPROTO', 'file') -test_dir = os.environ.get('TEST_DIR') -sock_dir = os.environ.get('SOCK_DIR') output_dir = os.environ.get('OUTPUT_DIR', '.') -cachemode = os.environ.get('CACHEMODE') -aiomode = os.environ.get('AIOMODE') -qemu_default_machine = os.environ.get('QEMU_DEFAULT_MACHINE') + +try: + test_dir = os.environ['TEST_DIR'] + sock_dir = os.environ['SOCK_DIR'] + cachemode = os.environ['CACHEMODE'] + aiomode = os.environ['AIOMODE'] + qemu_default_machine = os.environ['QEMU_DEFAULT_MACHINE'] +except KeyError: + # We are using these variables as proxies to indicate that we're + # not being run via "check". There may be other things set up by + # "check" that individual test cases rely on. + sys.stderr.write('Please run this test via the "check" script\n') + sys.exit(os.EX_USAGE) socket_scm_helper = os.environ.get('SOCKET_SCM_HELPER', 'socket_scm_helper') @@ -XXX,XX +XXX,XX @@ def execute_setup_common(supported_fmts: Sequence[str] = (), """ # Note: Python 3.6 and pylint do not like 'Collection' so use 'Sequence'. - # We are using TEST_DIR and QEMU_DEFAULT_MACHINE as proxies to - # indicate that we're not being run via "check". There may be - # other things set up by "check" that individual test cases rely - # on. - if test_dir is None or qemu_default_machine is None: - sys.stderr.write('Please run this test via the "check" script\n') - sys.exit(os.EX_USAGE) - debug = '-d' in sys.argv if debug: sys.argv.remove('-d') -- 2.29.2 Instead of checking iotests.py only, check all Python files in the qemu-iotests/ directory. Of course, most of them do not pass, so there is an extensive skip list for now. (The only files that do pass are 209, 254, 283, and iotests.py.) (Alternatively, we could have the opposite, i.e. an explicit list of files that we do want to check, but I think it is better to check files by default.) Unless started in debug mode (./check -d), the output has no information on which files are tested, so we will not have a problem e.g. with backports, where some files may be missing when compared to upstream. Besides the technical rewrite, some more things are changed: - For the pylint invocation, PYTHONPATH is adjusted. This mirrors setting MYPYPATH for mypy. - Also, MYPYPATH is now derived from PYTHONPATH, so that we include paths set by the environment. Maybe at some point we want to let the check script add '../../python/' to PYTHONPATH so that iotests.py does not need to do that. - Passing --notes=FIXME,XXX to pylint suppresses warnings for TODO comments. TODO is fine, we do not need 297 to complain about such comments. - The "Success" line from mypy's output is suppressed, because (A) it does not add useful information, and (B) it would leak information about the files having been tested to the reference output, which we decidedly do not want. Suggested-by: Vladimir Sementsov-Ogievskiy <vsementsov@virtuozzo.com> Signed-off-by: Max Reitz <mreitz@redhat.com> Message-Id: <20210118105720.14824-3-mreitz@redhat.com> Reviewed-by: Vladimir Sementsov-Ogievskiy <vsementsov@virtuozzo.com> --- tests/qemu-iotests/297 | 112 +++++++++++++++++++++++++++++-------- tests/qemu-iotests/297.out | 5 +- 2 files changed, 92 insertions(+), 25 deletions(-) diff --git a/tests/qemu-iotests/297 b/tests/qemu-iotests/297 index XXXXXXX..XXXXXXX 100755 --- a/tests/qemu-iotests/297 +++ b/tests/qemu-iotests/297 @@ -XXX,XX +XXX,XX @@ -#!/usr/bin/env bash +#!/usr/bin/env python3 # group: meta # # Copyright (C) 2020 Red Hat, Inc. @@ -XXX,XX +XXX,XX @@ # You should have received a copy of the GNU General Public License # along with this program. If not, see <http://www.gnu.org/licenses/>. -seq=$(basename $0) -echo "QA output created by $seq" +import os +import re +import shutil +import subprocess +import sys -status=1 # failure is the default! +import iotests -# get standard environment -. ./common.rc -if ! type -p "pylint-3" > /dev/null; then - _notrun "pylint-3 not found" -fi -if ! type -p "mypy" > /dev/null; then - _notrun "mypy not found" -fi +# TODO: Empty this list! +SKIP_FILES = ( + '030', '040', '041', '044', '045', '055', '056', '057', '065', '093', + '096', '118', '124', '129', '132', '136', '139', '147', '148', '149', + '151', '152', '155', '163', '165', '169', '194', '196', '199', '202', + '203', '205', '206', '207', '208', '210', '211', '212', '213', '216', + '218', '219', '222', '224', '228', '234', '235', '236', '237', '238', + '240', '242', '245', '246', '248', '255', '256', '257', '258', '260', + '262', '264', '266', '274', '277', '280', '281', '295', '296', '298', + '299', '300', '302', '303', '304', '307', + 'nbd-fault-injector.py', 'qcow2.py', 'qcow2_format.py', 'qed.py' +) -pylint-3 --score=n iotests.py -MYPYPATH=../../python/ mypy --warn-unused-configs --disallow-subclassing-any \ - --disallow-any-generics --disallow-incomplete-defs \ - --disallow-untyped-decorators --no-implicit-optional \ - --warn-redundant-casts --warn-unused-ignores \ - --no-implicit-reexport iotests.py +def is_python_file(filename): + if not os.path.isfile(filename): + return False -# success, all done -echo "*** done" -rm -f $seq.full -status=0 + if filename.endswith('.py'): + return True + + with open(filename) as f: + try: + first_line = f.readline() + return re.match('^#!.*python', first_line) is not None + except UnicodeDecodeError: # Ignore binary files + return False + + +def run_linters(): + files = [filename for filename in (set(os.listdir('.')) - set(SKIP_FILES)) + if is_python_file(filename)] + + iotests.logger.debug('Files to be checked:') + iotests.logger.debug(', '.join(sorted(files))) + + print('=== pylint ===') + sys.stdout.flush() + + # Todo notes are fine, but fixme's or xxx's should probably just be + # fixed (in tests, at least) + env = os.environ.copy() + qemu_module_path = os.path.join(os.path.dirname(__file__), + '..', '..', 'python') + try: + env['PYTHONPATH'] += os.pathsep + qemu_module_path + except KeyError: + env['PYTHONPATH'] = qemu_module_path + subprocess.run(('pylint-3', '--score=n', '--notes=FIXME,XXX', *files), + env=env, check=False) + + print('=== mypy ===') + sys.stdout.flush() + + # We have to call mypy separately for each file. Otherwise, it + # will interpret all given files as belonging together (i.e., they + # may not both define the same classes, etc.; most notably, they + # must not both define the __main__ module). + env['MYPYPATH'] = env['PYTHONPATH'] + for filename in files: + p = subprocess.run(('mypy', + '--warn-unused-configs', + '--disallow-subclassing-any', + '--disallow-any-generics', + '--disallow-incomplete-defs', + '--disallow-untyped-decorators', + '--no-implicit-optional', + '--warn-redundant-casts', + '--warn-unused-ignores', + '--no-implicit-reexport', + filename), + env=env, + check=False, + stdout=subprocess.PIPE, + stderr=subprocess.STDOUT, + universal_newlines=True) + + if p.returncode != 0: + print(p.stdout) + + +for linter in ('pylint-3', 'mypy'): + if shutil.which(linter) is None: + iotests.notrun(f'{linter} not found') + +iotests.script_main(run_linters) diff --git a/tests/qemu-iotests/297.out b/tests/qemu-iotests/297.out index XXXXXXX..XXXXXXX 100644 --- a/tests/qemu-iotests/297.out +++ b/tests/qemu-iotests/297.out @@ -XXX,XX +XXX,XX @@ -QA output created by 297 -Success: no issues found in 1 source file -*** done +=== pylint === +=== mypy === -- 2.29.2 Signed-off-by: Max Reitz <mreitz@redhat.com> Reviewed-by: Eric Blake <eblake@redhat.com> Reviewed-by: Vladimir Sementsov-Ogievskiy <vsementsov@virtuozzo.com> Reviewed-by: Willian Rampazzo <willianr@redhat.com> Message-Id: <20210118105720.14824-4-mreitz@redhat.com> --- tests/qemu-iotests/124 | 8 +------- tests/qemu-iotests/iotests.py | 11 +++++++---- 2 files changed, 8 insertions(+), 11 deletions(-) diff --git a/tests/qemu-iotests/124 b/tests/qemu-iotests/124 index XXXXXXX..XXXXXXX 100755 --- a/tests/qemu-iotests/124 +++ b/tests/qemu-iotests/124 @@ -XXX,XX +XXX,XX @@ import os import iotests +from iotests import try_remove def io_write_patterns(img, patterns): @@ -XXX,XX +XXX,XX @@ def io_write_patterns(img, patterns): iotests.qemu_io('-c', 'write -P%s %s %s' % pattern, img) -def try_remove(img): - try: - os.remove(img) - except OSError: - pass - - def transaction_action(action, **kwargs): return { 'type': action, diff --git a/tests/qemu-iotests/iotests.py b/tests/qemu-iotests/iotests.py index XXXXXXX..XXXXXXX 100644 --- a/tests/qemu-iotests/iotests.py +++ b/tests/qemu-iotests/iotests.py @@ -XXX,XX +XXX,XX @@ class FilePath: return False +def try_remove(img): + try: + os.remove(img) + except OSError: + pass + def file_path_remover(): for path in reversed(file_path_remover.paths): - try: - os.remove(path) - except OSError: - pass + try_remove(path) def file_path(*names, base_dir=test_dir): -- 2.29.2 Signed-off-by: Max Reitz <mreitz@redhat.com> Reviewed-by: Vladimir Sementsov-Ogievskiy <vsementsov@virtuozzo.com> Reviewed-by: Eric Blake <eblake@redhat.com> Reviewed-by: Willian Rampazzo <willianr@redhat.com> Message-Id: <20210118105720.14824-5-mreitz@redhat.com> --- tests/qemu-iotests/129 | 2 ++ 1 file changed, 2 insertions(+) diff --git a/tests/qemu-iotests/129 b/tests/qemu-iotests/129 index XXXXXXX..XXXXXXX 100755 --- a/tests/qemu-iotests/129 +++ b/tests/qemu-iotests/129 @@ -XXX,XX +XXX,XX @@ class TestStopWithBlockJob(iotests.QMPTestCase): result = self.vm.qmp("block_set_io_throttle", conv_keys=False, **params) self.vm.shutdown() + for img in (self.test_img, self.target_img, self.base_img): + iotests.try_remove(img) def do_test_stop(self, cmd, **args): """Test 'stop' while block job is running on a throttled drive. -- 2.29.2 @busy is false when the job is paused, which happens all the time because that is how jobs yield (e.g. for mirror at least since commit 565ac01f8d3). Back when 129 was added (2015), perhaps there was no better way of checking whether the job was still actually running. Now we have the @status field (as of 58b295ba52c, i.e. 2018), which can give us exactly that information. Signed-off-by: Max Reitz <mreitz@redhat.com> Reviewed-by: Eric Blake <eblake@redhat.com> Reviewed-by: Vladimir Sementsov-Ogievskiy <vsementsov@virtuozzo.com> Reviewed-by: Willian Rampazzo <willianr@redhat.com> Message-Id: <20210118105720.14824-6-mreitz@redhat.com> --- tests/qemu-iotests/129 | 2 +- 1 file changed, 1 insertion(+), 1 deletion(-) diff --git a/tests/qemu-iotests/129 b/tests/qemu-iotests/129 index XXXXXXX..XXXXXXX 100755 --- a/tests/qemu-iotests/129 +++ b/tests/qemu-iotests/129 @@ -XXX,XX +XXX,XX @@ class TestStopWithBlockJob(iotests.QMPTestCase): result = self.vm.qmp("stop") self.assert_qmp(result, 'return', {}) result = self.vm.qmp("query-block-jobs") - self.assert_qmp(result, 'return[0]/busy', True) + self.assert_qmp(result, 'return[0]/status', 'running') self.assert_qmp(result, 'return[0]/ready', False) def test_drive_mirror(self): -- 2.29.2 Throttling on the BB has not affected block jobs in a while, so it is possible that one of the jobs in 129 finishes before the VM is stopped. We can fix that by running the job from a throttle node. Signed-off-by: Max Reitz <mreitz@redhat.com> Reviewed-by: Eric Blake <eblake@redhat.com> Reviewed-by: Vladimir Sementsov-Ogievskiy <vsementsov@virtuozzo.com> Reviewed-by: Willian Rampazzo <willianr@redhat.com> Message-Id: <20210118105720.14824-7-mreitz@redhat.com> --- tests/qemu-iotests/129 | 37 +++++++++++++------------------------ 1 file changed, 13 insertions(+), 24 deletions(-) diff --git a/tests/qemu-iotests/129 b/tests/qemu-iotests/129 index XXXXXXX..XXXXXXX 100755 --- a/tests/qemu-iotests/129 +++ b/tests/qemu-iotests/129 @@ -XXX,XX +XXX,XX @@ class TestStopWithBlockJob(iotests.QMPTestCase): iotests.qemu_img('create', '-f', iotests.imgfmt, self.test_img, "-b", self.base_img, '-F', iotests.imgfmt) iotests.qemu_io('-f', iotests.imgfmt, '-c', 'write -P0x5d 1M 128M', self.test_img) - self.vm = iotests.VM().add_drive(self.test_img) + self.vm = iotests.VM() + self.vm.add_object('throttle-group,id=tg0,x-bps-total=1024') + + source_drive = 'driver=throttle,' \ + 'throttle-group=tg0,' \ + f'file.driver={iotests.imgfmt},' \ + f'file.file.filename={self.test_img}' + + self.vm.add_drive(None, source_drive) self.vm.launch() def tearDown(self): - params = {"device": "drive0", - "bps": 0, - "bps_rd": 0, - "bps_wr": 0, - "iops": 0, - "iops_rd": 0, - "iops_wr": 0, - } - result = self.vm.qmp("block_set_io_throttle", conv_keys=False, - **params) self.vm.shutdown() for img in (self.test_img, self.target_img, self.base_img): iotests.try_remove(img) @@ -XXX,XX +XXX,XX @@ class TestStopWithBlockJob(iotests.QMPTestCase): def do_test_stop(self, cmd, **args): """Test 'stop' while block job is running on a throttled drive. The 'stop' command shouldn't drain the job""" - params = {"device": "drive0", - "bps": 1024, - "bps_rd": 0, - "bps_wr": 0, - "iops": 0, - "iops_rd": 0, - "iops_wr": 0, - } - result = self.vm.qmp("block_set_io_throttle", conv_keys=False, - **params) - self.assert_qmp(result, 'return', {}) result = self.vm.qmp(cmd, **args) self.assert_qmp(result, 'return', {}) + result = self.vm.qmp("stop") self.assert_qmp(result, 'return', {}) result = self.vm.qmp("query-block-jobs") + self.assert_qmp(result, 'return[0]/status', 'running') self.assert_qmp(result, 'return[0]/ready', False) def test_drive_mirror(self): self.do_test_stop("drive-mirror", device="drive0", - target=self.target_img, + target=self.target_img, format=iotests.imgfmt, sync="full") def test_drive_backup(self): self.do_test_stop("drive-backup", device="drive0", - target=self.target_img, + target=self.target_img, format=iotests.imgfmt, sync="full") def test_block_commit(self): -- 2.29.2 Before this patch, test_block_commit() performs an active commit, which under the hood is a mirror job. If we want to test various different block jobs, we should perhaps run an actual commit job instead. Doing so requires adding an overlay above the source node before the commit is done (and then specifying the source node as the top node for the commit job). Signed-off-by: Max Reitz <mreitz@redhat.com> Reviewed-by: Eric Blake <eblake@redhat.com> Reviewed-by: Vladimir Sementsov-Ogievskiy <vsementsov@virtuozzo.com> Reviewed-by: Willian Rampazzo <willianr@redhat.com> Message-Id: <20210118105720.14824-8-mreitz@redhat.com> --- tests/qemu-iotests/129 | 27 +++++++++++++++++++++++++-- 1 file changed, 25 insertions(+), 2 deletions(-) diff --git a/tests/qemu-iotests/129 b/tests/qemu-iotests/129 index XXXXXXX..XXXXXXX 100755 --- a/tests/qemu-iotests/129 +++ b/tests/qemu-iotests/129 @@ -XXX,XX +XXX,XX @@ class TestStopWithBlockJob(iotests.QMPTestCase): test_img = os.path.join(iotests.test_dir, 'test.img') target_img = os.path.join(iotests.test_dir, 'target.img') base_img = os.path.join(iotests.test_dir, 'base.img') + overlay_img = os.path.join(iotests.test_dir, 'overlay.img') def setUp(self): iotests.qemu_img('create', '-f', iotests.imgfmt, self.base_img, "1G") @@ -XXX,XX +XXX,XX @@ class TestStopWithBlockJob(iotests.QMPTestCase): self.vm.add_object('throttle-group,id=tg0,x-bps-total=1024') source_drive = 'driver=throttle,' \ + 'node-name=source,' \ 'throttle-group=tg0,' \ f'file.driver={iotests.imgfmt},' \ f'file.file.filename={self.test_img}' @@ -XXX,XX +XXX,XX @@ class TestStopWithBlockJob(iotests.QMPTestCase): def tearDown(self): self.vm.shutdown() - for img in (self.test_img, self.target_img, self.base_img): + for img in (self.test_img, self.target_img, self.base_img, + self.overlay_img): iotests.try_remove(img) def do_test_stop(self, cmd, **args): @@ -XXX,XX +XXX,XX @@ class TestStopWithBlockJob(iotests.QMPTestCase): sync="full") def test_block_commit(self): - self.do_test_stop("block-commit", device="drive0") + # Add overlay above the source node so that we actually use a + # commit job instead of a mirror job + + iotests.qemu_img('create', '-f', iotests.imgfmt, self.overlay_img, + '1G') + + result = self.vm.qmp('blockdev-add', **{ + 'node-name': 'overlay', + 'driver': iotests.imgfmt, + 'file': { + 'driver': 'file', + 'filename': self.overlay_img + } + }) + self.assert_qmp(result, 'return', {}) + + result = self.vm.qmp('blockdev-snapshot', + node='source', overlay='overlay') + self.assert_qmp(result, 'return', {}) + + self.do_test_stop('block-commit', device='drive0', top_node='source') if __name__ == '__main__': iotests.main(supported_fmts=["qcow2"], -- 2.29.2 Issuing 'stop' on the VM drains all nodes. If the mirror job has many large requests in flight, this may lead to significant I/O that looks a bit like 'stop' would make the job try to complete (which is what 129 should verify not to happen). We can limit the I/O in flight by limiting the buffer size, so mirror will make very little progress during the 'stop' drain. (We do not need to do anything about commit, which has a buffer size of 512 kB by default; or backup, which goes cluster by cluster. Once we have asynchronous requests for backup, that will change, but then we can fine-tune the backup job to only perform a single request on a very small chunk, too.) Signed-off-by: Max Reitz <mreitz@redhat.com> Reviewed-by: Eric Blake <eblake@redhat.com> Reviewed-by: Vladimir Sementsov-Ogievskiy <vsementsov@virtuozzo.com> Reviewed-by: Willian Rampazzo <willianr@redhat.com> Message-Id: <20210118105720.14824-9-mreitz@redhat.com> --- tests/qemu-iotests/129 | 2 +- 1 file changed, 1 insertion(+), 1 deletion(-) diff --git a/tests/qemu-iotests/129 b/tests/qemu-iotests/129 index XXXXXXX..XXXXXXX 100755 --- a/tests/qemu-iotests/129 +++ b/tests/qemu-iotests/129 @@ -XXX,XX +XXX,XX @@ class TestStopWithBlockJob(iotests.QMPTestCase): def test_drive_mirror(self): self.do_test_stop("drive-mirror", device="drive0", target=self.target_img, format=iotests.imgfmt, - sync="full") + sync="full", buf_size=65536) def test_drive_backup(self): self.do_test_stop("drive-backup", device="drive0", -- 2.29.2 And consequentially drop it from 297's skip list. Signed-off-by: Max Reitz <mreitz@redhat.com> Reviewed-by: Willian Rampazzo <willianr@redhat.com> Reviewed-by: Vladimir Sementsov-Ogievskiy <vsementsov@virtuozzo.com> Message-Id: <20210118105720.14824-10-mreitz@redhat.com> --- tests/qemu-iotests/129 | 4 ++-- tests/qemu-iotests/297 | 2 +- 2 files changed, 3 insertions(+), 3 deletions(-) diff --git a/tests/qemu-iotests/129 b/tests/qemu-iotests/129 index XXXXXXX..XXXXXXX 100755 --- a/tests/qemu-iotests/129 +++ b/tests/qemu-iotests/129 @@ -XXX,XX +XXX,XX @@ import os import iotests -import time class TestStopWithBlockJob(iotests.QMPTestCase): test_img = os.path.join(iotests.test_dir, 'test.img') @@ -XXX,XX +XXX,XX @@ class TestStopWithBlockJob(iotests.QMPTestCase): iotests.qemu_img('create', '-f', iotests.imgfmt, self.base_img, "1G") iotests.qemu_img('create', '-f', iotests.imgfmt, self.test_img, "-b", self.base_img, '-F', iotests.imgfmt) - iotests.qemu_io('-f', iotests.imgfmt, '-c', 'write -P0x5d 1M 128M', self.test_img) + iotests.qemu_io('-f', iotests.imgfmt, '-c', 'write -P0x5d 1M 128M', + self.test_img) self.vm = iotests.VM() self.vm.add_object('throttle-group,id=tg0,x-bps-total=1024') diff --git a/tests/qemu-iotests/297 b/tests/qemu-iotests/297 index XXXXXXX..XXXXXXX 100755 --- a/tests/qemu-iotests/297 +++ b/tests/qemu-iotests/297 @@ -XXX,XX +XXX,XX @@ import iotests # TODO: Empty this list! SKIP_FILES = ( '030', '040', '041', '044', '045', '055', '056', '057', '065', '093', - '096', '118', '124', '129', '132', '136', '139', '147', '148', '149', + '096', '118', '124', '132', '136', '139', '147', '148', '149', '151', '152', '155', '163', '165', '169', '194', '196', '199', '202', '203', '205', '206', '207', '208', '210', '211', '212', '213', '216', '218', '219', '222', '224', '228', '234', '235', '236', '237', '238', -- 2.29.2 And consequentially drop it from 297's skip list. Signed-off-by: Max Reitz <mreitz@redhat.com> Reviewed-by: Vladimir Sementsov-Ogievskiy <vsementsov@virtuozzo.com> Reviewed-by: Willian Rampazzo <willianr@redhat.com> Message-Id: <20210118105720.14824-11-mreitz@redhat.com> --- tests/qemu-iotests/297 | 2 +- tests/qemu-iotests/300 | 18 +++++++++++++++--- 2 files changed, 16 insertions(+), 4 deletions(-) diff --git a/tests/qemu-iotests/297 b/tests/qemu-iotests/297 index XXXXXXX..XXXXXXX 100755 --- a/tests/qemu-iotests/297 +++ b/tests/qemu-iotests/297 @@ -XXX,XX +XXX,XX @@ SKIP_FILES = ( '218', '219', '222', '224', '228', '234', '235', '236', '237', '238', '240', '242', '245', '246', '248', '255', '256', '257', '258', '260', '262', '264', '266', '274', '277', '280', '281', '295', '296', '298', - '299', '300', '302', '303', '304', '307', + '299', '302', '303', '304', '307', 'nbd-fault-injector.py', 'qcow2.py', 'qcow2_format.py', 'qed.py' ) diff --git a/tests/qemu-iotests/300 b/tests/qemu-iotests/300 index XXXXXXX..XXXXXXX 100755 --- a/tests/qemu-iotests/300 +++ b/tests/qemu-iotests/300 @@ -XXX,XX +XXX,XX @@ import os import random import re from typing import Dict, List, Optional, Union + import iotests + +# Import qemu after iotests.py has amended sys.path +# pylint: disable=wrong-import-order import qemu BlockBitmapMapping = List[Dict[str, Union[str, List[Dict[str, str]]]]] @@ -XXX,XX +XXX,XX @@ class TestDirtyBitmapMigration(iotests.QMPTestCase): If @msg is None, check that there has not been any error. """ self.vm_b.shutdown() + + log = self.vm_b.get_log() + assert log is not None # Loaded after shutdown + if msg is None: - self.assertNotIn('qemu-system-', self.vm_b.get_log()) + self.assertNotIn('qemu-system-', log) else: - self.assertIn(msg, self.vm_b.get_log()) + self.assertIn(msg, log) @staticmethod def mapping(node_name: str, node_alias: str, @@ -XXX,XX +XXX,XX @@ class TestBlockBitmapMappingErrors(TestDirtyBitmapMigration): # Check for the error in the source's log self.vm_a.shutdown() + + log = self.vm_a.get_log() + assert log is not None # Loaded after shutdown + self.assertIn(f"Cannot migrate bitmap '{name}' on node " f"'{self.src_node_name}': Name is longer than 255 bytes", - self.vm_a.get_log()) + log) # Expect abnormal shutdown of the destination VM because of # the failed migration -- 2.29.2 Disposition (action) for any given signal is global for the process. When two threads run coroutine-sigaltstack's qemu_coroutine_new() concurrently, they may interfere with each other: One of them may revert the SIGUSR2 handler to SIG_DFL, between the other thread (a) setting up coroutine_trampoline() as the handler and (b) raising SIGUSR2. That SIGUSR2 will then terminate the QEMU process abnormally. We have to ensure that only one thread at a time can modify the process-global SIGUSR2 handler. To do so, wrap the whole section where that is done in a mutex. Alternatively, we could for example have the SIGUSR2 handler always be coroutine_trampoline(), so there would be no need to invoke sigaction() in qemu_coroutine_new(). Laszlo has posted a patch to do so here: https://lists.nongnu.org/archive/html/qemu-devel/2021-01/msg05962.html However, given that coroutine-sigaltstack is more of a fallback implementation for platforms that do not support ucontext, that change may be a bit too invasive to be comfortable with it. The mutex proposed here may negatively impact performance, but the change is much simpler. Signed-off-by: Max Reitz <mreitz@redhat.com> Message-Id: <20210125120305.19520-1-mreitz@redhat.com> Reviewed-by: Laszlo Ersek <lersek@redhat.com> Reviewed-by: Vladimir Sementsov-Ogievskiy <vsementsov@virtuozzo.com> --- util/coroutine-sigaltstack.c | 9 +++++++++ 1 file changed, 9 insertions(+) diff --git a/util/coroutine-sigaltstack.c b/util/coroutine-sigaltstack.c index XXXXXXX..XXXXXXX 100644 --- a/util/coroutine-sigaltstack.c +++ b/util/coroutine-sigaltstack.c @@ -XXX,XX +XXX,XX @@ Coroutine *qemu_coroutine_new(void) sigset_t sigs; sigset_t osigs; sigjmp_buf old_env; + static pthread_mutex_t sigusr2_mutex = PTHREAD_MUTEX_INITIALIZER; /* The way to manipulate stack is with the sigaltstack function. We * prepare a stack, with it delivering a signal to ourselves and then @@ -XXX,XX +XXX,XX @@ Coroutine *qemu_coroutine_new(void) sa.sa_handler = coroutine_trampoline; sigfillset(&sa.sa_mask); sa.sa_flags = SA_ONSTACK; + + /* + * sigaction() is a process-global operation. We must not run + * this code in multiple threads at once. + */ + pthread_mutex_lock(&sigusr2_mutex); if (sigaction(SIGUSR2, &sa, &osa) != 0) { abort(); } @@ -XXX,XX +XXX,XX @@ Coroutine *qemu_coroutine_new(void) * Restore the old SIGUSR2 signal handler and mask */ sigaction(SIGUSR2, &osa, NULL); + pthread_mutex_unlock(&sigusr2_mutex); + pthread_sigmask(SIG_SETMASK, &osigs, NULL); /* -- 2.29.2 From: Vladimir Sementsov-Ogievskiy <vsementsov@virtuozzo.com> Experiments show, that copy_range is not always making things faster. So, to make experimentation simpler, let's add a parameter. Some more perf parameters will be added soon, so here is a new struct. For now, add new backup qmp parameter with x- prefix for the following reasons: - We are going to add more performance parameters, some will be related to the whole block-copy process, some only to background copying in backup (ignored for copy-before-write operations). - On the other hand, we are going to use block-copy interface in other block jobs, which will need performance options as well.. And it should be the same structure or at least somehow related. So, there are too much unclean things about how the interface and now we need the new options mostly for testing. Let's keep them experimental for a while. In do_backup_common() new x-perf parameter handled in a way to make further options addition simpler. We add use-copy-range with default=true, and we'll change the default in further patch, after moving backup to use block-copy. Signed-off-by: Vladimir Sementsov-Ogievskiy <vsementsov@virtuozzo.com> Reviewed-by: Max Reitz <mreitz@redhat.com> Message-Id: <20210116214705.822267-2-vsementsov@virtuozzo.com> [mreitz: s/5\.2/6.0/] Signed-off-by: Max Reitz <mreitz@redhat.com> --- qapi/block-core.json | 17 ++++++++++++++++- block/backup-top.h | 1 + include/block/block-copy.h | 2 +- include/block/block_int.h | 3 +++ block/backup-top.c | 4 +++- block/backup.c | 6 +++++- block/block-copy.c | 4 ++-- block/replication.c | 2 ++ blockdev.c | 8 ++++++++ 9 files changed, 41 insertions(+), 6 deletions(-) diff --git a/qapi/block-core.json b/qapi/block-core.json index XXXXXXX..XXXXXXX 100644 --- a/qapi/block-core.json +++ b/qapi/block-core.json @@ -XXX,XX +XXX,XX @@ { 'struct': 'BlockdevSnapshot', 'data': { 'node': 'str', 'overlay': 'str' } } +## +# @BackupPerf: +# +# Optional parameters for backup. These parameters don't affect +# functionality, but may significantly affect performance. +# +# @use-copy-range: Use copy offloading. Default true. +# +# Since: 6.0 +## +{ 'struct': 'BackupPerf', + 'data': { '*use-copy-range': 'bool' }} + ## # @BackupCommon: # @@ -XXX,XX +XXX,XX @@ # above node specified by @drive. If this option is not given, # a node name is autogenerated. (Since: 4.2) # +# @x-perf: Performance options. (Since 6.0) +# # Note: @on-source-error and @on-target-error only affect background # I/O. If an error occurs during a guest write request, the device's # rerror/werror actions will be used. @@ -XXX,XX +XXX,XX @@ '*on-source-error': 'BlockdevOnError', '*on-target-error': 'BlockdevOnError', '*auto-finalize': 'bool', '*auto-dismiss': 'bool', - '*filter-node-name': 'str' } } + '*filter-node-name': 'str', '*x-perf': 'BackupPerf' } } ## # @DriveBackup: diff --git a/block/backup-top.h b/block/backup-top.h index XXXXXXX..XXXXXXX 100644 --- a/block/backup-top.h +++ b/block/backup-top.h @@ -XXX,XX +XXX,XX @@ BlockDriverState *bdrv_backup_top_append(BlockDriverState *source, BlockDriverState *target, const char *filter_node_name, uint64_t cluster_size, + BackupPerf *perf, BdrvRequestFlags write_flags, BlockCopyState **bcs, Error **errp); diff --git a/include/block/block-copy.h b/include/block/block-copy.h index XXXXXXX..XXXXXXX 100644 --- a/include/block/block-copy.h +++ b/include/block/block-copy.h @@ -XXX,XX +XXX,XX @@ typedef void (*ProgressBytesCallbackFunc)(int64_t bytes, void *opaque); typedef struct BlockCopyState BlockCopyState; BlockCopyState *block_copy_state_new(BdrvChild *source, BdrvChild *target, - int64_t cluster_size, + int64_t cluster_size, bool use_copy_range, BdrvRequestFlags write_flags, Error **errp); diff --git a/include/block/block_int.h b/include/block/block_int.h index XXXXXXX..XXXXXXX 100644 --- a/include/block/block_int.h +++ b/include/block/block_int.h @@ -XXX,XX +XXX,XX @@ void mirror_start(const char *job_id, BlockDriverState *bs, * @sync_mode: What parts of the disk image should be copied to the destination. * @sync_bitmap: The dirty bitmap if sync_mode is 'bitmap' or 'incremental' * @bitmap_mode: The bitmap synchronization policy to use. + * @perf: Performance options. All actual fields assumed to be present, + * all ".has_*" fields are ignored. * @on_source_error: The action to take upon error reading from the source. * @on_target_error: The action to take upon error writing to the target. * @creation_flags: Flags that control the behavior of the Job lifetime. @@ -XXX,XX +XXX,XX @@ BlockJob *backup_job_create(const char *job_id, BlockDriverState *bs, BitmapSyncMode bitmap_mode, bool compress, const char *filter_node_name, + BackupPerf *perf, BlockdevOnError on_source_error, BlockdevOnError on_target_error, int creation_flags, diff --git a/block/backup-top.c b/block/backup-top.c index XXXXXXX..XXXXXXX 100644 --- a/block/backup-top.c +++ b/block/backup-top.c @@ -XXX,XX +XXX,XX @@ BlockDriverState *bdrv_backup_top_append(BlockDriverState *source, BlockDriverState *target, const char *filter_node_name, uint64_t cluster_size, + BackupPerf *perf, BdrvRequestFlags write_flags, BlockCopyState **bcs, Error **errp) @@ -XXX,XX +XXX,XX @@ BlockDriverState *bdrv_backup_top_append(BlockDriverState *source, state->cluster_size = cluster_size; state->bcs = block_copy_state_new(top->backing, state->target, - cluster_size, write_flags, &local_err); + cluster_size, perf->use_copy_range, + write_flags, &local_err); if (local_err) { error_prepend(&local_err, "Cannot create block-copy-state: "); goto fail; diff --git a/block/backup.c b/block/backup.c index XXXXXXX..XXXXXXX 100644 --- a/block/backup.c +++ b/block/backup.c @@ -XXX,XX +XXX,XX @@ typedef struct BackupBlockJob { uint64_t len; uint64_t bytes_read; int64_t cluster_size; + BackupPerf perf; BlockCopyState *bcs; } BackupBlockJob; @@ -XXX,XX +XXX,XX @@ BlockJob *backup_job_create(const char *job_id, BlockDriverState *bs, BitmapSyncMode bitmap_mode, bool compress, const char *filter_node_name, + BackupPerf *perf, BlockdevOnError on_source_error, BlockdevOnError on_target_error, int creation_flags, @@ -XXX,XX +XXX,XX @@ BlockJob *backup_job_create(const char *job_id, BlockDriverState *bs, (compress ? BDRV_REQ_WRITE_COMPRESSED : 0), backup_top = bdrv_backup_top_append(bs, target, filter_node_name, - cluster_size, write_flags, &bcs, errp); + cluster_size, perf, + write_flags, &bcs, errp); if (!backup_top) { goto error; } @@ -XXX,XX +XXX,XX @@ BlockJob *backup_job_create(const char *job_id, BlockDriverState *bs, job->bcs = bcs; job->cluster_size = cluster_size; job->len = len; + job->perf = *perf; block_copy_set_progress_callback(bcs, backup_progress_bytes_callback, job); block_copy_set_progress_meter(bcs, &job->common.job.progress); diff --git a/block/block-copy.c b/block/block-copy.c index XXXXXXX..XXXXXXX 100644 --- a/block/block-copy.c +++ b/block/block-copy.c @@ -XXX,XX +XXX,XX @@ static uint32_t block_copy_max_transfer(BdrvChild *source, BdrvChild *target) } BlockCopyState *block_copy_state_new(BdrvChild *source, BdrvChild *target, - int64_t cluster_size, + int64_t cluster_size, bool use_copy_range, BdrvRequestFlags write_flags, Error **errp) { BlockCopyState *s; @@ -XXX,XX +XXX,XX @@ BlockCopyState *block_copy_state_new(BdrvChild *source, BdrvChild *target, * We enable copy-range, but keep small copy_size, until first * successful copy_range (look at block_copy_do_copy). */ - s->use_copy_range = true; + s->use_copy_range = use_copy_range; s->copy_size = MAX(s->cluster_size, BLOCK_COPY_MAX_BUFFER); } diff --git a/block/replication.c b/block/replication.c index XXXXXXX..XXXXXXX 100644 --- a/block/replication.c +++ b/block/replication.c @@ -XXX,XX +XXX,XX @@ static void replication_start(ReplicationState *rs, ReplicationMode mode, int64_t active_length, hidden_length, disk_length; AioContext *aio_context; Error *local_err = NULL; + BackupPerf perf = { .use_copy_range = true }; aio_context = bdrv_get_aio_context(bs); aio_context_acquire(aio_context); @@ -XXX,XX +XXX,XX @@ static void replication_start(ReplicationState *rs, ReplicationMode mode, s->backup_job = backup_job_create( NULL, s->secondary_disk->bs, s->hidden_disk->bs, 0, MIRROR_SYNC_MODE_NONE, NULL, 0, false, NULL, + &perf, BLOCKDEV_ON_ERROR_REPORT, BLOCKDEV_ON_ERROR_REPORT, JOB_INTERNAL, backup_job_completed, bs, NULL, &local_err); diff --git a/blockdev.c b/blockdev.c index XXXXXXX..XXXXXXX 100644 --- a/blockdev.c +++ b/blockdev.c @@ -XXX,XX +XXX,XX @@ static BlockJob *do_backup_common(BackupCommon *backup, { BlockJob *job = NULL; BdrvDirtyBitmap *bmap = NULL; + BackupPerf perf = { .use_copy_range = true }; int job_flags = JOB_DEFAULT; if (!backup->has_speed) { @@ -XXX,XX +XXX,XX @@ static BlockJob *do_backup_common(BackupCommon *backup, backup->compress = false; } + if (backup->x_perf) { + if (backup->x_perf->has_use_copy_range) { + perf.use_copy_range = backup->x_perf->use_copy_range; + } + } + if ((backup->sync == MIRROR_SYNC_MODE_BITMAP) || (backup->sync == MIRROR_SYNC_MODE_INCREMENTAL)) { /* done before desugaring 'incremental' to print the right message */ @@ -XXX,XX +XXX,XX @@ static BlockJob *do_backup_common(BackupCommon *backup, backup->sync, bmap, backup->bitmap_mode, backup->compress, backup->filter_node_name, + &perf, backup->on_source_error, backup->on_target_error, job_flags, NULL, NULL, txn, errp); -- 2.29.2 From: Vladimir Sementsov-Ogievskiy <vsementsov@virtuozzo.com> Refactor common path to use BlockCopyCallState pointer as parameter, to prepare it for use in asynchronous block-copy (at least, we'll need to run block-copy in a coroutine, passing the whole parameters as one pointer). Signed-off-by: Vladimir Sementsov-Ogievskiy <vsementsov@virtuozzo.com> Reviewed-by: Max Reitz <mreitz@redhat.com> Message-Id: <20210116214705.822267-3-vsementsov@virtuozzo.com> Signed-off-by: Max Reitz <mreitz@redhat.com> --- block/block-copy.c | 51 ++++++++++++++++++++++++++++++++++------------ 1 file changed, 38 insertions(+), 13 deletions(-) diff --git a/block/block-copy.c b/block/block-copy.c index XXXXXXX..XXXXXXX 100644 --- a/block/block-copy.c +++ b/block/block-copy.c @@ -XXX,XX +XXX,XX @@ static coroutine_fn int block_copy_task_entry(AioTask *task); typedef struct BlockCopyCallState { + /* IN parameters */ + BlockCopyState *s; + int64_t offset; + int64_t bytes; + + /* State */ bool failed; + + /* OUT parameters */ bool error_is_read; } BlockCopyCallState; @@ -XXX,XX +XXX,XX @@ int64_t block_copy_reset_unallocated(BlockCopyState *s, * Returns 1 if dirty clusters found and successfully copied, 0 if no dirty * clusters found and -errno on failure. */ -static int coroutine_fn block_copy_dirty_clusters(BlockCopyState *s, - int64_t offset, int64_t bytes, - bool *error_is_read) +static int coroutine_fn +block_copy_dirty_clusters(BlockCopyCallState *call_state) { + BlockCopyState *s = call_state->s; + int64_t offset = call_state->offset; + int64_t bytes = call_state->bytes; + int ret = 0; bool found_dirty = false; int64_t end = offset + bytes; AioTaskPool *aio = NULL; - BlockCopyCallState call_state = {false, false}; /* * block_copy() user is responsible for keeping source and target in same @@ -XXX,XX +XXX,XX @@ static int coroutine_fn block_copy_dirty_clusters(BlockCopyState *s, BlockCopyTask *task; int64_t status_bytes; - task = block_copy_task_create(s, &call_state, offset, bytes); + task = block_copy_task_create(s, call_state, offset, bytes); if (!task) { /* No more dirty bits in the bitmap */ trace_block_copy_skip_range(s, offset, bytes); @@ -XXX,XX +XXX,XX @@ out: aio_task_pool_free(aio); } - if (error_is_read && ret < 0) { - *error_is_read = call_state.error_is_read; - } return ret < 0 ? ret : found_dirty; } /* - * block_copy + * block_copy_common * * Copy requested region, accordingly to dirty bitmap. * Collaborate with parallel block_copy requests: if they succeed it will help @@ -XXX,XX +XXX,XX @@ out: * it means that some I/O operation failed in context of _this_ block_copy call, * not some parallel operation. */ -int coroutine_fn block_copy(BlockCopyState *s, int64_t offset, int64_t bytes, - bool *error_is_read) +static int coroutine_fn block_copy_common(BlockCopyCallState *call_state) { int ret; do { - ret = block_copy_dirty_clusters(s, offset, bytes, error_is_read); + ret = block_copy_dirty_clusters(call_state); if (ret == 0) { - ret = block_copy_wait_one(s, offset, bytes); + ret = block_copy_wait_one(call_state->s, call_state->offset, + call_state->bytes); } /* @@ -XXX,XX +XXX,XX @@ int coroutine_fn block_copy(BlockCopyState *s, int64_t offset, int64_t bytes, return ret; } +int coroutine_fn block_copy(BlockCopyState *s, int64_t start, int64_t bytes, + bool *error_is_read) +{ + BlockCopyCallState call_state = { + .s = s, + .offset = start, + .bytes = bytes, + }; + + int ret = block_copy_common(&call_state); + + if (error_is_read && ret < 0) { + *error_is_read = call_state.error_is_read; + } + + return ret; +} + BdrvDirtyBitmap *block_copy_dirty_bitmap(BlockCopyState *s) { return s->copy_bitmap; -- 2.29.2 From: Vladimir Sementsov-Ogievskiy <vsementsov@virtuozzo.com> We'll need async block-copy invocation to use in backup directly. Signed-off-by: Vladimir Sementsov-Ogievskiy <vsementsov@virtuozzo.com> Reviewed-by: Max Reitz <mreitz@redhat.com> Message-Id: <20210116214705.822267-4-vsementsov@virtuozzo.com> Signed-off-by: Max Reitz <mreitz@redhat.com> --- include/block/block-copy.h | 29 ++++++++++++++ block/block-copy.c | 81 ++++++++++++++++++++++++++++++++++++-- 2 files changed, 106 insertions(+), 4 deletions(-) diff --git a/include/block/block-copy.h b/include/block/block-copy.h index XXXXXXX..XXXXXXX 100644 --- a/include/block/block-copy.h +++ b/include/block/block-copy.h @@ -XXX,XX +XXX,XX @@ #include "qemu/co-shared-resource.h" typedef void (*ProgressBytesCallbackFunc)(int64_t bytes, void *opaque); +typedef void (*BlockCopyAsyncCallbackFunc)(void *opaque); typedef struct BlockCopyState BlockCopyState; +typedef struct BlockCopyCallState BlockCopyCallState; BlockCopyState *block_copy_state_new(BdrvChild *source, BdrvChild *target, int64_t cluster_size, bool use_copy_range, @@ -XXX,XX +XXX,XX @@ int64_t block_copy_reset_unallocated(BlockCopyState *s, int coroutine_fn block_copy(BlockCopyState *s, int64_t offset, int64_t bytes, bool *error_is_read); +/* + * Run block-copy in a coroutine, create corresponding BlockCopyCallState + * object and return pointer to it. Never returns NULL. + * + * Caller is responsible to call block_copy_call_free() to free + * BlockCopyCallState object. + */ +BlockCopyCallState *block_copy_async(BlockCopyState *s, + int64_t offset, int64_t bytes, + BlockCopyAsyncCallbackFunc cb, + void *cb_opaque); + +/* + * Free finished BlockCopyCallState. Trying to free running + * block-copy will crash. + */ +void block_copy_call_free(BlockCopyCallState *call_state); + +/* + * Note, that block-copy call is marked finished prior to calling + * the callback. + */ +bool block_copy_call_finished(BlockCopyCallState *call_state); +bool block_copy_call_succeeded(BlockCopyCallState *call_state); +bool block_copy_call_failed(BlockCopyCallState *call_state); +int block_copy_call_status(BlockCopyCallState *call_state, bool *error_is_read); + BdrvDirtyBitmap *block_copy_dirty_bitmap(BlockCopyState *s); void block_copy_set_skip_unallocated(BlockCopyState *s, bool skip); diff --git a/block/block-copy.c b/block/block-copy.c index XXXXXXX..XXXXXXX 100644 --- a/block/block-copy.c +++ b/block/block-copy.c @@ -XXX,XX +XXX,XX @@ static coroutine_fn int block_copy_task_entry(AioTask *task); typedef struct BlockCopyCallState { - /* IN parameters */ + /* IN parameters. Initialized in block_copy_async() and never changed. */ BlockCopyState *s; int64_t offset; int64_t bytes; + BlockCopyAsyncCallbackFunc cb; + void *cb_opaque; + + /* Coroutine where async block-copy is running */ + Coroutine *co; /* State */ - bool failed; + int ret; + bool finished; /* OUT parameters */ bool error_is_read; @@ -XXX,XX +XXX,XX @@ static coroutine_fn int block_copy_task_entry(AioTask *task) ret = block_copy_do_copy(t->s, t->offset, t->bytes, t->zeroes, &error_is_read); - if (ret < 0 && !t->call_state->failed) { - t->call_state->failed = true; + if (ret < 0 && !t->call_state->ret) { + t->call_state->ret = ret; t->call_state->error_is_read = error_is_read; } else { progress_work_done(t->s->progress, t->bytes); @@ -XXX,XX +XXX,XX @@ static int coroutine_fn block_copy_common(BlockCopyCallState *call_state) */ } while (ret > 0); + call_state->finished = true; + + if (call_state->cb) { + call_state->cb(call_state->cb_opaque); + } + return ret; } @@ -XXX,XX +XXX,XX @@ int coroutine_fn block_copy(BlockCopyState *s, int64_t start, int64_t bytes, return ret; } +static void coroutine_fn block_copy_async_co_entry(void *opaque) +{ + block_copy_common(opaque); +} + +BlockCopyCallState *block_copy_async(BlockCopyState *s, + int64_t offset, int64_t bytes, + BlockCopyAsyncCallbackFunc cb, + void *cb_opaque) +{ + BlockCopyCallState *call_state = g_new(BlockCopyCallState, 1); + + *call_state = (BlockCopyCallState) { + .s = s, + .offset = offset, + .bytes = bytes, + .cb = cb, + .cb_opaque = cb_opaque, + + .co = qemu_coroutine_create(block_copy_async_co_entry, call_state), + }; + + qemu_coroutine_enter(call_state->co); + + return call_state; +} + +void block_copy_call_free(BlockCopyCallState *call_state) +{ + if (!call_state) { + return; + } + + assert(call_state->finished); + g_free(call_state); +} + +bool block_copy_call_finished(BlockCopyCallState *call_state) +{ + return call_state->finished; +} + +bool block_copy_call_succeeded(BlockCopyCallState *call_state) +{ + return call_state->finished && call_state->ret == 0; +} + +bool block_copy_call_failed(BlockCopyCallState *call_state) +{ + return call_state->finished && call_state->ret < 0; +} + +int block_copy_call_status(BlockCopyCallState *call_state, bool *error_is_read) +{ + assert(call_state->finished); + if (error_is_read) { + *error_is_read = call_state->error_is_read; + } + return call_state->ret; +} + BdrvDirtyBitmap *block_copy_dirty_bitmap(BlockCopyState *s) { return s->copy_bitmap; -- 2.29.2 From: Vladimir Sementsov-Ogievskiy <vsementsov@virtuozzo.com> They will be used for backup. Signed-off-by: Vladimir Sementsov-Ogievskiy <vsementsov@virtuozzo.com> Reviewed-by: Max Reitz <mreitz@redhat.com> Message-Id: <20210116214705.822267-5-vsementsov@virtuozzo.com> Signed-off-by: Max Reitz <mreitz@redhat.com> --- include/block/block-copy.h | 6 ++++++ block/block-copy.c | 11 +++++++++-- 2 files changed, 15 insertions(+), 2 deletions(-) diff --git a/include/block/block-copy.h b/include/block/block-copy.h index XXXXXXX..XXXXXXX 100644 --- a/include/block/block-copy.h +++ b/include/block/block-copy.h @@ -XXX,XX +XXX,XX @@ int coroutine_fn block_copy(BlockCopyState *s, int64_t offset, int64_t bytes, * * Caller is responsible to call block_copy_call_free() to free * BlockCopyCallState object. + * + * @max_workers means maximum of parallel coroutines to execute sub-requests, + * must be > 0. + * + * @max_chunk means maximum length for one IO operation. Zero means unlimited. */ BlockCopyCallState *block_copy_async(BlockCopyState *s, int64_t offset, int64_t bytes, + int max_workers, int64_t max_chunk, BlockCopyAsyncCallbackFunc cb, void *cb_opaque); diff --git a/block/block-copy.c b/block/block-copy.c index XXXXXXX..XXXXXXX 100644 --- a/block/block-copy.c +++ b/block/block-copy.c @@ -XXX,XX +XXX,XX @@ typedef struct BlockCopyCallState { BlockCopyState *s; int64_t offset; int64_t bytes; + int max_workers; + int64_t max_chunk; BlockCopyAsyncCallbackFunc cb; void *cb_opaque; @@ -XXX,XX +XXX,XX @@ static BlockCopyTask *block_copy_task_create(BlockCopyState *s, int64_t offset, int64_t bytes) { BlockCopyTask *task; + int64_t max_chunk = MIN_NON_ZERO(s->copy_size, call_state->max_chunk); if (!bdrv_dirty_bitmap_next_dirty_area(s->copy_bitmap, offset, offset + bytes, - s->copy_size, &offset, &bytes)) + max_chunk, &offset, &bytes)) { return NULL; } @@ -XXX,XX +XXX,XX @@ block_copy_dirty_clusters(BlockCopyCallState *call_state) bytes = end - offset; if (!aio && bytes) { - aio = aio_task_pool_new(BLOCK_COPY_MAX_WORKERS); + aio = aio_task_pool_new(call_state->max_workers); } ret = block_copy_task_run(aio, task); @@ -XXX,XX +XXX,XX @@ int coroutine_fn block_copy(BlockCopyState *s, int64_t start, int64_t bytes, .s = s, .offset = start, .bytes = bytes, + .max_workers = BLOCK_COPY_MAX_WORKERS, }; int ret = block_copy_common(&call_state); @@ -XXX,XX +XXX,XX @@ static void coroutine_fn block_copy_async_co_entry(void *opaque) BlockCopyCallState *block_copy_async(BlockCopyState *s, int64_t offset, int64_t bytes, + int max_workers, int64_t max_chunk, BlockCopyAsyncCallbackFunc cb, void *cb_opaque) { @@ -XXX,XX +XXX,XX @@ BlockCopyCallState *block_copy_async(BlockCopyState *s, .s = s, .offset = offset, .bytes = bytes, + .max_workers = max_workers, + .max_chunk = max_chunk, .cb = cb, .cb_opaque = cb_opaque, -- 2.29.2 From: Vladimir Sementsov-Ogievskiy <vsementsov@virtuozzo.com> It simplifies debugging. Signed-off-by: Vladimir Sementsov-Ogievskiy <vsementsov@virtuozzo.com> Reviewed-by: Max Reitz <mreitz@redhat.com> Message-Id: <20210116214705.822267-6-vsementsov@virtuozzo.com> Signed-off-by: Max Reitz <mreitz@redhat.com> --- block/block-copy.c | 11 ++++++++++- 1 file changed, 10 insertions(+), 1 deletion(-) diff --git a/block/block-copy.c b/block/block-copy.c index XXXXXXX..XXXXXXX 100644 --- a/block/block-copy.c +++ b/block/block-copy.c @@ -XXX,XX +XXX,XX @@ typedef struct BlockCopyCallState { /* Coroutine where async block-copy is running */ Coroutine *co; + /* To reference all call states from BlockCopyState */ + QLIST_ENTRY(BlockCopyCallState) list; + /* State */ int ret; bool finished; @@ -XXX,XX +XXX,XX @@ typedef struct BlockCopyState { bool use_copy_range; int64_t copy_size; uint64_t len; - QLIST_HEAD(, BlockCopyTask) tasks; + QLIST_HEAD(, BlockCopyTask) tasks; /* All tasks from all block-copy calls */ + QLIST_HEAD(, BlockCopyCallState) calls; BdrvRequestFlags write_flags; @@ -XXX,XX +XXX,XX @@ BlockCopyState *block_copy_state_new(BdrvChild *source, BdrvChild *target, } QLIST_INIT(&s->tasks); + QLIST_INIT(&s->calls); return s; } @@ -XXX,XX +XXX,XX @@ static int coroutine_fn block_copy_common(BlockCopyCallState *call_state) { int ret; + QLIST_INSERT_HEAD(&call_state->s->calls, call_state, list); + do { ret = block_copy_dirty_clusters(call_state); @@ -XXX,XX +XXX,XX @@ static int coroutine_fn block_copy_common(BlockCopyCallState *call_state) call_state->cb(call_state->cb_opaque); } + QLIST_REMOVE(call_state, list); + return ret; } -- 2.29.2 From: Vladimir Sementsov-Ogievskiy <vsementsov@virtuozzo.com> We are going to directly use one async block-copy operation for backup job, so we need rate limiter. We want to maintain current backup behavior: only background copying is limited and copy-before-write operations only participate in limit calculation. Therefore we need one rate limiter for block-copy state and boolean flag for block-copy call state for actual limitation. Note, that we can't just calculate each chunk in limiter after successful copying: it will not save us from starting a lot of async sub-requests which will exceed limit too much. Instead let's use the following scheme on sub-request creation: 1. If at the moment limit is not exceeded, create the request and account it immediately. 2. If at the moment limit is already exceeded, drop create sub-request and handle limit instead (by sleep). With this approach we'll never exceed the limit more than by one sub-request (which pretty much matches current backup behavior). Note also, that if there is in-flight block-copy async call, block_copy_kick() should be used after set-speed to apply new setup faster. For that block_copy_kick() published in this patch. Signed-off-by: Vladimir Sementsov-Ogievskiy <vsementsov@virtuozzo.com> Reviewed-by: Max Reitz <mreitz@redhat.com> Message-Id: <20210116214705.822267-7-vsementsov@virtuozzo.com> Signed-off-by: Max Reitz <mreitz@redhat.com> --- include/block/block-copy.h | 5 ++++- block/backup-top.c | 2 +- block/backup.c | 2 +- block/block-copy.c | 46 +++++++++++++++++++++++++++++++++++++- 4 files changed, 51 insertions(+), 4 deletions(-) diff --git a/include/block/block-copy.h b/include/block/block-copy.h index XXXXXXX..XXXXXXX 100644 --- a/include/block/block-copy.h +++ b/include/block/block-copy.h @@ -XXX,XX +XXX,XX @@ int64_t block_copy_reset_unallocated(BlockCopyState *s, int64_t offset, int64_t *count); int coroutine_fn block_copy(BlockCopyState *s, int64_t offset, int64_t bytes, - bool *error_is_read); + bool ignore_ratelimit, bool *error_is_read); /* * Run block-copy in a coroutine, create corresponding BlockCopyCallState @@ -XXX,XX +XXX,XX @@ bool block_copy_call_succeeded(BlockCopyCallState *call_state); bool block_copy_call_failed(BlockCopyCallState *call_state); int block_copy_call_status(BlockCopyCallState *call_state, bool *error_is_read); +void block_copy_set_speed(BlockCopyState *s, uint64_t speed); +void block_copy_kick(BlockCopyCallState *call_state); + BdrvDirtyBitmap *block_copy_dirty_bitmap(BlockCopyState *s); void block_copy_set_skip_unallocated(BlockCopyState *s, bool skip); diff --git a/block/backup-top.c b/block/backup-top.c index XXXXXXX..XXXXXXX 100644 --- a/block/backup-top.c +++ b/block/backup-top.c @@ -XXX,XX +XXX,XX @@ static coroutine_fn int backup_top_cbw(BlockDriverState *bs, uint64_t offset, off = QEMU_ALIGN_DOWN(offset, s->cluster_size); end = QEMU_ALIGN_UP(offset + bytes, s->cluster_size); - return block_copy(s->bcs, off, end - off, NULL); + return block_copy(s->bcs, off, end - off, true, NULL); } static int coroutine_fn backup_top_co_pdiscard(BlockDriverState *bs, diff --git a/block/backup.c b/block/backup.c index XXXXXXX..XXXXXXX 100644 --- a/block/backup.c +++ b/block/backup.c @@ -XXX,XX +XXX,XX @@ static int coroutine_fn backup_do_cow(BackupBlockJob *job, trace_backup_do_cow_enter(job, start, offset, bytes); - ret = block_copy(job->bcs, start, end - start, error_is_read); + ret = block_copy(job->bcs, start, end - start, true, error_is_read); trace_backup_do_cow_return(job, offset, bytes, ret); diff --git a/block/block-copy.c b/block/block-copy.c index XXXXXXX..XXXXXXX 100644 --- a/block/block-copy.c +++ b/block/block-copy.c @@ -XXX,XX +XXX,XX @@ #define BLOCK_COPY_MAX_BUFFER (1 * MiB) #define BLOCK_COPY_MAX_MEM (128 * MiB) #define BLOCK_COPY_MAX_WORKERS 64 +#define BLOCK_COPY_SLICE_TIME 100000000ULL /* ns */ static coroutine_fn int block_copy_task_entry(AioTask *task); @@ -XXX,XX +XXX,XX @@ typedef struct BlockCopyCallState { int64_t bytes; int max_workers; int64_t max_chunk; + bool ignore_ratelimit; BlockCopyAsyncCallbackFunc cb; void *cb_opaque; @@ -XXX,XX +XXX,XX @@ typedef struct BlockCopyCallState { /* State */ int ret; bool finished; + QemuCoSleepState *sleep_state; /* OUT parameters */ bool error_is_read; @@ -XXX,XX +XXX,XX @@ typedef struct BlockCopyState { void *progress_opaque; SharedResource *mem; + + uint64_t speed; + RateLimit rate_limit; } BlockCopyState; static BlockCopyTask *find_conflicting_task(BlockCopyState *s, @@ -XXX,XX +XXX,XX @@ block_copy_dirty_clusters(BlockCopyCallState *call_state) } task->zeroes = ret & BDRV_BLOCK_ZERO; + if (s->speed) { + if (!call_state->ignore_ratelimit) { + uint64_t ns = ratelimit_calculate_delay(&s->rate_limit, 0); + if (ns > 0) { + block_copy_task_end(task, -EAGAIN); + g_free(task); + qemu_co_sleep_ns_wakeable(QEMU_CLOCK_REALTIME, ns, + &call_state->sleep_state); + continue; + } + } + + ratelimit_calculate_delay(&s->rate_limit, task->bytes); + } + trace_block_copy_process(s, task->offset); co_get_from_shres(s->mem, task->bytes); @@ -XXX,XX +XXX,XX @@ out: return ret < 0 ? ret : found_dirty; } +void block_copy_kick(BlockCopyCallState *call_state) +{ + if (call_state->sleep_state) { + qemu_co_sleep_wake(call_state->sleep_state); + } +} + /* * block_copy_common * @@ -XXX,XX +XXX,XX @@ static int coroutine_fn block_copy_common(BlockCopyCallState *call_state) } int coroutine_fn block_copy(BlockCopyState *s, int64_t start, int64_t bytes, - bool *error_is_read) + bool ignore_ratelimit, bool *error_is_read) { BlockCopyCallState call_state = { .s = s, .offset = start, .bytes = bytes, + .ignore_ratelimit = ignore_ratelimit, .max_workers = BLOCK_COPY_MAX_WORKERS, }; @@ -XXX,XX +XXX,XX @@ void block_copy_set_skip_unallocated(BlockCopyState *s, bool skip) { s->skip_unallocated = skip; } + +void block_copy_set_speed(BlockCopyState *s, uint64_t speed) +{ + s->speed = speed; + if (speed > 0) { + ratelimit_set_speed(&s->rate_limit, speed, BLOCK_COPY_SLICE_TIME); + } + + /* + * Note: it's good to kick all call states from here, but it should be done + * only from a coroutine, to not crash if s->calls list changed while + * entering one call. So for now, the only user of this function kicks its + * only one call_state by hand. + */ +} -- 2.29.2 From: Vladimir Sementsov-Ogievskiy <vsementsov@virtuozzo.com> Add function to cancel running async block-copy call. It will be used in backup. Signed-off-by: Vladimir Sementsov-Ogievskiy <vsementsov@virtuozzo.com> Reviewed-by: Max Reitz <mreitz@redhat.com> Message-Id: <20210116214705.822267-8-vsementsov@virtuozzo.com> Signed-off-by: Max Reitz <mreitz@redhat.com> --- include/block/block-copy.h | 13 +++++++++++++ block/block-copy.c | 24 +++++++++++++++++++----- 2 files changed, 32 insertions(+), 5 deletions(-) diff --git a/include/block/block-copy.h b/include/block/block-copy.h index XXXXXXX..XXXXXXX 100644 --- a/include/block/block-copy.h +++ b/include/block/block-copy.h @@ -XXX,XX +XXX,XX @@ void block_copy_call_free(BlockCopyCallState *call_state); bool block_copy_call_finished(BlockCopyCallState *call_state); bool block_copy_call_succeeded(BlockCopyCallState *call_state); bool block_copy_call_failed(BlockCopyCallState *call_state); +bool block_copy_call_cancelled(BlockCopyCallState *call_state); int block_copy_call_status(BlockCopyCallState *call_state, bool *error_is_read); void block_copy_set_speed(BlockCopyState *s, uint64_t speed); void block_copy_kick(BlockCopyCallState *call_state); +/* + * Cancel running block-copy call. + * + * Cancel leaves block-copy state valid: dirty bits are correct and you may use + * cancel + <run block_copy with same parameters> to emulate pause/resume. + * + * Note also, that the cancel is async: it only marks block-copy call to be + * cancelled. So, the call may be cancelled (block_copy_call_cancelled() reports + * true) but not yet finished (block_copy_call_finished() reports false). + */ +void block_copy_call_cancel(BlockCopyCallState *call_state); + BdrvDirtyBitmap *block_copy_dirty_bitmap(BlockCopyState *s); void block_copy_set_skip_unallocated(BlockCopyState *s, bool skip); diff --git a/block/block-copy.c b/block/block-copy.c index XXXXXXX..XXXXXXX 100644 --- a/block/block-copy.c +++ b/block/block-copy.c @@ -XXX,XX +XXX,XX @@ typedef struct BlockCopyCallState { int ret; bool finished; QemuCoSleepState *sleep_state; + bool cancelled; /* OUT parameters */ bool error_is_read; @@ -XXX,XX +XXX,XX @@ block_copy_dirty_clusters(BlockCopyCallState *call_state) assert(QEMU_IS_ALIGNED(offset, s->cluster_size)); assert(QEMU_IS_ALIGNED(bytes, s->cluster_size)); - while (bytes && aio_task_pool_status(aio) == 0) { + while (bytes && aio_task_pool_status(aio) == 0 && !call_state->cancelled) { BlockCopyTask *task; int64_t status_bytes; @@ -XXX,XX +XXX,XX @@ static int coroutine_fn block_copy_common(BlockCopyCallState *call_state) do { ret = block_copy_dirty_clusters(call_state); - if (ret == 0) { + if (ret == 0 && !call_state->cancelled) { ret = block_copy_wait_one(call_state->s, call_state->offset, call_state->bytes); } @@ -XXX,XX +XXX,XX @@ static int coroutine_fn block_copy_common(BlockCopyCallState *call_state) * 2. We have waited for some intersecting block-copy request * It may have failed and produced new dirty bits. */ - } while (ret > 0); + } while (ret > 0 && !call_state->cancelled); call_state->finished = true; @@ -XXX,XX +XXX,XX @@ bool block_copy_call_finished(BlockCopyCallState *call_state) bool block_copy_call_succeeded(BlockCopyCallState *call_state) { - return call_state->finished && call_state->ret == 0; + return call_state->finished && !call_state->cancelled && + call_state->ret == 0; } bool block_copy_call_failed(BlockCopyCallState *call_state) { - return call_state->finished && call_state->ret < 0; + return call_state->finished && !call_state->cancelled && + call_state->ret < 0; +} + +bool block_copy_call_cancelled(BlockCopyCallState *call_state) +{ + return call_state->cancelled; } int block_copy_call_status(BlockCopyCallState *call_state, bool *error_is_read) @@ -XXX,XX +XXX,XX @@ int block_copy_call_status(BlockCopyCallState *call_state, bool *error_is_read) return call_state->ret; } +void block_copy_call_cancel(BlockCopyCallState *call_state) +{ + call_state->cancelled = true; + block_copy_kick(call_state); +} + BdrvDirtyBitmap *block_copy_dirty_bitmap(BlockCopyState *s) { return s->copy_bitmap; -- 2.29.2 From: Vladimir Sementsov-Ogievskiy <vsementsov@virtuozzo.com> We are going to use async block-copy call in backup, so we'll need to passthrough setting backup speed to block-copy call. Signed-off-by: Vladimir Sementsov-Ogievskiy <vsementsov@virtuozzo.com> Reviewed-by: Max Reitz <mreitz@redhat.com> Message-Id: <20210116214705.822267-9-vsementsov@virtuozzo.com> Signed-off-by: Max Reitz <mreitz@redhat.com> --- include/block/blockjob_int.h | 2 ++ blockjob.c | 6 ++++++ 2 files changed, 8 insertions(+) diff --git a/include/block/blockjob_int.h b/include/block/blockjob_int.h index XXXXXXX..XXXXXXX 100644 --- a/include/block/blockjob_int.h +++ b/include/block/blockjob_int.h @@ -XXX,XX +XXX,XX @@ struct BlockJobDriver { * besides job->blk to the new AioContext. */ void (*attached_aio_context)(BlockJob *job, AioContext *new_context); + + void (*set_speed)(BlockJob *job, int64_t speed); }; /** diff --git a/blockjob.c b/blockjob.c index XXXXXXX..XXXXXXX 100644 --- a/blockjob.c +++ b/blockjob.c @@ -XXX,XX +XXX,XX @@ static bool job_timer_pending(Job *job) void block_job_set_speed(BlockJob *job, int64_t speed, Error **errp) { + const BlockJobDriver *drv = block_job_driver(job); int64_t old_speed = job->speed; if (job_apply_verb(&job->job, JOB_VERB_SET_SPEED, errp)) { @@ -XXX,XX +XXX,XX @@ void block_job_set_speed(BlockJob *job, int64_t speed, Error **errp) ratelimit_set_speed(&job->limit, speed, BLOCK_JOB_SLICE_TIME); job->speed = speed; + + if (drv->set_speed) { + drv->set_speed(job, speed); + } + if (speed && speed <= old_speed) { return; } -- 2.29.2 From: Vladimir Sementsov-Ogievskiy <vsementsov@virtuozzo.com> If main job coroutine called job_yield (while some background process is in progress), we should give it a chance to call job_pause_point(). It will be used in backup, when moved on async block-copy. Note, that job_user_pause is not enough: we want to handle child_job_drained_begin() as well, which call job_pause(). Still, if job is already in job_do_yield() in job_pause_point() we should not enter it. iotest 109 output is modified: on stop we do bdrv_drain_all() which now triggers job pause immediately (and pause after ready is standby). Signed-off-by: Vladimir Sementsov-Ogievskiy <vsementsov@virtuozzo.com> Message-Id: <20210116214705.822267-10-vsementsov@virtuozzo.com> Reviewed-by: Max Reitz <mreitz@redhat.com> Signed-off-by: Max Reitz <mreitz@redhat.com> --- job.c | 3 +++ tests/qemu-iotests/109.out | 24 ++++++++++++++++++++++++ 2 files changed, 27 insertions(+) diff --git a/job.c b/job.c index XXXXXXX..XXXXXXX 100644 --- a/job.c +++ b/job.c @@ -XXX,XX +XXX,XX @@ static bool job_timer_not_pending(Job *job) void job_pause(Job *job) { job->pause_count++; + if (!job->paused) { + job_enter(job); + } } void job_resume(Job *job) diff --git a/tests/qemu-iotests/109.out b/tests/qemu-iotests/109.out index XXXXXXX..XXXXXXX 100644 --- a/tests/qemu-iotests/109.out +++ b/tests/qemu-iotests/109.out @@ -XXX,XX +XXX,XX @@ read 512/512 bytes at offset 0 {"execute":"quit"} {"return": {}} {"timestamp": {"seconds": TIMESTAMP, "microseconds": TIMESTAMP}, "event": "SHUTDOWN", "data": {"guest": false, "reason": "host-qmp-quit"}} +{"timestamp": {"seconds": TIMESTAMP, "microseconds": TIMESTAMP}, "event": "JOB_STATUS_CHANGE", "data": {"status": "standby", "id": "src"}} +{"timestamp": {"seconds": TIMESTAMP, "microseconds": TIMESTAMP}, "event": "JOB_STATUS_CHANGE", "data": {"status": "ready", "id": "src"}} {"timestamp": {"seconds": TIMESTAMP, "microseconds": TIMESTAMP}, "event": "JOB_STATUS_CHANGE", "data": {"status": "waiting", "id": "src"}} {"timestamp": {"seconds": TIMESTAMP, "microseconds": TIMESTAMP}, "event": "JOB_STATUS_CHANGE", "data": {"status": "pending", "id": "src"}} {"timestamp": {"seconds": TIMESTAMP, "microseconds": TIMESTAMP}, "event": "BLOCK_JOB_COMPLETED", "data": {"device": "src", "len": 1024, "offset": 1024, "speed": 0, "type": "mirror"}} @@ -XXX,XX +XXX,XX @@ read 512/512 bytes at offset 0 {"execute":"quit"} {"return": {}} {"timestamp": {"seconds": TIMESTAMP, "microseconds": TIMESTAMP}, "event": "SHUTDOWN", "data": {"guest": false, "reason": "host-qmp-quit"}} +{"timestamp": {"seconds": TIMESTAMP, "microseconds": TIMESTAMP}, "event": "JOB_STATUS_CHANGE", "data": {"status": "standby", "id": "src"}} +{"timestamp": {"seconds": TIMESTAMP, "microseconds": TIMESTAMP}, "event": "JOB_STATUS_CHANGE", "data": {"status": "ready", "id": "src"}} {"timestamp": {"seconds": TIMESTAMP, "microseconds": TIMESTAMP}, "event": "JOB_STATUS_CHANGE", "data": {"status": "waiting", "id": "src"}} {"timestamp": {"seconds": TIMESTAMP, "microseconds": TIMESTAMP}, "event": "JOB_STATUS_CHANGE", "data": {"status": "pending", "id": "src"}} {"timestamp": {"seconds": TIMESTAMP, "microseconds": TIMESTAMP}, "event": "BLOCK_JOB_COMPLETED", "data": {"device": "src", "len": 197120, "offset": 197120, "speed": 0, "type": "mirror"}} @@ -XXX,XX +XXX,XX @@ read 512/512 bytes at offset 0 {"execute":"quit"} {"return": {}} {"timestamp": {"seconds": TIMESTAMP, "microseconds": TIMESTAMP}, "event": "SHUTDOWN", "data": {"guest": false, "reason": "host-qmp-quit"}} +{"timestamp": {"seconds": TIMESTAMP, "microseconds": TIMESTAMP}, "event": "JOB_STATUS_CHANGE", "data": {"status": "standby", "id": "src"}} +{"timestamp": {"seconds": TIMESTAMP, "microseconds": TIMESTAMP}, "event": "JOB_STATUS_CHANGE", "data": {"status": "ready", "id": "src"}} {"timestamp": {"seconds": TIMESTAMP, "microseconds": TIMESTAMP}, "event": "JOB_STATUS_CHANGE", "data": {"status": "waiting", "id": "src"}} {"timestamp": {"seconds": TIMESTAMP, "microseconds": TIMESTAMP}, "event": "JOB_STATUS_CHANGE", "data": {"status": "pending", "id": "src"}} {"timestamp": {"seconds": TIMESTAMP, "microseconds": TIMESTAMP}, "event": "BLOCK_JOB_COMPLETED", "data": {"device": "src", "len": 327680, "offset": 327680, "speed": 0, "type": "mirror"}} @@ -XXX,XX +XXX,XX @@ read 512/512 bytes at offset 0 {"execute":"quit"} {"return": {}} {"timestamp": {"seconds": TIMESTAMP, "microseconds": TIMESTAMP}, "event": "SHUTDOWN", "data": {"guest": false, "reason": "host-qmp-quit"}} +{"timestamp": {"seconds": TIMESTAMP, "microseconds": TIMESTAMP}, "event": "JOB_STATUS_CHANGE", "data": {"status": "standby", "id": "src"}} +{"timestamp": {"seconds": TIMESTAMP, "microseconds": TIMESTAMP}, "event": "JOB_STATUS_CHANGE", "data": {"status": "ready", "id": "src"}} {"timestamp": {"seconds": TIMESTAMP, "microseconds": TIMESTAMP}, "event": "JOB_STATUS_CHANGE", "data": {"status": "waiting", "id": "src"}} {"timestamp": {"seconds": TIMESTAMP, "microseconds": TIMESTAMP}, "event": "JOB_STATUS_CHANGE", "data": {"status": "pending", "id": "src"}} {"timestamp": {"seconds": TIMESTAMP, "microseconds": TIMESTAMP}, "event": "BLOCK_JOB_COMPLETED", "data": {"device": "src", "len": 1024, "offset": 1024, "speed": 0, "type": "mirror"}} @@ -XXX,XX +XXX,XX @@ read 512/512 bytes at offset 0 {"execute":"quit"} {"return": {}} {"timestamp": {"seconds": TIMESTAMP, "microseconds": TIMESTAMP}, "event": "SHUTDOWN", "data": {"guest": false, "reason": "host-qmp-quit"}} +{"timestamp": {"seconds": TIMESTAMP, "microseconds": TIMESTAMP}, "event": "JOB_STATUS_CHANGE", "data": {"status": "standby", "id": "src"}} +{"timestamp": {"seconds": TIMESTAMP, "microseconds": TIMESTAMP}, "event": "JOB_STATUS_CHANGE", "data": {"status": "ready", "id": "src"}} {"timestamp": {"seconds": TIMESTAMP, "microseconds": TIMESTAMP}, "event": "JOB_STATUS_CHANGE", "data": {"status": "waiting", "id": "src"}} {"timestamp": {"seconds": TIMESTAMP, "microseconds": TIMESTAMP}, "event": "JOB_STATUS_CHANGE", "data": {"status": "pending", "id": "src"}} {"timestamp": {"seconds": TIMESTAMP, "microseconds": TIMESTAMP}, "event": "BLOCK_JOB_COMPLETED", "data": {"device": "src", "len": 65536, "offset": 65536, "speed": 0, "type": "mirror"}} @@ -XXX,XX +XXX,XX @@ read 512/512 bytes at offset 0 {"execute":"quit"} {"return": {}} {"timestamp": {"seconds": TIMESTAMP, "microseconds": TIMESTAMP}, "event": "SHUTDOWN", "data": {"guest": false, "reason": "host-qmp-quit"}} +{"timestamp": {"seconds": TIMESTAMP, "microseconds": TIMESTAMP}, "event": "JOB_STATUS_CHANGE", "data": {"status": "standby", "id": "src"}} +{"timestamp": {"seconds": TIMESTAMP, "microseconds": TIMESTAMP}, "event": "JOB_STATUS_CHANGE", "data": {"status": "ready", "id": "src"}} {"timestamp": {"seconds": TIMESTAMP, "microseconds": TIMESTAMP}, "event": "JOB_STATUS_CHANGE", "data": {"status": "waiting", "id": "src"}} {"timestamp": {"seconds": TIMESTAMP, "microseconds": TIMESTAMP}, "event": "JOB_STATUS_CHANGE", "data": {"status": "pending", "id": "src"}} {"timestamp": {"seconds": TIMESTAMP, "microseconds": TIMESTAMP}, "event": "BLOCK_JOB_COMPLETED", "data": {"device": "src", "len": 2560, "offset": 2560, "speed": 0, "type": "mirror"}} @@ -XXX,XX +XXX,XX @@ read 512/512 bytes at offset 0 {"execute":"quit"} {"return": {}} {"timestamp": {"seconds": TIMESTAMP, "microseconds": TIMESTAMP}, "event": "SHUTDOWN", "data": {"guest": false, "reason": "host-qmp-quit"}} +{"timestamp": {"seconds": TIMESTAMP, "microseconds": TIMESTAMP}, "event": "JOB_STATUS_CHANGE", "data": {"status": "standby", "id": "src"}} +{"timestamp": {"seconds": TIMESTAMP, "microseconds": TIMESTAMP}, "event": "JOB_STATUS_CHANGE", "data": {"status": "ready", "id": "src"}} {"timestamp": {"seconds": TIMESTAMP, "microseconds": TIMESTAMP}, "event": "JOB_STATUS_CHANGE", "data": {"status": "waiting", "id": "src"}} {"timestamp": {"seconds": TIMESTAMP, "microseconds": TIMESTAMP}, "event": "JOB_STATUS_CHANGE", "data": {"status": "pending", "id": "src"}} {"timestamp": {"seconds": TIMESTAMP, "microseconds": TIMESTAMP}, "event": "BLOCK_JOB_COMPLETED", "data": {"device": "src", "len": 2560, "offset": 2560, "speed": 0, "type": "mirror"}} @@ -XXX,XX +XXX,XX @@ read 512/512 bytes at offset 0 {"execute":"quit"} {"return": {}} {"timestamp": {"seconds": TIMESTAMP, "microseconds": TIMESTAMP}, "event": "SHUTDOWN", "data": {"guest": false, "reason": "host-qmp-quit"}} +{"timestamp": {"seconds": TIMESTAMP, "microseconds": TIMESTAMP}, "event": "JOB_STATUS_CHANGE", "data": {"status": "standby", "id": "src"}} +{"timestamp": {"seconds": TIMESTAMP, "microseconds": TIMESTAMP}, "event": "JOB_STATUS_CHANGE", "data": {"status": "ready", "id": "src"}} {"timestamp": {"seconds": TIMESTAMP, "microseconds": TIMESTAMP}, "event": "JOB_STATUS_CHANGE", "data": {"status": "waiting", "id": "src"}} {"timestamp": {"seconds": TIMESTAMP, "microseconds": TIMESTAMP}, "event": "JOB_STATUS_CHANGE", "data": {"status": "pending", "id": "src"}} {"timestamp": {"seconds": TIMESTAMP, "microseconds": TIMESTAMP}, "event": "BLOCK_JOB_COMPLETED", "data": {"device": "src", "len": 31457280, "offset": 31457280, "speed": 0, "type": "mirror"}} @@ -XXX,XX +XXX,XX @@ read 512/512 bytes at offset 0 {"execute":"quit"} {"return": {}} {"timestamp": {"seconds": TIMESTAMP, "microseconds": TIMESTAMP}, "event": "SHUTDOWN", "data": {"guest": false, "reason": "host-qmp-quit"}} +{"timestamp": {"seconds": TIMESTAMP, "microseconds": TIMESTAMP}, "event": "JOB_STATUS_CHANGE", "data": {"status": "standby", "id": "src"}} +{"timestamp": {"seconds": TIMESTAMP, "microseconds": TIMESTAMP}, "event": "JOB_STATUS_CHANGE", "data": {"status": "ready", "id": "src"}} {"timestamp": {"seconds": TIMESTAMP, "microseconds": TIMESTAMP}, "event": "JOB_STATUS_CHANGE", "data": {"status": "waiting", "id": "src"}} {"timestamp": {"seconds": TIMESTAMP, "microseconds": TIMESTAMP}, "event": "JOB_STATUS_CHANGE", "data": {"status": "pending", "id": "src"}} {"timestamp": {"seconds": TIMESTAMP, "microseconds": TIMESTAMP}, "event": "BLOCK_JOB_COMPLETED", "data": {"device": "src", "len": 327680, "offset": 327680, "speed": 0, "type": "mirror"}} @@ -XXX,XX +XXX,XX @@ read 512/512 bytes at offset 0 {"execute":"quit"} {"return": {}} {"timestamp": {"seconds": TIMESTAMP, "microseconds": TIMESTAMP}, "event": "SHUTDOWN", "data": {"guest": false, "reason": "host-qmp-quit"}} +{"timestamp": {"seconds": TIMESTAMP, "microseconds": TIMESTAMP}, "event": "JOB_STATUS_CHANGE", "data": {"status": "standby", "id": "src"}} +{"timestamp": {"seconds": TIMESTAMP, "microseconds": TIMESTAMP}, "event": "JOB_STATUS_CHANGE", "data": {"status": "ready", "id": "src"}} {"timestamp": {"seconds": TIMESTAMP, "microseconds": TIMESTAMP}, "event": "JOB_STATUS_CHANGE", "data": {"status": "waiting", "id": "src"}} {"timestamp": {"seconds": TIMESTAMP, "microseconds": TIMESTAMP}, "event": "JOB_STATUS_CHANGE", "data": {"status": "pending", "id": "src"}} {"timestamp": {"seconds": TIMESTAMP, "microseconds": TIMESTAMP}, "event": "BLOCK_JOB_COMPLETED", "data": {"device": "src", "len": 2048, "offset": 2048, "speed": 0, "type": "mirror"}} @@ -XXX,XX +XXX,XX @@ WARNING: Image format was not specified for 'TEST_DIR/t.raw' and probing guessed {"execute":"quit"} {"return": {}} {"timestamp": {"seconds": TIMESTAMP, "microseconds": TIMESTAMP}, "event": "SHUTDOWN", "data": {"guest": false, "reason": "host-qmp-quit"}} +{"timestamp": {"seconds": TIMESTAMP, "microseconds": TIMESTAMP}, "event": "JOB_STATUS_CHANGE", "data": {"status": "standby", "id": "src"}} +{"timestamp": {"seconds": TIMESTAMP, "microseconds": TIMESTAMP}, "event": "JOB_STATUS_CHANGE", "data": {"status": "ready", "id": "src"}} {"timestamp": {"seconds": TIMESTAMP, "microseconds": TIMESTAMP}, "event": "JOB_STATUS_CHANGE", "data": {"status": "waiting", "id": "src"}} {"timestamp": {"seconds": TIMESTAMP, "microseconds": TIMESTAMP}, "event": "JOB_STATUS_CHANGE", "data": {"status": "pending", "id": "src"}} {"timestamp": {"seconds": TIMESTAMP, "microseconds": TIMESTAMP}, "event": "BLOCK_JOB_COMPLETED", "data": {"device": "src", "len": 512, "offset": 512, "speed": 0, "type": "mirror"}} @@ -XXX,XX +XXX,XX @@ Images are identical. {"execute":"quit"} {"return": {}} {"timestamp": {"seconds": TIMESTAMP, "microseconds": TIMESTAMP}, "event": "SHUTDOWN", "data": {"guest": false, "reason": "host-qmp-quit"}} +{"timestamp": {"seconds": TIMESTAMP, "microseconds": TIMESTAMP}, "event": "JOB_STATUS_CHANGE", "data": {"status": "standby", "id": "src"}} +{"timestamp": {"seconds": TIMESTAMP, "microseconds": TIMESTAMP}, "event": "JOB_STATUS_CHANGE", "data": {"status": "ready", "id": "src"}} {"timestamp": {"seconds": TIMESTAMP, "microseconds": TIMESTAMP}, "event": "JOB_STATUS_CHANGE", "data": {"status": "waiting", "id": "src"}} {"timestamp": {"seconds": TIMESTAMP, "microseconds": TIMESTAMP}, "event": "JOB_STATUS_CHANGE", "data": {"status": "pending", "id": "src"}} {"timestamp": {"seconds": TIMESTAMP, "microseconds": TIMESTAMP}, "event": "BLOCK_JOB_COMPLETED", "data": {"device": "src", "len": 512, "offset": 512, "speed": 0, "type": "mirror"}} -- 2.29.2 From: Vladimir Sementsov-Ogievskiy <vsementsov@virtuozzo.com> Add new parameters to configure future backup features. The patch doesn't introduce aio backup requests (so we actually have only one worker) neither requests larger than one cluster. Still, formally we satisfy these maximums anyway, so add the parameters now, to facilitate further patch which will really change backup job behavior. Signed-off-by: Vladimir Sementsov-Ogievskiy <vsementsov@virtuozzo.com> Reviewed-by: Max Reitz <mreitz@redhat.com> Message-Id: <20210116214705.822267-11-vsementsov@virtuozzo.com> Signed-off-by: Max Reitz <mreitz@redhat.com> --- qapi/block-core.json | 13 ++++++++++++- block/backup.c | 28 +++++++++++++++++++++++----- block/replication.c | 2 +- blockdev.c | 8 +++++++- 4 files changed, 43 insertions(+), 8 deletions(-) diff --git a/qapi/block-core.json b/qapi/block-core.json index XXXXXXX..XXXXXXX 100644 --- a/qapi/block-core.json +++ b/qapi/block-core.json @@ -XXX,XX +XXX,XX @@ # # @use-copy-range: Use copy offloading. Default true. # +# @max-workers: Maximum number of parallel requests for the sustained background +# copying process. Doesn't influence copy-before-write operations. +# Default 64. +# +# @max-chunk: Maximum request length for the sustained background copying +# process. Doesn't influence copy-before-write operations. +# 0 means unlimited. If max-chunk is non-zero then it should not be +# less than job cluster size which is calculated as maximum of +# target image cluster size and 64k. Default 0. +# # Since: 6.0 ## { 'struct': 'BackupPerf', - 'data': { '*use-copy-range': 'bool' }} + 'data': { '*use-copy-range': 'bool', + '*max-workers': 'int', '*max-chunk': 'int64' } } ## # @BackupCommon: diff --git a/block/backup.c b/block/backup.c index XXXXXXX..XXXXXXX 100644 --- a/block/backup.c +++ b/block/backup.c @@ -XXX,XX +XXX,XX @@ BlockJob *backup_job_create(const char *job_id, BlockDriverState *bs, return NULL; } + cluster_size = backup_calculate_cluster_size(target, errp); + if (cluster_size < 0) { + goto error; + } + + if (perf->max_workers < 1) { + error_setg(errp, "max-workers must be greater than zero"); + return NULL; + } + + if (perf->max_chunk < 0) { + error_setg(errp, "max-chunk must be zero (which means no limit) or " + "positive"); + return NULL; + } + + if (perf->max_chunk && perf->max_chunk < cluster_size) { + error_setg(errp, "Required max-chunk (%" PRIi64 ") is less than backup " + "cluster size (%" PRIi64 ")", perf->max_chunk, cluster_size); + return NULL; + } + + if (sync_bitmap) { /* If we need to write to this bitmap, check that we can: */ if (bitmap_mode != BITMAP_SYNC_MODE_NEVER && @@ -XXX,XX +XXX,XX @@ BlockJob *backup_job_create(const char *job_id, BlockDriverState *bs, goto error; } - cluster_size = backup_calculate_cluster_size(target, errp); - if (cluster_size < 0) { - goto error; - } - /* * If source is in backing chain of target assume that target is going to be * used for "image fleecing", i.e. it should represent a kind of snapshot of diff --git a/block/replication.c b/block/replication.c index XXXXXXX..XXXXXXX 100644 --- a/block/replication.c +++ b/block/replication.c @@ -XXX,XX +XXX,XX @@ static void replication_start(ReplicationState *rs, ReplicationMode mode, int64_t active_length, hidden_length, disk_length; AioContext *aio_context; Error *local_err = NULL; - BackupPerf perf = { .use_copy_range = true }; + BackupPerf perf = { .use_copy_range = true, .max_workers = 1 }; aio_context = bdrv_get_aio_context(bs); aio_context_acquire(aio_context); diff --git a/blockdev.c b/blockdev.c index XXXXXXX..XXXXXXX 100644 --- a/blockdev.c +++ b/blockdev.c @@ -XXX,XX +XXX,XX @@ static BlockJob *do_backup_common(BackupCommon *backup, { BlockJob *job = NULL; BdrvDirtyBitmap *bmap = NULL; - BackupPerf perf = { .use_copy_range = true }; + BackupPerf perf = { .use_copy_range = true, .max_workers = 64 }; int job_flags = JOB_DEFAULT; if (!backup->has_speed) { @@ -XXX,XX +XXX,XX @@ static BlockJob *do_backup_common(BackupCommon *backup, if (backup->x_perf->has_use_copy_range) { perf.use_copy_range = backup->x_perf->use_copy_range; } + if (backup->x_perf->has_max_workers) { + perf.max_workers = backup->x_perf->max_workers; + } + if (backup->x_perf->has_max_chunk) { + perf.max_chunk = backup->x_perf->max_chunk; + } } if ((backup->sync == MIRROR_SYNC_MODE_BITMAP) || -- 2.29.2 From: Vladimir Sementsov-Ogievskiy <vsementsov@virtuozzo.com> After introducing parallel async copy requests instead of plain cluster-by-cluster copying loop, we'll have to wait for paused status, as we need to wait for several parallel request. So, let's gently wait instead of just asserting that job already paused. Signed-off-by: Vladimir Sementsov-Ogievskiy <vsementsov@virtuozzo.com> Reviewed-by: Max Reitz <mreitz@redhat.com> Message-Id: <20210116214705.822267-12-vsementsov@virtuozzo.com> Signed-off-by: Max Reitz <mreitz@redhat.com> --- tests/qemu-iotests/056 | 9 +++++++-- 1 file changed, 7 insertions(+), 2 deletions(-) diff --git a/tests/qemu-iotests/056 b/tests/qemu-iotests/056 index XXXXXXX..XXXXXXX 100755 --- a/tests/qemu-iotests/056 +++ b/tests/qemu-iotests/056 @@ -XXX,XX +XXX,XX @@ class BackupTest(iotests.QMPTestCase): event = self.vm.event_wait(name="BLOCK_JOB_ERROR", match={'data': {'device': 'drive0'}}) self.assertNotEqual(event, None) - # OK, job should be wedged - res = self.vm.qmp('query-block-jobs') + # OK, job should pause, but it can't do it immediately, as it can't + # cancel other parallel requests (which didn't fail) + with iotests.Timeout(60, "Timeout waiting for backup actually paused"): + while True: + res = self.vm.qmp('query-block-jobs') + if res['return'][0]['status'] == 'paused': + break self.assert_qmp(res, 'return[0]/status', 'paused') res = self.vm.qmp('block-job-dismiss', id='drive0') self.assert_qmp(res, 'error/desc', -- 2.29.2 Right now, this does not change anything, because backup ignores max-chunk and max-workers. However, as soon as backup is switched over to block-copy for the background copying process, we will need it to keep 129 passing. Signed-off-by: Max Reitz <mreitz@redhat.com> Message-Id: <20210120102043.28346-1-mreitz@redhat.com> Reviewed-by: Vladimir Sementsov-Ogievskiy <vsementsov@virtuozzo.com> --- tests/qemu-iotests/129 | 7 ++++++- 1 file changed, 6 insertions(+), 1 deletion(-) diff --git a/tests/qemu-iotests/129 b/tests/qemu-iotests/129 index XXXXXXX..XXXXXXX 100755 --- a/tests/qemu-iotests/129 +++ b/tests/qemu-iotests/129 @@ -XXX,XX +XXX,XX @@ class TestStopWithBlockJob(iotests.QMPTestCase): sync="full", buf_size=65536) def test_drive_backup(self): + # Limit max-chunk and max-workers so that block-copy will not + # launch so many workers working on so much data each that + # stop's bdrv_drain_all() would finish the job self.do_test_stop("drive-backup", device="drive0", target=self.target_img, format=iotests.imgfmt, - sync="full") + sync="full", + x_perf={ 'max-chunk': 65536, + 'max-workers': 8 }) def test_block_commit(self): # Add overlay above the source node so that we actually use a -- 2.29.2 From: Vladimir Sementsov-Ogievskiy <vsementsov@virtuozzo.com> The further change of moving backup to be a one block-copy call will make copying chunk-size and cluster-size two separate things. So, even with 64k cluster sized qcow2 image, default chunk would be 1M. 185 test however assumes, that with speed limited to 64K, one iteration would result in offset=64K. It will change, as first iteration would result in offset=1M independently of speed. So, let's explicitly specify, what test wants: set max-chunk to 64K, so that one iteration is 64K. Note, that we don't need to limit max-workers, as block-copy rate limiter will handle the situation and wouldn't start new workers when speed limit is obviously reached. Signed-off-by: Vladimir Sementsov-Ogievskiy <vsementsov@virtuozzo.com> Reviewed-by: Max Reitz <mreitz@redhat.com> Message-Id: <20210116214705.822267-13-vsementsov@virtuozzo.com> Signed-off-by: Max Reitz <mreitz@redhat.com> --- tests/qemu-iotests/185 | 3 ++- tests/qemu-iotests/185.out | 3 ++- 2 files changed, 4 insertions(+), 2 deletions(-) diff --git a/tests/qemu-iotests/185 b/tests/qemu-iotests/185 index XXXXXXX..XXXXXXX 100755 --- a/tests/qemu-iotests/185 +++ b/tests/qemu-iotests/185 @@ -XXX,XX +XXX,XX @@ _send_qemu_cmd $h \ 'target': '$TEST_IMG.copy', 'format': '$IMGFMT', 'sync': 'full', - 'speed': 65536 } }" \ + 'speed': 65536, + 'x-perf': {'max-chunk': 65536} } }" \ "return" # If we don't sleep here 'quit' command races with disk I/O diff --git a/tests/qemu-iotests/185.out b/tests/qemu-iotests/185.out index XXXXXXX..XXXXXXX 100644 --- a/tests/qemu-iotests/185.out +++ b/tests/qemu-iotests/185.out @@ -XXX,XX +XXX,XX @@ Formatting 'TEST_DIR/t.qcow2.copy', fmt=qcow2 cluster_size=65536 extended_l2=off 'target': 'TEST_DIR/t.IMGFMT.copy', 'format': 'IMGFMT', 'sync': 'full', - 'speed': 65536 } } + 'speed': 65536, + 'x-perf': { 'max-chunk': 65536 } } } Formatting 'TEST_DIR/t.qcow2.copy', fmt=qcow2 cluster_size=65536 extended_l2=off compression_type=zlib size=67108864 lazy_refcounts=off refcount_bits=16 {"timestamp": {"seconds": TIMESTAMP, "microseconds": TIMESTAMP}, "event": "JOB_STATUS_CHANGE", "data": {"status": "created", "id": "disk"}} {"timestamp": {"seconds": TIMESTAMP, "microseconds": TIMESTAMP}, "event": "JOB_STATUS_CHANGE", "data": {"status": "running", "id": "disk"}} -- 2.29.2 From: Vladimir Sementsov-Ogievskiy <vsementsov@virtuozzo.com> The further change of moving backup to be a one block-copy call will make copying chunk-size and cluster-size two separate things. So, even with 64k cluster sized qcow2 image, default chunk would be 1M. Test 219 depends on specified chunk-size. Update it for explicit chunk-size for backup as for mirror. Signed-off-by: Vladimir Sementsov-Ogievskiy <vsementsov@virtuozzo.com> Reviewed-by: Max Reitz <mreitz@redhat.com> Message-Id: <20210116214705.822267-14-vsementsov@virtuozzo.com> Signed-off-by: Max Reitz <mreitz@redhat.com> --- tests/qemu-iotests/219 | 13 +++++++------ 1 file changed, 7 insertions(+), 6 deletions(-) diff --git a/tests/qemu-iotests/219 b/tests/qemu-iotests/219 index XXXXXXX..XXXXXXX 100755 --- a/tests/qemu-iotests/219 +++ b/tests/qemu-iotests/219 @@ -XXX,XX +XXX,XX @@ with iotests.FilePath('disk.img') as disk_path, \ # but related to this also automatic state transitions like job # completion), but still get pause points often enough to avoid making this # test very slow, it's important to have the right ratio between speed and - # buf_size. + # copy-chunk-size. # - # For backup, buf_size is hard-coded to the source image cluster size (64k), - # so we'll pick the same for mirror. The slice time, i.e. the granularity - # of the rate limiting is 100ms. With a speed of 256k per second, we can - # get four pause points per second. This gives us 250ms per iteration, - # which should be enough to stay deterministic. + # Chose 64k copy-chunk-size both for mirror (by buf_size) and backup (by + # x-max-chunk). The slice time, i.e. the granularity of the rate limiting + # is 100ms. With a speed of 256k per second, we can get four pause points + # per second. This gives us 250ms per iteration, which should be enough to + # stay deterministic. test_job_lifecycle(vm, 'drive-mirror', has_ready=True, job_args={ 'device': 'drive0-node', @@ -XXX,XX +XXX,XX @@ with iotests.FilePath('disk.img') as disk_path, \ 'target': copy_path, 'sync': 'full', 'speed': 262144, + 'x-perf': {'max-chunk': 65536}, 'auto-finalize': auto_finalize, 'auto-dismiss': auto_dismiss, }) -- 2.29.2 From: Vladimir Sementsov-Ogievskiy <vsementsov@virtuozzo.com> Iotest 257 dumps a lot of in-progress information of backup job, such as offset and bitmap dirtiness. Further commit will move backup to be one block-copy call, which will introduce async parallel requests instead of plain cluster-by-cluster copying. To keep things deterministic, allow only one worker (only one copy request at a time) for this test. Signed-off-by: Vladimir Sementsov-Ogievskiy <vsementsov@virtuozzo.com> Reviewed-by: Max Reitz <mreitz@redhat.com> Message-Id: <20210116214705.822267-15-vsementsov@virtuozzo.com> Signed-off-by: Max Reitz <mreitz@redhat.com> --- tests/qemu-iotests/257 | 1 + tests/qemu-iotests/257.out | 306 ++++++++++++++++++------------------- 2 files changed, 154 insertions(+), 153 deletions(-) diff --git a/tests/qemu-iotests/257 b/tests/qemu-iotests/257 index XXXXXXX..XXXXXXX 100755 --- a/tests/qemu-iotests/257 +++ b/tests/qemu-iotests/257 @@ -XXX,XX +XXX,XX @@ def blockdev_backup(vm, device, target, sync, **kwargs): target=target, sync=sync, filter_node_name='backup-top', + x_perf={'max-workers': 1}, **kwargs) return result diff --git a/tests/qemu-iotests/257.out b/tests/qemu-iotests/257.out index XXXXXXX..XXXXXXX 100644 --- a/tests/qemu-iotests/257.out +++ b/tests/qemu-iotests/257.out @@ -XXX,XX +XXX,XX @@ write -P0x76 0x3ff0000 0x10000 {"execute": "job-dismiss", "arguments": {"id": "bdc-fmt-job"}} {"return": {}} {} -{"execute": "blockdev-backup", "arguments": {"device": "drive0", "filter-node-name": "backup-top", "job-id": "ref_backup_0", "sync": "full", "target": "ref_target_0"}} +{"execute": "blockdev-backup", "arguments": {"device": "drive0", "filter-node-name": "backup-top", "job-id": "ref_backup_0", "sync": "full", "target": "ref_target_0", "x-perf": {"max-workers": 1}}} {"return": {}} {"data": {"device": "ref_backup_0", "len": 67108864, "offset": 67108864, "speed": 0, "type": "backup"}, "event": "BLOCK_JOB_COMPLETED", "timestamp": {"microseconds": "USECS", "seconds": "SECS"}} @@ -XXX,XX +XXX,XX @@ expecting 6 dirty sectors; have 6. OK! {"execute": "job-dismiss", "arguments": {"id": "bdc-fmt-job"}} {"return": {}} {} -{"execute": "blockdev-backup", "arguments": {"device": "drive0", "filter-node-name": "backup-top", "job-id": "ref_backup_1", "sync": "full", "target": "ref_target_1"}} +{"execute": "blockdev-backup", "arguments": {"device": "drive0", "filter-node-name": "backup-top", "job-id": "ref_backup_1", "sync": "full", "target": "ref_target_1", "x-perf": {"max-workers": 1}}} {"return": {}} {"data": {"device": "ref_backup_1", "len": 67108864, "offset": 67108864, "speed": 0, "type": "backup"}, "event": "BLOCK_JOB_COMPLETED", "timestamp": {"microseconds": "USECS", "seconds": "SECS"}} @@ -XXX,XX +XXX,XX @@ expecting 6 dirty sectors; have 6. OK! {"execute": "job-dismiss", "arguments": {"id": "bdc-fmt-job"}} {"return": {}} {} -{"execute": "blockdev-backup", "arguments": {"auto-finalize": false, "bitmap": "bitmap0", "bitmap-mode": "never", "device": "drive0", "filter-node-name": "backup-top", "job-id": "backup_1", "sync": "bitmap", "target": "backup_target_1"}} +{"execute": "blockdev-backup", "arguments": {"auto-finalize": false, "bitmap": "bitmap0", "bitmap-mode": "never", "device": "drive0", "filter-node-name": "backup-top", "job-id": "backup_1", "sync": "bitmap", "target": "backup_target_1", "x-perf": {"max-workers": 1}}} {"return": {}} --- Write #2 --- @@ -XXX,XX +XXX,XX @@ expecting 15 dirty sectors; have 15. OK! {"execute": "job-dismiss", "arguments": {"id": "bdc-fmt-job"}} {"return": {}} {} -{"execute": "blockdev-backup", "arguments": {"device": "drive0", "filter-node-name": "backup-top", "job-id": "ref_backup_2", "sync": "full", "target": "ref_target_2"}} +{"execute": "blockdev-backup", "arguments": {"device": "drive0", "filter-node-name": "backup-top", "job-id": "ref_backup_2", "sync": "full", "target": "ref_target_2", "x-perf": {"max-workers": 1}}} {"return": {}} {"data": {"device": "ref_backup_2", "len": 67108864, "offset": 67108864, "speed": 0, "type": "backup"}, "event": "BLOCK_JOB_COMPLETED", "timestamp": {"microseconds": "USECS", "seconds": "SECS"}} @@ -XXX,XX +XXX,XX @@ expecting 15 dirty sectors; have 15. OK! {"execute": "job-dismiss", "arguments": {"id": "bdc-fmt-job"}} {"return": {}} {} -{"execute": "blockdev-backup", "arguments": {"auto-finalize": false, "bitmap": "bitmap0", "bitmap-mode": "never", "device": "drive0", "filter-node-name": "backup-top", "job-id": "backup_2", "sync": "bitmap", "target": "backup_target_2"}} +{"execute": "blockdev-backup", "arguments": {"auto-finalize": false, "bitmap": "bitmap0", "bitmap-mode": "never", "device": "drive0", "filter-node-name": "backup-top", "job-id": "backup_2", "sync": "bitmap", "target": "backup_target_2", "x-perf": {"max-workers": 1}}} {"return": {}} {"execute": "job-finalize", "arguments": {"id": "backup_2"}} {"return": {}} @@ -XXX,XX +XXX,XX @@ write -P0x76 0x3ff0000 0x10000 {"execute": "job-dismiss", "arguments": {"id": "bdc-fmt-job"}} {"return": {}} {} -{"execute": "blockdev-backup", "arguments": {"device": "drive0", "filter-node-name": "backup-top", "job-id": "ref_backup_0", "sync": "full", "target": "ref_target_0"}} +{"execute": "blockdev-backup", "arguments": {"device": "drive0", "filter-node-name": "backup-top", "job-id": "ref_backup_0", "sync": "full", "target": "ref_target_0", "x-perf": {"max-workers": 1}}} {"return": {}} {"data": {"device": "ref_backup_0", "len": 67108864, "offset": 67108864, "speed": 0, "type": "backup"}, "event": "BLOCK_JOB_COMPLETED", "timestamp": {"microseconds": "USECS", "seconds": "SECS"}} @@ -XXX,XX +XXX,XX @@ expecting 6 dirty sectors; have 6. OK! {"execute": "job-dismiss", "arguments": {"id": "bdc-fmt-job"}} {"return": {}} {} -{"execute": "blockdev-backup", "arguments": {"device": "drive0", "filter-node-name": "backup-top", "job-id": "ref_backup_1", "sync": "full", "target": "ref_target_1"}} +{"execute": "blockdev-backup", "arguments": {"device": "drive0", "filter-node-name": "backup-top", "job-id": "ref_backup_1", "sync": "full", "target": "ref_target_1", "x-perf": {"max-workers": 1}}} {"return": {}} {"data": {"device": "ref_backup_1", "len": 67108864, "offset": 67108864, "speed": 0, "type": "backup"}, "event": "BLOCK_JOB_COMPLETED", "timestamp": {"microseconds": "USECS", "seconds": "SECS"}} @@ -XXX,XX +XXX,XX @@ expecting 6 dirty sectors; have 6. OK! {"execute": "job-dismiss", "arguments": {"id": "bdc-fmt-job"}} {"return": {}} {} -{"execute": "blockdev-backup", "arguments": {"auto-finalize": false, "bitmap": "bitmap0", "bitmap-mode": "never", "device": "drive0", "filter-node-name": "backup-top", "job-id": "backup_1", "sync": "bitmap", "target": "backup_target_1"}} +{"execute": "blockdev-backup", "arguments": {"auto-finalize": false, "bitmap": "bitmap0", "bitmap-mode": "never", "device": "drive0", "filter-node-name": "backup-top", "job-id": "backup_1", "sync": "bitmap", "target": "backup_target_1", "x-perf": {"max-workers": 1}}} {"return": {}} {"data": {"action": "report", "device": "backup_1", "operation": "read"}, "event": "BLOCK_JOB_ERROR", "timestamp": {"microseconds": "USECS", "seconds": "SECS"}} {"data": {"device": "backup_1", "error": "Input/output error", "len": 393216, "offset": 65536, "speed": 0, "type": "backup"}, "event": "BLOCK_JOB_COMPLETED", "timestamp": {"microseconds": "USECS", "seconds": "SECS"}} @@ -XXX,XX +XXX,XX @@ expecting 14 dirty sectors; have 14. OK! {"execute": "job-dismiss", "arguments": {"id": "bdc-fmt-job"}} {"return": {}} {} -{"execute": "blockdev-backup", "arguments": {"device": "drive0", "filter-node-name": "backup-top", "job-id": "ref_backup_2", "sync": "full", "target": "ref_target_2"}} +{"execute": "blockdev-backup", "arguments": {"device": "drive0", "filter-node-name": "backup-top", "job-id": "ref_backup_2", "sync": "full", "target": "ref_target_2", "x-perf": {"max-workers": 1}}} {"return": {}} {"data": {"device": "ref_backup_2", "len": 67108864, "offset": 67108864, "speed": 0, "type": "backup"}, "event": "BLOCK_JOB_COMPLETED", "timestamp": {"microseconds": "USECS", "seconds": "SECS"}} @@ -XXX,XX +XXX,XX @@ expecting 14 dirty sectors; have 14. OK! {"execute": "job-dismiss", "arguments": {"id": "bdc-fmt-job"}} {"return": {}} {} -{"execute": "blockdev-backup", "arguments": {"auto-finalize": false, "bitmap": "bitmap0", "bitmap-mode": "never", "device": "drive0", "filter-node-name": "backup-top", "job-id": "backup_2", "sync": "bitmap", "target": "backup_target_2"}} +{"execute": "blockdev-backup", "arguments": {"auto-finalize": false, "bitmap": "bitmap0", "bitmap-mode": "never", "device": "drive0", "filter-node-name": "backup-top", "job-id": "backup_2", "sync": "bitmap", "target": "backup_target_2", "x-perf": {"max-workers": 1}}} {"return": {}} {"execute": "job-finalize", "arguments": {"id": "backup_2"}} {"return": {}} @@ -XXX,XX +XXX,XX @@ write -P0x76 0x3ff0000 0x10000 {"execute": "job-dismiss", "arguments": {"id": "bdc-fmt-job"}} {"return": {}} {} -{"execute": "blockdev-backup", "arguments": {"device": "drive0", "filter-node-name": "backup-top", "job-id": "ref_backup_0", "sync": "full", "target": "ref_target_0"}} +{"execute": "blockdev-backup", "arguments": {"device": "drive0", "filter-node-name": "backup-top", "job-id": "ref_backup_0", "sync": "full", "target": "ref_target_0", "x-perf": {"max-workers": 1}}} {"return": {}} {"data": {"device": "ref_backup_0", "len": 67108864, "offset": 67108864, "speed": 0, "type": "backup"}, "event": "BLOCK_JOB_COMPLETED", "timestamp": {"microseconds": "USECS", "seconds": "SECS"}} @@ -XXX,XX +XXX,XX @@ expecting 6 dirty sectors; have 6. OK! {"execute": "job-dismiss", "arguments": {"id": "bdc-fmt-job"}} {"return": {}} {} -{"execute": "blockdev-backup", "arguments": {"device": "drive0", "filter-node-name": "backup-top", "job-id": "ref_backup_1", "sync": "full", "target": "ref_target_1"}} +{"execute": "blockdev-backup", "arguments": {"device": "drive0", "filter-node-name": "backup-top", "job-id": "ref_backup_1", "sync": "full", "target": "ref_target_1", "x-perf": {"max-workers": 1}}} {"return": {}} {"data": {"device": "ref_backup_1", "len": 67108864, "offset": 67108864, "speed": 0, "type": "backup"}, "event": "BLOCK_JOB_COMPLETED", "timestamp": {"microseconds": "USECS", "seconds": "SECS"}} @@ -XXX,XX +XXX,XX @@ expecting 6 dirty sectors; have 6. OK! {"execute": "job-dismiss", "arguments": {"id": "bdc-fmt-job"}} {"return": {}} {} -{"execute": "blockdev-backup", "arguments": {"auto-finalize": false, "bitmap": "bitmap0", "bitmap-mode": "never", "device": "drive0", "filter-node-name": "backup-top", "job-id": "backup_1", "sync": "bitmap", "target": "backup_target_1"}} +{"execute": "blockdev-backup", "arguments": {"auto-finalize": false, "bitmap": "bitmap0", "bitmap-mode": "never", "device": "drive0", "filter-node-name": "backup-top", "job-id": "backup_1", "sync": "bitmap", "target": "backup_target_1", "x-perf": {"max-workers": 1}}} {"return": {}} --- Write #2 --- @@ -XXX,XX +XXX,XX @@ expecting 15 dirty sectors; have 15. OK! {"execute": "job-dismiss", "arguments": {"id": "bdc-fmt-job"}} {"return": {}} {} -{"execute": "blockdev-backup", "arguments": {"device": "drive0", "filter-node-name": "backup-top", "job-id": "ref_backup_2", "sync": "full", "target": "ref_target_2"}} +{"execute": "blockdev-backup", "arguments": {"device": "drive0", "filter-node-name": "backup-top", "job-id": "ref_backup_2", "sync": "full", "target": "ref_target_2", "x-perf": {"max-workers": 1}}} {"return": {}} {"data": {"device": "ref_backup_2", "len": 67108864, "offset": 67108864, "speed": 0, "type": "backup"}, "event": "BLOCK_JOB_COMPLETED", "timestamp": {"microseconds": "USECS", "seconds": "SECS"}} @@ -XXX,XX +XXX,XX @@ expecting 15 dirty sectors; have 15. OK! {"execute": "job-dismiss", "arguments": {"id": "bdc-fmt-job"}} {"return": {}} {} -{"execute": "blockdev-backup", "arguments": {"auto-finalize": false, "bitmap": "bitmap0", "bitmap-mode": "never", "device": "drive0", "filter-node-name": "backup-top", "job-id": "backup_2", "sync": "bitmap", "target": "backup_target_2"}} +{"execute": "blockdev-backup", "arguments": {"auto-finalize": false, "bitmap": "bitmap0", "bitmap-mode": "never", "device": "drive0", "filter-node-name": "backup-top", "job-id": "backup_2", "sync": "bitmap", "target": "backup_target_2", "x-perf": {"max-workers": 1}}} {"return": {}} {"execute": "job-finalize", "arguments": {"id": "backup_2"}} {"return": {}} @@ -XXX,XX +XXX,XX @@ write -P0x76 0x3ff0000 0x10000 {"execute": "job-dismiss", "arguments": {"id": "bdc-fmt-job"}} {"return": {}} {} -{"execute": "blockdev-backup", "arguments": {"device": "drive0", "filter-node-name": "backup-top", "job-id": "ref_backup_0", "sync": "full", "target": "ref_target_0"}} +{"execute": "blockdev-backup", "arguments": {"device": "drive0", "filter-node-name": "backup-top", "job-id": "ref_backup_0", "sync": "full", "target": "ref_target_0", "x-perf": {"max-workers": 1}}} {"return": {}} {"data": {"device": "ref_backup_0", "len": 67108864, "offset": 67108864, "speed": 0, "type": "backup"}, "event": "BLOCK_JOB_COMPLETED", "timestamp": {"microseconds": "USECS", "seconds": "SECS"}} @@ -XXX,XX +XXX,XX @@ expecting 6 dirty sectors; have 6. OK! {"execute": "job-dismiss", "arguments": {"id": "bdc-fmt-job"}} {"return": {}} {} -{"execute": "blockdev-backup", "arguments": {"device": "drive0", "filter-node-name": "backup-top", "job-id": "ref_backup_1", "sync": "full", "target": "ref_target_1"}} +{"execute": "blockdev-backup", "arguments": {"device": "drive0", "filter-node-name": "backup-top", "job-id": "ref_backup_1", "sync": "full", "target": "ref_target_1", "x-perf": {"max-workers": 1}}} {"return": {}} {"data": {"device": "ref_backup_1", "len": 67108864, "offset": 67108864, "speed": 0, "type": "backup"}, "event": "BLOCK_JOB_COMPLETED", "timestamp": {"microseconds": "USECS", "seconds": "SECS"}} @@ -XXX,XX +XXX,XX @@ expecting 6 dirty sectors; have 6. OK! {"execute": "job-dismiss", "arguments": {"id": "bdc-fmt-job"}} {"return": {}} {} -{"execute": "blockdev-backup", "arguments": {"auto-finalize": false, "bitmap": "bitmap0", "bitmap-mode": "on-success", "device": "drive0", "filter-node-name": "backup-top", "job-id": "backup_1", "sync": "bitmap", "target": "backup_target_1"}} +{"execute": "blockdev-backup", "arguments": {"auto-finalize": false, "bitmap": "bitmap0", "bitmap-mode": "on-success", "device": "drive0", "filter-node-name": "backup-top", "job-id": "backup_1", "sync": "bitmap", "target": "backup_target_1", "x-perf": {"max-workers": 1}}} {"return": {}} --- Write #2 --- @@ -XXX,XX +XXX,XX @@ expecting 15 dirty sectors; have 15. OK! {"execute": "job-dismiss", "arguments": {"id": "bdc-fmt-job"}} {"return": {}} {} -{"execute": "blockdev-backup", "arguments": {"device": "drive0", "filter-node-name": "backup-top", "job-id": "ref_backup_2", "sync": "full", "target": "ref_target_2"}} +{"execute": "blockdev-backup", "arguments": {"device": "drive0", "filter-node-name": "backup-top", "job-id": "ref_backup_2", "sync": "full", "target": "ref_target_2", "x-perf": {"max-workers": 1}}} {"return": {}} {"data": {"device": "ref_backup_2", "len": 67108864, "offset": 67108864, "speed": 0, "type": "backup"}, "event": "BLOCK_JOB_COMPLETED", "timestamp": {"microseconds": "USECS", "seconds": "SECS"}} @@ -XXX,XX +XXX,XX @@ expecting 15 dirty sectors; have 15. OK! {"execute": "job-dismiss", "arguments": {"id": "bdc-fmt-job"}} {"return": {}} {} -{"execute": "blockdev-backup", "arguments": {"auto-finalize": false, "bitmap": "bitmap0", "bitmap-mode": "on-success", "device": "drive0", "filter-node-name": "backup-top", "job-id": "backup_2", "sync": "bitmap", "target": "backup_target_2"}} +{"execute": "blockdev-backup", "arguments": {"auto-finalize": false, "bitmap": "bitmap0", "bitmap-mode": "on-success", "device": "drive0", "filter-node-name": "backup-top", "job-id": "backup_2", "sync": "bitmap", "target": "backup_target_2", "x-perf": {"max-workers": 1}}} {"return": {}} {"execute": "job-finalize", "arguments": {"id": "backup_2"}} {"return": {}} @@ -XXX,XX +XXX,XX @@ write -P0x76 0x3ff0000 0x10000 {"execute": "job-dismiss", "arguments": {"id": "bdc-fmt-job"}} {"return": {}} {} -{"execute": "blockdev-backup", "arguments": {"device": "drive0", "filter-node-name": "backup-top", "job-id": "ref_backup_0", "sync": "full", "target": "ref_target_0"}} +{"execute": "blockdev-backup", "arguments": {"device": "drive0", "filter-node-name": "backup-top", "job-id": "ref_backup_0", "sync": "full", "target": "ref_target_0", "x-perf": {"max-workers": 1}}} {"return": {}} {"data": {"device": "ref_backup_0", "len": 67108864, "offset": 67108864, "speed": 0, "type": "backup"}, "event": "BLOCK_JOB_COMPLETED", "timestamp": {"microseconds": "USECS", "seconds": "SECS"}} @@ -XXX,XX +XXX,XX @@ expecting 6 dirty sectors; have 6. OK! {"execute": "job-dismiss", "arguments": {"id": "bdc-fmt-job"}} {"return": {}} {} -{"execute": "blockdev-backup", "arguments": {"device": "drive0", "filter-node-name": "backup-top", "job-id": "ref_backup_1", "sync": "full", "target": "ref_target_1"}} +{"execute": "blockdev-backup", "arguments": {"device": "drive0", "filter-node-name": "backup-top", "job-id": "ref_backup_1", "sync": "full", "target": "ref_target_1", "x-perf": {"max-workers": 1}}} {"return": {}} {"data": {"device": "ref_backup_1", "len": 67108864, "offset": 67108864, "speed": 0, "type": "backup"}, "event": "BLOCK_JOB_COMPLETED", "timestamp": {"microseconds": "USECS", "seconds": "SECS"}} @@ -XXX,XX +XXX,XX @@ expecting 6 dirty sectors; have 6. OK! {"execute": "job-dismiss", "arguments": {"id": "bdc-fmt-job"}} {"return": {}} {} -{"execute": "blockdev-backup", "arguments": {"auto-finalize": false, "bitmap": "bitmap0", "bitmap-mode": "on-success", "device": "drive0", "filter-node-name": "backup-top", "job-id": "backup_1", "sync": "bitmap", "target": "backup_target_1"}} +{"execute": "blockdev-backup", "arguments": {"auto-finalize": false, "bitmap": "bitmap0", "bitmap-mode": "on-success", "device": "drive0", "filter-node-name": "backup-top", "job-id": "backup_1", "sync": "bitmap", "target": "backup_target_1", "x-perf": {"max-workers": 1}}} {"return": {}} {"data": {"action": "report", "device": "backup_1", "operation": "read"}, "event": "BLOCK_JOB_ERROR", "timestamp": {"microseconds": "USECS", "seconds": "SECS"}} {"data": {"device": "backup_1", "error": "Input/output error", "len": 393216, "offset": 65536, "speed": 0, "type": "backup"}, "event": "BLOCK_JOB_COMPLETED", "timestamp": {"microseconds": "USECS", "seconds": "SECS"}} @@ -XXX,XX +XXX,XX @@ expecting 14 dirty sectors; have 14. OK! {"execute": "job-dismiss", "arguments": {"id": "bdc-fmt-job"}} {"return": {}} {} -{"execute": "blockdev-backup", "arguments": {"device": "drive0", "filter-node-name": "backup-top", "job-id": "ref_backup_2", "sync": "full", "target": "ref_target_2"}} +{"execute": "blockdev-backup", "arguments": {"device": "drive0", "filter-node-name": "backup-top", "job-id": "ref_backup_2", "sync": "full", "target": "ref_target_2", "x-perf": {"max-workers": 1}}} {"return": {}} {"data": {"device": "ref_backup_2", "len": 67108864, "offset": 67108864, "speed": 0, "type": "backup"}, "event": "BLOCK_JOB_COMPLETED", "timestamp": {"microseconds": "USECS", "seconds": "SECS"}} @@ -XXX,XX +XXX,XX @@ expecting 14 dirty sectors; have 14. OK! {"execute": "job-dismiss", "arguments": {"id": "bdc-fmt-job"}} {"return": {}} {} -{"execute": "blockdev-backup", "arguments": {"auto-finalize": false, "bitmap": "bitmap0", "bitmap-mode": "on-success", "device": "drive0", "filter-node-name": "backup-top", "job-id": "backup_2", "sync": "bitmap", "target": "backup_target_2"}} +{"execute": "blockdev-backup", "arguments": {"auto-finalize": false, "bitmap": "bitmap0", "bitmap-mode": "on-success", "device": "drive0", "filter-node-name": "backup-top", "job-id": "backup_2", "sync": "bitmap", "target": "backup_target_2", "x-perf": {"max-workers": 1}}} {"return": {}} {"execute": "job-finalize", "arguments": {"id": "backup_2"}} {"return": {}} @@ -XXX,XX +XXX,XX @@ write -P0x76 0x3ff0000 0x10000 {"execute": "job-dismiss", "arguments": {"id": "bdc-fmt-job"}} {"return": {}} {} -{"execute": "blockdev-backup", "arguments": {"device": "drive0", "filter-node-name": "backup-top", "job-id": "ref_backup_0", "sync": "full", "target": "ref_target_0"}} +{"execute": "blockdev-backup", "arguments": {"device": "drive0", "filter-node-name": "backup-top", "job-id": "ref_backup_0", "sync": "full", "target": "ref_target_0", "x-perf": {"max-workers": 1}}} {"return": {}} {"data": {"device": "ref_backup_0", "len": 67108864, "offset": 67108864, "speed": 0, "type": "backup"}, "event": "BLOCK_JOB_COMPLETED", "timestamp": {"microseconds": "USECS", "seconds": "SECS"}} @@ -XXX,XX +XXX,XX @@ expecting 6 dirty sectors; have 6. OK! {"execute": "job-dismiss", "arguments": {"id": "bdc-fmt-job"}} {"return": {}} {} -{"execute": "blockdev-backup", "arguments": {"device": "drive0", "filter-node-name": "backup-top", "job-id": "ref_backup_1", "sync": "full", "target": "ref_target_1"}} +{"execute": "blockdev-backup", "arguments": {"device": "drive0", "filter-node-name": "backup-top", "job-id": "ref_backup_1", "sync": "full", "target": "ref_target_1", "x-perf": {"max-workers": 1}}} {"return": {}} {"data": {"device": "ref_backup_1", "len": 67108864, "offset": 67108864, "speed": 0, "type": "backup"}, "event": "BLOCK_JOB_COMPLETED", "timestamp": {"microseconds": "USECS", "seconds": "SECS"}} @@ -XXX,XX +XXX,XX @@ expecting 6 dirty sectors; have 6. OK! {"execute": "job-dismiss", "arguments": {"id": "bdc-fmt-job"}} {"return": {}} {} -{"execute": "blockdev-backup", "arguments": {"auto-finalize": false, "bitmap": "bitmap0", "bitmap-mode": "on-success", "device": "drive0", "filter-node-name": "backup-top", "job-id": "backup_1", "sync": "bitmap", "target": "backup_target_1"}} +{"execute": "blockdev-backup", "arguments": {"auto-finalize": false, "bitmap": "bitmap0", "bitmap-mode": "on-success", "device": "drive0", "filter-node-name": "backup-top", "job-id": "backup_1", "sync": "bitmap", "target": "backup_target_1", "x-perf": {"max-workers": 1}}} {"return": {}} --- Write #2 --- @@ -XXX,XX +XXX,XX @@ expecting 12 dirty sectors; have 12. OK! {"execute": "job-dismiss", "arguments": {"id": "bdc-fmt-job"}} {"return": {}} {} -{"execute": "blockdev-backup", "arguments": {"device": "drive0", "filter-node-name": "backup-top", "job-id": "ref_backup_2", "sync": "full", "target": "ref_target_2"}} +{"execute": "blockdev-backup", "arguments": {"device": "drive0", "filter-node-name": "backup-top", "job-id": "ref_backup_2", "sync": "full", "target": "ref_target_2", "x-perf": {"max-workers": 1}}} {"return": {}} {"data": {"device": "ref_backup_2", "len": 67108864, "offset": 67108864, "speed": 0, "type": "backup"}, "event": "BLOCK_JOB_COMPLETED", "timestamp": {"microseconds": "USECS", "seconds": "SECS"}} @@ -XXX,XX +XXX,XX @@ expecting 12 dirty sectors; have 12. OK! {"execute": "job-dismiss", "arguments": {"id": "bdc-fmt-job"}} {"return": {}} {} -{"execute": "blockdev-backup", "arguments": {"auto-finalize": false, "bitmap": "bitmap0", "bitmap-mode": "on-success", "device": "drive0", "filter-node-name": "backup-top", "job-id": "backup_2", "sync": "bitmap", "target": "backup_target_2"}} +{"execute": "blockdev-backup", "arguments": {"auto-finalize": false, "bitmap": "bitmap0", "bitmap-mode": "on-success", "device": "drive0", "filter-node-name": "backup-top", "job-id": "backup_2", "sync": "bitmap", "target": "backup_target_2", "x-perf": {"max-workers": 1}}} {"return": {}} {"execute": "job-finalize", "arguments": {"id": "backup_2"}} {"return": {}} @@ -XXX,XX +XXX,XX @@ write -P0x76 0x3ff0000 0x10000 {"execute": "job-dismiss", "arguments": {"id": "bdc-fmt-job"}} {"return": {}} {} -{"execute": "blockdev-backup", "arguments": {"device": "drive0", "filter-node-name": "backup-top", "job-id": "ref_backup_0", "sync": "full", "target": "ref_target_0"}} +{"execute": "blockdev-backup", "arguments": {"device": "drive0", "filter-node-name": "backup-top", "job-id": "ref_backup_0", "sync": "full", "target": "ref_target_0", "x-perf": {"max-workers": 1}}} {"return": {}} {"data": {"device": "ref_backup_0", "len": 67108864, "offset": 67108864, "speed": 0, "type": "backup"}, "event": "BLOCK_JOB_COMPLETED", "timestamp": {"microseconds": "USECS", "seconds": "SECS"}} @@ -XXX,XX +XXX,XX @@ expecting 6 dirty sectors; have 6. OK! {"execute": "job-dismiss", "arguments": {"id": "bdc-fmt-job"}} {"return": {}} {} -{"execute": "blockdev-backup", "arguments": {"device": "drive0", "filter-node-name": "backup-top", "job-id": "ref_backup_1", "sync": "full", "target": "ref_target_1"}} +{"execute": "blockdev-backup", "arguments": {"device": "drive0", "filter-node-name": "backup-top", "job-id": "ref_backup_1", "sync": "full", "target": "ref_target_1", "x-perf": {"max-workers": 1}}} {"return": {}} {"data": {"device": "ref_backup_1", "len": 67108864, "offset": 67108864, "speed": 0, "type": "backup"}, "event": "BLOCK_JOB_COMPLETED", "timestamp": {"microseconds": "USECS", "seconds": "SECS"}} @@ -XXX,XX +XXX,XX @@ expecting 6 dirty sectors; have 6. OK! {"execute": "job-dismiss", "arguments": {"id": "bdc-fmt-job"}} {"return": {}} {} -{"execute": "blockdev-backup", "arguments": {"auto-finalize": false, "bitmap": "bitmap0", "bitmap-mode": "always", "device": "drive0", "filter-node-name": "backup-top", "job-id": "backup_1", "sync": "bitmap", "target": "backup_target_1"}} +{"execute": "blockdev-backup", "arguments": {"auto-finalize": false, "bitmap": "bitmap0", "bitmap-mode": "always", "device": "drive0", "filter-node-name": "backup-top", "job-id": "backup_1", "sync": "bitmap", "target": "backup_target_1", "x-perf": {"max-workers": 1}}} {"return": {}} --- Write #2 --- @@ -XXX,XX +XXX,XX @@ expecting 12 dirty sectors; have 12. OK! {"execute": "job-dismiss", "arguments": {"id": "bdc-fmt-job"}} {"return": {}} {} -{"execute": "blockdev-backup", "arguments": {"device": "drive0", "filter-node-name": "backup-top", "job-id": "ref_backup_2", "sync": "full", "target": "ref_target_2"}} +{"execute": "blockdev-backup", "arguments": {"device": "drive0", "filter-node-name": "backup-top", "job-id": "ref_backup_2", "sync": "full", "target": "ref_target_2", "x-perf": {"max-workers": 1}}} {"return": {}} {"data": {"device": "ref_backup_2", "len": 67108864, "offset": 67108864, "speed": 0, "type": "backup"}, "event": "BLOCK_JOB_COMPLETED", "timestamp": {"microseconds": "USECS", "seconds": "SECS"}} @@ -XXX,XX +XXX,XX @@ expecting 12 dirty sectors; have 12. OK! {"execute": "job-dismiss", "arguments": {"id": "bdc-fmt-job"}} {"return": {}} {} -{"execute": "blockdev-backup", "arguments": {"auto-finalize": false, "bitmap": "bitmap0", "bitmap-mode": "always", "device": "drive0", "filter-node-name": "backup-top", "job-id": "backup_2", "sync": "bitmap", "target": "backup_target_2"}} +{"execute": "blockdev-backup", "arguments": {"auto-finalize": false, "bitmap": "bitmap0", "bitmap-mode": "always", "device": "drive0", "filter-node-name": "backup-top", "job-id": "backup_2", "sync": "bitmap", "target": "backup_target_2", "x-perf": {"max-workers": 1}}} {"return": {}} {"execute": "job-finalize", "arguments": {"id": "backup_2"}} {"return": {}} @@ -XXX,XX +XXX,XX @@ write -P0x76 0x3ff0000 0x10000 {"execute": "job-dismiss", "arguments": {"id": "bdc-fmt-job"}} {"return": {}} {} -{"execute": "blockdev-backup", "arguments": {"device": "drive0", "filter-node-name": "backup-top", "job-id": "ref_backup_0", "sync": "full", "target": "ref_target_0"}} +{"execute": "blockdev-backup", "arguments": {"device": "drive0", "filter-node-name": "backup-top", "job-id": "ref_backup_0", "sync": "full", "target": "ref_target_0", "x-perf": {"max-workers": 1}}} {"return": {}} {"data": {"device": "ref_backup_0", "len": 67108864, "offset": 67108864, "speed": 0, "type": "backup"}, "event": "BLOCK_JOB_COMPLETED", "timestamp": {"microseconds": "USECS", "seconds": "SECS"}} @@ -XXX,XX +XXX,XX @@ expecting 6 dirty sectors; have 6. OK! {"execute": "job-dismiss", "arguments": {"id": "bdc-fmt-job"}} {"return": {}} {} -{"execute": "blockdev-backup", "arguments": {"device": "drive0", "filter-node-name": "backup-top", "job-id": "ref_backup_1", "sync": "full", "target": "ref_target_1"}} +{"execute": "blockdev-backup", "arguments": {"device": "drive0", "filter-node-name": "backup-top", "job-id": "ref_backup_1", "sync": "full", "target": "ref_target_1", "x-perf": {"max-workers": 1}}} {"return": {}} {"data": {"device": "ref_backup_1", "len": 67108864, "offset": 67108864, "speed": 0, "type": "backup"}, "event": "BLOCK_JOB_COMPLETED", "timestamp": {"microseconds": "USECS", "seconds": "SECS"}} @@ -XXX,XX +XXX,XX @@ expecting 6 dirty sectors; have 6. OK! {"execute": "job-dismiss", "arguments": {"id": "bdc-fmt-job"}} {"return": {}} {} -{"execute": "blockdev-backup", "arguments": {"auto-finalize": false, "bitmap": "bitmap0", "bitmap-mode": "always", "device": "drive0", "filter-node-name": "backup-top", "job-id": "backup_1", "sync": "bitmap", "target": "backup_target_1"}} +{"execute": "blockdev-backup", "arguments": {"auto-finalize": false, "bitmap": "bitmap0", "bitmap-mode": "always", "device": "drive0", "filter-node-name": "backup-top", "job-id": "backup_1", "sync": "bitmap", "target": "backup_target_1", "x-perf": {"max-workers": 1}}} {"return": {}} {"data": {"action": "report", "device": "backup_1", "operation": "read"}, "event": "BLOCK_JOB_ERROR", "timestamp": {"microseconds": "USECS", "seconds": "SECS"}} {"data": {"device": "backup_1", "error": "Input/output error", "len": 393216, "offset": 65536, "speed": 0, "type": "backup"}, "event": "BLOCK_JOB_COMPLETED", "timestamp": {"microseconds": "USECS", "seconds": "SECS"}} @@ -XXX,XX +XXX,XX @@ expecting 13 dirty sectors; have 13. OK! {"execute": "job-dismiss", "arguments": {"id": "bdc-fmt-job"}} {"return": {}} {} -{"execute": "blockdev-backup", "arguments": {"device": "drive0", "filter-node-name": "backup-top", "job-id": "ref_backup_2", "sync": "full", "target": "ref_target_2"}} +{"execute": "blockdev-backup", "arguments": {"device": "drive0", "filter-node-name": "backup-top", "job-id": "ref_backup_2", "sync": "full", "target": "ref_target_2", "x-perf": {"max-workers": 1}}} {"return": {}} {"data": {"device": "ref_backup_2", "len": 67108864, "offset": 67108864, "speed": 0, "type": "backup"}, "event": "BLOCK_JOB_COMPLETED", "timestamp": {"microseconds": "USECS", "seconds": "SECS"}} @@ -XXX,XX +XXX,XX @@ expecting 13 dirty sectors; have 13. OK! {"execute": "job-dismiss", "arguments": {"id": "bdc-fmt-job"}} {"return": {}} {} -{"execute": "blockdev-backup", "arguments": {"auto-finalize": false, "bitmap": "bitmap0", "bitmap-mode": "always", "device": "drive0", "filter-node-name": "backup-top", "job-id": "backup_2", "sync": "bitmap", "target": "backup_target_2"}} +{"execute": "blockdev-backup", "arguments": {"auto-finalize": false, "bitmap": "bitmap0", "bitmap-mode": "always", "device": "drive0", "filter-node-name": "backup-top", "job-id": "backup_2", "sync": "bitmap", "target": "backup_target_2", "x-perf": {"max-workers": 1}}} {"return": {}} {"execute": "job-finalize", "arguments": {"id": "backup_2"}} {"return": {}} @@ -XXX,XX +XXX,XX @@ write -P0x76 0x3ff0000 0x10000 {"execute": "job-dismiss", "arguments": {"id": "bdc-fmt-job"}} {"return": {}} {} -{"execute": "blockdev-backup", "arguments": {"device": "drive0", "filter-node-name": "backup-top", "job-id": "ref_backup_0", "sync": "full", "target": "ref_target_0"}} +{"execute": "blockdev-backup", "arguments": {"device": "drive0", "filter-node-name": "backup-top", "job-id": "ref_backup_0", "sync": "full", "target": "ref_target_0", "x-perf": {"max-workers": 1}}} {"return": {}} {"data": {"device": "ref_backup_0", "len": 67108864, "offset": 67108864, "speed": 0, "type": "backup"}, "event": "BLOCK_JOB_COMPLETED", "timestamp": {"microseconds": "USECS", "seconds": "SECS"}} @@ -XXX,XX +XXX,XX @@ expecting 6 dirty sectors; have 6. OK! {"execute": "job-dismiss", "arguments": {"id": "bdc-fmt-job"}} {"return": {}} {} -{"execute": "blockdev-backup", "arguments": {"device": "drive0", "filter-node-name": "backup-top", "job-id": "ref_backup_1", "sync": "full", "target": "ref_target_1"}} +{"execute": "blockdev-backup", "arguments": {"device": "drive0", "filter-node-name": "backup-top", "job-id": "ref_backup_1", "sync": "full", "target": "ref_target_1", "x-perf": {"max-workers": 1}}} {"return": {}} {"data": {"device": "ref_backup_1", "len": 67108864, "offset": 67108864, "speed": 0, "type": "backup"}, "event": "BLOCK_JOB_COMPLETED", "timestamp": {"microseconds": "USECS", "seconds": "SECS"}} @@ -XXX,XX +XXX,XX @@ expecting 6 dirty sectors; have 6. OK! {"execute": "job-dismiss", "arguments": {"id": "bdc-fmt-job"}} {"return": {}} {} -{"execute": "blockdev-backup", "arguments": {"auto-finalize": false, "bitmap": "bitmap0", "bitmap-mode": "always", "device": "drive0", "filter-node-name": "backup-top", "job-id": "backup_1", "sync": "bitmap", "target": "backup_target_1"}} +{"execute": "blockdev-backup", "arguments": {"auto-finalize": false, "bitmap": "bitmap0", "bitmap-mode": "always", "device": "drive0", "filter-node-name": "backup-top", "job-id": "backup_1", "sync": "bitmap", "target": "backup_target_1", "x-perf": {"max-workers": 1}}} {"return": {}} --- Write #2 --- @@ -XXX,XX +XXX,XX @@ expecting 12 dirty sectors; have 12. OK! {"execute": "job-dismiss", "arguments": {"id": "bdc-fmt-job"}} {"return": {}} {} -{"execute": "blockdev-backup", "arguments": {"device": "drive0", "filter-node-name": "backup-top", "job-id": "ref_backup_2", "sync": "full", "target": "ref_target_2"}} +{"execute": "blockdev-backup", "arguments": {"device": "drive0", "filter-node-name": "backup-top", "job-id": "ref_backup_2", "sync": "full", "target": "ref_target_2", "x-perf": {"max-workers": 1}}} {"return": {}} {"data": {"device": "ref_backup_2", "len": 67108864, "offset": 67108864, "speed": 0, "type": "backup"}, "event": "BLOCK_JOB_COMPLETED", "timestamp": {"microseconds": "USECS", "seconds": "SECS"}} @@ -XXX,XX +XXX,XX @@ expecting 12 dirty sectors; have 12. OK! {"execute": "job-dismiss", "arguments": {"id": "bdc-fmt-job"}} {"return": {}} {} -{"execute": "blockdev-backup", "arguments": {"auto-finalize": false, "bitmap": "bitmap0", "bitmap-mode": "always", "device": "drive0", "filter-node-name": "backup-top", "job-id": "backup_2", "sync": "bitmap", "target": "backup_target_2"}} +{"execute": "blockdev-backup", "arguments": {"auto-finalize": false, "bitmap": "bitmap0", "bitmap-mode": "always", "device": "drive0", "filter-node-name": "backup-top", "job-id": "backup_2", "sync": "bitmap", "target": "backup_target_2", "x-perf": {"max-workers": 1}}} {"return": {}} {"execute": "job-finalize", "arguments": {"id": "backup_2"}} {"return": {}} @@ -XXX,XX +XXX,XX @@ write -P0x76 0x3ff0000 0x10000 {"execute": "job-dismiss", "arguments": {"id": "bdc-fmt-job"}} {"return": {}} {} -{"execute": "blockdev-backup", "arguments": {"device": "drive0", "filter-node-name": "backup-top", "job-id": "ref_backup_0", "sync": "full", "target": "ref_target_0"}} +{"execute": "blockdev-backup", "arguments": {"device": "drive0", "filter-node-name": "backup-top", "job-id": "ref_backup_0", "sync": "full", "target": "ref_target_0", "x-perf": {"max-workers": 1}}} {"return": {}} {"data": {"device": "ref_backup_0", "len": 67108864, "offset": 67108864, "speed": 0, "type": "backup"}, "event": "BLOCK_JOB_COMPLETED", "timestamp": {"microseconds": "USECS", "seconds": "SECS"}} @@ -XXX,XX +XXX,XX @@ expecting 6 dirty sectors; have 6. OK! {"execute": "job-dismiss", "arguments": {"id": "bdc-fmt-job"}} {"return": {}} {} -{"execute": "blockdev-backup", "arguments": {"device": "drive0", "filter-node-name": "backup-top", "job-id": "ref_backup_1", "sync": "full", "target": "ref_target_1"}} +{"execute": "blockdev-backup", "arguments": {"device": "drive0", "filter-node-name": "backup-top", "job-id": "ref_backup_1", "sync": "full", "target": "ref_target_1", "x-perf": {"max-workers": 1}}} {"return": {}} {"data": {"device": "ref_backup_1", "len": 67108864, "offset": 67108864, "speed": 0, "type": "backup"}, "event": "BLOCK_JOB_COMPLETED", "timestamp": {"microseconds": "USECS", "seconds": "SECS"}} @@ -XXX,XX +XXX,XX @@ expecting 6 dirty sectors; have 6. OK! {"execute": "job-dismiss", "arguments": {"id": "bdc-fmt-job"}} {"return": {}} {} -{"execute": "blockdev-backup", "arguments": {"auto-finalize": false, "bitmap": "bitmap0", "bitmap-mode": "on-success", "device": "drive0", "filter-node-name": "backup-top", "job-id": "backup_1", "sync": "full", "target": "backup_target_1"}} +{"execute": "blockdev-backup", "arguments": {"auto-finalize": false, "bitmap": "bitmap0", "bitmap-mode": "on-success", "device": "drive0", "filter-node-name": "backup-top", "job-id": "backup_1", "sync": "full", "target": "backup_target_1", "x-perf": {"max-workers": 1}}} {"return": {}} --- Write #2 --- @@ -XXX,XX +XXX,XX @@ expecting 15 dirty sectors; have 15. OK! {"execute": "job-dismiss", "arguments": {"id": "bdc-fmt-job"}} {"return": {}} {} -{"execute": "blockdev-backup", "arguments": {"device": "drive0", "filter-node-name": "backup-top", "job-id": "ref_backup_2", "sync": "full", "target": "ref_target_2"}} +{"execute": "blockdev-backup", "arguments": {"device": "drive0", "filter-node-name": "backup-top", "job-id": "ref_backup_2", "sync": "full", "target": "ref_target_2", "x-perf": {"max-workers": 1}}} {"return": {}} {"data": {"device": "ref_backup_2", "len": 67108864, "offset": 67108864, "speed": 0, "type": "backup"}, "event": "BLOCK_JOB_COMPLETED", "timestamp": {"microseconds": "USECS", "seconds": "SECS"}} @@ -XXX,XX +XXX,XX @@ expecting 15 dirty sectors; have 15. OK! {"execute": "job-dismiss", "arguments": {"id": "bdc-fmt-job"}} {"return": {}} {} -{"execute": "blockdev-backup", "arguments": {"auto-finalize": false, "bitmap": "bitmap0", "bitmap-mode": "on-success", "device": "drive0", "filter-node-name": "backup-top", "job-id": "backup_2", "sync": "bitmap", "target": "backup_target_2"}} +{"execute": "blockdev-backup", "arguments": {"auto-finalize": false, "bitmap": "bitmap0", "bitmap-mode": "on-success", "device": "drive0", "filter-node-name": "backup-top", "job-id": "backup_2", "sync": "bitmap", "target": "backup_target_2", "x-perf": {"max-workers": 1}}} {"return": {}} {"execute": "job-finalize", "arguments": {"id": "backup_2"}} {"return": {}} @@ -XXX,XX +XXX,XX @@ write -P0x76 0x3ff0000 0x10000 {"execute": "job-dismiss", "arguments": {"id": "bdc-fmt-job"}} {"return": {}} {} -{"execute": "blockdev-backup", "arguments": {"device": "drive0", "filter-node-name": "backup-top", "job-id": "ref_backup_0", "sync": "full", "target": "ref_target_0"}} +{"execute": "blockdev-backup", "arguments": {"device": "drive0", "filter-node-name": "backup-top", "job-id": "ref_backup_0", "sync": "full", "target": "ref_target_0", "x-perf": {"max-workers": 1}}} {"return": {}} {"data": {"device": "ref_backup_0", "len": 67108864, "offset": 67108864, "speed": 0, "type": "backup"}, "event": "BLOCK_JOB_COMPLETED", "timestamp": {"microseconds": "USECS", "seconds": "SECS"}} @@ -XXX,XX +XXX,XX @@ expecting 6 dirty sectors; have 6. OK! {"execute": "job-dismiss", "arguments": {"id": "bdc-fmt-job"}} {"return": {}} {} -{"execute": "blockdev-backup", "arguments": {"device": "drive0", "filter-node-name": "backup-top", "job-id": "ref_backup_1", "sync": "full", "target": "ref_target_1"}} +{"execute": "blockdev-backup", "arguments": {"device": "drive0", "filter-node-name": "backup-top", "job-id": "ref_backup_1", "sync": "full", "target": "ref_target_1", "x-perf": {"max-workers": 1}}} {"return": {}} {"data": {"device": "ref_backup_1", "len": 67108864, "offset": 67108864, "speed": 0, "type": "backup"}, "event": "BLOCK_JOB_COMPLETED", "timestamp": {"microseconds": "USECS", "seconds": "SECS"}} @@ -XXX,XX +XXX,XX @@ expecting 6 dirty sectors; have 6. OK! {"execute": "job-dismiss", "arguments": {"id": "bdc-fmt-job"}} {"return": {}} {} -{"execute": "blockdev-backup", "arguments": {"auto-finalize": false, "bitmap": "bitmap0", "bitmap-mode": "on-success", "device": "drive0", "filter-node-name": "backup-top", "job-id": "backup_1", "sync": "full", "target": "backup_target_1"}} +{"execute": "blockdev-backup", "arguments": {"auto-finalize": false, "bitmap": "bitmap0", "bitmap-mode": "on-success", "device": "drive0", "filter-node-name": "backup-top", "job-id": "backup_1", "sync": "full", "target": "backup_target_1", "x-perf": {"max-workers": 1}}} {"return": {}} {"data": {"action": "report", "device": "backup_1", "operation": "read"}, "event": "BLOCK_JOB_ERROR", "timestamp": {"microseconds": "USECS", "seconds": "SECS"}} {"data": {"device": "backup_1", "error": "Input/output error", "len": 67108864, "offset": 983040, "speed": 0, "type": "backup"}, "event": "BLOCK_JOB_COMPLETED", "timestamp": {"microseconds": "USECS", "seconds": "SECS"}} @@ -XXX,XX +XXX,XX @@ expecting 14 dirty sectors; have 14. OK! {"execute": "job-dismiss", "arguments": {"id": "bdc-fmt-job"}} {"return": {}} {} -{"execute": "blockdev-backup", "arguments": {"device": "drive0", "filter-node-name": "backup-top", "job-id": "ref_backup_2", "sync": "full", "target": "ref_target_2"}} +{"execute": "blockdev-backup", "arguments": {"device": "drive0", "filter-node-name": "backup-top", "job-id": "ref_backup_2", "sync": "full", "target": "ref_target_2", "x-perf": {"max-workers": 1}}} {"return": {}} {"data": {"device": "ref_backup_2", "len": 67108864, "offset": 67108864, "speed": 0, "type": "backup"}, "event": "BLOCK_JOB_COMPLETED", "timestamp": {"microseconds": "USECS", "seconds": "SECS"}} @@ -XXX,XX +XXX,XX @@ expecting 14 dirty sectors; have 14. OK! {"execute": "job-dismiss", "arguments": {"id": "bdc-fmt-job"}} {"return": {}} {} -{"execute": "blockdev-backup", "arguments": {"auto-finalize": false, "bitmap": "bitmap0", "bitmap-mode": "on-success", "device": "drive0", "filter-node-name": "backup-top", "job-id": "backup_2", "sync": "bitmap", "target": "backup_target_2"}} +{"execute": "blockdev-backup", "arguments": {"auto-finalize": false, "bitmap": "bitmap0", "bitmap-mode": "on-success", "device": "drive0", "filter-node-name": "backup-top", "job-id": "backup_2", "sync": "bitmap", "target": "backup_target_2", "x-perf": {"max-workers": 1}}} {"return": {}} {"execute": "job-finalize", "arguments": {"id": "backup_2"}} {"return": {}} @@ -XXX,XX +XXX,XX @@ write -P0x76 0x3ff0000 0x10000 {"execute": "job-dismiss", "arguments": {"id": "bdc-fmt-job"}} {"return": {}} {} -{"execute": "blockdev-backup", "arguments": {"device": "drive0", "filter-node-name": "backup-top", "job-id": "ref_backup_0", "sync": "full", "target": "ref_target_0"}} +{"execute": "blockdev-backup", "arguments": {"device": "drive0", "filter-node-name": "backup-top", "job-id": "ref_backup_0", "sync": "full", "target": "ref_target_0", "x-perf": {"max-workers": 1}}} {"return": {}} {"data": {"device": "ref_backup_0", "len": 67108864, "offset": 67108864, "speed": 0, "type": "backup"}, "event": "BLOCK_JOB_COMPLETED", "timestamp": {"microseconds": "USECS", "seconds": "SECS"}} @@ -XXX,XX +XXX,XX @@ expecting 6 dirty sectors; have 6. OK! {"execute": "job-dismiss", "arguments": {"id": "bdc-fmt-job"}} {"return": {}} {} -{"execute": "blockdev-backup", "arguments": {"device": "drive0", "filter-node-name": "backup-top", "job-id": "ref_backup_1", "sync": "full", "target": "ref_target_1"}} +{"execute": "blockdev-backup", "arguments": {"device": "drive0", "filter-node-name": "backup-top", "job-id": "ref_backup_1", "sync": "full", "target": "ref_target_1", "x-perf": {"max-workers": 1}}} {"return": {}} {"data": {"device": "ref_backup_1", "len": 67108864, "offset": 67108864, "speed": 0, "type": "backup"}, "event": "BLOCK_JOB_COMPLETED", "timestamp": {"microseconds": "USECS", "seconds": "SECS"}} @@ -XXX,XX +XXX,XX @@ expecting 6 dirty sectors; have 6. OK! {"execute": "job-dismiss", "arguments": {"id": "bdc-fmt-job"}} {"return": {}} {} -{"execute": "blockdev-backup", "arguments": {"auto-finalize": false, "bitmap": "bitmap0", "bitmap-mode": "on-success", "device": "drive0", "filter-node-name": "backup-top", "job-id": "backup_1", "sync": "full", "target": "backup_target_1"}} +{"execute": "blockdev-backup", "arguments": {"auto-finalize": false, "bitmap": "bitmap0", "bitmap-mode": "on-success", "device": "drive0", "filter-node-name": "backup-top", "job-id": "backup_1", "sync": "full", "target": "backup_target_1", "x-perf": {"max-workers": 1}}} {"return": {}} --- Write #2 --- @@ -XXX,XX +XXX,XX @@ expecting 12 dirty sectors; have 12. OK! {"execute": "job-dismiss", "arguments": {"id": "bdc-fmt-job"}} {"return": {}} {} -{"execute": "blockdev-backup", "arguments": {"device": "drive0", "filter-node-name": "backup-top", "job-id": "ref_backup_2", "sync": "full", "target": "ref_target_2"}} +{"execute": "blockdev-backup", "arguments": {"device": "drive0", "filter-node-name": "backup-top", "job-id": "ref_backup_2", "sync": "full", "target": "ref_target_2", "x-perf": {"max-workers": 1}}} {"return": {}} {"data": {"device": "ref_backup_2", "len": 67108864, "offset": 67108864, "speed": 0, "type": "backup"}, "event": "BLOCK_JOB_COMPLETED", "timestamp": {"microseconds": "USECS", "seconds": "SECS"}} @@ -XXX,XX +XXX,XX @@ expecting 12 dirty sectors; have 12. OK! {"execute": "job-dismiss", "arguments": {"id": "bdc-fmt-job"}} {"return": {}} {} -{"execute": "blockdev-backup", "arguments": {"auto-finalize": false, "bitmap": "bitmap0", "bitmap-mode": "on-success", "device": "drive0", "filter-node-name": "backup-top", "job-id": "backup_2", "sync": "bitmap", "target": "backup_target_2"}} +{"execute": "blockdev-backup", "arguments": {"auto-finalize": false, "bitmap": "bitmap0", "bitmap-mode": "on-success", "device": "drive0", "filter-node-name": "backup-top", "job-id": "backup_2", "sync": "bitmap", "target": "backup_target_2", "x-perf": {"max-workers": 1}}} {"return": {}} {"execute": "job-finalize", "arguments": {"id": "backup_2"}} {"return": {}} @@ -XXX,XX +XXX,XX @@ write -P0x76 0x3ff0000 0x10000 {"execute": "job-dismiss", "arguments": {"id": "bdc-fmt-job"}} {"return": {}} {} -{"execute": "blockdev-backup", "arguments": {"device": "drive0", "filter-node-name": "backup-top", "job-id": "ref_backup_0", "sync": "full", "target": "ref_target_0"}} +{"execute": "blockdev-backup", "arguments": {"device": "drive0", "filter-node-name": "backup-top", "job-id": "ref_backup_0", "sync": "full", "target": "ref_target_0", "x-perf": {"max-workers": 1}}} {"return": {}} {"data": {"device": "ref_backup_0", "len": 67108864, "offset": 67108864, "speed": 0, "type": "backup"}, "event": "BLOCK_JOB_COMPLETED", "timestamp": {"microseconds": "USECS", "seconds": "SECS"}} @@ -XXX,XX +XXX,XX @@ expecting 6 dirty sectors; have 6. OK! {"execute": "job-dismiss", "arguments": {"id": "bdc-fmt-job"}} {"return": {}} {} -{"execute": "blockdev-backup", "arguments": {"device": "drive0", "filter-node-name": "backup-top", "job-id": "ref_backup_1", "sync": "full", "target": "ref_target_1"}} +{"execute": "blockdev-backup", "arguments": {"device": "drive0", "filter-node-name": "backup-top", "job-id": "ref_backup_1", "sync": "full", "target": "ref_target_1", "x-perf": {"max-workers": 1}}} {"return": {}} {"data": {"device": "ref_backup_1", "len": 67108864, "offset": 67108864, "speed": 0, "type": "backup"}, "event": "BLOCK_JOB_COMPLETED", "timestamp": {"microseconds": "USECS", "seconds": "SECS"}} @@ -XXX,XX +XXX,XX @@ expecting 6 dirty sectors; have 6. OK! {"execute": "job-dismiss", "arguments": {"id": "bdc-fmt-job"}} {"return": {}} {} -{"execute": "blockdev-backup", "arguments": {"auto-finalize": false, "bitmap": "bitmap0", "bitmap-mode": "always", "device": "drive0", "filter-node-name": "backup-top", "job-id": "backup_1", "sync": "full", "target": "backup_target_1"}} +{"execute": "blockdev-backup", "arguments": {"auto-finalize": false, "bitmap": "bitmap0", "bitmap-mode": "always", "device": "drive0", "filter-node-name": "backup-top", "job-id": "backup_1", "sync": "full", "target": "backup_target_1", "x-perf": {"max-workers": 1}}} {"return": {}} --- Write #2 --- @@ -XXX,XX +XXX,XX @@ expecting 12 dirty sectors; have 12. OK! {"execute": "job-dismiss", "arguments": {"id": "bdc-fmt-job"}} {"return": {}} {} -{"execute": "blockdev-backup", "arguments": {"device": "drive0", "filter-node-name": "backup-top", "job-id": "ref_backup_2", "sync": "full", "target": "ref_target_2"}} +{"execute": "blockdev-backup", "arguments": {"device": "drive0", "filter-node-name": "backup-top", "job-id": "ref_backup_2", "sync": "full", "target": "ref_target_2", "x-perf": {"max-workers": 1}}} {"return": {}} {"data": {"device": "ref_backup_2", "len": 67108864, "offset": 67108864, "speed": 0, "type": "backup"}, "event": "BLOCK_JOB_COMPLETED", "timestamp": {"microseconds": "USECS", "seconds": "SECS"}} @@ -XXX,XX +XXX,XX @@ expecting 12 dirty sectors; have 12. OK! {"execute": "job-dismiss", "arguments": {"id": "bdc-fmt-job"}} {"return": {}} {} -{"execute": "blockdev-backup", "arguments": {"auto-finalize": false, "bitmap": "bitmap0", "bitmap-mode": "always", "device": "drive0", "filter-node-name": "backup-top", "job-id": "backup_2", "sync": "bitmap", "target": "backup_target_2"}} +{"execute": "blockdev-backup", "arguments": {"auto-finalize": false, "bitmap": "bitmap0", "bitmap-mode": "always", "device": "drive0", "filter-node-name": "backup-top", "job-id": "backup_2", "sync": "bitmap", "target": "backup_target_2", "x-perf": {"max-workers": 1}}} {"return": {}} {"execute": "job-finalize", "arguments": {"id": "backup_2"}} {"return": {}} @@ -XXX,XX +XXX,XX @@ write -P0x76 0x3ff0000 0x10000 {"execute": "job-dismiss", "arguments": {"id": "bdc-fmt-job"}} {"return": {}} {} -{"execute": "blockdev-backup", "arguments": {"device": "drive0", "filter-node-name": "backup-top", "job-id": "ref_backup_0", "sync": "full", "target": "ref_target_0"}} +{"execute": "blockdev-backup", "arguments": {"device": "drive0", "filter-node-name": "backup-top", "job-id": "ref_backup_0", "sync": "full", "target": "ref_target_0", "x-perf": {"max-workers": 1}}} {"return": {}} {"data": {"device": "ref_backup_0", "len": 67108864, "offset": 67108864, "speed": 0, "type": "backup"}, "event": "BLOCK_JOB_COMPLETED", "timestamp": {"microseconds": "USECS", "seconds": "SECS"}} @@ -XXX,XX +XXX,XX @@ expecting 6 dirty sectors; have 6. OK! {"execute": "job-dismiss", "arguments": {"id": "bdc-fmt-job"}} {"return": {}} {} -{"execute": "blockdev-backup", "arguments": {"device": "drive0", "filter-node-name": "backup-top", "job-id": "ref_backup_1", "sync": "full", "target": "ref_target_1"}} +{"execute": "blockdev-backup", "arguments": {"device": "drive0", "filter-node-name": "backup-top", "job-id": "ref_backup_1", "sync": "full", "target": "ref_target_1", "x-perf": {"max-workers": 1}}} {"return": {}} {"data": {"device": "ref_backup_1", "len": 67108864, "offset": 67108864, "speed": 0, "type": "backup"}, "event": "BLOCK_JOB_COMPLETED", "timestamp": {"microseconds": "USECS", "seconds": "SECS"}} @@ -XXX,XX +XXX,XX @@ expecting 6 dirty sectors; have 6. OK! {"execute": "job-dismiss", "arguments": {"id": "bdc-fmt-job"}} {"return": {}} {} -{"execute": "blockdev-backup", "arguments": {"auto-finalize": false, "bitmap": "bitmap0", "bitmap-mode": "always", "device": "drive0", "filter-node-name": "backup-top", "job-id": "backup_1", "sync": "full", "target": "backup_target_1"}} +{"execute": "blockdev-backup", "arguments": {"auto-finalize": false, "bitmap": "bitmap0", "bitmap-mode": "always", "device": "drive0", "filter-node-name": "backup-top", "job-id": "backup_1", "sync": "full", "target": "backup_target_1", "x-perf": {"max-workers": 1}}} {"return": {}} {"data": {"action": "report", "device": "backup_1", "operation": "read"}, "event": "BLOCK_JOB_ERROR", "timestamp": {"microseconds": "USECS", "seconds": "SECS"}} {"data": {"device": "backup_1", "error": "Input/output error", "len": 67108864, "offset": 983040, "speed": 0, "type": "backup"}, "event": "BLOCK_JOB_COMPLETED", "timestamp": {"microseconds": "USECS", "seconds": "SECS"}} @@ -XXX,XX +XXX,XX @@ expecting 1014 dirty sectors; have 1014. OK! {"execute": "job-dismiss", "arguments": {"id": "bdc-fmt-job"}} {"return": {}} {} -{"execute": "blockdev-backup", "arguments": {"device": "drive0", "filter-node-name": "backup-top", "job-id": "ref_backup_2", "sync": "full", "target": "ref_target_2"}} +{"execute": "blockdev-backup", "arguments": {"device": "drive0", "filter-node-name": "backup-top", "job-id": "ref_backup_2", "sync": "full", "target": "ref_target_2", "x-perf": {"max-workers": 1}}} {"return": {}} {"data": {"device": "ref_backup_2", "len": 67108864, "offset": 67108864, "speed": 0, "type": "backup"}, "event": "BLOCK_JOB_COMPLETED", "timestamp": {"microseconds": "USECS", "seconds": "SECS"}} @@ -XXX,XX +XXX,XX @@ expecting 1014 dirty sectors; have 1014. OK! {"execute": "job-dismiss", "arguments": {"id": "bdc-fmt-job"}} {"return": {}} {} -{"execute": "blockdev-backup", "arguments": {"auto-finalize": false, "bitmap": "bitmap0", "bitmap-mode": "always", "device": "drive0", "filter-node-name": "backup-top", "job-id": "backup_2", "sync": "bitmap", "target": "backup_target_2"}} +{"execute": "blockdev-backup", "arguments": {"auto-finalize": false, "bitmap": "bitmap0", "bitmap-mode": "always", "device": "drive0", "filter-node-name": "backup-top", "job-id": "backup_2", "sync": "bitmap", "target": "backup_target_2", "x-perf": {"max-workers": 1}}} {"return": {}} {"execute": "job-finalize", "arguments": {"id": "backup_2"}} {"return": {}} @@ -XXX,XX +XXX,XX @@ write -P0x76 0x3ff0000 0x10000 {"execute": "job-dismiss", "arguments": {"id": "bdc-fmt-job"}} {"return": {}} {} -{"execute": "blockdev-backup", "arguments": {"device": "drive0", "filter-node-name": "backup-top", "job-id": "ref_backup_0", "sync": "full", "target": "ref_target_0"}} +{"execute": "blockdev-backup", "arguments": {"device": "drive0", "filter-node-name": "backup-top", "job-id": "ref_backup_0", "sync": "full", "target": "ref_target_0", "x-perf": {"max-workers": 1}}} {"return": {}} {"data": {"device": "ref_backup_0", "len": 67108864, "offset": 67108864, "speed": 0, "type": "backup"}, "event": "BLOCK_JOB_COMPLETED", "timestamp": {"microseconds": "USECS", "seconds": "SECS"}} @@ -XXX,XX +XXX,XX @@ expecting 6 dirty sectors; have 6. OK! {"execute": "job-dismiss", "arguments": {"id": "bdc-fmt-job"}} {"return": {}} {} -{"execute": "blockdev-backup", "arguments": {"device": "drive0", "filter-node-name": "backup-top", "job-id": "ref_backup_1", "sync": "full", "target": "ref_target_1"}} +{"execute": "blockdev-backup", "arguments": {"device": "drive0", "filter-node-name": "backup-top", "job-id": "ref_backup_1", "sync": "full", "target": "ref_target_1", "x-perf": {"max-workers": 1}}} {"return": {}} {"data": {"device": "ref_backup_1", "len": 67108864, "offset": 67108864, "speed": 0, "type": "backup"}, "event": "BLOCK_JOB_COMPLETED", "timestamp": {"microseconds": "USECS", "seconds": "SECS"}} @@ -XXX,XX +XXX,XX @@ expecting 6 dirty sectors; have 6. OK! {"execute": "job-dismiss", "arguments": {"id": "bdc-fmt-job"}} {"return": {}} {} -{"execute": "blockdev-backup", "arguments": {"auto-finalize": false, "bitmap": "bitmap0", "bitmap-mode": "always", "device": "drive0", "filter-node-name": "backup-top", "job-id": "backup_1", "sync": "full", "target": "backup_target_1"}} +{"execute": "blockdev-backup", "arguments": {"auto-finalize": false, "bitmap": "bitmap0", "bitmap-mode": "always", "device": "drive0", "filter-node-name": "backup-top", "job-id": "backup_1", "sync": "full", "target": "backup_target_1", "x-perf": {"max-workers": 1}}} {"return": {}} --- Write #2 --- @@ -XXX,XX +XXX,XX @@ expecting 12 dirty sectors; have 12. OK! {"execute": "job-dismiss", "arguments": {"id": "bdc-fmt-job"}} {"return": {}} {} -{"execute": "blockdev-backup", "arguments": {"device": "drive0", "filter-node-name": "backup-top", "job-id": "ref_backup_2", "sync": "full", "target": "ref_target_2"}} +{"execute": "blockdev-backup", "arguments": {"device": "drive0", "filter-node-name": "backup-top", "job-id": "ref_backup_2", "sync": "full", "target": "ref_target_2", "x-perf": {"max-workers": 1}}} {"return": {}} {"data": {"device": "ref_backup_2", "len": 67108864, "offset": 67108864, "speed": 0, "type": "backup"}, "event": "BLOCK_JOB_COMPLETED", "timestamp": {"microseconds": "USECS", "seconds": "SECS"}} @@ -XXX,XX +XXX,XX @@ expecting 12 dirty sectors; have 12. OK! {"execute": "job-dismiss", "arguments": {"id": "bdc-fmt-job"}} {"return": {}} {} -{"execute": "blockdev-backup", "arguments": {"auto-finalize": false, "bitmap": "bitmap0", "bitmap-mode": "always", "device": "drive0", "filter-node-name": "backup-top", "job-id": "backup_2", "sync": "bitmap", "target": "backup_target_2"}} +{"execute": "blockdev-backup", "arguments": {"auto-finalize": false, "bitmap": "bitmap0", "bitmap-mode": "always", "device": "drive0", "filter-node-name": "backup-top", "job-id": "backup_2", "sync": "bitmap", "target": "backup_target_2", "x-perf": {"max-workers": 1}}} {"return": {}} {"execute": "job-finalize", "arguments": {"id": "backup_2"}} {"return": {}} @@ -XXX,XX +XXX,XX @@ write -P0x76 0x3ff0000 0x10000 {"execute": "job-dismiss", "arguments": {"id": "bdc-fmt-job"}} {"return": {}} {} -{"execute": "blockdev-backup", "arguments": {"device": "drive0", "filter-node-name": "backup-top", "job-id": "ref_backup_0", "sync": "full", "target": "ref_target_0"}} +{"execute": "blockdev-backup", "arguments": {"device": "drive0", "filter-node-name": "backup-top", "job-id": "ref_backup_0", "sync": "full", "target": "ref_target_0", "x-perf": {"max-workers": 1}}} {"return": {}} {"data": {"device": "ref_backup_0", "len": 67108864, "offset": 67108864, "speed": 0, "type": "backup"}, "event": "BLOCK_JOB_COMPLETED", "timestamp": {"microseconds": "USECS", "seconds": "SECS"}} @@ -XXX,XX +XXX,XX @@ expecting 6 dirty sectors; have 6. OK! {"execute": "job-dismiss", "arguments": {"id": "bdc-fmt-job"}} {"return": {}} {} -{"execute": "blockdev-backup", "arguments": {"device": "drive0", "filter-node-name": "backup-top", "job-id": "ref_backup_1", "sync": "full", "target": "ref_target_1"}} +{"execute": "blockdev-backup", "arguments": {"device": "drive0", "filter-node-name": "backup-top", "job-id": "ref_backup_1", "sync": "full", "target": "ref_target_1", "x-perf": {"max-workers": 1}}} {"return": {}} {"data": {"device": "ref_backup_1", "len": 67108864, "offset": 67108864, "speed": 0, "type": "backup"}, "event": "BLOCK_JOB_COMPLETED", "timestamp": {"microseconds": "USECS", "seconds": "SECS"}} @@ -XXX,XX +XXX,XX @@ expecting 6 dirty sectors; have 6. OK! {"execute": "job-dismiss", "arguments": {"id": "bdc-fmt-job"}} {"return": {}} {} -{"execute": "blockdev-backup", "arguments": {"auto-finalize": false, "bitmap": "bitmap0", "bitmap-mode": "on-success", "device": "drive0", "filter-node-name": "backup-top", "job-id": "backup_1", "sync": "top", "target": "backup_target_1"}} +{"execute": "blockdev-backup", "arguments": {"auto-finalize": false, "bitmap": "bitmap0", "bitmap-mode": "on-success", "device": "drive0", "filter-node-name": "backup-top", "job-id": "backup_1", "sync": "top", "target": "backup_target_1", "x-perf": {"max-workers": 1}}} {"return": {}} --- Write #2 --- @@ -XXX,XX +XXX,XX @@ expecting 15 dirty sectors; have 15. OK! {"execute": "job-dismiss", "arguments": {"id": "bdc-fmt-job"}} {"return": {}} {} -{"execute": "blockdev-backup", "arguments": {"device": "drive0", "filter-node-name": "backup-top", "job-id": "ref_backup_2", "sync": "full", "target": "ref_target_2"}} +{"execute": "blockdev-backup", "arguments": {"device": "drive0", "filter-node-name": "backup-top", "job-id": "ref_backup_2", "sync": "full", "target": "ref_target_2", "x-perf": {"max-workers": 1}}} {"return": {}} {"data": {"device": "ref_backup_2", "len": 67108864, "offset": 67108864, "speed": 0, "type": "backup"}, "event": "BLOCK_JOB_COMPLETED", "timestamp": {"microseconds": "USECS", "seconds": "SECS"}} @@ -XXX,XX +XXX,XX @@ expecting 15 dirty sectors; have 15. OK! {"execute": "job-dismiss", "arguments": {"id": "bdc-fmt-job"}} {"return": {}} {} -{"execute": "blockdev-backup", "arguments": {"auto-finalize": false, "bitmap": "bitmap0", "bitmap-mode": "on-success", "device": "drive0", "filter-node-name": "backup-top", "job-id": "backup_2", "sync": "bitmap", "target": "backup_target_2"}} +{"execute": "blockdev-backup", "arguments": {"auto-finalize": false, "bitmap": "bitmap0", "bitmap-mode": "on-success", "device": "drive0", "filter-node-name": "backup-top", "job-id": "backup_2", "sync": "bitmap", "target": "backup_target_2", "x-perf": {"max-workers": 1}}} {"return": {}} {"execute": "job-finalize", "arguments": {"id": "backup_2"}} {"return": {}} @@ -XXX,XX +XXX,XX @@ write -P0x76 0x3ff0000 0x10000 {"execute": "job-dismiss", "arguments": {"id": "bdc-fmt-job"}} {"return": {}} {} -{"execute": "blockdev-backup", "arguments": {"device": "drive0", "filter-node-name": "backup-top", "job-id": "ref_backup_0", "sync": "full", "target": "ref_target_0"}} +{"execute": "blockdev-backup", "arguments": {"device": "drive0", "filter-node-name": "backup-top", "job-id": "ref_backup_0", "sync": "full", "target": "ref_target_0", "x-perf": {"max-workers": 1}}} {"return": {}} {"data": {"device": "ref_backup_0", "len": 67108864, "offset": 67108864, "speed": 0, "type": "backup"}, "event": "BLOCK_JOB_COMPLETED", "timestamp": {"microseconds": "USECS", "seconds": "SECS"}} @@ -XXX,XX +XXX,XX @@ expecting 6 dirty sectors; have 6. OK! {"execute": "job-dismiss", "arguments": {"id": "bdc-fmt-job"}} {"return": {}} {} -{"execute": "blockdev-backup", "arguments": {"device": "drive0", "filter-node-name": "backup-top", "job-id": "ref_backup_1", "sync": "full", "target": "ref_target_1"}} +{"execute": "blockdev-backup", "arguments": {"device": "drive0", "filter-node-name": "backup-top", "job-id": "ref_backup_1", "sync": "full", "target": "ref_target_1", "x-perf": {"max-workers": 1}}} {"return": {}} {"data": {"device": "ref_backup_1", "len": 67108864, "offset": 67108864, "speed": 0, "type": "backup"}, "event": "BLOCK_JOB_COMPLETED", "timestamp": {"microseconds": "USECS", "seconds": "SECS"}} @@ -XXX,XX +XXX,XX @@ expecting 6 dirty sectors; have 6. OK! {"execute": "job-dismiss", "arguments": {"id": "bdc-fmt-job"}} {"return": {}} {} -{"execute": "blockdev-backup", "arguments": {"auto-finalize": false, "bitmap": "bitmap0", "bitmap-mode": "on-success", "device": "drive0", "filter-node-name": "backup-top", "job-id": "backup_1", "sync": "top", "target": "backup_target_1"}} +{"execute": "blockdev-backup", "arguments": {"auto-finalize": false, "bitmap": "bitmap0", "bitmap-mode": "on-success", "device": "drive0", "filter-node-name": "backup-top", "job-id": "backup_1", "sync": "top", "target": "backup_target_1", "x-perf": {"max-workers": 1}}} {"return": {}} {"data": {"action": "report", "device": "backup_1", "operation": "read"}, "event": "BLOCK_JOB_ERROR", "timestamp": {"microseconds": "USECS", "seconds": "SECS"}} {"data": {"device": "backup_1", "error": "Input/output error", "len": 458752, "offset": 65536, "speed": 0, "type": "backup"}, "event": "BLOCK_JOB_COMPLETED", "timestamp": {"microseconds": "USECS", "seconds": "SECS"}} @@ -XXX,XX +XXX,XX @@ expecting 14 dirty sectors; have 14. OK! {"execute": "job-dismiss", "arguments": {"id": "bdc-fmt-job"}} {"return": {}} {} -{"execute": "blockdev-backup", "arguments": {"device": "drive0", "filter-node-name": "backup-top", "job-id": "ref_backup_2", "sync": "full", "target": "ref_target_2"}} +{"execute": "blockdev-backup", "arguments": {"device": "drive0", "filter-node-name": "backup-top", "job-id": "ref_backup_2", "sync": "full", "target": "ref_target_2", "x-perf": {"max-workers": 1}}} {"return": {}} {"data": {"device": "ref_backup_2", "len": 67108864, "offset": 67108864, "speed": 0, "type": "backup"}, "event": "BLOCK_JOB_COMPLETED", "timestamp": {"microseconds": "USECS", "seconds": "SECS"}} @@ -XXX,XX +XXX,XX @@ expecting 14 dirty sectors; have 14. OK! {"execute": "job-dismiss", "arguments": {"id": "bdc-fmt-job"}} {"return": {}} {} -{"execute": "blockdev-backup", "arguments": {"auto-finalize": false, "bitmap": "bitmap0", "bitmap-mode": "on-success", "device": "drive0", "filter-node-name": "backup-top", "job-id": "backup_2", "sync": "bitmap", "target": "backup_target_2"}} +{"execute": "blockdev-backup", "arguments": {"auto-finalize": false, "bitmap": "bitmap0", "bitmap-mode": "on-success", "device": "drive0", "filter-node-name": "backup-top", "job-id": "backup_2", "sync": "bitmap", "target": "backup_target_2", "x-perf": {"max-workers": 1}}} {"return": {}} {"execute": "job-finalize", "arguments": {"id": "backup_2"}} {"return": {}} @@ -XXX,XX +XXX,XX @@ write -P0x76 0x3ff0000 0x10000 {"execute": "job-dismiss", "arguments": {"id": "bdc-fmt-job"}} {"return": {}} {} -{"execute": "blockdev-backup", "arguments": {"device": "drive0", "filter-node-name": "backup-top", "job-id": "ref_backup_0", "sync": "full", "target": "ref_target_0"}} +{"execute": "blockdev-backup", "arguments": {"device": "drive0", "filter-node-name": "backup-top", "job-id": "ref_backup_0", "sync": "full", "target": "ref_target_0", "x-perf": {"max-workers": 1}}} {"return": {}} {"data": {"device": "ref_backup_0", "len": 67108864, "offset": 67108864, "speed": 0, "type": "backup"}, "event": "BLOCK_JOB_COMPLETED", "timestamp": {"microseconds": "USECS", "seconds": "SECS"}} @@ -XXX,XX +XXX,XX @@ expecting 6 dirty sectors; have 6. OK! {"execute": "job-dismiss", "arguments": {"id": "bdc-fmt-job"}} {"return": {}} {} -{"execute": "blockdev-backup", "arguments": {"device": "drive0", "filter-node-name": "backup-top", "job-id": "ref_backup_1", "sync": "full", "target": "ref_target_1"}} +{"execute": "blockdev-backup", "arguments": {"device": "drive0", "filter-node-name": "backup-top", "job-id": "ref_backup_1", "sync": "full", "target": "ref_target_1", "x-perf": {"max-workers": 1}}} {"return": {}} {"data": {"device": "ref_backup_1", "len": 67108864, "offset": 67108864, "speed": 0, "type": "backup"}, "event": "BLOCK_JOB_COMPLETED", "timestamp": {"microseconds": "USECS", "seconds": "SECS"}} @@ -XXX,XX +XXX,XX @@ expecting 6 dirty sectors; have 6. OK! {"execute": "job-dismiss", "arguments": {"id": "bdc-fmt-job"}} {"return": {}} {} -{"execute": "blockdev-backup", "arguments": {"auto-finalize": false, "bitmap": "bitmap0", "bitmap-mode": "on-success", "device": "drive0", "filter-node-name": "backup-top", "job-id": "backup_1", "sync": "top", "target": "backup_target_1"}} +{"execute": "blockdev-backup", "arguments": {"auto-finalize": false, "bitmap": "bitmap0", "bitmap-mode": "on-success", "device": "drive0", "filter-node-name": "backup-top", "job-id": "backup_1", "sync": "top", "target": "backup_target_1", "x-perf": {"max-workers": 1}}} {"return": {}} --- Write #2 --- @@ -XXX,XX +XXX,XX @@ expecting 12 dirty sectors; have 12. OK! {"execute": "job-dismiss", "arguments": {"id": "bdc-fmt-job"}} {"return": {}} {} -{"execute": "blockdev-backup", "arguments": {"device": "drive0", "filter-node-name": "backup-top", "job-id": "ref_backup_2", "sync": "full", "target": "ref_target_2"}} +{"execute": "blockdev-backup", "arguments": {"device": "drive0", "filter-node-name": "backup-top", "job-id": "ref_backup_2", "sync": "full", "target": "ref_target_2", "x-perf": {"max-workers": 1}}} {"return": {}} {"data": {"device": "ref_backup_2", "len": 67108864, "offset": 67108864, "speed": 0, "type": "backup"}, "event": "BLOCK_JOB_COMPLETED", "timestamp": {"microseconds": "USECS", "seconds": "SECS"}} @@ -XXX,XX +XXX,XX @@ expecting 12 dirty sectors; have 12. OK! {"execute": "job-dismiss", "arguments": {"id": "bdc-fmt-job"}} {"return": {}} {} -{"execute": "blockdev-backup", "arguments": {"auto-finalize": false, "bitmap": "bitmap0", "bitmap-mode": "on-success", "device": "drive0", "filter-node-name": "backup-top", "job-id": "backup_2", "sync": "bitmap", "target": "backup_target_2"}} +{"execute": "blockdev-backup", "arguments": {"auto-finalize": false, "bitmap": "bitmap0", "bitmap-mode": "on-success", "device": "drive0", "filter-node-name": "backup-top", "job-id": "backup_2", "sync": "bitmap", "target": "backup_target_2", "x-perf": {"max-workers": 1}}} {"return": {}} {"execute": "job-finalize", "arguments": {"id": "backup_2"}} {"return": {}} @@ -XXX,XX +XXX,XX @@ write -P0x76 0x3ff0000 0x10000 {"execute": "job-dismiss", "arguments": {"id": "bdc-fmt-job"}} {"return": {}} {} -{"execute": "blockdev-backup", "arguments": {"device": "drive0", "filter-node-name": "backup-top", "job-id": "ref_backup_0", "sync": "full", "target": "ref_target_0"}} +{"execute": "blockdev-backup", "arguments": {"device": "drive0", "filter-node-name": "backup-top", "job-id": "ref_backup_0", "sync": "full", "target": "ref_target_0", "x-perf": {"max-workers": 1}}} {"return": {}} {"data": {"device": "ref_backup_0", "len": 67108864, "offset": 67108864, "speed": 0, "type": "backup"}, "event": "BLOCK_JOB_COMPLETED", "timestamp": {"microseconds": "USECS", "seconds": "SECS"}} @@ -XXX,XX +XXX,XX @@ expecting 6 dirty sectors; have 6. OK! {"execute": "job-dismiss", "arguments": {"id": "bdc-fmt-job"}} {"return": {}} {} -{"execute": "blockdev-backup", "arguments": {"device": "drive0", "filter-node-name": "backup-top", "job-id": "ref_backup_1", "sync": "full", "target": "ref_target_1"}} +{"execute": "blockdev-backup", "arguments": {"device": "drive0", "filter-node-name": "backup-top", "job-id": "ref_backup_1", "sync": "full", "target": "ref_target_1", "x-perf": {"max-workers": 1}}} {"return": {}} {"data": {"device": "ref_backup_1", "len": 67108864, "offset": 67108864, "speed": 0, "type": "backup"}, "event": "BLOCK_JOB_COMPLETED", "timestamp": {"microseconds": "USECS", "seconds": "SECS"}} @@ -XXX,XX +XXX,XX @@ expecting 6 dirty sectors; have 6. OK! {"execute": "job-dismiss", "arguments": {"id": "bdc-fmt-job"}} {"return": {}} {} -{"execute": "blockdev-backup", "arguments": {"auto-finalize": false, "bitmap": "bitmap0", "bitmap-mode": "always", "device": "drive0", "filter-node-name": "backup-top", "job-id": "backup_1", "sync": "top", "target": "backup_target_1"}} +{"execute": "blockdev-backup", "arguments": {"auto-finalize": false, "bitmap": "bitmap0", "bitmap-mode": "always", "device": "drive0", "filter-node-name": "backup-top", "job-id": "backup_1", "sync": "top", "target": "backup_target_1", "x-perf": {"max-workers": 1}}} {"return": {}} --- Write #2 --- @@ -XXX,XX +XXX,XX @@ expecting 12 dirty sectors; have 12. OK! {"execute": "job-dismiss", "arguments": {"id": "bdc-fmt-job"}} {"return": {}} {} -{"execute": "blockdev-backup", "arguments": {"device": "drive0", "filter-node-name": "backup-top", "job-id": "ref_backup_2", "sync": "full", "target": "ref_target_2"}} +{"execute": "blockdev-backup", "arguments": {"device": "drive0", "filter-node-name": "backup-top", "job-id": "ref_backup_2", "sync": "full", "target": "ref_target_2", "x-perf": {"max-workers": 1}}} {"return": {}} {"data": {"device": "ref_backup_2", "len": 67108864, "offset": 67108864, "speed": 0, "type": "backup"}, "event": "BLOCK_JOB_COMPLETED", "timestamp": {"microseconds": "USECS", "seconds": "SECS"}} @@ -XXX,XX +XXX,XX @@ expecting 12 dirty sectors; have 12. OK! {"execute": "job-dismiss", "arguments": {"id": "bdc-fmt-job"}} {"return": {}} {} -{"execute": "blockdev-backup", "arguments": {"auto-finalize": false, "bitmap": "bitmap0", "bitmap-mode": "always", "device": "drive0", "filter-node-name": "backup-top", "job-id": "backup_2", "sync": "bitmap", "target": "backup_target_2"}} +{"execute": "blockdev-backup", "arguments": {"auto-finalize": false, "bitmap": "bitmap0", "bitmap-mode": "always", "device": "drive0", "filter-node-name": "backup-top", "job-id": "backup_2", "sync": "bitmap", "target": "backup_target_2", "x-perf": {"max-workers": 1}}} {"return": {}} {"execute": "job-finalize", "arguments": {"id": "backup_2"}} {"return": {}} @@ -XXX,XX +XXX,XX @@ write -P0x76 0x3ff0000 0x10000 {"execute": "job-dismiss", "arguments": {"id": "bdc-fmt-job"}} {"return": {}} {} -{"execute": "blockdev-backup", "arguments": {"device": "drive0", "filter-node-name": "backup-top", "job-id": "ref_backup_0", "sync": "full", "target": "ref_target_0"}} +{"execute": "blockdev-backup", "arguments": {"device": "drive0", "filter-node-name": "backup-top", "job-id": "ref_backup_0", "sync": "full", "target": "ref_target_0", "x-perf": {"max-workers": 1}}} {"return": {}} {"data": {"device": "ref_backup_0", "len": 67108864, "offset": 67108864, "speed": 0, "type": "backup"}, "event": "BLOCK_JOB_COMPLETED", "timestamp": {"microseconds": "USECS", "seconds": "SECS"}} @@ -XXX,XX +XXX,XX @@ expecting 6 dirty sectors; have 6. OK! {"execute": "job-dismiss", "arguments": {"id": "bdc-fmt-job"}} {"return": {}} {} -{"execute": "blockdev-backup", "arguments": {"device": "drive0", "filter-node-name": "backup-top", "job-id": "ref_backup_1", "sync": "full", "target": "ref_target_1"}} +{"execute": "blockdev-backup", "arguments": {"device": "drive0", "filter-node-name": "backup-top", "job-id": "ref_backup_1", "sync": "full", "target": "ref_target_1", "x-perf": {"max-workers": 1}}} {"return": {}} {"data": {"device": "ref_backup_1", "len": 67108864, "offset": 67108864, "speed": 0, "type": "backup"}, "event": "BLOCK_JOB_COMPLETED", "timestamp": {"microseconds": "USECS", "seconds": "SECS"}} @@ -XXX,XX +XXX,XX @@ expecting 6 dirty sectors; have 6. OK! {"execute": "job-dismiss", "arguments": {"id": "bdc-fmt-job"}} {"return": {}} {} -{"execute": "blockdev-backup", "arguments": {"auto-finalize": false, "bitmap": "bitmap0", "bitmap-mode": "always", "device": "drive0", "filter-node-name": "backup-top", "job-id": "backup_1", "sync": "top", "target": "backup_target_1"}} +{"execute": "blockdev-backup", "arguments": {"auto-finalize": false, "bitmap": "bitmap0", "bitmap-mode": "always", "device": "drive0", "filter-node-name": "backup-top", "job-id": "backup_1", "sync": "top", "target": "backup_target_1", "x-perf": {"max-workers": 1}}} {"return": {}} {"data": {"action": "report", "device": "backup_1", "operation": "read"}, "event": "BLOCK_JOB_ERROR", "timestamp": {"microseconds": "USECS", "seconds": "SECS"}} {"data": {"device": "backup_1", "error": "Input/output error", "len": 458752, "offset": 65536, "speed": 0, "type": "backup"}, "event": "BLOCK_JOB_COMPLETED", "timestamp": {"microseconds": "USECS", "seconds": "SECS"}} @@ -XXX,XX +XXX,XX @@ expecting 14 dirty sectors; have 14. OK! {"execute": "job-dismiss", "arguments": {"id": "bdc-fmt-job"}} {"return": {}} {} -{"execute": "blockdev-backup", "arguments": {"device": "drive0", "filter-node-name": "backup-top", "job-id": "ref_backup_2", "sync": "full", "target": "ref_target_2"}} +{"execute": "blockdev-backup", "arguments": {"device": "drive0", "filter-node-name": "backup-top", "job-id": "ref_backup_2", "sync": "full", "target": "ref_target_2", "x-perf": {"max-workers": 1}}} {"return": {}} {"data": {"device": "ref_backup_2", "len": 67108864, "offset": 67108864, "speed": 0, "type": "backup"}, "event": "BLOCK_JOB_COMPLETED", "timestamp": {"microseconds": "USECS", "seconds": "SECS"}} @@ -XXX,XX +XXX,XX @@ expecting 14 dirty sectors; have 14. OK! {"execute": "job-dismiss", "arguments": {"id": "bdc-fmt-job"}} {"return": {}} {} -{"execute": "blockdev-backup", "arguments": {"auto-finalize": false, "bitmap": "bitmap0", "bitmap-mode": "always", "device": "drive0", "filter-node-name": "backup-top", "job-id": "backup_2", "sync": "bitmap", "target": "backup_target_2"}} +{"execute": "blockdev-backup", "arguments": {"auto-finalize": false, "bitmap": "bitmap0", "bitmap-mode": "always", "device": "drive0", "filter-node-name": "backup-top", "job-id": "backup_2", "sync": "bitmap", "target": "backup_target_2", "x-perf": {"max-workers": 1}}} {"return": {}} {"execute": "job-finalize", "arguments": {"id": "backup_2"}} {"return": {}} @@ -XXX,XX +XXX,XX @@ write -P0x76 0x3ff0000 0x10000 {"execute": "job-dismiss", "arguments": {"id": "bdc-fmt-job"}} {"return": {}} {} -{"execute": "blockdev-backup", "arguments": {"device": "drive0", "filter-node-name": "backup-top", "job-id": "ref_backup_0", "sync": "full", "target": "ref_target_0"}} +{"execute": "blockdev-backup", "arguments": {"device": "drive0", "filter-node-name": "backup-top", "job-id": "ref_backup_0", "sync": "full", "target": "ref_target_0", "x-perf": {"max-workers": 1}}} {"return": {}} {"data": {"device": "ref_backup_0", "len": 67108864, "offset": 67108864, "speed": 0, "type": "backup"}, "event": "BLOCK_JOB_COMPLETED", "timestamp": {"microseconds": "USECS", "seconds": "SECS"}} @@ -XXX,XX +XXX,XX @@ expecting 6 dirty sectors; have 6. OK! {"execute": "job-dismiss", "arguments": {"id": "bdc-fmt-job"}} {"return": {}} {} -{"execute": "blockdev-backup", "arguments": {"device": "drive0", "filter-node-name": "backup-top", "job-id": "ref_backup_1", "sync": "full", "target": "ref_target_1"}} +{"execute": "blockdev-backup", "arguments": {"device": "drive0", "filter-node-name": "backup-top", "job-id": "ref_backup_1", "sync": "full", "target": "ref_target_1", "x-perf": {"max-workers": 1}}} {"return": {}} {"data": {"device": "ref_backup_1", "len": 67108864, "offset": 67108864, "speed": 0, "type": "backup"}, "event": "BLOCK_JOB_COMPLETED", "timestamp": {"microseconds": "USECS", "seconds": "SECS"}} @@ -XXX,XX +XXX,XX @@ expecting 6 dirty sectors; have 6. OK! {"execute": "job-dismiss", "arguments": {"id": "bdc-fmt-job"}} {"return": {}} {} -{"execute": "blockdev-backup", "arguments": {"auto-finalize": false, "bitmap": "bitmap0", "bitmap-mode": "always", "device": "drive0", "filter-node-name": "backup-top", "job-id": "backup_1", "sync": "top", "target": "backup_target_1"}} +{"execute": "blockdev-backup", "arguments": {"auto-finalize": false, "bitmap": "bitmap0", "bitmap-mode": "always", "device": "drive0", "filter-node-name": "backup-top", "job-id": "backup_1", "sync": "top", "target": "backup_target_1", "x-perf": {"max-workers": 1}}} {"return": {}} --- Write #2 --- @@ -XXX,XX +XXX,XX @@ expecting 12 dirty sectors; have 12. OK! {"execute": "job-dismiss", "arguments": {"id": "bdc-fmt-job"}} {"return": {}} {} -{"execute": "blockdev-backup", "arguments": {"device": "drive0", "filter-node-name": "backup-top", "job-id": "ref_backup_2", "sync": "full", "target": "ref_target_2"}} +{"execute": "blockdev-backup", "arguments": {"device": "drive0", "filter-node-name": "backup-top", "job-id": "ref_backup_2", "sync": "full", "target": "ref_target_2", "x-perf": {"max-workers": 1}}} {"return": {}} {"data": {"device": "ref_backup_2", "len": 67108864, "offset": 67108864, "speed": 0, "type": "backup"}, "event": "BLOCK_JOB_COMPLETED", "timestamp": {"microseconds": "USECS", "seconds": "SECS"}} @@ -XXX,XX +XXX,XX @@ expecting 12 dirty sectors; have 12. OK! {"execute": "job-dismiss", "arguments": {"id": "bdc-fmt-job"}} {"return": {}} {} -{"execute": "blockdev-backup", "arguments": {"auto-finalize": false, "bitmap": "bitmap0", "bitmap-mode": "always", "device": "drive0", "filter-node-name": "backup-top", "job-id": "backup_2", "sync": "bitmap", "target": "backup_target_2"}} +{"execute": "blockdev-backup", "arguments": {"auto-finalize": false, "bitmap": "bitmap0", "bitmap-mode": "always", "device": "drive0", "filter-node-name": "backup-top", "job-id": "backup_2", "sync": "bitmap", "target": "backup_target_2", "x-perf": {"max-workers": 1}}} {"return": {}} {"execute": "job-finalize", "arguments": {"id": "backup_2"}} {"return": {}} @@ -XXX,XX +XXX,XX @@ qemu_img compare "TEST_DIR/PID-img" "TEST_DIR/PID-fbackup2" ==> Identical, OK! -- Sync mode incremental tests -- -{"execute": "blockdev-backup", "arguments": {"bitmap-mode": "on-success", "device": "drive0", "filter-node-name": "backup-top", "job-id": "api_job", "sync": "incremental", "target": "backup_target"}} +{"execute": "blockdev-backup", "arguments": {"bitmap-mode": "on-success", "device": "drive0", "filter-node-name": "backup-top", "job-id": "api_job", "sync": "incremental", "target": "backup_target", "x-perf": {"max-workers": 1}}} {"error": {"class": "GenericError", "desc": "must provide a valid bitmap name for 'incremental' sync mode"}} -{"execute": "blockdev-backup", "arguments": {"bitmap-mode": "always", "device": "drive0", "filter-node-name": "backup-top", "job-id": "api_job", "sync": "incremental", "target": "backup_target"}} +{"execute": "blockdev-backup", "arguments": {"bitmap-mode": "always", "device": "drive0", "filter-node-name": "backup-top", "job-id": "api_job", "sync": "incremental", "target": "backup_target", "x-perf": {"max-workers": 1}}} {"error": {"class": "GenericError", "desc": "must provide a valid bitmap name for 'incremental' sync mode"}} -{"execute": "blockdev-backup", "arguments": {"bitmap-mode": "never", "device": "drive0", "filter-node-name": "backup-top", "job-id": "api_job", "sync": "incremental", "target": "backup_target"}} +{"execute": "blockdev-backup", "arguments": {"bitmap-mode": "never", "device": "drive0", "filter-node-name": "backup-top", "job-id": "api_job", "sync": "incremental", "target": "backup_target", "x-perf": {"max-workers": 1}}} {"error": {"class": "GenericError", "desc": "must provide a valid bitmap name for 'incremental' sync mode"}} -{"execute": "blockdev-backup", "arguments": {"device": "drive0", "filter-node-name": "backup-top", "job-id": "api_job", "sync": "incremental", "target": "backup_target"}} +{"execute": "blockdev-backup", "arguments": {"device": "drive0", "filter-node-name": "backup-top", "job-id": "api_job", "sync": "incremental", "target": "backup_target", "x-perf": {"max-workers": 1}}} {"error": {"class": "GenericError", "desc": "must provide a valid bitmap name for 'incremental' sync mode"}} -{"execute": "blockdev-backup", "arguments": {"bitmap": "bitmap404", "bitmap-mode": "on-success", "device": "drive0", "filter-node-name": "backup-top", "job-id": "api_job", "sync": "incremental", "target": "backup_target"}} +{"execute": "blockdev-backup", "arguments": {"bitmap": "bitmap404", "bitmap-mode": "on-success", "device": "drive0", "filter-node-name": "backup-top", "job-id": "api_job", "sync": "incremental", "target": "backup_target", "x-perf": {"max-workers": 1}}} {"error": {"class": "GenericError", "desc": "Bitmap 'bitmap404' could not be found"}} -{"execute": "blockdev-backup", "arguments": {"bitmap": "bitmap404", "bitmap-mode": "always", "device": "drive0", "filter-node-name": "backup-top", "job-id": "api_job", "sync": "incremental", "target": "backup_target"}} +{"execute": "blockdev-backup", "arguments": {"bitmap": "bitmap404", "bitmap-mode": "always", "device": "drive0", "filter-node-name": "backup-top", "job-id": "api_job", "sync": "incremental", "target": "backup_target", "x-perf": {"max-workers": 1}}} {"error": {"class": "GenericError", "desc": "Bitmap sync mode must be 'on-success' when using sync mode 'incremental'"}} -{"execute": "blockdev-backup", "arguments": {"bitmap": "bitmap404", "bitmap-mode": "never", "device": "drive0", "filter-node-name": "backup-top", "job-id": "api_job", "sync": "incremental", "target": "backup_target"}} +{"execute": "blockdev-backup", "arguments": {"bitmap": "bitmap404", "bitmap-mode": "never", "device": "drive0", "filter-node-name": "backup-top", "job-id": "api_job", "sync": "incremental", "target": "backup_target", "x-perf": {"max-workers": 1}}} {"error": {"class": "GenericError", "desc": "Bitmap sync mode must be 'on-success' when using sync mode 'incremental'"}} -{"execute": "blockdev-backup", "arguments": {"bitmap": "bitmap404", "device": "drive0", "filter-node-name": "backup-top", "job-id": "api_job", "sync": "incremental", "target": "backup_target"}} +{"execute": "blockdev-backup", "arguments": {"bitmap": "bitmap404", "device": "drive0", "filter-node-name": "backup-top", "job-id": "api_job", "sync": "incremental", "target": "backup_target", "x-perf": {"max-workers": 1}}} {"error": {"class": "GenericError", "desc": "Bitmap 'bitmap404' could not be found"}} -{"execute": "blockdev-backup", "arguments": {"bitmap": "bitmap0", "bitmap-mode": "always", "device": "drive0", "filter-node-name": "backup-top", "job-id": "api_job", "sync": "incremental", "target": "backup_target"}} +{"execute": "blockdev-backup", "arguments": {"bitmap": "bitmap0", "bitmap-mode": "always", "device": "drive0", "filter-node-name": "backup-top", "job-id": "api_job", "sync": "incremental", "target": "backup_target", "x-perf": {"max-workers": 1}}} {"error": {"class": "GenericError", "desc": "Bitmap sync mode must be 'on-success' when using sync mode 'incremental'"}} -{"execute": "blockdev-backup", "arguments": {"bitmap": "bitmap0", "bitmap-mode": "never", "device": "drive0", "filter-node-name": "backup-top", "job-id": "api_job", "sync": "incremental", "target": "backup_target"}} +{"execute": "blockdev-backup", "arguments": {"bitmap": "bitmap0", "bitmap-mode": "never", "device": "drive0", "filter-node-name": "backup-top", "job-id": "api_job", "sync": "incremental", "target": "backup_target", "x-perf": {"max-workers": 1}}} {"error": {"class": "GenericError", "desc": "Bitmap sync mode must be 'on-success' when using sync mode 'incremental'"}} -- Sync mode bitmap tests -- -{"execute": "blockdev-backup", "arguments": {"bitmap-mode": "on-success", "device": "drive0", "filter-node-name": "backup-top", "job-id": "api_job", "sync": "bitmap", "target": "backup_target"}} +{"execute": "blockdev-backup", "arguments": {"bitmap-mode": "on-success", "device": "drive0", "filter-node-name": "backup-top", "job-id": "api_job", "sync": "bitmap", "target": "backup_target", "x-perf": {"max-workers": 1}}} {"error": {"class": "GenericError", "desc": "must provide a valid bitmap name for 'bitmap' sync mode"}} -{"execute": "blockdev-backup", "arguments": {"bitmap-mode": "always", "device": "drive0", "filter-node-name": "backup-top", "job-id": "api_job", "sync": "bitmap", "target": "backup_target"}} +{"execute": "blockdev-backup", "arguments": {"bitmap-mode": "always", "device": "drive0", "filter-node-name": "backup-top", "job-id": "api_job", "sync": "bitmap", "target": "backup_target", "x-perf": {"max-workers": 1}}} {"error": {"class": "GenericError", "desc": "must provide a valid bitmap name for 'bitmap' sync mode"}} -{"execute": "blockdev-backup", "arguments": {"bitmap-mode": "never", "device": "drive0", "filter-node-name": "backup-top", "job-id": "api_job", "sync": "bitmap", "target": "backup_target"}} +{"execute": "blockdev-backup", "arguments": {"bitmap-mode": "never", "device": "drive0", "filter-node-name": "backup-top", "job-id": "api_job", "sync": "bitmap", "target": "backup_target", "x-perf": {"max-workers": 1}}} {"error": {"class": "GenericError", "desc": "must provide a valid bitmap name for 'bitmap' sync mode"}} -{"execute": "blockdev-backup", "arguments": {"device": "drive0", "filter-node-name": "backup-top", "job-id": "api_job", "sync": "bitmap", "target": "backup_target"}} +{"execute": "blockdev-backup", "arguments": {"device": "drive0", "filter-node-name": "backup-top", "job-id": "api_job", "sync": "bitmap", "target": "backup_target", "x-perf": {"max-workers": 1}}} {"error": {"class": "GenericError", "desc": "must provide a valid bitmap name for 'bitmap' sync mode"}} -{"execute": "blockdev-backup", "arguments": {"bitmap": "bitmap404", "bitmap-mode": "on-success", "device": "drive0", "filter-node-name": "backup-top", "job-id": "api_job", "sync": "bitmap", "target": "backup_target"}} +{"execute": "blockdev-backup", "arguments": {"bitmap": "bitmap404", "bitmap-mode": "on-success", "device": "drive0", "filter-node-name": "backup-top", "job-id": "api_job", "sync": "bitmap", "target": "backup_target", "x-perf": {"max-workers": 1}}} {"error": {"class": "GenericError", "desc": "Bitmap 'bitmap404' could not be found"}} -{"execute": "blockdev-backup", "arguments": {"bitmap": "bitmap404", "bitmap-mode": "always", "device": "drive0", "filter-node-name": "backup-top", "job-id": "api_job", "sync": "bitmap", "target": "backup_target"}} +{"execute": "blockdev-backup", "arguments": {"bitmap": "bitmap404", "bitmap-mode": "always", "device": "drive0", "filter-node-name": "backup-top", "job-id": "api_job", "sync": "bitmap", "target": "backup_target", "x-perf": {"max-workers": 1}}} {"error": {"class": "GenericError", "desc": "Bitmap 'bitmap404' could not be found"}} -{"execute": "blockdev-backup", "arguments": {"bitmap": "bitmap404", "bitmap-mode": "never", "device": "drive0", "filter-node-name": "backup-top", "job-id": "api_job", "sync": "bitmap", "target": "backup_target"}} +{"execute": "blockdev-backup", "arguments": {"bitmap": "bitmap404", "bitmap-mode": "never", "device": "drive0", "filter-node-name": "backup-top", "job-id": "api_job", "sync": "bitmap", "target": "backup_target", "x-perf": {"max-workers": 1}}} {"error": {"class": "GenericError", "desc": "Bitmap 'bitmap404' could not be found"}} -{"execute": "blockdev-backup", "arguments": {"bitmap": "bitmap404", "device": "drive0", "filter-node-name": "backup-top", "job-id": "api_job", "sync": "bitmap", "target": "backup_target"}} +{"execute": "blockdev-backup", "arguments": {"bitmap": "bitmap404", "device": "drive0", "filter-node-name": "backup-top", "job-id": "api_job", "sync": "bitmap", "target": "backup_target", "x-perf": {"max-workers": 1}}} {"error": {"class": "GenericError", "desc": "Bitmap 'bitmap404' could not be found"}} -{"execute": "blockdev-backup", "arguments": {"bitmap": "bitmap0", "device": "drive0", "filter-node-name": "backup-top", "job-id": "api_job", "sync": "bitmap", "target": "backup_target"}} +{"execute": "blockdev-backup", "arguments": {"bitmap": "bitmap0", "device": "drive0", "filter-node-name": "backup-top", "job-id": "api_job", "sync": "bitmap", "target": "backup_target", "x-perf": {"max-workers": 1}}} {"error": {"class": "GenericError", "desc": "Bitmap sync mode must be given when providing a bitmap"}} -- Sync mode full tests -- -{"execute": "blockdev-backup", "arguments": {"bitmap-mode": "on-success", "device": "drive0", "filter-node-name": "backup-top", "job-id": "api_job", "sync": "full", "target": "backup_target"}} +{"execute": "blockdev-backup", "arguments": {"bitmap-mode": "on-success", "device": "drive0", "filter-node-name": "backup-top", "job-id": "api_job", "sync": "full", "target": "backup_target", "x-perf": {"max-workers": 1}}} {"error": {"class": "GenericError", "desc": "Cannot specify bitmap sync mode without a bitmap"}} -{"execute": "blockdev-backup", "arguments": {"bitmap-mode": "always", "device": "drive0", "filter-node-name": "backup-top", "job-id": "api_job", "sync": "full", "target": "backup_target"}} +{"execute": "blockdev-backup", "arguments": {"bitmap-mode": "always", "device": "drive0", "filter-node-name": "backup-top", "job-id": "api_job", "sync": "full", "target": "backup_target", "x-perf": {"max-workers": 1}}} {"error": {"class": "GenericError", "desc": "Cannot specify bitmap sync mode without a bitmap"}} -{"execute": "blockdev-backup", "arguments": {"bitmap-mode": "never", "device": "drive0", "filter-node-name": "backup-top", "job-id": "api_job", "sync": "full", "target": "backup_target"}} +{"execute": "blockdev-backup", "arguments": {"bitmap-mode": "never", "device": "drive0", "filter-node-name": "backup-top", "job-id": "api_job", "sync": "full", "target": "backup_target", "x-perf": {"max-workers": 1}}} {"error": {"class": "GenericError", "desc": "Cannot specify bitmap sync mode without a bitmap"}} -{"execute": "blockdev-backup", "arguments": {"bitmap": "bitmap404", "bitmap-mode": "on-success", "device": "drive0", "filter-node-name": "backup-top", "job-id": "api_job", "sync": "full", "target": "backup_target"}} +{"execute": "blockdev-backup", "arguments": {"bitmap": "bitmap404", "bitmap-mode": "on-success", "device": "drive0", "filter-node-name": "backup-top", "job-id": "api_job", "sync": "full", "target": "backup_target", "x-perf": {"max-workers": 1}}} {"error": {"class": "GenericError", "desc": "Bitmap 'bitmap404' could not be found"}} -{"execute": "blockdev-backup", "arguments": {"bitmap": "bitmap404", "bitmap-mode": "always", "device": "drive0", "filter-node-name": "backup-top", "job-id": "api_job", "sync": "full", "target": "backup_target"}} +{"execute": "blockdev-backup", "arguments": {"bitmap": "bitmap404", "bitmap-mode": "always", "device": "drive0", "filter-node-name": "backup-top", "job-id": "api_job", "sync": "full", "target": "backup_target", "x-perf": {"max-workers": 1}}} {"error": {"class": "GenericError", "desc": "Bitmap 'bitmap404' could not be found"}} -{"execute": "blockdev-backup", "arguments": {"bitmap": "bitmap404", "bitmap-mode": "never", "device": "drive0", "filter-node-name": "backup-top", "job-id": "api_job", "sync": "full", "target": "backup_target"}} +{"execute": "blockdev-backup", "arguments": {"bitmap": "bitmap404", "bitmap-mode": "never", "device": "drive0", "filter-node-name": "backup-top", "job-id": "api_job", "sync": "full", "target": "backup_target", "x-perf": {"max-workers": 1}}} {"error": {"class": "GenericError", "desc": "Bitmap 'bitmap404' could not be found"}} -{"execute": "blockdev-backup", "arguments": {"bitmap": "bitmap404", "device": "drive0", "filter-node-name": "backup-top", "job-id": "api_job", "sync": "full", "target": "backup_target"}} +{"execute": "blockdev-backup", "arguments": {"bitmap": "bitmap404", "device": "drive0", "filter-node-name": "backup-top", "job-id": "api_job", "sync": "full", "target": "backup_target", "x-perf": {"max-workers": 1}}} {"error": {"class": "GenericError", "desc": "Bitmap 'bitmap404' could not be found"}} -{"execute": "blockdev-backup", "arguments": {"bitmap": "bitmap0", "bitmap-mode": "never", "device": "drive0", "filter-node-name": "backup-top", "job-id": "api_job", "sync": "full", "target": "backup_target"}} +{"execute": "blockdev-backup", "arguments": {"bitmap": "bitmap0", "bitmap-mode": "never", "device": "drive0", "filter-node-name": "backup-top", "job-id": "api_job", "sync": "full", "target": "backup_target", "x-perf": {"max-workers": 1}}} {"error": {"class": "GenericError", "desc": "Bitmap sync mode 'never' has no meaningful effect when combined with sync mode 'full'"}} -{"execute": "blockdev-backup", "arguments": {"bitmap": "bitmap0", "device": "drive0", "filter-node-name": "backup-top", "job-id": "api_job", "sync": "full", "target": "backup_target"}} +{"execute": "blockdev-backup", "arguments": {"bitmap": "bitmap0", "device": "drive0", "filter-node-name": "backup-top", "job-id": "api_job", "sync": "full", "target": "backup_target", "x-perf": {"max-workers": 1}}} {"error": {"class": "GenericError", "desc": "Bitmap sync mode must be given when providing a bitmap"}} -- Sync mode top tests -- -{"execute": "blockdev-backup", "arguments": {"bitmap-mode": "on-success", "device": "drive0", "filter-node-name": "backup-top", "job-id": "api_job", "sync": "top", "target": "backup_target"}} +{"execute": "blockdev-backup", "arguments": {"bitmap-mode": "on-success", "device": "drive0", "filter-node-name": "backup-top", "job-id": "api_job", "sync": "top", "target": "backup_target", "x-perf": {"max-workers": 1}}} {"error": {"class": "GenericError", "desc": "Cannot specify bitmap sync mode without a bitmap"}} -{"execute": "blockdev-backup", "arguments": {"bitmap-mode": "always", "device": "drive0", "filter-node-name": "backup-top", "job-id": "api_job", "sync": "top", "target": "backup_target"}} +{"execute": "blockdev-backup", "arguments": {"bitmap-mode": "always", "device": "drive0", "filter-node-name": "backup-top", "job-id": "api_job", "sync": "top", "target": "backup_target", "x-perf": {"max-workers": 1}}} {"error": {"class": "GenericError", "desc": "Cannot specify bitmap sync mode without a bitmap"}} -{"execute": "blockdev-backup", "arguments": {"bitmap-mode": "never", "device": "drive0", "filter-node-name": "backup-top", "job-id": "api_job", "sync": "top", "target": "backup_target"}} +{"execute": "blockdev-backup", "arguments": {"bitmap-mode": "never", "device": "drive0", "filter-node-name": "backup-top", "job-id": "api_job", "sync": "top", "target": "backup_target", "x-perf": {"max-workers": 1}}} {"error": {"class": "GenericError", "desc": "Cannot specify bitmap sync mode without a bitmap"}} -{"execute": "blockdev-backup", "arguments": {"bitmap": "bitmap404", "bitmap-mode": "on-success", "device": "drive0", "filter-node-name": "backup-top", "job-id": "api_job", "sync": "top", "target": "backup_target"}} +{"execute": "blockdev-backup", "arguments": {"bitmap": "bitmap404", "bitmap-mode": "on-success", "device": "drive0", "filter-node-name": "backup-top", "job-id": "api_job", "sync": "top", "target": "backup_target", "x-perf": {"max-workers": 1}}} {"error": {"class": "GenericError", "desc": "Bitmap 'bitmap404' could not be found"}} -{"execute": "blockdev-backup", "arguments": {"bitmap": "bitmap404", "bitmap-mode": "always", "device": "drive0", "filter-node-name": "backup-top", "job-id": "api_job", "sync": "top", "target": "backup_target"}} +{"execute": "blockdev-backup", "arguments": {"bitmap": "bitmap404", "bitmap-mode": "always", "device": "drive0", "filter-node-name": "backup-top", "job-id": "api_job", "sync": "top", "target": "backup_target", "x-perf": {"max-workers": 1}}} {"error": {"class": "GenericError", "desc": "Bitmap 'bitmap404' could not be found"}} -{"execute": "blockdev-backup", "arguments": {"bitmap": "bitmap404", "bitmap-mode": "never", "device": "drive0", "filter-node-name": "backup-top", "job-id": "api_job", "sync": "top", "target": "backup_target"}} +{"execute": "blockdev-backup", "arguments": {"bitmap": "bitmap404", "bitmap-mode": "never", "device": "drive0", "filter-node-name": "backup-top", "job-id": "api_job", "sync": "top", "target": "backup_target", "x-perf": {"max-workers": 1}}} {"error": {"class": "GenericError", "desc": "Bitmap 'bitmap404' could not be found"}} -{"execute": "blockdev-backup", "arguments": {"bitmap": "bitmap404", "device": "drive0", "filter-node-name": "backup-top", "job-id": "api_job", "sync": "top", "target": "backup_target"}} +{"execute": "blockdev-backup", "arguments": {"bitmap": "bitmap404", "device": "drive0", "filter-node-name": "backup-top", "job-id": "api_job", "sync": "top", "target": "backup_target", "x-perf": {"max-workers": 1}}} {"error": {"class": "GenericError", "desc": "Bitmap 'bitmap404' could not be found"}} -{"execute": "blockdev-backup", "arguments": {"bitmap": "bitmap0", "bitmap-mode": "never", "device": "drive0", "filter-node-name": "backup-top", "job-id": "api_job", "sync": "top", "target": "backup_target"}} +{"execute": "blockdev-backup", "arguments": {"bitmap": "bitmap0", "bitmap-mode": "never", "device": "drive0", "filter-node-name": "backup-top", "job-id": "api_job", "sync": "top", "target": "backup_target", "x-perf": {"max-workers": 1}}} {"error": {"class": "GenericError", "desc": "Bitmap sync mode 'never' has no meaningful effect when combined with sync mode 'top'"}} -{"execute": "blockdev-backup", "arguments": {"bitmap": "bitmap0", "device": "drive0", "filter-node-name": "backup-top", "job-id": "api_job", "sync": "top", "target": "backup_target"}} +{"execute": "blockdev-backup", "arguments": {"bitmap": "bitmap0", "device": "drive0", "filter-node-name": "backup-top", "job-id": "api_job", "sync": "top", "target": "backup_target", "x-perf": {"max-workers": 1}}} {"error": {"class": "GenericError", "desc": "Bitmap sync mode must be given when providing a bitmap"}} -- Sync mode none tests -- -{"execute": "blockdev-backup", "arguments": {"bitmap-mode": "on-success", "device": "drive0", "filter-node-name": "backup-top", "job-id": "api_job", "sync": "none", "target": "backup_target"}} +{"execute": "blockdev-backup", "arguments": {"bitmap-mode": "on-success", "device": "drive0", "filter-node-name": "backup-top", "job-id": "api_job", "sync": "none", "target": "backup_target", "x-perf": {"max-workers": 1}}} {"error": {"class": "GenericError", "desc": "Cannot specify bitmap sync mode without a bitmap"}} -{"execute": "blockdev-backup", "arguments": {"bitmap-mode": "always", "device": "drive0", "filter-node-name": "backup-top", "job-id": "api_job", "sync": "none", "target": "backup_target"}} +{"execute": "blockdev-backup", "arguments": {"bitmap-mode": "always", "device": "drive0", "filter-node-name": "backup-top", "job-id": "api_job", "sync": "none", "target": "backup_target", "x-perf": {"max-workers": 1}}} {"error": {"class": "GenericError", "desc": "Cannot specify bitmap sync mode without a bitmap"}} -{"execute": "blockdev-backup", "arguments": {"bitmap-mode": "never", "device": "drive0", "filter-node-name": "backup-top", "job-id": "api_job", "sync": "none", "target": "backup_target"}} +{"execute": "blockdev-backup", "arguments": {"bitmap-mode": "never", "device": "drive0", "filter-node-name": "backup-top", "job-id": "api_job", "sync": "none", "target": "backup_target", "x-perf": {"max-workers": 1}}} {"error": {"class": "GenericError", "desc": "Cannot specify bitmap sync mode without a bitmap"}} -{"execute": "blockdev-backup", "arguments": {"bitmap": "bitmap404", "bitmap-mode": "on-success", "device": "drive0", "filter-node-name": "backup-top", "job-id": "api_job", "sync": "none", "target": "backup_target"}} +{"execute": "blockdev-backup", "arguments": {"bitmap": "bitmap404", "bitmap-mode": "on-success", "device": "drive0", "filter-node-name": "backup-top", "job-id": "api_job", "sync": "none", "target": "backup_target", "x-perf": {"max-workers": 1}}} {"error": {"class": "GenericError", "desc": "Bitmap 'bitmap404' could not be found"}} -{"execute": "blockdev-backup", "arguments": {"bitmap": "bitmap404", "bitmap-mode": "always", "device": "drive0", "filter-node-name": "backup-top", "job-id": "api_job", "sync": "none", "target": "backup_target"}} +{"execute": "blockdev-backup", "arguments": {"bitmap": "bitmap404", "bitmap-mode": "always", "device": "drive0", "filter-node-name": "backup-top", "job-id": "api_job", "sync": "none", "target": "backup_target", "x-perf": {"max-workers": 1}}} {"error": {"class": "GenericError", "desc": "Bitmap 'bitmap404' could not be found"}} -{"execute": "blockdev-backup", "arguments": {"bitmap": "bitmap404", "bitmap-mode": "never", "device": "drive0", "filter-node-name": "backup-top", "job-id": "api_job", "sync": "none", "target": "backup_target"}} +{"execute": "blockdev-backup", "arguments": {"bitmap": "bitmap404", "bitmap-mode": "never", "device": "drive0", "filter-node-name": "backup-top", "job-id": "api_job", "sync": "none", "target": "backup_target", "x-perf": {"max-workers": 1}}} {"error": {"class": "GenericError", "desc": "Bitmap 'bitmap404' could not be found"}} -{"execute": "blockdev-backup", "arguments": {"bitmap": "bitmap404", "device": "drive0", "filter-node-name": "backup-top", "job-id": "api_job", "sync": "none", "target": "backup_target"}} +{"execute": "blockdev-backup", "arguments": {"bitmap": "bitmap404", "device": "drive0", "filter-node-name": "backup-top", "job-id": "api_job", "sync": "none", "target": "backup_target", "x-perf": {"max-workers": 1}}} {"error": {"class": "GenericError", "desc": "Bitmap 'bitmap404' could not be found"}} -{"execute": "blockdev-backup", "arguments": {"bitmap": "bitmap0", "bitmap-mode": "on-success", "device": "drive0", "filter-node-name": "backup-top", "job-id": "api_job", "sync": "none", "target": "backup_target"}} +{"execute": "blockdev-backup", "arguments": {"bitmap": "bitmap0", "bitmap-mode": "on-success", "device": "drive0", "filter-node-name": "backup-top", "job-id": "api_job", "sync": "none", "target": "backup_target", "x-perf": {"max-workers": 1}}} {"error": {"class": "GenericError", "desc": "sync mode 'none' does not produce meaningful bitmap outputs"}} -{"execute": "blockdev-backup", "arguments": {"bitmap": "bitmap0", "bitmap-mode": "always", "device": "drive0", "filter-node-name": "backup-top", "job-id": "api_job", "sync": "none", "target": "backup_target"}} +{"execute": "blockdev-backup", "arguments": {"bitmap": "bitmap0", "bitmap-mode": "always", "device": "drive0", "filter-node-name": "backup-top", "job-id": "api_job", "sync": "none", "target": "backup_target", "x-perf": {"max-workers": 1}}} {"error": {"class": "GenericError", "desc": "sync mode 'none' does not produce meaningful bitmap outputs"}} -{"execute": "blockdev-backup", "arguments": {"bitmap": "bitmap0", "bitmap-mode": "never", "device": "drive0", "filter-node-name": "backup-top", "job-id": "api_job", "sync": "none", "target": "backup_target"}} +{"execute": "blockdev-backup", "arguments": {"bitmap": "bitmap0", "bitmap-mode": "never", "device": "drive0", "filter-node-name": "backup-top", "job-id": "api_job", "sync": "none", "target": "backup_target", "x-perf": {"max-workers": 1}}} {"error": {"class": "GenericError", "desc": "sync mode 'none' does not produce meaningful bitmap outputs"}} -{"execute": "blockdev-backup", "arguments": {"bitmap": "bitmap0", "device": "drive0", "filter-node-name": "backup-top", "job-id": "api_job", "sync": "none", "target": "backup_target"}} +{"execute": "blockdev-backup", "arguments": {"bitmap": "bitmap0", "device": "drive0", "filter-node-name": "backup-top", "job-id": "api_job", "sync": "none", "target": "backup_target", "x-perf": {"max-workers": 1}}} {"error": {"class": "GenericError", "desc": "Bitmap sync mode must be given when providing a bitmap"}} -- 2.29.2 From: Vladimir Sementsov-Ogievskiy <vsementsov@virtuozzo.com> We are going to stop use of this callback in the following commit. Still the callback handling code will be dropped in a separate commit. So, for now let's make it optional. Signed-off-by: Vladimir Sementsov-Ogievskiy <vsementsov@virtuozzo.com> Reviewed-by: Max Reitz <mreitz@redhat.com> Message-Id: <20210116214705.822267-16-vsementsov@virtuozzo.com> Signed-off-by: Max Reitz <mreitz@redhat.com> --- block/block-copy.c | 4 +++- 1 file changed, 3 insertions(+), 1 deletion(-) diff --git a/block/block-copy.c b/block/block-copy.c index XXXXXXX..XXXXXXX 100644 --- a/block/block-copy.c +++ b/block/block-copy.c @@ -XXX,XX +XXX,XX @@ static coroutine_fn int block_copy_task_entry(AioTask *task) t->call_state->error_is_read = error_is_read; } else { progress_work_done(t->s->progress, t->bytes); - t->s->progress_bytes_callback(t->bytes, t->s->progress_opaque); + if (t->s->progress_bytes_callback) { + t->s->progress_bytes_callback(t->bytes, t->s->progress_opaque); + } } co_put_to_shres(t->s->mem, t->bytes); block_copy_task_end(t, ret); -- 2.29.2 From: Vladimir Sementsov-Ogievskiy <vsementsov@virtuozzo.com> Signed-off-by: Vladimir Sementsov-Ogievskiy <vsementsov@virtuozzo.com> Reviewed-by: Max Reitz <mreitz@redhat.com> Message-Id: <20210116214705.822267-17-vsementsov@virtuozzo.com> Signed-off-by: Max Reitz <mreitz@redhat.com> --- block/backup.c | 12 +++++------- 1 file changed, 5 insertions(+), 7 deletions(-) diff --git a/block/backup.c b/block/backup.c index XXXXXXX..XXXXXXX 100644 --- a/block/backup.c +++ b/block/backup.c @@ -XXX,XX +XXX,XX @@ static void backup_init_bcs_bitmap(BackupBlockJob *job) static int coroutine_fn backup_run(Job *job, Error **errp) { BackupBlockJob *s = container_of(job, BackupBlockJob, common.job); - int ret = 0; + int ret; backup_init_bcs_bitmap(s); @@ -XXX,XX +XXX,XX @@ static int coroutine_fn backup_run(Job *job, Error **errp) for (offset = 0; offset < s->len; ) { if (yield_and_check(s)) { - ret = -ECANCELED; - goto out; + return -ECANCELED; } ret = block_copy_reset_unallocated(s->bcs, offset, &count); if (ret < 0) { - goto out; + return ret; } offset += count; @@ -XXX,XX +XXX,XX @@ static int coroutine_fn backup_run(Job *job, Error **errp) job_yield(job); } } else { - ret = backup_loop(s); + return backup_loop(s); } - out: - return ret; + return 0; } static const BlockJobDriver backup_job_driver = { -- 2.29.2 From: Vladimir Sementsov-Ogievskiy <vsementsov@virtuozzo.com> This brings async request handling and block-status driven chunk sizes to backup out of the box, which improves backup performance. Signed-off-by: Vladimir Sementsov-Ogievskiy <vsementsov@virtuozzo.com> Reviewed-by: Max Reitz <mreitz@redhat.com> Message-Id: <20210116214705.822267-18-vsementsov@virtuozzo.com> Signed-off-by: Max Reitz <mreitz@redhat.com> --- block/backup.c | 187 +++++++++++++++++++++++++++++++------------------ 1 file changed, 120 insertions(+), 67 deletions(-) diff --git a/block/backup.c b/block/backup.c index XXXXXXX..XXXXXXX 100644 --- a/block/backup.c +++ b/block/backup.c @@ -XXX,XX +XXX,XX @@ #include "block/block-copy.h" #include "qapi/error.h" #include "qapi/qmp/qerror.h" -#include "qemu/ratelimit.h" #include "qemu/cutils.h" #include "sysemu/block-backend.h" #include "qemu/bitmap.h" @@ -XXX,XX +XXX,XX @@ typedef struct BackupBlockJob { BlockdevOnError on_source_error; BlockdevOnError on_target_error; uint64_t len; - uint64_t bytes_read; int64_t cluster_size; BackupPerf perf; BlockCopyState *bcs; + + bool wait; + BlockCopyCallState *bg_bcs_call; } BackupBlockJob; static const BlockJobDriver backup_job_driver; -static void backup_progress_bytes_callback(int64_t bytes, void *opaque) -{ - BackupBlockJob *s = opaque; - - s->bytes_read += bytes; -} - -static int coroutine_fn backup_do_cow(BackupBlockJob *job, - int64_t offset, uint64_t bytes, - bool *error_is_read) -{ - int ret = 0; - int64_t start, end; /* bytes */ - - start = QEMU_ALIGN_DOWN(offset, job->cluster_size); - end = QEMU_ALIGN_UP(bytes + offset, job->cluster_size); - - trace_backup_do_cow_enter(job, start, offset, bytes); - - ret = block_copy(job->bcs, start, end - start, true, error_is_read); - - trace_backup_do_cow_return(job, offset, bytes, ret); - - return ret; -} - static void backup_cleanup_sync_bitmap(BackupBlockJob *job, int ret) { BdrvDirtyBitmap *bm; @@ -XXX,XX +XXX,XX @@ static BlockErrorAction backup_error_action(BackupBlockJob *job, } } -static bool coroutine_fn yield_and_check(BackupBlockJob *job) +static void coroutine_fn backup_block_copy_callback(void *opaque) { - uint64_t delay_ns; - - if (job_is_cancelled(&job->common.job)) { - return true; - } - - /* - * We need to yield even for delay_ns = 0 so that bdrv_drain_all() can - * return. Without a yield, the VM would not reboot. - */ - delay_ns = block_job_ratelimit_get_delay(&job->common, job->bytes_read); - job->bytes_read = 0; - job_sleep_ns(&job->common.job, delay_ns); + BackupBlockJob *s = opaque; - if (job_is_cancelled(&job->common.job)) { - return true; + if (s->wait) { + s->wait = false; + aio_co_wake(s->common.job.co); + } else { + job_enter(&s->common.job); } - - return false; } static int coroutine_fn backup_loop(BackupBlockJob *job) { - bool error_is_read; - int64_t offset; - BdrvDirtyBitmapIter *bdbi; + BlockCopyCallState *s = NULL; int ret = 0; + bool error_is_read; + BlockErrorAction act; + + while (true) { /* retry loop */ + job->bg_bcs_call = s = block_copy_async(job->bcs, 0, + QEMU_ALIGN_UP(job->len, job->cluster_size), + job->perf.max_workers, job->perf.max_chunk, + backup_block_copy_callback, job); + + while (!block_copy_call_finished(s) && + !job_is_cancelled(&job->common.job)) + { + job_yield(&job->common.job); + } - bdbi = bdrv_dirty_iter_new(block_copy_dirty_bitmap(job->bcs)); - while ((offset = bdrv_dirty_iter_next(bdbi)) != -1) { - do { - if (yield_and_check(job)) { - goto out; - } - ret = backup_do_cow(job, offset, job->cluster_size, &error_is_read); - if (ret < 0 && backup_error_action(job, error_is_read, -ret) == - BLOCK_ERROR_ACTION_REPORT) - { - goto out; - } - } while (ret < 0); + if (!block_copy_call_finished(s)) { + assert(job_is_cancelled(&job->common.job)); + /* + * Note that we can't use job_yield() here, as it doesn't work for + * cancelled job. + */ + block_copy_call_cancel(s); + job->wait = true; + qemu_coroutine_yield(); + assert(block_copy_call_finished(s)); + ret = 0; + goto out; + } + + if (job_is_cancelled(&job->common.job) || + block_copy_call_succeeded(s)) + { + ret = 0; + goto out; + } + + if (block_copy_call_cancelled(s)) { + /* + * Job is not cancelled but only block-copy call. This is possible + * after job pause. Now the pause is finished, start new block-copy + * iteration. + */ + block_copy_call_free(s); + continue; + } + + /* The only remaining case is failed block-copy call. */ + assert(block_copy_call_failed(s)); + + ret = block_copy_call_status(s, &error_is_read); + act = backup_error_action(job, error_is_read, -ret); + switch (act) { + case BLOCK_ERROR_ACTION_REPORT: + goto out; + case BLOCK_ERROR_ACTION_STOP: + /* + * Go to pause prior to starting new block-copy call on the next + * iteration. + */ + job_pause_point(&job->common.job); + break; + case BLOCK_ERROR_ACTION_IGNORE: + /* Proceed to new block-copy call to retry. */ + break; + default: + abort(); + } + + block_copy_call_free(s); } - out: - bdrv_dirty_iter_free(bdbi); +out: + block_copy_call_free(s); + job->bg_bcs_call = NULL; return ret; } @@ -XXX,XX +XXX,XX @@ static int coroutine_fn backup_run(Job *job, Error **errp) int64_t count; for (offset = 0; offset < s->len; ) { - if (yield_and_check(s)) { + if (job_is_cancelled(job)) { + return -ECANCELED; + } + + job_pause_point(job); + + if (job_is_cancelled(job)) { return -ECANCELED; } @@ -XXX,XX +XXX,XX @@ static int coroutine_fn backup_run(Job *job, Error **errp) return 0; } +static void coroutine_fn backup_pause(Job *job) +{ + BackupBlockJob *s = container_of(job, BackupBlockJob, common.job); + + if (s->bg_bcs_call && !block_copy_call_finished(s->bg_bcs_call)) { + block_copy_call_cancel(s->bg_bcs_call); + s->wait = true; + qemu_coroutine_yield(); + } +} + +static void coroutine_fn backup_set_speed(BlockJob *job, int64_t speed) +{ + BackupBlockJob *s = container_of(job, BackupBlockJob, common); + + /* + * block_job_set_speed() is called first from block_job_create(), when we + * don't yet have s->bcs. + */ + if (s->bcs) { + block_copy_set_speed(s->bcs, speed); + if (s->bg_bcs_call) { + block_copy_kick(s->bg_bcs_call); + } + } +} + static const BlockJobDriver backup_job_driver = { .job_driver = { .instance_size = sizeof(BackupBlockJob), @@ -XXX,XX +XXX,XX @@ static const BlockJobDriver backup_job_driver = { .commit = backup_commit, .abort = backup_abort, .clean = backup_clean, - } + .pause = backup_pause, + }, + .set_speed = backup_set_speed, }; static int64_t backup_calculate_cluster_size(BlockDriverState *target, @@ -XXX,XX +XXX,XX @@ BlockJob *backup_job_create(const char *job_id, BlockDriverState *bs, job->len = len; job->perf = *perf; - block_copy_set_progress_callback(bcs, backup_progress_bytes_callback, job); block_copy_set_progress_meter(bcs, &job->common.job.progress); + block_copy_set_speed(bcs, speed); /* Required permissions are already taken by backup-top target */ block_job_add_bdrv(&job->common, "target", target, 0, BLK_PERM_ALL, -- 2.29.2 From: Vladimir Sementsov-Ogievskiy <vsementsov@virtuozzo.com> Further commit will add a benchmark (scripts/simplebench/bench-backup.py), which will show that backup works better with async parallel requests (previous commit) and disabled copy_range. So, let's disable copy_range by default. Note: the option was added several commits ago with default to true, to follow old behavior (the feature was enabled unconditionally), and only now we are going to change the default behavior. Signed-off-by: Vladimir Sementsov-Ogievskiy <vsementsov@virtuozzo.com> Reviewed-by: Max Reitz <mreitz@redhat.com> Message-Id: <20210116214705.822267-19-vsementsov@virtuozzo.com> Signed-off-by: Max Reitz <mreitz@redhat.com> --- qapi/block-core.json | 2 +- blockdev.c | 2 +- 2 files changed, 2 insertions(+), 2 deletions(-) diff --git a/qapi/block-core.json b/qapi/block-core.json index XXXXXXX..XXXXXXX 100644 --- a/qapi/block-core.json +++ b/qapi/block-core.json @@ -XXX,XX +XXX,XX @@ # Optional parameters for backup. These parameters don't affect # functionality, but may significantly affect performance. # -# @use-copy-range: Use copy offloading. Default true. +# @use-copy-range: Use copy offloading. Default false. # # @max-workers: Maximum number of parallel requests for the sustained background # copying process. Doesn't influence copy-before-write operations. diff --git a/blockdev.c b/blockdev.c index XXXXXXX..XXXXXXX 100644 --- a/blockdev.c +++ b/blockdev.c @@ -XXX,XX +XXX,XX @@ static BlockJob *do_backup_common(BackupCommon *backup, { BlockJob *job = NULL; BdrvDirtyBitmap *bmap = NULL; - BackupPerf perf = { .use_copy_range = true, .max_workers = 64 }; + BackupPerf perf = { .max_workers = 64 }; int job_flags = JOB_DEFAULT; if (!backup->has_speed) { -- 2.29.2 From: Vladimir Sementsov-Ogievskiy <vsementsov@virtuozzo.com> Drop unused code. Signed-off-by: Vladimir Sementsov-Ogievskiy <vsementsov@virtuozzo.com> Reviewed-by: Max Reitz <mreitz@redhat.com> Message-Id: <20210116214705.822267-20-vsementsov@virtuozzo.com> Signed-off-by: Max Reitz <mreitz@redhat.com> --- include/block/block-copy.h | 6 ------ block/block-copy.c | 15 --------------- 2 files changed, 21 deletions(-) diff --git a/include/block/block-copy.h b/include/block/block-copy.h index XXXXXXX..XXXXXXX 100644 --- a/include/block/block-copy.h +++ b/include/block/block-copy.h @@ -XXX,XX +XXX,XX @@ #include "block/block.h" #include "qemu/co-shared-resource.h" -typedef void (*ProgressBytesCallbackFunc)(int64_t bytes, void *opaque); typedef void (*BlockCopyAsyncCallbackFunc)(void *opaque); typedef struct BlockCopyState BlockCopyState; typedef struct BlockCopyCallState BlockCopyCallState; @@ -XXX,XX +XXX,XX @@ BlockCopyState *block_copy_state_new(BdrvChild *source, BdrvChild *target, BdrvRequestFlags write_flags, Error **errp); -void block_copy_set_progress_callback( - BlockCopyState *s, - ProgressBytesCallbackFunc progress_bytes_callback, - void *progress_opaque); - void block_copy_set_progress_meter(BlockCopyState *s, ProgressMeter *pm); void block_copy_state_free(BlockCopyState *s); diff --git a/block/block-copy.c b/block/block-copy.c index XXXXXXX..XXXXXXX 100644 --- a/block/block-copy.c +++ b/block/block-copy.c @@ -XXX,XX +XXX,XX @@ typedef struct BlockCopyState { bool skip_unallocated; ProgressMeter *progress; - /* progress_bytes_callback: called when some copying progress is done. */ - ProgressBytesCallbackFunc progress_bytes_callback; - void *progress_opaque; SharedResource *mem; @@ -XXX,XX +XXX,XX @@ BlockCopyState *block_copy_state_new(BdrvChild *source, BdrvChild *target, return s; } -void block_copy_set_progress_callback( - BlockCopyState *s, - ProgressBytesCallbackFunc progress_bytes_callback, - void *progress_opaque) -{ - s->progress_bytes_callback = progress_bytes_callback; - s->progress_opaque = progress_opaque; -} - void block_copy_set_progress_meter(BlockCopyState *s, ProgressMeter *pm) { s->progress = pm; @@ -XXX,XX +XXX,XX @@ static coroutine_fn int block_copy_task_entry(AioTask *task) t->call_state->error_is_read = error_is_read; } else { progress_work_done(t->s->progress, t->bytes); - if (t->s->progress_bytes_callback) { - t->s->progress_bytes_callback(t->bytes, t->s->progress_opaque); - } } co_put_to_shres(t->s->mem, t->bytes); block_copy_task_end(t, ret); -- 2.29.2 From: Vladimir Sementsov-Ogievskiy <vsementsov@virtuozzo.com> Signed-off-by: Vladimir Sementsov-Ogievskiy <vsementsov@virtuozzo.com> Reviewed-by: Max Reitz <mreitz@redhat.com> Message-Id: <20210116214705.822267-21-vsementsov@virtuozzo.com> Signed-off-by: Max Reitz <mreitz@redhat.com> --- include/block/block-copy.h | 2 +- block/backup-top.c | 2 +- block/block-copy.c | 10 ++-------- 3 files changed, 4 insertions(+), 10 deletions(-) diff --git a/include/block/block-copy.h b/include/block/block-copy.h index XXXXXXX..XXXXXXX 100644 --- a/include/block/block-copy.h +++ b/include/block/block-copy.h @@ -XXX,XX +XXX,XX @@ int64_t block_copy_reset_unallocated(BlockCopyState *s, int64_t offset, int64_t *count); int coroutine_fn block_copy(BlockCopyState *s, int64_t offset, int64_t bytes, - bool ignore_ratelimit, bool *error_is_read); + bool ignore_ratelimit); /* * Run block-copy in a coroutine, create corresponding BlockCopyCallState diff --git a/block/backup-top.c b/block/backup-top.c index XXXXXXX..XXXXXXX 100644 --- a/block/backup-top.c +++ b/block/backup-top.c @@ -XXX,XX +XXX,XX @@ static coroutine_fn int backup_top_cbw(BlockDriverState *bs, uint64_t offset, off = QEMU_ALIGN_DOWN(offset, s->cluster_size); end = QEMU_ALIGN_UP(offset + bytes, s->cluster_size); - return block_copy(s->bcs, off, end - off, true, NULL); + return block_copy(s->bcs, off, end - off, true); } static int coroutine_fn backup_top_co_pdiscard(BlockDriverState *bs, diff --git a/block/block-copy.c b/block/block-copy.c index XXXXXXX..XXXXXXX 100644 --- a/block/block-copy.c +++ b/block/block-copy.c @@ -XXX,XX +XXX,XX @@ static int coroutine_fn block_copy_common(BlockCopyCallState *call_state) } int coroutine_fn block_copy(BlockCopyState *s, int64_t start, int64_t bytes, - bool ignore_ratelimit, bool *error_is_read) + bool ignore_ratelimit) { BlockCopyCallState call_state = { .s = s, @@ -XXX,XX +XXX,XX @@ int coroutine_fn block_copy(BlockCopyState *s, int64_t start, int64_t bytes, .max_workers = BLOCK_COPY_MAX_WORKERS, }; - int ret = block_copy_common(&call_state); - - if (error_is_read && ret < 0) { - *error_is_read = call_state.error_is_read; - } - - return ret; + return block_copy_common(&call_state); } static void coroutine_fn block_copy_async_co_entry(void *opaque) -- 2.29.2 From: Vladimir Sementsov-Ogievskiy <vsementsov@virtuozzo.com> Signed-off-by: Vladimir Sementsov-Ogievskiy <vsementsov@virtuozzo.com> Reviewed-by: Max Reitz <mreitz@redhat.com> Message-Id: <20210116214705.822267-22-vsementsov@virtuozzo.com> Signed-off-by: Max Reitz <mreitz@redhat.com> --- scripts/simplebench/bench_block_job.py | 2 +- 1 file changed, 1 insertion(+), 1 deletion(-) diff --git a/scripts/simplebench/bench_block_job.py b/scripts/simplebench/bench_block_job.py index XXXXXXX..XXXXXXX 100755 --- a/scripts/simplebench/bench_block_job.py +++ b/scripts/simplebench/bench_block_job.py @@ -XXX,XX +XXX,XX @@ -#!/usr/bin/env python +#!/usr/bin/env python3 # # Benchmark block jobs # -- 2.29.2 From: Vladimir Sementsov-Ogievskiy <vsementsov@virtuozzo.com> Add argument to allow additional block-job options. Signed-off-by: Vladimir Sementsov-Ogievskiy <vsementsov@virtuozzo.com> Reviewed-by: Max Reitz <mreitz@redhat.com> Message-Id: <20210116214705.822267-23-vsementsov@virtuozzo.com> Signed-off-by: Max Reitz <mreitz@redhat.com> --- scripts/simplebench/bench-example.py | 2 +- scripts/simplebench/bench_block_job.py | 11 +++++++---- 2 files changed, 8 insertions(+), 5 deletions(-) diff --git a/scripts/simplebench/bench-example.py b/scripts/simplebench/bench-example.py index XXXXXXX..XXXXXXX 100644 --- a/scripts/simplebench/bench-example.py +++ b/scripts/simplebench/bench-example.py @@ -XXX,XX +XXX,XX @@ from bench_block_job import bench_block_copy, drv_file, drv_nbd def bench_func(env, case): """ Handle one "cell" of benchmarking table. """ - return bench_block_copy(env['qemu_binary'], env['cmd'], + return bench_block_copy(env['qemu_binary'], env['cmd'], {} case['source'], case['target']) diff --git a/scripts/simplebench/bench_block_job.py b/scripts/simplebench/bench_block_job.py index XXXXXXX..XXXXXXX 100755 --- a/scripts/simplebench/bench_block_job.py +++ b/scripts/simplebench/bench_block_job.py @@ -XXX,XX +XXX,XX @@ def bench_block_job(cmd, cmd_args, qemu_args): # Bench backup or mirror -def bench_block_copy(qemu_binary, cmd, source, target): +def bench_block_copy(qemu_binary, cmd, cmd_options, source, target): """Helper to run bench_block_job() for mirror or backup""" assert cmd in ('blockdev-backup', 'blockdev-mirror') source['node-name'] = 'source' target['node-name'] = 'target' - return bench_block_job(cmd, - {'job-id': 'job0', 'device': 'source', - 'target': 'target', 'sync': 'full'}, + cmd_options['job-id'] = 'job0' + cmd_options['device'] = 'source' + cmd_options['target'] = 'target' + cmd_options['sync'] = 'full' + + return bench_block_job(cmd, cmd_options, [qemu_binary, '-blockdev', json.dumps(source), '-blockdev', json.dumps(target)]) -- 2.29.2 From: Vladimir Sementsov-Ogievskiy <vsementsov@virtuozzo.com> Add script to benchmark new backup architecture. Signed-off-by: Vladimir Sementsov-Ogievskiy <vsementsov@virtuozzo.com> Message-Id: <20210116214705.822267-24-vsementsov@virtuozzo.com> [mreitz: s/not unsupported/not supported/] Signed-off-by: Max Reitz <mreitz@redhat.com> --- scripts/simplebench/bench-backup.py | 167 ++++++++++++++++++++++++++++ 1 file changed, 167 insertions(+) create mode 100755 scripts/simplebench/bench-backup.py diff --git a/scripts/simplebench/bench-backup.py b/scripts/simplebench/bench-backup.py new file mode 100755 index XXXXXXX..XXXXXXX --- /dev/null +++ b/scripts/simplebench/bench-backup.py @@ -XXX,XX +XXX,XX @@ +#!/usr/bin/env python3 +# +# Bench backup block-job +# +# Copyright (c) 2020 Virtuozzo International GmbH. +# +# This program is free software; you can redistribute it and/or modify +# it under the terms of the GNU General Public License as published by +# the Free Software Foundation; either version 2 of the License, or +# (at your option) any later version. +# +# This program is distributed in the hope that it will be useful, +# but WITHOUT ANY WARRANTY; without even the implied warranty of +# MERCHANTABILITY or FITNESS FOR A PARTICULAR PURPOSE. See the +# GNU General Public License for more details. +# +# You should have received a copy of the GNU General Public License +# along with this program. If not, see <http://www.gnu.org/licenses/>. +# + +import argparse +import json + +import simplebench +from results_to_text import results_to_text +from bench_block_job import bench_block_copy, drv_file, drv_nbd + + +def bench_func(env, case): + """ Handle one "cell" of benchmarking table. """ + cmd_options = env['cmd-options'] if 'cmd-options' in env else {} + return bench_block_copy(env['qemu-binary'], env['cmd'], + cmd_options, + case['source'], case['target']) + + +def bench(args): + test_cases = [] + + sources = {} + targets = {} + for d in args.dir: + label, path = d.split(':') # paths with colon not supported + sources[label] = drv_file(path + '/test-source') + targets[label] = drv_file(path + '/test-target') + + if args.nbd: + nbd = args.nbd.split(':') + host = nbd[0] + port = '10809' if len(nbd) == 1 else nbd[1] + drv = drv_nbd(host, port) + sources['nbd'] = drv + targets['nbd'] = drv + + for t in args.test: + src, dst = t.split(':') + + test_cases.append({ + 'id': t, + 'source': sources[src], + 'target': targets[dst] + }) + + binaries = [] # list of (<label>, <path>, [<options>]) + for i, q in enumerate(args.env): + name_path = q.split(':') + if len(name_path) == 1: + label = f'q{i}' + path_opts = name_path[0].split(',') + else: + assert len(name_path) == 2 # paths with colon not supported + label = name_path[0] + path_opts = name_path[1].split(',') + + binaries.append((label, path_opts[0], path_opts[1:])) + + test_envs = [] + + bin_paths = {} + for i, q in enumerate(args.env): + opts = q.split(',') + label_path = opts[0] + opts = opts[1:] + + if ':' in label_path: + # path with colon inside is not supported + label, path = label_path.split(':') + bin_paths[label] = path + elif label_path in bin_paths: + label = label_path + path = bin_paths[label] + else: + path = label_path + label = f'q{i}' + bin_paths[label] = path + + x_perf = {} + is_mirror = False + for opt in opts: + if opt == 'mirror': + is_mirror = True + elif opt == 'copy-range=on': + x_perf['use-copy-range'] = True + elif opt == 'copy-range=off': + x_perf['use-copy-range'] = False + elif opt.startswith('max-workers='): + x_perf['max-workers'] = int(opt.split('=')[1]) + + if is_mirror: + assert not x_perf + test_envs.append({ + 'id': f'mirror({label})', + 'cmd': 'blockdev-mirror', + 'qemu-binary': path + }) + else: + test_envs.append({ + 'id': f'backup({label})\n' + '\n'.join(opts), + 'cmd': 'blockdev-backup', + 'cmd-options': {'x-perf': x_perf} if x_perf else {}, + 'qemu-binary': path + }) + + result = simplebench.bench(bench_func, test_envs, test_cases, count=3) + with open('results.json', 'w') as f: + json.dump(result, f, indent=4) + print(results_to_text(result)) + + +class ExtendAction(argparse.Action): + def __call__(self, parser, namespace, values, option_string=None): + items = getattr(namespace, self.dest) or [] + items.extend(values) + setattr(namespace, self.dest, items) + + +if __name__ == '__main__': + p = argparse.ArgumentParser('Backup benchmark', epilog=''' +ENV format + + (LABEL:PATH|LABEL|PATH)[,max-workers=N][,use-copy-range=(on|off)][,mirror] + + LABEL short name for the binary + PATH path to the binary + max-workers set x-perf.max-workers of backup job + use-copy-range set x-perf.use-copy-range of backup job + mirror use mirror job instead of backup''', + formatter_class=argparse.RawTextHelpFormatter) + p.add_argument('--env', nargs='+', help='''\ +Qemu binaries with labels and options, see below +"ENV format" section''', + action=ExtendAction) + p.add_argument('--dir', nargs='+', help='''\ +Directories, each containing "test-source" and/or +"test-target" files, raw images to used in +benchmarking. File path with label, like +label:/path/to/directory''', + action=ExtendAction) + p.add_argument('--nbd', help='''\ +host:port for remote NBD image, (or just host, for +default port 10809). Use it in tests, label is "nbd" +(but you cannot create test nbd:nbd).''') + p.add_argument('--test', nargs='+', help='''\ +Tests, in form source-dir-label:target-dir-label''', + action=ExtendAction) + + bench(p.parse_args()) -- 2.29.2 From: David Edmondson <david.edmondson@oracle.com> When a call to fcntl(2) for the purpose of adding file locks fails with an error other than EAGAIN or EACCES, report the error returned by fcntl. EAGAIN or EACCES are elided as they are considered to be common failures, indicating that a conflicting lock is held by another process. No errors are elided when removing file locks. Signed-off-by: David Edmondson <david.edmondson@oracle.com> Message-Id: <20210113164447.2545785-1-david.edmondson@oracle.com> Reviewed-by: Vladimir Sementsov-Ogievskiy <vsementsov@virtuozzo.com> Signed-off-by: Max Reitz <mreitz@redhat.com> --- block/file-posix.c | 38 ++++++++++++++++++++++++++++---------- 1 file changed, 28 insertions(+), 10 deletions(-) diff --git a/block/file-posix.c b/block/file-posix.c index XXXXXXX..XXXXXXX 100644 --- a/block/file-posix.c +++ b/block/file-posix.c @@ -XXX,XX +XXX,XX @@ typedef struct RawPosixAIOData { static int cdrom_reopen(BlockDriverState *bs); #endif +/* + * Elide EAGAIN and EACCES details when failing to lock, as this + * indicates that the specified file region is already locked by + * another process, which is considered a common scenario. + */ +#define raw_lock_error_setg_errno(errp, err, fmt, ...) \ + do { \ + if ((err) == EAGAIN || (err) == EACCES) { \ + error_setg((errp), (fmt), ## __VA_ARGS__); \ + } else { \ + error_setg_errno((errp), (err), (fmt), ## __VA_ARGS__); \ + } \ + } while (0) + #if defined(__NetBSD__) static int raw_normalize_devicepath(const char **filename, Error **errp) { @@ -XXX,XX +XXX,XX @@ static int raw_apply_lock_bytes(BDRVRawState *s, int fd, if ((perm_lock_bits & bit) && !(locked_perm & bit)) { ret = qemu_lock_fd(fd, off, 1, false); if (ret) { - error_setg(errp, "Failed to lock byte %d", off); + raw_lock_error_setg_errno(errp, -ret, "Failed to lock byte %d", + off); return ret; } else if (s) { s->locked_perm |= bit; @@ -XXX,XX +XXX,XX @@ static int raw_apply_lock_bytes(BDRVRawState *s, int fd, } else if (unlock && (locked_perm & bit) && !(perm_lock_bits & bit)) { ret = qemu_unlock_fd(fd, off, 1); if (ret) { - error_setg(errp, "Failed to unlock byte %d", off); + error_setg_errno(errp, -ret, "Failed to unlock byte %d", off); return ret; } else if (s) { s->locked_perm &= ~bit; @@ -XXX,XX +XXX,XX @@ static int raw_apply_lock_bytes(BDRVRawState *s, int fd, if ((shared_perm_lock_bits & bit) && !(locked_shared_perm & bit)) { ret = qemu_lock_fd(fd, off, 1, false); if (ret) { - error_setg(errp, "Failed to lock byte %d", off); + raw_lock_error_setg_errno(errp, -ret, "Failed to lock byte %d", + off); return ret; } else if (s) { s->locked_shared_perm |= bit; @@ -XXX,XX +XXX,XX @@ static int raw_apply_lock_bytes(BDRVRawState *s, int fd, !(shared_perm_lock_bits & bit)) { ret = qemu_unlock_fd(fd, off, 1); if (ret) { - error_setg(errp, "Failed to unlock byte %d", off); + error_setg_errno(errp, -ret, "Failed to unlock byte %d", off); return ret; } else if (s) { s->locked_shared_perm &= ~bit; @@ -XXX,XX +XXX,XX @@ static int raw_check_lock_bytes(int fd, uint64_t perm, uint64_t shared_perm, ret = qemu_lock_fd_test(fd, off, 1, true); if (ret) { char *perm_name = bdrv_perm_names(p); - error_setg(errp, - "Failed to get \"%s\" lock", - perm_name); + + raw_lock_error_setg_errno(errp, -ret, + "Failed to get \"%s\" lock", + perm_name); g_free(perm_name); return ret; } @@ -XXX,XX +XXX,XX @@ static int raw_check_lock_bytes(int fd, uint64_t perm, uint64_t shared_perm, ret = qemu_lock_fd_test(fd, off, 1, true); if (ret) { char *perm_name = bdrv_perm_names(p); - error_setg(errp, - "Failed to get shared \"%s\" lock", - perm_name); + + raw_lock_error_setg_errno(errp, -ret, + "Failed to get shared \"%s\" lock", + perm_name); g_free(perm_name); return ret; } -- 2.29.2 From: Alberto Garcia <berto@igalia.com> Signed-off-by: Alberto Garcia <berto@igalia.com> Suggested-by: Maxim Levitsky <mlevitsk@redhat.com> Reviewed-by: Maxim Levitsky <mlevitsk@redhat.com> Message-Id: <20210112170540.2912-1-berto@igalia.com> [mreitz: Add "# group:" line] Signed-off-by: Max Reitz <mreitz@redhat.com> --- tests/qemu-iotests/313 | 104 +++++++++++++++++++++++++++++++++++++ tests/qemu-iotests/313.out | 29 +++++++++++ tests/qemu-iotests/group | 1 + 3 files changed, 134 insertions(+) create mode 100755 tests/qemu-iotests/313 create mode 100644 tests/qemu-iotests/313.out diff --git a/tests/qemu-iotests/313 b/tests/qemu-iotests/313 new file mode 100755 index XXXXXXX..XXXXXXX --- /dev/null +++ b/tests/qemu-iotests/313 @@ -XXX,XX +XXX,XX @@ +#!/usr/bin/env bash +# group: rw auto quick +# +# Test for the regression fixed in commit c8bf9a9169 +# +# Copyright (C) 2020 Igalia, S.L. +# Author: Alberto Garcia <berto@igalia.com> +# Based on a test case by Maxim Levitsky <mlevitsk@redhat.com> +# +# This program is free software; you can redistribute it and/or modify +# it under the terms of the GNU General Public License as published by +# the Free Software Foundation; either version 2 of the License, or +# (at your option) any later version. +# +# This program is distributed in the hope that it will be useful, +# but WITHOUT ANY WARRANTY; without even the implied warranty of +# MERCHANTABILITY or FITNESS FOR A PARTICULAR PURPOSE. See the +# GNU General Public License for more details. +# +# You should have received a copy of the GNU General Public License +# along with this program. If not, see <http://www.gnu.org/licenses/>. +# + +# creator +owner=berto@igalia.com + +seq=`basename $0` +echo "QA output created by $seq" + +status=1 # failure is the default! + +_cleanup() +{ + _cleanup_test_img +} +trap "_cleanup; exit \$status" 0 1 2 3 15 + +# get standard environment, filters and checks +. ./common.rc +. ./common.filter + +_supported_fmt qcow2 +_supported_proto file +_supported_os Linux +_unsupported_imgopts cluster_size refcount_bits extended_l2 compat=0.10 data_file + +# The cluster size must be at least the granularity of the mirror job (4KB) +# Note that larger cluster sizes will produce very large images (several GBs) +cluster_size=4096 +refcount_bits=64 # Make it equal to the L2 entry size for convenience +options="cluster_size=${cluster_size},refcount_bits=${refcount_bits}" + +# Number of refcount entries per refcount blocks +ref_entries=$(( ${cluster_size} * 8 / ${refcount_bits} )) + +# Number of data clusters needed to fill a refcount block +# Equals ${ref_entries} minus two (one L2 table and one refcount block) +data_clusters_per_refblock=$(( ${ref_entries} - 2 )) + +# Number of entries in the refcount cache +ref_blocks=4 + +# Write enough data clusters to fill the refcount cache and allocate +# one more refcount block. +# Subtract 3 clusters from the total: qcow2 header, refcount table, L1 table +total_data_clusters=$(( ${data_clusters_per_refblock} * ${ref_blocks} + 1 - 3 )) + +# Total size to write in bytes +total_size=$(( ${total_data_clusters} * ${cluster_size} )) + +echo +echo '### Create the image' +echo +TEST_IMG_FILE=$TEST_IMG.base _make_test_img -o $options $total_size | _filter_img_create_size + +echo +echo '### Write data to allocate more refcount blocks than the cache can hold' +echo +$QEMU_IO -c "write -P 1 0 $total_size" $TEST_IMG.base | _filter_qemu_io + +echo +echo '### Create an overlay' +echo +_make_test_img -F $IMGFMT -b $TEST_IMG.base -o $options | _filter_img_create_size + +echo +echo '### Fill the overlay with zeroes' +echo +$QEMU_IO -c "write -z 0 $total_size" $TEST_IMG | _filter_qemu_io + +echo +echo '### Commit changes to the base image' +echo +$QEMU_IMG commit $TEST_IMG + +echo +echo '### Check the base image' +echo +$QEMU_IMG check $TEST_IMG.base + +# success, all done +echo "*** done" +rm -f $seq.full +status=0 diff --git a/tests/qemu-iotests/313.out b/tests/qemu-iotests/313.out new file mode 100644 index XXXXXXX..XXXXXXX --- /dev/null +++ b/tests/qemu-iotests/313.out @@ -XXX,XX +XXX,XX @@ +QA output created by 313 + +### Create the image + +Formatting 'TEST_DIR/t.IMGFMT.base', fmt=IMGFMT size=SIZE + +### Write data to allocate more refcount blocks than the cache can hold + +wrote 8347648/8347648 bytes at offset 0 +7.961 MiB, X ops; XX:XX:XX.X (XXX YYY/sec and XXX ops/sec) + +### Create an overlay + +Formatting 'TEST_DIR/t.IMGFMT', fmt=IMGFMT size=SIZE backing_file=TEST_DIR/t.IMGFMT.base backing_fmt=IMGFMT + +### Fill the overlay with zeroes + +wrote 8347648/8347648 bytes at offset 0 +7.961 MiB, X ops; XX:XX:XX.X (XXX YYY/sec and XXX ops/sec) + +### Commit changes to the base image + +Image committed. + +### Check the base image + +No errors were found on the image. +Image end offset: 8396800 +*** done diff --git a/tests/qemu-iotests/group b/tests/qemu-iotests/group index XXXXXXX..XXXXXXX 100644 --- a/tests/qemu-iotests/group +++ b/tests/qemu-iotests/group @@ -XXX,XX +XXX,XX @@ 309 rw auto quick 310 rw quick 312 rw quick +313 rw auto quick -- 2.29.2 Commit 0afec75734331 removed the 'change' QMP command, so we can no longer test it in 118. Fixes: 0afec75734331a0b52fa3aa4235220eda8c7846f ('qmp: remove deprecated "change" command') Signed-off-by: Max Reitz <mreitz@redhat.com> Message-Id: <20210126104833.57026-1-mreitz@redhat.com> Reviewed-by: Philippe Mathieu-Daudé <philmd@redhat.com> --- tests/qemu-iotests/118 | 20 +------------------- tests/qemu-iotests/118.out | 4 ++-- 2 files changed, 3 insertions(+), 21 deletions(-) diff --git a/tests/qemu-iotests/118 b/tests/qemu-iotests/118 index XXXXXXX..XXXXXXX 100755 --- a/tests/qemu-iotests/118 +++ b/tests/qemu-iotests/118 @@ -XXX,XX +XXX,XX @@ #!/usr/bin/env python3 # group: rw # -# Test case for the QMP 'change' command and all other associated -# commands +# Test case for media change monitor commands # # Copyright (C) 2015 Red Hat, Inc. # @@ -XXX,XX +XXX,XX @@ class ChangeBaseClass(iotests.QMPTestCase): class GeneralChangeTestsBaseClass(ChangeBaseClass): - def test_change(self): - # 'change' requires a drive name, so skip the test for blockdev - if not self.use_drive: - return - - result = self.vm.qmp('change', device='drive0', target=new_img, - arg=iotests.imgfmt) - self.assert_qmp(result, 'return', {}) - - self.wait_for_open() - self.wait_for_close() - - result = self.vm.qmp('query-block') - if self.has_real_tray: - self.assert_qmp(result, 'return[0]/tray_open', False) - self.assert_qmp(result, 'return[0]/inserted/image/filename', new_img) - def test_blockdev_change_medium(self): result = self.vm.qmp('blockdev-change-medium', id=self.device_name, filename=new_img, diff --git a/tests/qemu-iotests/118.out b/tests/qemu-iotests/118.out index XXXXXXX..XXXXXXX 100644 --- a/tests/qemu-iotests/118.out +++ b/tests/qemu-iotests/118.out @@ -XXX,XX +XXX,XX @@ -....................................................................................................................................................................... +........................................................................................................................................................... ---------------------------------------------------------------------- -Ran 167 tests +Ran 155 tests OK -- 2.29.2 ccd3b3b8112 has deprecated short-hand boolean options (i.e., options with values). All options without values are interpreted as boolean options, so this includes the invalid option "snapshot.foo" used in iotest 178. So after ccd3b3b8112, 178 fails with: +qemu-img: warning: short-form boolean option 'snapshot.foo' deprecated +Please use snapshot.foo=on instead Suppress that deprecation warning by passing some value to it (it does not matter which, because the option is invalid anyway). Fixes: ccd3b3b8112b670fdccf8a392b8419b173ffccb4 ("qemu-option: warn for short-form boolean options") Signed-off-by: Max Reitz <mreitz@redhat.com> Message-Id: <20210126123834.115915-1-mreitz@redhat.com> --- tests/qemu-iotests/178 | 2 +- tests/qemu-iotests/178.out.qcow2 | 2 +- tests/qemu-iotests/178.out.raw | 2 +- 3 files changed, 3 insertions(+), 3 deletions(-) diff --git a/tests/qemu-iotests/178 b/tests/qemu-iotests/178 index XXXXXXX..XXXXXXX 100755 --- a/tests/qemu-iotests/178 +++ b/tests/qemu-iotests/178 @@ -XXX,XX +XXX,XX @@ $QEMU_IMG measure --image-opts # missing filename $QEMU_IMG measure -f qcow2 # missing filename $QEMU_IMG measure -l snap1 # missing filename $QEMU_IMG measure -o , # invalid option list -$QEMU_IMG measure -l snapshot.foo # invalid snapshot option +$QEMU_IMG measure -l snapshot.foo=bar # invalid snapshot option $QEMU_IMG measure --output foo # invalid output format $QEMU_IMG measure --size -1 # invalid image size $QEMU_IMG measure -O foo "$TEST_IMG" # unknown image file format diff --git a/tests/qemu-iotests/178.out.qcow2 b/tests/qemu-iotests/178.out.qcow2 index XXXXXXX..XXXXXXX 100644 --- a/tests/qemu-iotests/178.out.qcow2 +++ b/tests/qemu-iotests/178.out.qcow2 @@ -XXX,XX +XXX,XX @@ qemu-img: --image-opts, -f, and -l require a filename argument. qemu-img: --image-opts, -f, and -l require a filename argument. qemu-img: Invalid option list: , qemu-img: Invalid parameter 'snapshot.foo' -qemu-img: Failed in parsing snapshot param 'snapshot.foo' +qemu-img: Failed in parsing snapshot param 'snapshot.foo=bar' qemu-img: --output must be used with human or json as argument. qemu-img: Invalid image size specified. Must be between 0 and 9223372036854775807. qemu-img: Unknown file format 'foo' diff --git a/tests/qemu-iotests/178.out.raw b/tests/qemu-iotests/178.out.raw index XXXXXXX..XXXXXXX 100644 --- a/tests/qemu-iotests/178.out.raw +++ b/tests/qemu-iotests/178.out.raw @@ -XXX,XX +XXX,XX @@ qemu-img: --image-opts, -f, and -l require a filename argument. qemu-img: --image-opts, -f, and -l require a filename argument. qemu-img: Invalid option list: , qemu-img: Invalid parameter 'snapshot.foo' -qemu-img: Failed in parsing snapshot param 'snapshot.foo' +qemu-img: Failed in parsing snapshot param 'snapshot.foo=bar' qemu-img: --output must be used with human or json as argument. qemu-img: Invalid image size specified. Must be between 0 and 9223372036854775807. qemu-img: Unknown file format 'foo' -- 2.29.2 The following changes since commit 56f9e46b841c7be478ca038d8d4085d776ab4b0d: Merge remote-tracking branch 'remotes/armbru/tags/pull-qapi-2017-02-20' into staging (2017-02-20 17:42:47 +0000) are available in the git repository at: git://github.com/stefanha/qemu.git tags/block-pull-request for you to fetch changes up to a7b91d35bab97a2d3e779d0c64c9b837b52a6cf7: coroutine-lock: make CoRwlock thread-safe and fair (2017-02-21 11:39:40 +0000) ---------------------------------------------------------------- Pull request v2: * Rebased to resolve scsi conflicts ---------------------------------------------------------------- Paolo Bonzini (24): block: move AioContext, QEMUTimer, main-loop to libqemuutil aio: introduce aio_co_schedule and aio_co_wake block-backend: allow blk_prw from coroutine context test-thread-pool: use generic AioContext infrastructure io: add methods to set I/O handlers on AioContext io: make qio_channel_yield aware of AioContexts nbd: convert to use qio_channel_yield coroutine-lock: reschedule coroutine on the AioContext it was running on blkdebug: reschedule coroutine on the AioContext it is running on qed: introduce qed_aio_start_io and qed_aio_next_io_cb aio: push aio_context_acquire/release down to dispatching block: explicitly acquire aiocontext in timers that need it block: explicitly acquire aiocontext in callbacks that need it block: explicitly acquire aiocontext in bottom halves that need it block: explicitly acquire aiocontext in aio callbacks that need it aio-posix: partially inline aio_dispatch into aio_poll async: remove unnecessary inc/dec pairs block: document fields protected by AioContext lock coroutine-lock: make CoMutex thread-safe coroutine-lock: add limited spinning to CoMutex test-aio-multithread: add performance comparison with thread-based mutexes coroutine-lock: place CoMutex before CoQueue in header coroutine-lock: add mutex argument to CoQueue APIs coroutine-lock: make CoRwlock thread-safe and fair Makefile.objs | 4 - stubs/Makefile.objs | 1 + tests/Makefile.include | 19 +- util/Makefile.objs | 6 +- block/nbd-client.h | 2 +- block/qed.h | 3 + include/block/aio.h | 38 ++- include/block/block_int.h | 64 +++-- include/io/channel.h | 72 +++++- include/qemu/coroutine.h | 84 ++++--- include/qemu/coroutine_int.h | 11 +- include/sysemu/block-backend.h | 14 +- tests/iothread.h | 25 ++ block/backup.c | 2 +- block/blkdebug.c | 9 +- block/blkreplay.c | 2 +- block/block-backend.c | 13 +- block/curl.c | 44 +++- block/gluster.c | 9 +- block/io.c | 42 +--- block/iscsi.c | 15 +- block/linux-aio.c | 10 +- block/mirror.c | 12 +- block/nbd-client.c | 119 +++++---- block/nfs.c | 9 +- block/qcow2-cluster.c | 4 +- block/qed-cluster.c | 2 + block/qed-table.c | 12 +- block/qed.c | 58 +++-- block/sheepdog.c | 31 +-- block/ssh.c | 29 +-- block/throttle-groups.c | 4 +- block/win32-aio.c | 9 +- dma-helpers.c | 2 + hw/9pfs/9p.c | 2 +- hw/block/virtio-blk.c | 19 +- hw/scsi/scsi-bus.c | 2 + hw/scsi/scsi-disk.c | 15 ++ hw/scsi/scsi-generic.c | 20 +- hw/scsi/virtio-scsi.c | 7 + io/channel-command.c | 13 + io/channel-file.c | 11 + io/channel-socket.c | 16 +- io/channel-tls.c | 12 + io/channel-watch.c | 6 + io/channel.c | 97 ++++++-- nbd/client.c | 2 +- nbd/common.c | 9 +- nbd/server.c | 94 +++----- stubs/linux-aio.c | 32 +++ stubs/set-fd-handler.c | 11 - tests/iothread.c | 91 +++++++ tests/test-aio-multithread.c | 463 ++++++++++++++++++++++++++++++++++++ tests/test-thread-pool.c | 12 +- aio-posix.c => util/aio-posix.c | 62 ++--- aio-win32.c => util/aio-win32.c | 30 +-- util/aiocb.c | 55 +++++ async.c => util/async.c | 84 ++++++- iohandler.c => util/iohandler.c | 0 main-loop.c => util/main-loop.c | 0 util/qemu-coroutine-lock.c | 254 ++++++++++++++++++-- util/qemu-coroutine-sleep.c | 2 +- util/qemu-coroutine.c | 8 + qemu-timer.c => util/qemu-timer.c | 0 thread-pool.c => util/thread-pool.c | 8 +- trace-events | 11 - util/trace-events | 17 +- 67 files changed, 1712 insertions(+), 533 deletions(-) create mode 100644 tests/iothread.h create mode 100644 stubs/linux-aio.c create mode 100644 tests/iothread.c create mode 100644 tests/test-aio-multithread.c rename aio-posix.c => util/aio-posix.c (94%) rename aio-win32.c => util/aio-win32.c (95%) create mode 100644 util/aiocb.c rename async.c => util/async.c (82%) rename iohandler.c => util/iohandler.c (100%) rename main-loop.c => util/main-loop.c (100%) rename qemu-timer.c => util/qemu-timer.c (100%) rename thread-pool.c => util/thread-pool.c (97%) -- 2.9.3 From: Paolo Bonzini <pbonzini@redhat.com> AioContext is fairly self contained, the only dependency is QEMUTimer but that in turn doesn't need anything else. So move them out of block-obj-y to avoid introducing a dependency from io/ to block-obj-y. main-loop and its dependency iohandler also need to be moved, because later in this series io/ will call iohandler_get_aio_context. [Changed copyright "the QEMU team" to "other QEMU contributors" as suggested by Daniel Berrange and agreed by Paolo. --Stefan] Signed-off-by: Paolo Bonzini <pbonzini@redhat.com> Reviewed-by: Fam Zheng <famz@redhat.com> Message-id: 20170213135235.12274-2-pbonzini@redhat.com Signed-off-by: Stefan Hajnoczi <stefanha@redhat.com> --- Makefile.objs | 4 --- stubs/Makefile.objs | 1 + tests/Makefile.include | 11 ++++---- util/Makefile.objs | 6 +++- block/io.c | 29 ------------------- stubs/linux-aio.c | 32 +++++++++++++++++++++ stubs/set-fd-handler.c | 11 -------- aio-posix.c => util/aio-posix.c | 2 +- aio-win32.c => util/aio-win32.c | 0 util/aiocb.c | 55 +++++++++++++++++++++++++++++++++++++ async.c => util/async.c | 3 +- iohandler.c => util/iohandler.c | 0 main-loop.c => util/main-loop.c | 0 qemu-timer.c => util/qemu-timer.c | 0 thread-pool.c => util/thread-pool.c | 2 +- trace-events | 11 -------- util/trace-events | 11 ++++++++ 17 files changed, 114 insertions(+), 64 deletions(-) create mode 100644 stubs/linux-aio.c rename aio-posix.c => util/aio-posix.c (99%) rename aio-win32.c => util/aio-win32.c (100%) create mode 100644 util/aiocb.c rename async.c => util/async.c (99%) rename iohandler.c => util/iohandler.c (100%) rename main-loop.c => util/main-loop.c (100%) rename qemu-timer.c => util/qemu-timer.c (100%) rename thread-pool.c => util/thread-pool.c (99%) diff --git a/Makefile.objs b/Makefile.objs index XXXXXXX..XXXXXXX 100644 --- a/Makefile.objs +++ b/Makefile.objs @@ -XXX,XX +XXX,XX @@ chardev-obj-y = chardev/ ####################################################################### # block-obj-y is code used by both qemu system emulation and qemu-img -block-obj-y = async.o thread-pool.o block-obj-y += nbd/ block-obj-y += block.o blockjob.o -block-obj-y += main-loop.o iohandler.o qemu-timer.o -block-obj-$(CONFIG_POSIX) += aio-posix.o -block-obj-$(CONFIG_WIN32) += aio-win32.o block-obj-y += block/ block-obj-y += qemu-io-cmds.o block-obj-$(CONFIG_REPLICATION) += replication.o diff --git a/stubs/Makefile.objs b/stubs/Makefile.objs index XXXXXXX..XXXXXXX 100644 --- a/stubs/Makefile.objs +++ b/stubs/Makefile.objs @@ -XXX,XX +XXX,XX @@ stub-obj-y += get-vm-name.o stub-obj-y += iothread.o stub-obj-y += iothread-lock.o stub-obj-y += is-daemonized.o +stub-obj-$(CONFIG_LINUX_AIO) += linux-aio.o stub-obj-y += machine-init-done.o stub-obj-y += migr-blocker.o stub-obj-y += monitor.o diff --git a/tests/Makefile.include b/tests/Makefile.include index XXXXXXX..XXXXXXX 100644 --- a/tests/Makefile.include +++ b/tests/Makefile.include @@ -XXX,XX +XXX,XX @@ check-unit-y += tests/test-visitor-serialization$(EXESUF) check-unit-y += tests/test-iov$(EXESUF) gcov-files-test-iov-y = util/iov.c check-unit-y += tests/test-aio$(EXESUF) +gcov-files-test-aio-y = util/async.c util/qemu-timer.o +gcov-files-test-aio-$(CONFIG_WIN32) += util/aio-win32.c +gcov-files-test-aio-$(CONFIG_POSIX) += util/aio-posix.c check-unit-y += tests/test-throttle$(EXESUF) gcov-files-test-aio-$(CONFIG_WIN32) = aio-win32.c gcov-files-test-aio-$(CONFIG_POSIX) = aio-posix.c @@ -XXX,XX +XXX,XX @@ tests/check-qjson$(EXESUF): tests/check-qjson.o $(test-util-obj-y) tests/check-qom-interface$(EXESUF): tests/check-qom-interface.o $(test-qom-obj-y) tests/check-qom-proplist$(EXESUF): tests/check-qom-proplist.o $(test-qom-obj-y) -tests/test-char$(EXESUF): tests/test-char.o qemu-timer.o \ - $(test-util-obj-y) $(qtest-obj-y) $(test-block-obj-y) $(chardev-obj-y) +tests/test-char$(EXESUF): tests/test-char.o $(test-util-obj-y) $(qtest-obj-y) $(test-io-obj-y) $(chardev-obj-y) tests/test-coroutine$(EXESUF): tests/test-coroutine.o $(test-block-obj-y) tests/test-aio$(EXESUF): tests/test-aio.o $(test-block-obj-y) tests/test-throttle$(EXESUF): tests/test-throttle.o $(test-block-obj-y) @@ -XXX,XX +XXX,XX @@ tests/test-vmstate$(EXESUF): tests/test-vmstate.o \ migration/vmstate.o migration/qemu-file.o \ migration/qemu-file-channel.o migration/qjson.o \ $(test-io-obj-y) -tests/test-timed-average$(EXESUF): tests/test-timed-average.o qemu-timer.o \ - $(test-util-obj-y) +tests/test-timed-average$(EXESUF): tests/test-timed-average.o $(test-util-obj-y) tests/test-base64$(EXESUF): tests/test-base64.o \ libqemuutil.a libqemustub.a tests/ptimer-test$(EXESUF): tests/ptimer-test.o tests/ptimer-test-stubs.o hw/core/ptimer.o libqemustub.a @@ -XXX,XX +XXX,XX @@ tests/usb-hcd-ehci-test$(EXESUF): tests/usb-hcd-ehci-test.o $(libqos-usb-obj-y) tests/usb-hcd-xhci-test$(EXESUF): tests/usb-hcd-xhci-test.o $(libqos-usb-obj-y) tests/pc-cpu-test$(EXESUF): tests/pc-cpu-test.o tests/postcopy-test$(EXESUF): tests/postcopy-test.o -tests/vhost-user-test$(EXESUF): tests/vhost-user-test.o qemu-timer.o \ +tests/vhost-user-test$(EXESUF): tests/vhost-user-test.o $(test-util-obj-y) \ $(qtest-obj-y) $(test-io-obj-y) $(libqos-virtio-obj-y) $(libqos-pc-obj-y) \ $(chardev-obj-y) tests/qemu-iotests/socket_scm_helper$(EXESUF): tests/qemu-iotests/socket_scm_helper.o diff --git a/util/Makefile.objs b/util/Makefile.objs index XXXXXXX..XXXXXXX 100644 --- a/util/Makefile.objs +++ b/util/Makefile.objs @@ -XXX,XX +XXX,XX @@ util-obj-y = osdep.o cutils.o unicode.o qemu-timer-common.o util-obj-y += bufferiszero.o util-obj-y += lockcnt.o +util-obj-y += aiocb.o async.o thread-pool.o qemu-timer.o +util-obj-y += main-loop.o iohandler.o +util-obj-$(CONFIG_POSIX) += aio-posix.o util-obj-$(CONFIG_POSIX) += compatfd.o util-obj-$(CONFIG_POSIX) += event_notifier-posix.o util-obj-$(CONFIG_POSIX) += mmap-alloc.o util-obj-$(CONFIG_POSIX) += oslib-posix.o util-obj-$(CONFIG_POSIX) += qemu-openpty.o util-obj-$(CONFIG_POSIX) += qemu-thread-posix.o -util-obj-$(CONFIG_WIN32) += event_notifier-win32.o util-obj-$(CONFIG_POSIX) += memfd.o +util-obj-$(CONFIG_WIN32) += aio-win32.o +util-obj-$(CONFIG_WIN32) += event_notifier-win32.o util-obj-$(CONFIG_WIN32) += oslib-win32.o util-obj-$(CONFIG_WIN32) += qemu-thread-win32.o util-obj-y += envlist.o path.o module.o diff --git a/block/io.c b/block/io.c index XXXXXXX..XXXXXXX 100644 --- a/block/io.c +++ b/block/io.c @@ -XXX,XX +XXX,XX @@ BlockAIOCB *bdrv_aio_flush(BlockDriverState *bs, return &acb->common; } -void *qemu_aio_get(const AIOCBInfo *aiocb_info, BlockDriverState *bs, - BlockCompletionFunc *cb, void *opaque) -{ - BlockAIOCB *acb; - - acb = g_malloc(aiocb_info->aiocb_size); - acb->aiocb_info = aiocb_info; - acb->bs = bs; - acb->cb = cb; - acb->opaque = opaque; - acb->refcnt = 1; - return acb; -} - -void qemu_aio_ref(void *p) -{ - BlockAIOCB *acb = p; - acb->refcnt++; -} - -void qemu_aio_unref(void *p) -{ - BlockAIOCB *acb = p; - assert(acb->refcnt > 0); - if (--acb->refcnt == 0) { - g_free(acb); - } -} - /**************************************************************/ /* Coroutine block device emulation */ diff --git a/stubs/linux-aio.c b/stubs/linux-aio.c new file mode 100644 index XXXXXXX..XXXXXXX --- /dev/null +++ b/stubs/linux-aio.c @@ -XXX,XX +XXX,XX @@ +/* + * Linux native AIO support. + * + * Copyright (C) 2009 IBM, Corp. + * Copyright (C) 2009 Red Hat, Inc. + * + * This work is licensed under the terms of the GNU GPL, version 2 or later. + * See the COPYING file in the top-level directory. + */ +#include "qemu/osdep.h" +#include "block/aio.h" +#include "block/raw-aio.h" + +void laio_detach_aio_context(LinuxAioState *s, AioContext *old_context) +{ + abort(); +} + +void laio_attach_aio_context(LinuxAioState *s, AioContext *new_context) +{ + abort(); +} + +LinuxAioState *laio_init(void) +{ + abort(); +} + +void laio_cleanup(LinuxAioState *s) +{ + abort(); +} diff --git a/stubs/set-fd-handler.c b/stubs/set-fd-handler.c index XXXXXXX..XXXXXXX 100644 --- a/stubs/set-fd-handler.c +++ b/stubs/set-fd-handler.c @@ -XXX,XX +XXX,XX @@ void qemu_set_fd_handler(int fd, { abort(); } - -void aio_set_fd_handler(AioContext *ctx, - int fd, - bool is_external, - IOHandler *io_read, - IOHandler *io_write, - AioPollFn *io_poll, - void *opaque) -{ - abort(); -} diff --git a/aio-posix.c b/util/aio-posix.c similarity index 99% rename from aio-posix.c rename to util/aio-posix.c index XXXXXXX..XXXXXXX 100644 --- a/aio-posix.c +++ b/util/aio-posix.c @@ -XXX,XX +XXX,XX @@ #include "qemu/rcu_queue.h" #include "qemu/sockets.h" #include "qemu/cutils.h" -#include "trace-root.h" +#include "trace.h" #ifdef CONFIG_EPOLL_CREATE1 #include <sys/epoll.h> #endif diff --git a/aio-win32.c b/util/aio-win32.c similarity index 100% rename from aio-win32.c rename to util/aio-win32.c diff --git a/util/aiocb.c b/util/aiocb.c new file mode 100644 index XXXXXXX..XXXXXXX --- /dev/null +++ b/util/aiocb.c @@ -XXX,XX +XXX,XX @@ +/* + * BlockAIOCB allocation + * + * Copyright (c) 2003-2017 Fabrice Bellard and other QEMU contributors + * + * Permission is hereby granted, free of charge, to any person obtaining a copy + * of this software and associated documentation files (the "Software"), to deal + * in the Software without restriction, including without limitation the rights + * to use, copy, modify, merge, publish, distribute, sublicense, and/or sell + * copies of the Software, and to permit persons to whom the Software is + * furnished to do so, subject to the following conditions: + * + * The above copyright notice and this permission notice shall be included in + * all copies or substantial portions of the Software. + * + * THE SOFTWARE IS PROVIDED "AS IS", WITHOUT WARRANTY OF ANY KIND, EXPRESS OR + * IMPLIED, INCLUDING BUT NOT LIMITED TO THE WARRANTIES OF MERCHANTABILITY, + * FITNESS FOR A PARTICULAR PURPOSE AND NONINFRINGEMENT. IN NO EVENT SHALL + * THE AUTHORS OR COPYRIGHT HOLDERS BE LIABLE FOR ANY CLAIM, DAMAGES OR OTHER + * LIABILITY, WHETHER IN AN ACTION OF CONTRACT, TORT OR OTHERWISE, ARISING FROM, + * OUT OF OR IN CONNECTION WITH THE SOFTWARE OR THE USE OR OTHER DEALINGS IN + * THE SOFTWARE. + */ + +#include "qemu/osdep.h" +#include "block/aio.h" + +void *qemu_aio_get(const AIOCBInfo *aiocb_info, BlockDriverState *bs, + BlockCompletionFunc *cb, void *opaque) +{ + BlockAIOCB *acb; + + acb = g_malloc(aiocb_info->aiocb_size); + acb->aiocb_info = aiocb_info; + acb->bs = bs; + acb->cb = cb; + acb->opaque = opaque; + acb->refcnt = 1; + return acb; +} + +void qemu_aio_ref(void *p) +{ + BlockAIOCB *acb = p; + acb->refcnt++; +} + +void qemu_aio_unref(void *p) +{ + BlockAIOCB *acb = p; + assert(acb->refcnt > 0); + if (--acb->refcnt == 0) { + g_free(acb); + } +} diff --git a/async.c b/util/async.c similarity index 99% rename from async.c rename to util/async.c index XXXXXXX..XXXXXXX 100644 --- a/async.c +++ b/util/async.c @@ -XXX,XX +XXX,XX @@ /* - * QEMU System Emulator + * Data plane event loop * * Copyright (c) 2003-2008 Fabrice Bellard + * Copyright (c) 2009-2017 QEMU contributors * * Permission is hereby granted, free of charge, to any person obtaining a copy * of this software and associated documentation files (the "Software"), to deal diff --git a/iohandler.c b/util/iohandler.c similarity index 100% rename from iohandler.c rename to util/iohandler.c diff --git a/main-loop.c b/util/main-loop.c similarity index 100% rename from main-loop.c rename to util/main-loop.c diff --git a/qemu-timer.c b/util/qemu-timer.c similarity index 100% rename from qemu-timer.c rename to util/qemu-timer.c diff --git a/thread-pool.c b/util/thread-pool.c similarity index 99% rename from thread-pool.c rename to util/thread-pool.c index XXXXXXX..XXXXXXX 100644 --- a/thread-pool.c +++ b/util/thread-pool.c @@ -XXX,XX +XXX,XX @@ #include "qemu/queue.h" #include "qemu/thread.h" #include "qemu/coroutine.h" -#include "trace-root.h" +#include "trace.h" #include "block/thread-pool.h" #include "qemu/main-loop.h" diff --git a/trace-events b/trace-events index XXXXXXX..XXXXXXX 100644 --- a/trace-events +++ b/trace-events @@ -XXX,XX +XXX,XX @@ # # The <format-string> should be a sprintf()-compatible format string. -# aio-posix.c -run_poll_handlers_begin(void *ctx, int64_t max_ns) "ctx %p max_ns %"PRId64 -run_poll_handlers_end(void *ctx, bool progress) "ctx %p progress %d" -poll_shrink(void *ctx, int64_t old, int64_t new) "ctx %p old %"PRId64" new %"PRId64 -poll_grow(void *ctx, int64_t old, int64_t new) "ctx %p old %"PRId64" new %"PRId64 - -# thread-pool.c -thread_pool_submit(void *pool, void *req, void *opaque) "pool %p req %p opaque %p" -thread_pool_complete(void *pool, void *req, void *opaque, int ret) "pool %p req %p opaque %p ret %d" -thread_pool_cancel(void *req, void *opaque) "req %p opaque %p" - # ioport.c cpu_in(unsigned int addr, char size, unsigned int val) "addr %#x(%c) value %u" cpu_out(unsigned int addr, char size, unsigned int val) "addr %#x(%c) value %u" diff --git a/util/trace-events b/util/trace-events index XXXXXXX..XXXXXXX 100644 --- a/util/trace-events +++ b/util/trace-events @@ -XXX,XX +XXX,XX @@ # See docs/tracing.txt for syntax documentation. +# util/aio-posix.c +run_poll_handlers_begin(void *ctx, int64_t max_ns) "ctx %p max_ns %"PRId64 +run_poll_handlers_end(void *ctx, bool progress) "ctx %p progress %d" +poll_shrink(void *ctx, int64_t old, int64_t new) "ctx %p old %"PRId64" new %"PRId64 +poll_grow(void *ctx, int64_t old, int64_t new) "ctx %p old %"PRId64" new %"PRId64 + +# util/thread-pool.c +thread_pool_submit(void *pool, void *req, void *opaque) "pool %p req %p opaque %p" +thread_pool_complete(void *pool, void *req, void *opaque, int ret) "pool %p req %p opaque %p ret %d" +thread_pool_cancel(void *req, void *opaque) "req %p opaque %p" + # util/buffer.c buffer_resize(const char *buf, size_t olen, size_t len) "%s: old %zd, new %zd" buffer_move_empty(const char *buf, size_t len, const char *from) "%s: %zd bytes from %s" -- 2.9.3 From: Paolo Bonzini <pbonzini@redhat.com> aio_co_wake provides the infrastructure to start a coroutine on a "home" AioContext. It will be used by CoMutex and CoQueue, so that coroutines don't jump from one context to another when they go to sleep on a mutex or waitqueue. However, it can also be used as a more efficient alternative to one-shot bottom halves, and saves the effort of tracking which AioContext a coroutine is running on. aio_co_schedule is the part of aio_co_wake that starts a coroutine on a remove AioContext, but it is also useful to implement e.g. bdrv_set_aio_context callbacks. The implementation of aio_co_schedule is based on a lock-free multiple-producer, single-consumer queue. The multiple producers use cmpxchg to add to a LIFO stack. The consumer (a per-AioContext bottom half) grabs all items added so far, inverts the list to make it FIFO, and goes through it one item at a time until it's empty. The data structure was inspired by OSv, which uses it in the very code we'll "port" to QEMU for the thread-safe CoMutex. Most of the new code is really tests. Signed-off-by: Paolo Bonzini <pbonzini@redhat.com> Reviewed-by: Fam Zheng <famz@redhat.com> Message-id: 20170213135235.12274-3-pbonzini@redhat.com Signed-off-by: Stefan Hajnoczi <stefanha@redhat.com> --- tests/Makefile.include | 8 +- include/block/aio.h | 32 +++++++ include/qemu/coroutine_int.h | 11 ++- tests/iothread.h | 25 +++++ tests/iothread.c | 91 ++++++++++++++++++ tests/test-aio-multithread.c | 213 +++++++++++++++++++++++++++++++++++++++++++ util/async.c | 65 +++++++++++++ util/qemu-coroutine.c | 8 ++ util/trace-events | 4 + 9 files changed, 453 insertions(+), 4 deletions(-) create mode 100644 tests/iothread.h create mode 100644 tests/iothread.c create mode 100644 tests/test-aio-multithread.c diff --git a/tests/Makefile.include b/tests/Makefile.include index XXXXXXX..XXXXXXX 100644 --- a/tests/Makefile.include +++ b/tests/Makefile.include @@ -XXX,XX +XXX,XX @@ check-unit-y += tests/test-aio$(EXESUF) gcov-files-test-aio-y = util/async.c util/qemu-timer.o gcov-files-test-aio-$(CONFIG_WIN32) += util/aio-win32.c gcov-files-test-aio-$(CONFIG_POSIX) += util/aio-posix.c +check-unit-y += tests/test-aio-multithread$(EXESUF) +gcov-files-test-aio-multithread-y = $(gcov-files-test-aio-y) +gcov-files-test-aio-multithread-y += util/qemu-coroutine.c tests/iothread.c check-unit-y += tests/test-throttle$(EXESUF) -gcov-files-test-aio-$(CONFIG_WIN32) = aio-win32.c -gcov-files-test-aio-$(CONFIG_POSIX) = aio-posix.c check-unit-y += tests/test-thread-pool$(EXESUF) gcov-files-test-thread-pool-y = thread-pool.c gcov-files-test-hbitmap-y = util/hbitmap.c @@ -XXX,XX +XXX,XX @@ test-qapi-obj-y = tests/test-qapi-visit.o tests/test-qapi-types.o \ $(test-qom-obj-y) test-crypto-obj-y = $(crypto-obj-y) $(test-qom-obj-y) test-io-obj-y = $(io-obj-y) $(test-crypto-obj-y) -test-block-obj-y = $(block-obj-y) $(test-io-obj-y) +test-block-obj-y = $(block-obj-y) $(test-io-obj-y) tests/iothread.o tests/check-qint$(EXESUF): tests/check-qint.o $(test-util-obj-y) tests/check-qstring$(EXESUF): tests/check-qstring.o $(test-util-obj-y) @@ -XXX,XX +XXX,XX @@ tests/check-qom-proplist$(EXESUF): tests/check-qom-proplist.o $(test-qom-obj-y) tests/test-char$(EXESUF): tests/test-char.o $(test-util-obj-y) $(qtest-obj-y) $(test-io-obj-y) $(chardev-obj-y) tests/test-coroutine$(EXESUF): tests/test-coroutine.o $(test-block-obj-y) tests/test-aio$(EXESUF): tests/test-aio.o $(test-block-obj-y) +tests/test-aio-multithread$(EXESUF): tests/test-aio-multithread.o $(test-block-obj-y) tests/test-throttle$(EXESUF): tests/test-throttle.o $(test-block-obj-y) tests/test-blockjob$(EXESUF): tests/test-blockjob.o $(test-block-obj-y) $(test-util-obj-y) tests/test-blockjob-txn$(EXESUF): tests/test-blockjob-txn.o $(test-block-obj-y) $(test-util-obj-y) diff --git a/include/block/aio.h b/include/block/aio.h index XXXXXXX..XXXXXXX 100644 --- a/include/block/aio.h +++ b/include/block/aio.h @@ -XXX,XX +XXX,XX @@ typedef void QEMUBHFunc(void *opaque); typedef bool AioPollFn(void *opaque); typedef void IOHandler(void *opaque); +struct Coroutine; struct ThreadPool; struct LinuxAioState; @@ -XXX,XX +XXX,XX @@ struct AioContext { bool notified; EventNotifier notifier; + QSLIST_HEAD(, Coroutine) scheduled_coroutines; + QEMUBH *co_schedule_bh; + /* Thread pool for performing work and receiving completion callbacks. * Has its own locking. */ @@ -XXX,XX +XXX,XX @@ static inline bool aio_node_check(AioContext *ctx, bool is_external) } /** + * aio_co_schedule: + * @ctx: the aio context + * @co: the coroutine + * + * Start a coroutine on a remote AioContext. + * + * The coroutine must not be entered by anyone else while aio_co_schedule() + * is active. In addition the coroutine must have yielded unless ctx + * is the context in which the coroutine is running (i.e. the value of + * qemu_get_current_aio_context() from the coroutine itself). + */ +void aio_co_schedule(AioContext *ctx, struct Coroutine *co); + +/** + * aio_co_wake: + * @co: the coroutine + * + * Restart a coroutine on the AioContext where it was running last, thus + * preventing coroutines from jumping from one context to another when they + * go to sleep. + * + * aio_co_wake may be executed either in coroutine or non-coroutine + * context. The coroutine must not be entered by anyone else while + * aio_co_wake() is active. + */ +void aio_co_wake(struct Coroutine *co); + +/** * Return the AioContext whose event loop runs in the current thread. * * If called from an IOThread this will be the IOThread's AioContext. If diff --git a/include/qemu/coroutine_int.h b/include/qemu/coroutine_int.h index XXXXXXX..XXXXXXX 100644 --- a/include/qemu/coroutine_int.h +++ b/include/qemu/coroutine_int.h @@ -XXX,XX +XXX,XX @@ struct Coroutine { CoroutineEntry *entry; void *entry_arg; Coroutine *caller; + + /* Only used when the coroutine has terminated. */ QSLIST_ENTRY(Coroutine) pool_next; + size_t locks_held; - /* Coroutines that should be woken up when we yield or terminate */ + /* Coroutines that should be woken up when we yield or terminate. + * Only used when the coroutine is running. + */ QSIMPLEQ_HEAD(, Coroutine) co_queue_wakeup; + + /* Only used when the coroutine has yielded. */ + AioContext *ctx; QSIMPLEQ_ENTRY(Coroutine) co_queue_next; + QSLIST_ENTRY(Coroutine) co_scheduled_next; }; Coroutine *qemu_coroutine_new(void); diff --git a/tests/iothread.h b/tests/iothread.h new file mode 100644 index XXXXXXX..XXXXXXX --- /dev/null +++ b/tests/iothread.h @@ -XXX,XX +XXX,XX @@ +/* + * Event loop thread implementation for unit tests + * + * Copyright Red Hat Inc., 2013, 2016 + * + * Authors: + * Stefan Hajnoczi <stefanha@redhat.com> + * Paolo Bonzini <pbonzini@redhat.com> + * + * This work is licensed under the terms of the GNU GPL, version 2 or later. + * See the COPYING file in the top-level directory. + */ +#ifndef TEST_IOTHREAD_H +#define TEST_IOTHREAD_H + +#include "block/aio.h" +#include "qemu/thread.h" + +typedef struct IOThread IOThread; + +IOThread *iothread_new(void); +void iothread_join(IOThread *iothread); +AioContext *iothread_get_aio_context(IOThread *iothread); + +#endif diff --git a/tests/iothread.c b/tests/iothread.c new file mode 100644 index XXXXXXX..XXXXXXX --- /dev/null +++ b/tests/iothread.c @@ -XXX,XX +XXX,XX @@ +/* + * Event loop thread implementation for unit tests + * + * Copyright Red Hat Inc., 2013, 2016 + * + * Authors: + * Stefan Hajnoczi <stefanha@redhat.com> + * Paolo Bonzini <pbonzini@redhat.com> + * + * This work is licensed under the terms of the GNU GPL, version 2 or later. + * See the COPYING file in the top-level directory. + * + */ + +#include "qemu/osdep.h" +#include "qapi/error.h" +#include "block/aio.h" +#include "qemu/main-loop.h" +#include "qemu/rcu.h" +#include "iothread.h" + +struct IOThread { + AioContext *ctx; + + QemuThread thread; + QemuMutex init_done_lock; + QemuCond init_done_cond; /* is thread initialization done? */ + bool stopping; +}; + +static __thread IOThread *my_iothread; + +AioContext *qemu_get_current_aio_context(void) +{ + return my_iothread ? my_iothread->ctx : qemu_get_aio_context(); +} + +static void *iothread_run(void *opaque) +{ + IOThread *iothread = opaque; + + rcu_register_thread(); + + my_iothread = iothread; + qemu_mutex_lock(&iothread->init_done_lock); + iothread->ctx = aio_context_new(&error_abort); + qemu_cond_signal(&iothread->init_done_cond); + qemu_mutex_unlock(&iothread->init_done_lock); + + while (!atomic_read(&iothread->stopping)) { + aio_poll(iothread->ctx, true); + } + + rcu_unregister_thread(); + return NULL; +} + +void iothread_join(IOThread *iothread) +{ + iothread->stopping = true; + aio_notify(iothread->ctx); + qemu_thread_join(&iothread->thread); + qemu_cond_destroy(&iothread->init_done_cond); + qemu_mutex_destroy(&iothread->init_done_lock); + aio_context_unref(iothread->ctx); + g_free(iothread); +} + +IOThread *iothread_new(void) +{ + IOThread *iothread = g_new0(IOThread, 1); + + qemu_mutex_init(&iothread->init_done_lock); + qemu_cond_init(&iothread->init_done_cond); + qemu_thread_create(&iothread->thread, NULL, iothread_run, + iothread, QEMU_THREAD_JOINABLE); + + /* Wait for initialization to complete */ + qemu_mutex_lock(&iothread->init_done_lock); + while (iothread->ctx == NULL) { + qemu_cond_wait(&iothread->init_done_cond, + &iothread->init_done_lock); + } + qemu_mutex_unlock(&iothread->init_done_lock); + return iothread; +} + +AioContext *iothread_get_aio_context(IOThread *iothread) +{ + return iothread->ctx; +} diff --git a/tests/test-aio-multithread.c b/tests/test-aio-multithread.c new file mode 100644 index XXXXXXX..XXXXXXX --- /dev/null +++ b/tests/test-aio-multithread.c @@ -XXX,XX +XXX,XX @@ +/* + * AioContext multithreading tests + * + * Copyright Red Hat, Inc. 2016 + * + * Authors: + * Paolo Bonzini <pbonzini@redhat.com> + * + * This work is licensed under the terms of the GNU LGPL, version 2 or later. + * See the COPYING.LIB file in the top-level directory. + */ + +#include "qemu/osdep.h" +#include <glib.h> +#include "block/aio.h" +#include "qapi/error.h" +#include "qemu/coroutine.h" +#include "qemu/thread.h" +#include "qemu/error-report.h" +#include "iothread.h" + +/* AioContext management */ + +#define NUM_CONTEXTS 5 + +static IOThread *threads[NUM_CONTEXTS]; +static AioContext *ctx[NUM_CONTEXTS]; +static __thread int id = -1; + +static QemuEvent done_event; + +/* Run a function synchronously on a remote iothread. */ + +typedef struct CtxRunData { + QEMUBHFunc *cb; + void *arg; +} CtxRunData; + +static void ctx_run_bh_cb(void *opaque) +{ + CtxRunData *data = opaque; + + data->cb(data->arg); + qemu_event_set(&done_event); +} + +static void ctx_run(int i, QEMUBHFunc *cb, void *opaque) +{ + CtxRunData data = { + .cb = cb, + .arg = opaque + }; + + qemu_event_reset(&done_event); + aio_bh_schedule_oneshot(ctx[i], ctx_run_bh_cb, &data); + qemu_event_wait(&done_event); +} + +/* Starting the iothreads. */ + +static void set_id_cb(void *opaque) +{ + int *i = opaque; + + id = *i; +} + +static void create_aio_contexts(void) +{ + int i; + + for (i = 0; i < NUM_CONTEXTS; i++) { + threads[i] = iothread_new(); + ctx[i] = iothread_get_aio_context(threads[i]); + } + + qemu_event_init(&done_event, false); + for (i = 0; i < NUM_CONTEXTS; i++) { + ctx_run(i, set_id_cb, &i); + } +} + +/* Stopping the iothreads. */ + +static void join_aio_contexts(void) +{ + int i; + + for (i = 0; i < NUM_CONTEXTS; i++) { + aio_context_ref(ctx[i]); + } + for (i = 0; i < NUM_CONTEXTS; i++) { + iothread_join(threads[i]); + } + for (i = 0; i < NUM_CONTEXTS; i++) { + aio_context_unref(ctx[i]); + } + qemu_event_destroy(&done_event); +} + +/* Basic test for the stuff above. */ + +static void test_lifecycle(void) +{ + create_aio_contexts(); + join_aio_contexts(); +} + +/* aio_co_schedule test. */ + +static Coroutine *to_schedule[NUM_CONTEXTS]; + +static bool now_stopping; + +static int count_retry; +static int count_here; +static int count_other; + +static bool schedule_next(int n) +{ + Coroutine *co; + + co = atomic_xchg(&to_schedule[n], NULL); + if (!co) { + atomic_inc(&count_retry); + return false; + } + + if (n == id) { + atomic_inc(&count_here); + } else { + atomic_inc(&count_other); + } + + aio_co_schedule(ctx[n], co); + return true; +} + +static void finish_cb(void *opaque) +{ + schedule_next(id); +} + +static coroutine_fn void test_multi_co_schedule_entry(void *opaque) +{ + g_assert(to_schedule[id] == NULL); + atomic_mb_set(&to_schedule[id], qemu_coroutine_self()); + + while (!atomic_mb_read(&now_stopping)) { + int n; + + n = g_test_rand_int_range(0, NUM_CONTEXTS); + schedule_next(n); + qemu_coroutine_yield(); + + g_assert(to_schedule[id] == NULL); + atomic_mb_set(&to_schedule[id], qemu_coroutine_self()); + } +} + + +static void test_multi_co_schedule(int seconds) +{ + int i; + + count_here = count_other = count_retry = 0; + now_stopping = false; + + create_aio_contexts(); + for (i = 0; i < NUM_CONTEXTS; i++) { + Coroutine *co1 = qemu_coroutine_create(test_multi_co_schedule_entry, NULL); + aio_co_schedule(ctx[i], co1); + } + + g_usleep(seconds * 1000000); + + atomic_mb_set(&now_stopping, true); + for (i = 0; i < NUM_CONTEXTS; i++) { + ctx_run(i, finish_cb, NULL); + to_schedule[i] = NULL; + } + + join_aio_contexts(); + g_test_message("scheduled %d, queued %d, retry %d, total %d\n", + count_other, count_here, count_retry, + count_here + count_other + count_retry); +} + +static void test_multi_co_schedule_1(void) +{ + test_multi_co_schedule(1); +} + +static void test_multi_co_schedule_10(void) +{ + test_multi_co_schedule(10); +} + +/* End of tests. */ + +int main(int argc, char **argv) +{ + init_clocks(); + + g_test_init(&argc, &argv, NULL); + g_test_add_func("/aio/multi/lifecycle", test_lifecycle); + if (g_test_quick()) { + g_test_add_func("/aio/multi/schedule", test_multi_co_schedule_1); + } else { + g_test_add_func("/aio/multi/schedule", test_multi_co_schedule_10); + } + return g_test_run(); +} diff --git a/util/async.c b/util/async.c index XXXXXXX..XXXXXXX 100644 --- a/util/async.c +++ b/util/async.c @@ -XXX,XX +XXX,XX @@ #include "qemu/main-loop.h" #include "qemu/atomic.h" #include "block/raw-aio.h" +#include "qemu/coroutine_int.h" +#include "trace.h" /***********************************************************/ /* bottom halves (can be seen as timers which expire ASAP) */ @@ -XXX,XX +XXX,XX @@ aio_ctx_finalize(GSource *source) } #endif + assert(QSLIST_EMPTY(&ctx->scheduled_coroutines)); + qemu_bh_delete(ctx->co_schedule_bh); + qemu_lockcnt_lock(&ctx->list_lock); assert(!qemu_lockcnt_count(&ctx->list_lock)); while (ctx->first_bh) { @@ -XXX,XX +XXX,XX @@ static bool event_notifier_poll(void *opaque) return atomic_read(&ctx->notified); } +static void co_schedule_bh_cb(void *opaque) +{ + AioContext *ctx = opaque; + QSLIST_HEAD(, Coroutine) straight, reversed; + + QSLIST_MOVE_ATOMIC(&reversed, &ctx->scheduled_coroutines); + QSLIST_INIT(&straight); + + while (!QSLIST_EMPTY(&reversed)) { + Coroutine *co = QSLIST_FIRST(&reversed); + QSLIST_REMOVE_HEAD(&reversed, co_scheduled_next); + QSLIST_INSERT_HEAD(&straight, co, co_scheduled_next); + } + + while (!QSLIST_EMPTY(&straight)) { + Coroutine *co = QSLIST_FIRST(&straight); + QSLIST_REMOVE_HEAD(&straight, co_scheduled_next); + trace_aio_co_schedule_bh_cb(ctx, co); + qemu_coroutine_enter(co); + } +} + AioContext *aio_context_new(Error **errp) { int ret; @@ -XXX,XX +XXX,XX @@ AioContext *aio_context_new(Error **errp) } g_source_set_can_recurse(&ctx->source, true); qemu_lockcnt_init(&ctx->list_lock); + + ctx->co_schedule_bh = aio_bh_new(ctx, co_schedule_bh_cb, ctx); + QSLIST_INIT(&ctx->scheduled_coroutines); + aio_set_event_notifier(ctx, &ctx->notifier, false, (EventNotifierHandler *) @@ -XXX,XX +XXX,XX @@ fail: return NULL; } +void aio_co_schedule(AioContext *ctx, Coroutine *co) +{ + trace_aio_co_schedule(ctx, co); + QSLIST_INSERT_HEAD_ATOMIC(&ctx->scheduled_coroutines, + co, co_scheduled_next); + qemu_bh_schedule(ctx->co_schedule_bh); +} + +void aio_co_wake(struct Coroutine *co) +{ + AioContext *ctx; + + /* Read coroutine before co->ctx. Matches smp_wmb in + * qemu_coroutine_enter. + */ + smp_read_barrier_depends(); + ctx = atomic_read(&co->ctx); + + if (ctx != qemu_get_current_aio_context()) { + aio_co_schedule(ctx, co); + return; + } + + if (qemu_in_coroutine()) { + Coroutine *self = qemu_coroutine_self(); + assert(self != co); + QSIMPLEQ_INSERT_TAIL(&self->co_queue_wakeup, co, co_queue_next); + } else { + aio_context_acquire(ctx); + qemu_coroutine_enter(co); + aio_context_release(ctx); + } +} + void aio_context_ref(AioContext *ctx) { g_source_ref(&ctx->source); diff --git a/util/qemu-coroutine.c b/util/qemu-coroutine.c index XXXXXXX..XXXXXXX 100644 --- a/util/qemu-coroutine.c +++ b/util/qemu-coroutine.c @@ -XXX,XX +XXX,XX @@ #include "qemu/atomic.h" #include "qemu/coroutine.h" #include "qemu/coroutine_int.h" +#include "block/aio.h" enum { POOL_BATCH_SIZE = 64, @@ -XXX,XX +XXX,XX @@ void qemu_coroutine_enter(Coroutine *co) } co->caller = self; + co->ctx = qemu_get_current_aio_context(); + + /* Store co->ctx before anything that stores co. Matches + * barrier in aio_co_wake. + */ + smp_wmb(); + ret = qemu_coroutine_switch(self, co, COROUTINE_ENTER); qemu_co_queue_run_restart(co); diff --git a/util/trace-events b/util/trace-events index XXXXXXX..XXXXXXX 100644 --- a/util/trace-events +++ b/util/trace-events @@ -XXX,XX +XXX,XX @@ run_poll_handlers_end(void *ctx, bool progress) "ctx %p progress %d" poll_shrink(void *ctx, int64_t old, int64_t new) "ctx %p old %"PRId64" new %"PRId64 poll_grow(void *ctx, int64_t old, int64_t new) "ctx %p old %"PRId64" new %"PRId64 +# util/async.c +aio_co_schedule(void *ctx, void *co) "ctx %p co %p" +aio_co_schedule_bh_cb(void *ctx, void *co) "ctx %p co %p" + # util/thread-pool.c thread_pool_submit(void *pool, void *req, void *opaque) "pool %p req %p opaque %p" thread_pool_complete(void *pool, void *req, void *opaque, int ret) "pool %p req %p opaque %p ret %d" -- 2.9.3 From: Paolo Bonzini <pbonzini@redhat.com> qcow2_create2 calls this. Do not run a nested event loop, as that breaks when aio_co_wake tries to queue the coroutine on the co_queue_wakeup list of the currently running one. Reviewed-by: Stefan Hajnoczi <stefanha@redhat.com> Signed-off-by: Paolo Bonzini <pbonzini@redhat.com> Reviewed-by: Fam Zheng <famz@redhat.com> Message-id: 20170213135235.12274-4-pbonzini@redhat.com Signed-off-by: Stefan Hajnoczi <stefanha@redhat.com> --- block/block-backend.c | 12 ++++++++---- 1 file changed, 8 insertions(+), 4 deletions(-) diff --git a/block/block-backend.c b/block/block-backend.c index XXXXXXX..XXXXXXX 100644 --- a/block/block-backend.c +++ b/block/block-backend.c @@ -XXX,XX +XXX,XX @@ static int blk_prw(BlockBackend *blk, int64_t offset, uint8_t *buf, { QEMUIOVector qiov; struct iovec iov; - Coroutine *co; BlkRwCo rwco; iov = (struct iovec) { @@ -XXX,XX +XXX,XX @@ static int blk_prw(BlockBackend *blk, int64_t offset, uint8_t *buf, .ret = NOT_DONE, }; - co = qemu_coroutine_create(co_entry, &rwco); - qemu_coroutine_enter(co); - BDRV_POLL_WHILE(blk_bs(blk), rwco.ret == NOT_DONE); + if (qemu_in_coroutine()) { + /* Fast-path if already in coroutine context */ + co_entry(&rwco); + } else { + Coroutine *co = qemu_coroutine_create(co_entry, &rwco); + qemu_coroutine_enter(co); + BDRV_POLL_WHILE(blk_bs(blk), rwco.ret == NOT_DONE); + } return rwco.ret; } -- 2.9.3 From: Paolo Bonzini <pbonzini@redhat.com> Once the thread pool starts using aio_co_wake, it will also need qemu_get_current_aio_context(). Make test-thread-pool create an AioContext with qemu_init_main_loop, so that stubs/iothread.c and tests/iothread.c can provide the rest. Reviewed-by: Stefan Hajnoczi <stefanha@redhat.com> Signed-off-by: Paolo Bonzini <pbonzini@redhat.com> Reviewed-by: Fam Zheng <famz@redhat.com> Message-id: 20170213135235.12274-5-pbonzini@redhat.com Signed-off-by: Stefan Hajnoczi <stefanha@redhat.com> --- tests/test-thread-pool.c | 12 +++--------- 1 file changed, 3 insertions(+), 9 deletions(-) diff --git a/tests/test-thread-pool.c b/tests/test-thread-pool.c index XXXXXXX..XXXXXXX 100644 --- a/tests/test-thread-pool.c +++ b/tests/test-thread-pool.c @@ -XXX,XX +XXX,XX @@ #include "qapi/error.h" #include "qemu/timer.h" #include "qemu/error-report.h" +#include "qemu/main-loop.h" static AioContext *ctx; static ThreadPool *pool; @@ -XXX,XX +XXX,XX @@ static void test_cancel_async(void) int main(int argc, char **argv) { int ret; - Error *local_error = NULL; - init_clocks(); - - ctx = aio_context_new(&local_error); - if (!ctx) { - error_reportf_err(local_error, "Failed to create AIO Context: "); - exit(1); - } + qemu_init_main_loop(&error_abort); + ctx = qemu_get_current_aio_context(); pool = aio_get_thread_pool(ctx); g_test_init(&argc, &argv, NULL); @@ -XXX,XX +XXX,XX @@ int main(int argc, char **argv) ret = g_test_run(); - aio_context_unref(ctx); return ret; } -- 2.9.3 From: Paolo Bonzini <pbonzini@redhat.com> This is in preparation for making qio_channel_yield work on AioContexts other than the main one. Reviewed-by: Daniel P. Berrange <berrange@redhat.com> Reviewed-by: Stefan Hajnoczi <stefanha@redhat.com> Signed-off-by: Paolo Bonzini <pbonzini@redhat.com> Reviewed-by: Fam Zheng <famz@redhat.com> Message-id: 20170213135235.12274-6-pbonzini@redhat.com Signed-off-by: Stefan Hajnoczi <stefanha@redhat.com> --- include/io/channel.h | 25 +++++++++++++++++++++++++ io/channel-command.c | 13 +++++++++++++ io/channel-file.c | 11 +++++++++++ io/channel-socket.c | 16 +++++++++++----- io/channel-tls.c | 12 ++++++++++++ io/channel-watch.c | 6 ++++++ io/channel.c | 11 +++++++++++ 7 files changed, 89 insertions(+), 5 deletions(-) diff --git a/include/io/channel.h b/include/io/channel.h index XXXXXXX..XXXXXXX 100644 --- a/include/io/channel.h +++ b/include/io/channel.h @@ -XXX,XX +XXX,XX @@ #include "qemu-common.h" #include "qom/object.h" +#include "block/aio.h" #define TYPE_QIO_CHANNEL "qio-channel" #define QIO_CHANNEL(obj) \ @@ -XXX,XX +XXX,XX @@ struct QIOChannelClass { off_t offset, int whence, Error **errp); + void (*io_set_aio_fd_handler)(QIOChannel *ioc, + AioContext *ctx, + IOHandler *io_read, + IOHandler *io_write, + void *opaque); }; /* General I/O handling functions */ @@ -XXX,XX +XXX,XX @@ void qio_channel_yield(QIOChannel *ioc, void qio_channel_wait(QIOChannel *ioc, GIOCondition condition); +/** + * qio_channel_set_aio_fd_handler: + * @ioc: the channel object + * @ctx: the AioContext to set the handlers on + * @io_read: the read handler + * @io_write: the write handler + * @opaque: the opaque value passed to the handler + * + * This is used internally by qio_channel_yield(). It can + * be used by channel implementations to forward the handlers + * to another channel (e.g. from #QIOChannelTLS to the + * underlying socket). + */ +void qio_channel_set_aio_fd_handler(QIOChannel *ioc, + AioContext *ctx, + IOHandler *io_read, + IOHandler *io_write, + void *opaque); + #endif /* QIO_CHANNEL_H */ diff --git a/io/channel-command.c b/io/channel-command.c index XXXXXXX..XXXXXXX 100644 --- a/io/channel-command.c +++ b/io/channel-command.c @@ -XXX,XX +XXX,XX @@ static int qio_channel_command_close(QIOChannel *ioc, } +static void qio_channel_command_set_aio_fd_handler(QIOChannel *ioc, + AioContext *ctx, + IOHandler *io_read, + IOHandler *io_write, + void *opaque) +{ + QIOChannelCommand *cioc = QIO_CHANNEL_COMMAND(ioc); + aio_set_fd_handler(ctx, cioc->readfd, false, io_read, NULL, NULL, opaque); + aio_set_fd_handler(ctx, cioc->writefd, false, NULL, io_write, NULL, opaque); +} + + static GSource *qio_channel_command_create_watch(QIOChannel *ioc, GIOCondition condition) { @@ -XXX,XX +XXX,XX @@ static void qio_channel_command_class_init(ObjectClass *klass, ioc_klass->io_set_blocking = qio_channel_command_set_blocking; ioc_klass->io_close = qio_channel_command_close; ioc_klass->io_create_watch = qio_channel_command_create_watch; + ioc_klass->io_set_aio_fd_handler = qio_channel_command_set_aio_fd_handler; } static const TypeInfo qio_channel_command_info = { diff --git a/io/channel-file.c b/io/channel-file.c index XXXXXXX..XXXXXXX 100644 --- a/io/channel-file.c +++ b/io/channel-file.c @@ -XXX,XX +XXX,XX @@ static int qio_channel_file_close(QIOChannel *ioc, } +static void qio_channel_file_set_aio_fd_handler(QIOChannel *ioc, + AioContext *ctx, + IOHandler *io_read, + IOHandler *io_write, + void *opaque) +{ + QIOChannelFile *fioc = QIO_CHANNEL_FILE(ioc); + aio_set_fd_handler(ctx, fioc->fd, false, io_read, io_write, NULL, opaque); +} + static GSource *qio_channel_file_create_watch(QIOChannel *ioc, GIOCondition condition) { @@ -XXX,XX +XXX,XX @@ static void qio_channel_file_class_init(ObjectClass *klass, ioc_klass->io_seek = qio_channel_file_seek; ioc_klass->io_close = qio_channel_file_close; ioc_klass->io_create_watch = qio_channel_file_create_watch; + ioc_klass->io_set_aio_fd_handler = qio_channel_file_set_aio_fd_handler; } static const TypeInfo qio_channel_file_info = { diff --git a/io/channel-socket.c b/io/channel-socket.c index XXXXXXX..XXXXXXX 100644 --- a/io/channel-socket.c +++ b/io/channel-socket.c @@ -XXX,XX +XXX,XX @@ qio_channel_socket_set_blocking(QIOChannel *ioc, qemu_set_block(sioc->fd); } else { qemu_set_nonblock(sioc->fd); -#ifdef WIN32 - WSAEventSelect(sioc->fd, ioc->event, - FD_READ | FD_ACCEPT | FD_CLOSE | - FD_CONNECT | FD_WRITE | FD_OOB); -#endif } return 0; } @@ -XXX,XX +XXX,XX @@ qio_channel_socket_shutdown(QIOChannel *ioc, return 0; } +static void qio_channel_socket_set_aio_fd_handler(QIOChannel *ioc, + AioContext *ctx, + IOHandler *io_read, + IOHandler *io_write, + void *opaque) +{ + QIOChannelSocket *sioc = QIO_CHANNEL_SOCKET(ioc); + aio_set_fd_handler(ctx, sioc->fd, false, io_read, io_write, NULL, opaque); +} + static GSource *qio_channel_socket_create_watch(QIOChannel *ioc, GIOCondition condition) { @@ -XXX,XX +XXX,XX @@ static void qio_channel_socket_class_init(ObjectClass *klass, ioc_klass->io_set_cork = qio_channel_socket_set_cork; ioc_klass->io_set_delay = qio_channel_socket_set_delay; ioc_klass->io_create_watch = qio_channel_socket_create_watch; + ioc_klass->io_set_aio_fd_handler = qio_channel_socket_set_aio_fd_handler; } static const TypeInfo qio_channel_socket_info = { diff --git a/io/channel-tls.c b/io/channel-tls.c index XXXXXXX..XXXXXXX 100644 --- a/io/channel-tls.c +++ b/io/channel-tls.c @@ -XXX,XX +XXX,XX @@ static int qio_channel_tls_close(QIOChannel *ioc, return qio_channel_close(tioc->master, errp); } +static void qio_channel_tls_set_aio_fd_handler(QIOChannel *ioc, + AioContext *ctx, + IOHandler *io_read, + IOHandler *io_write, + void *opaque) +{ + QIOChannelTLS *tioc = QIO_CHANNEL_TLS(ioc); + + qio_channel_set_aio_fd_handler(tioc->master, ctx, io_read, io_write, opaque); +} + static GSource *qio_channel_tls_create_watch(QIOChannel *ioc, GIOCondition condition) { @@ -XXX,XX +XXX,XX @@ static void qio_channel_tls_class_init(ObjectClass *klass, ioc_klass->io_close = qio_channel_tls_close; ioc_klass->io_shutdown = qio_channel_tls_shutdown; ioc_klass->io_create_watch = qio_channel_tls_create_watch; + ioc_klass->io_set_aio_fd_handler = qio_channel_tls_set_aio_fd_handler; } static const TypeInfo qio_channel_tls_info = { diff --git a/io/channel-watch.c b/io/channel-watch.c index XXXXXXX..XXXXXXX 100644 --- a/io/channel-watch.c +++ b/io/channel-watch.c @@ -XXX,XX +XXX,XX @@ GSource *qio_channel_create_socket_watch(QIOChannel *ioc, GSource *source; QIOChannelSocketSource *ssource; +#ifdef WIN32 + WSAEventSelect(socket, ioc->event, + FD_READ | FD_ACCEPT | FD_CLOSE | + FD_CONNECT | FD_WRITE | FD_OOB); +#endif + source = g_source_new(&qio_channel_socket_source_funcs, sizeof(QIOChannelSocketSource)); ssource = (QIOChannelSocketSource *)source; diff --git a/io/channel.c b/io/channel.c index XXXXXXX..XXXXXXX 100644 --- a/io/channel.c +++ b/io/channel.c @@ -XXX,XX +XXX,XX @@ GSource *qio_channel_create_watch(QIOChannel *ioc, } +void qio_channel_set_aio_fd_handler(QIOChannel *ioc, + AioContext *ctx, + IOHandler *io_read, + IOHandler *io_write, + void *opaque) +{ + QIOChannelClass *klass = QIO_CHANNEL_GET_CLASS(ioc); + + klass->io_set_aio_fd_handler(ioc, ctx, io_read, io_write, opaque); +} + guint qio_channel_add_watch(QIOChannel *ioc, GIOCondition condition, QIOChannelFunc func, -- 2.9.3 From: Paolo Bonzini <pbonzini@redhat.com> Support separate coroutines for reading and writing, and place the read/write handlers on the AioContext that the QIOChannel is registered with. Reviewed-by: Daniel P. Berrange <berrange@redhat.com> Reviewed-by: Stefan Hajnoczi <stefanha@redhat.com> Signed-off-by: Paolo Bonzini <pbonzini@redhat.com> Reviewed-by: Fam Zheng <famz@redhat.com> Message-id: 20170213135235.12274-7-pbonzini@redhat.com Signed-off-by: Stefan Hajnoczi <stefanha@redhat.com> --- include/io/channel.h | 47 ++++++++++++++++++++++++++-- io/channel.c | 86 +++++++++++++++++++++++++++++++++++++++------------- 2 files changed, 109 insertions(+), 24 deletions(-) diff --git a/include/io/channel.h b/include/io/channel.h index XXXXXXX..XXXXXXX 100644 --- a/include/io/channel.h +++ b/include/io/channel.h @@ -XXX,XX +XXX,XX @@ #include "qemu-common.h" #include "qom/object.h" +#include "qemu/coroutine.h" #include "block/aio.h" #define TYPE_QIO_CHANNEL "qio-channel" @@ -XXX,XX +XXX,XX @@ struct QIOChannel { Object parent; unsigned int features; /* bitmask of QIOChannelFeatures */ char *name; + AioContext *ctx; + Coroutine *read_coroutine; + Coroutine *write_coroutine; #ifdef _WIN32 HANDLE event; /* For use with GSource on Win32 */ #endif @@ -XXX,XX +XXX,XX @@ guint qio_channel_add_watch(QIOChannel *ioc, /** + * qio_channel_attach_aio_context: + * @ioc: the channel object + * @ctx: the #AioContext to set the handlers on + * + * Request that qio_channel_yield() sets I/O handlers on + * the given #AioContext. If @ctx is %NULL, qio_channel_yield() + * uses QEMU's main thread event loop. + * + * You can move a #QIOChannel from one #AioContext to another even if + * I/O handlers are set for a coroutine. However, #QIOChannel provides + * no synchronization between the calls to qio_channel_yield() and + * qio_channel_attach_aio_context(). + * + * Therefore you should first call qio_channel_detach_aio_context() + * to ensure that the coroutine is not entered concurrently. Then, + * while the coroutine has yielded, call qio_channel_attach_aio_context(), + * and then aio_co_schedule() to place the coroutine on the new + * #AioContext. The calls to qio_channel_detach_aio_context() + * and qio_channel_attach_aio_context() should be protected with + * aio_context_acquire() and aio_context_release(). + */ +void qio_channel_attach_aio_context(QIOChannel *ioc, + AioContext *ctx); + +/** + * qio_channel_detach_aio_context: + * @ioc: the channel object + * + * Disable any I/O handlers set by qio_channel_yield(). With the + * help of aio_co_schedule(), this allows moving a coroutine that was + * paused by qio_channel_yield() to another context. + */ +void qio_channel_detach_aio_context(QIOChannel *ioc); + +/** * qio_channel_yield: * @ioc: the channel object * @condition: the I/O condition to wait for * - * Yields execution from the current coroutine until - * the condition indicated by @condition becomes - * available. + * Yields execution from the current coroutine until the condition + * indicated by @condition becomes available. @condition must + * be either %G_IO_IN or %G_IO_OUT; it cannot contain both. In + * addition, no two coroutine can be waiting on the same condition + * and channel at the same time. * * This must only be called from coroutine context */ diff --git a/io/channel.c b/io/channel.c index XXXXXXX..XXXXXXX 100644 --- a/io/channel.c +++ b/io/channel.c @@ -XXX,XX +XXX,XX @@ #include "qemu/osdep.h" #include "io/channel.h" #include "qapi/error.h" -#include "qemu/coroutine.h" +#include "qemu/main-loop.h" bool qio_channel_has_feature(QIOChannel *ioc, QIOChannelFeature feature) @@ -XXX,XX +XXX,XX @@ off_t qio_channel_io_seek(QIOChannel *ioc, } -typedef struct QIOChannelYieldData QIOChannelYieldData; -struct QIOChannelYieldData { - QIOChannel *ioc; - Coroutine *co; -}; +static void qio_channel_set_aio_fd_handlers(QIOChannel *ioc); +static void qio_channel_restart_read(void *opaque) +{ + QIOChannel *ioc = opaque; + Coroutine *co = ioc->read_coroutine; + + ioc->read_coroutine = NULL; + qio_channel_set_aio_fd_handlers(ioc); + aio_co_wake(co); +} -static gboolean qio_channel_yield_enter(QIOChannel *ioc, - GIOCondition condition, - gpointer opaque) +static void qio_channel_restart_write(void *opaque) { - QIOChannelYieldData *data = opaque; - qemu_coroutine_enter(data->co); - return FALSE; + QIOChannel *ioc = opaque; + Coroutine *co = ioc->write_coroutine; + + ioc->write_coroutine = NULL; + qio_channel_set_aio_fd_handlers(ioc); + aio_co_wake(co); } +static void qio_channel_set_aio_fd_handlers(QIOChannel *ioc) +{ + IOHandler *rd_handler = NULL, *wr_handler = NULL; + AioContext *ctx; + + if (ioc->read_coroutine) { + rd_handler = qio_channel_restart_read; + } + if (ioc->write_coroutine) { + wr_handler = qio_channel_restart_write; + } + + ctx = ioc->ctx ? ioc->ctx : iohandler_get_aio_context(); + qio_channel_set_aio_fd_handler(ioc, ctx, rd_handler, wr_handler, ioc); +} + +void qio_channel_attach_aio_context(QIOChannel *ioc, + AioContext *ctx) +{ + AioContext *old_ctx; + if (ioc->ctx == ctx) { + return; + } + + old_ctx = ioc->ctx ? ioc->ctx : iohandler_get_aio_context(); + qio_channel_set_aio_fd_handler(ioc, old_ctx, NULL, NULL, NULL); + ioc->ctx = ctx; + qio_channel_set_aio_fd_handlers(ioc); +} + +void qio_channel_detach_aio_context(QIOChannel *ioc) +{ + ioc->read_coroutine = NULL; + ioc->write_coroutine = NULL; + qio_channel_set_aio_fd_handlers(ioc); + ioc->ctx = NULL; +} void coroutine_fn qio_channel_yield(QIOChannel *ioc, GIOCondition condition) { - QIOChannelYieldData data; - assert(qemu_in_coroutine()); - data.ioc = ioc; - data.co = qemu_coroutine_self(); - qio_channel_add_watch(ioc, - condition, - qio_channel_yield_enter, - &data, - NULL); + if (condition == G_IO_IN) { + assert(!ioc->read_coroutine); + ioc->read_coroutine = qemu_coroutine_self(); + } else if (condition == G_IO_OUT) { + assert(!ioc->write_coroutine); + ioc->write_coroutine = qemu_coroutine_self(); + } else { + abort(); + } + qio_channel_set_aio_fd_handlers(ioc); qemu_coroutine_yield(); } -- 2.9.3 From: Paolo Bonzini <pbonzini@redhat.com> In the client, read the reply headers from a coroutine, switching the read side between the "read header" coroutine and the I/O coroutine that reads the body of the reply. In the server, if the server can read more requests it will create a new "read request" coroutine as soon as a request has been read. Otherwise, the new coroutine is created in nbd_request_put. Reviewed-by: Stefan Hajnoczi <stefanha@redhat.com> Signed-off-by: Paolo Bonzini <pbonzini@redhat.com> Reviewed-by: Fam Zheng <famz@redhat.com> Reviewed-by: Daniel P. Berrange <berrange@redhat.com> Message-id: 20170213135235.12274-8-pbonzini@redhat.com Signed-off-by: Stefan Hajnoczi <stefanha@redhat.com> --- block/nbd-client.h | 2 +- block/nbd-client.c | 117 ++++++++++++++++++++++++----------------------------- nbd/client.c | 2 +- nbd/common.c | 9 +---- nbd/server.c | 94 +++++++++++++----------------------------- 5 files changed, 83 insertions(+), 141 deletions(-) diff --git a/block/nbd-client.h b/block/nbd-client.h index XXXXXXX..XXXXXXX 100644 --- a/block/nbd-client.h +++ b/block/nbd-client.h @@ -XXX,XX +XXX,XX @@ typedef struct NBDClientSession { CoMutex send_mutex; CoQueue free_sema; - Coroutine *send_coroutine; + Coroutine *read_reply_co; int in_flight; Coroutine *recv_coroutine[MAX_NBD_REQUESTS]; diff --git a/block/nbd-client.c b/block/nbd-client.c index XXXXXXX..XXXXXXX 100644 --- a/block/nbd-client.c +++ b/block/nbd-client.c @@ -XXX,XX +XXX,XX @@ #define HANDLE_TO_INDEX(bs, handle) ((handle) ^ ((uint64_t)(intptr_t)bs)) #define INDEX_TO_HANDLE(bs, index) ((index) ^ ((uint64_t)(intptr_t)bs)) -static void nbd_recv_coroutines_enter_all(NBDClientSession *s) +static void nbd_recv_coroutines_enter_all(BlockDriverState *bs) { + NBDClientSession *s = nbd_get_client_session(bs); int i; for (i = 0; i < MAX_NBD_REQUESTS; i++) { @@ -XXX,XX +XXX,XX @@ static void nbd_recv_coroutines_enter_all(NBDClientSession *s) qemu_coroutine_enter(s->recv_coroutine[i]); } } + BDRV_POLL_WHILE(bs, s->read_reply_co); } static void nbd_teardown_connection(BlockDriverState *bs) @@ -XXX,XX +XXX,XX @@ static void nbd_teardown_connection(BlockDriverState *bs) qio_channel_shutdown(client->ioc, QIO_CHANNEL_SHUTDOWN_BOTH, NULL); - nbd_recv_coroutines_enter_all(client); + nbd_recv_coroutines_enter_all(bs); nbd_client_detach_aio_context(bs); object_unref(OBJECT(client->sioc)); @@ -XXX,XX +XXX,XX @@ static void nbd_teardown_connection(BlockDriverState *bs) client->ioc = NULL; } -static void nbd_reply_ready(void *opaque) +static coroutine_fn void nbd_read_reply_entry(void *opaque) { - BlockDriverState *bs = opaque; - NBDClientSession *s = nbd_get_client_session(bs); + NBDClientSession *s = opaque; uint64_t i; int ret; - if (!s->ioc) { /* Already closed */ - return; - } - - if (s->reply.handle == 0) { - /* No reply already in flight. Fetch a header. It is possible - * that another thread has done the same thing in parallel, so - * the socket is not readable anymore. - */ + for (;;) { + assert(s->reply.handle == 0); ret = nbd_receive_reply(s->ioc, &s->reply); - if (ret == -EAGAIN) { - return; - } if (ret < 0) { - s->reply.handle = 0; - goto fail; + break; } - } - /* There's no need for a mutex on the receive side, because the - * handler acts as a synchronization point and ensures that only - * one coroutine is called until the reply finishes. */ - i = HANDLE_TO_INDEX(s, s->reply.handle); - if (i >= MAX_NBD_REQUESTS) { - goto fail; - } + /* There's no need for a mutex on the receive side, because the + * handler acts as a synchronization point and ensures that only + * one coroutine is called until the reply finishes. + */ + i = HANDLE_TO_INDEX(s, s->reply.handle); + if (i >= MAX_NBD_REQUESTS || !s->recv_coroutine[i]) { + break; + } - if (s->recv_coroutine[i]) { - qemu_coroutine_enter(s->recv_coroutine[i]); - return; + /* We're woken up by the recv_coroutine itself. Note that there + * is no race between yielding and reentering read_reply_co. This + * is because: + * + * - if recv_coroutine[i] runs on the same AioContext, it is only + * entered after we yield + * + * - if recv_coroutine[i] runs on a different AioContext, reentering + * read_reply_co happens through a bottom half, which can only + * run after we yield. + */ + aio_co_wake(s->recv_coroutine[i]); + qemu_coroutine_yield(); } - -fail: - nbd_teardown_connection(bs); -} - -static void nbd_restart_write(void *opaque) -{ - BlockDriverState *bs = opaque; - - qemu_coroutine_enter(nbd_get_client_session(bs)->send_coroutine); + s->read_reply_co = NULL; } static int nbd_co_send_request(BlockDriverState *bs, @@ -XXX,XX +XXX,XX @@ static int nbd_co_send_request(BlockDriverState *bs, QEMUIOVector *qiov) { NBDClientSession *s = nbd_get_client_session(bs); - AioContext *aio_context; int rc, ret, i; qemu_co_mutex_lock(&s->send_mutex); @@ -XXX,XX +XXX,XX @@ static int nbd_co_send_request(BlockDriverState *bs, return -EPIPE; } - s->send_coroutine = qemu_coroutine_self(); - aio_context = bdrv_get_aio_context(bs); - - aio_set_fd_handler(aio_context, s->sioc->fd, false, - nbd_reply_ready, nbd_restart_write, NULL, bs); if (qiov) { qio_channel_set_cork(s->ioc, true); rc = nbd_send_request(s->ioc, request); @@ -XXX,XX +XXX,XX @@ static int nbd_co_send_request(BlockDriverState *bs, } else { rc = nbd_send_request(s->ioc, request); } - aio_set_fd_handler(aio_context, s->sioc->fd, false, - nbd_reply_ready, NULL, NULL, bs); - s->send_coroutine = NULL; qemu_co_mutex_unlock(&s->send_mutex); return rc; } @@ -XXX,XX +XXX,XX @@ static void nbd_co_receive_reply(NBDClientSession *s, { int ret; - /* Wait until we're woken up by the read handler. TODO: perhaps - * peek at the next reply and avoid yielding if it's ours? */ + /* Wait until we're woken up by nbd_read_reply_entry. */ qemu_coroutine_yield(); *reply = s->reply; if (reply->handle != request->handle || @@ -XXX,XX +XXX,XX @@ static void nbd_coroutine_start(NBDClientSession *s, /* s->recv_coroutine[i] is set as soon as we get the send_lock. */ } -static void nbd_coroutine_end(NBDClientSession *s, +static void nbd_coroutine_end(BlockDriverState *bs, NBDRequest *request) { + NBDClientSession *s = nbd_get_client_session(bs); int i = HANDLE_TO_INDEX(s, request->handle); + s->recv_coroutine[i] = NULL; - if (s->in_flight-- == MAX_NBD_REQUESTS) { - qemu_co_queue_next(&s->free_sema); + s->in_flight--; + qemu_co_queue_next(&s->free_sema); + + /* Kick the read_reply_co to get the next reply. */ + if (s->read_reply_co) { + aio_co_wake(s->read_reply_co); } } @@ -XXX,XX +XXX,XX @@ int nbd_client_co_preadv(BlockDriverState *bs, uint64_t offset, } else { nbd_co_receive_reply(client, &request, &reply, qiov); } - nbd_coroutine_end(client, &request); + nbd_coroutine_end(bs, &request); return -reply.error; } @@ -XXX,XX +XXX,XX @@ int nbd_client_co_pwritev(BlockDriverState *bs, uint64_t offset, } else { nbd_co_receive_reply(client, &request, &reply, NULL); } - nbd_coroutine_end(client, &request); + nbd_coroutine_end(bs, &request); return -reply.error; } @@ -XXX,XX +XXX,XX @@ int nbd_client_co_pwrite_zeroes(BlockDriverState *bs, int64_t offset, } else { nbd_co_receive_reply(client, &request, &reply, NULL); } - nbd_coroutine_end(client, &request); + nbd_coroutine_end(bs, &request); return -reply.error; } @@ -XXX,XX +XXX,XX @@ int nbd_client_co_flush(BlockDriverState *bs) } else { nbd_co_receive_reply(client, &request, &reply, NULL); } - nbd_coroutine_end(client, &request); + nbd_coroutine_end(bs, &request); return -reply.error; } @@ -XXX,XX +XXX,XX @@ int nbd_client_co_pdiscard(BlockDriverState *bs, int64_t offset, int count) } else { nbd_co_receive_reply(client, &request, &reply, NULL); } - nbd_coroutine_end(client, &request); + nbd_coroutine_end(bs, &request); return -reply.error; } void nbd_client_detach_aio_context(BlockDriverState *bs) { - aio_set_fd_handler(bdrv_get_aio_context(bs), - nbd_get_client_session(bs)->sioc->fd, - false, NULL, NULL, NULL, NULL); + NBDClientSession *client = nbd_get_client_session(bs); + qio_channel_detach_aio_context(QIO_CHANNEL(client->sioc)); } void nbd_client_attach_aio_context(BlockDriverState *bs, AioContext *new_context) { - aio_set_fd_handler(new_context, nbd_get_client_session(bs)->sioc->fd, - false, nbd_reply_ready, NULL, NULL, bs); + NBDClientSession *client = nbd_get_client_session(bs); + qio_channel_attach_aio_context(QIO_CHANNEL(client->sioc), new_context); + aio_co_schedule(new_context, client->read_reply_co); } void nbd_client_close(BlockDriverState *bs) @@ -XXX,XX +XXX,XX @@ int nbd_client_init(BlockDriverState *bs, /* Now that we're connected, set the socket to be non-blocking and * kick the reply mechanism. */ qio_channel_set_blocking(QIO_CHANNEL(sioc), false, NULL); - + client->read_reply_co = qemu_coroutine_create(nbd_read_reply_entry, client); nbd_client_attach_aio_context(bs, bdrv_get_aio_context(bs)); logout("Established connection with NBD server\n"); diff --git a/nbd/client.c b/nbd/client.c index XXXXXXX..XXXXXXX 100644 --- a/nbd/client.c +++ b/nbd/client.c @@ -XXX,XX +XXX,XX @@ ssize_t nbd_receive_reply(QIOChannel *ioc, NBDReply *reply) ssize_t ret; ret = read_sync(ioc, buf, sizeof(buf)); - if (ret < 0) { + if (ret <= 0) { return ret; } diff --git a/nbd/common.c b/nbd/common.c index XXXXXXX..XXXXXXX 100644 --- a/nbd/common.c +++ b/nbd/common.c @@ -XXX,XX +XXX,XX @@ ssize_t nbd_wr_syncv(QIOChannel *ioc, } if (len == QIO_CHANNEL_ERR_BLOCK) { if (qemu_in_coroutine()) { - /* XXX figure out if we can create a variant on - * qio_channel_yield() that works with AIO contexts - * and consider using that in this branch */ - qemu_coroutine_yield(); - } else if (done) { - /* XXX this is needed by nbd_reply_ready. */ - qio_channel_wait(ioc, - do_read ? G_IO_IN : G_IO_OUT); + qio_channel_yield(ioc, do_read ? G_IO_IN : G_IO_OUT); } else { return -EAGAIN; } diff --git a/nbd/server.c b/nbd/server.c index XXXXXXX..XXXXXXX 100644 --- a/nbd/server.c +++ b/nbd/server.c @@ -XXX,XX +XXX,XX @@ struct NBDClient { CoMutex send_lock; Coroutine *send_coroutine; - bool can_read; - QTAILQ_ENTRY(NBDClient) next; int nb_requests; bool closing; @@ -XXX,XX +XXX,XX @@ struct NBDClient { /* That's all folks */ -static void nbd_set_handlers(NBDClient *client); -static void nbd_unset_handlers(NBDClient *client); -static void nbd_update_can_read(NBDClient *client); +static void nbd_client_receive_next_request(NBDClient *client); static gboolean nbd_negotiate_continue(QIOChannel *ioc, GIOCondition condition, @@ -XXX,XX +XXX,XX @@ void nbd_client_put(NBDClient *client) */ assert(client->closing); - nbd_unset_handlers(client); + qio_channel_detach_aio_context(client->ioc); object_unref(OBJECT(client->sioc)); object_unref(OBJECT(client->ioc)); if (client->tlscreds) { @@ -XXX,XX +XXX,XX @@ static NBDRequestData *nbd_request_get(NBDClient *client) assert(client->nb_requests <= MAX_NBD_REQUESTS - 1); client->nb_requests++; - nbd_update_can_read(client); req = g_new0(NBDRequestData, 1); nbd_client_get(client); @@ -XXX,XX +XXX,XX @@ static void nbd_request_put(NBDRequestData *req) g_free(req); client->nb_requests--; - nbd_update_can_read(client); + nbd_client_receive_next_request(client); + nbd_client_put(client); } @@ -XXX,XX +XXX,XX @@ static void blk_aio_attached(AioContext *ctx, void *opaque) exp->ctx = ctx; QTAILQ_FOREACH(client, &exp->clients, next) { - nbd_set_handlers(client); + qio_channel_attach_aio_context(client->ioc, ctx); + if (client->recv_coroutine) { + aio_co_schedule(ctx, client->recv_coroutine); + } + if (client->send_coroutine) { + aio_co_schedule(ctx, client->send_coroutine); + } } } @@ -XXX,XX +XXX,XX @@ static void blk_aio_detach(void *opaque) TRACE("Export %s: Detaching clients from AIO context %p\n", exp->name, exp->ctx); QTAILQ_FOREACH(client, &exp->clients, next) { - nbd_unset_handlers(client); + qio_channel_detach_aio_context(client->ioc); } exp->ctx = NULL; @@ -XXX,XX +XXX,XX @@ static ssize_t nbd_co_send_reply(NBDRequestData *req, NBDReply *reply, g_assert(qemu_in_coroutine()); qemu_co_mutex_lock(&client->send_lock); client->send_coroutine = qemu_coroutine_self(); - nbd_set_handlers(client); if (!len) { rc = nbd_send_reply(client->ioc, reply); @@ -XXX,XX +XXX,XX @@ static ssize_t nbd_co_send_reply(NBDRequestData *req, NBDReply *reply, } client->send_coroutine = NULL; - nbd_set_handlers(client); qemu_co_mutex_unlock(&client->send_lock); return rc; } @@ -XXX,XX +XXX,XX @@ static ssize_t nbd_co_receive_request(NBDRequestData *req, ssize_t rc; g_assert(qemu_in_coroutine()); - client->recv_coroutine = qemu_coroutine_self(); - nbd_update_can_read(client); - + assert(client->recv_coroutine == qemu_coroutine_self()); rc = nbd_receive_request(client->ioc, request); if (rc < 0) { if (rc != -EAGAIN) { @@ -XXX,XX +XXX,XX @@ static ssize_t nbd_co_receive_request(NBDRequestData *req, out: client->recv_coroutine = NULL; - nbd_update_can_read(client); + nbd_client_receive_next_request(client); return rc; } -static void nbd_trip(void *opaque) +/* Owns a reference to the NBDClient passed as opaque. */ +static coroutine_fn void nbd_trip(void *opaque) { NBDClient *client = opaque; NBDExport *exp = client->exp; NBDRequestData *req; - NBDRequest request; + NBDRequest request = { 0 }; /* GCC thinks it can be used uninitialized */ NBDReply reply; ssize_t ret; int flags; TRACE("Reading request."); if (client->closing) { + nbd_client_put(client); return; } @@ -XXX,XX +XXX,XX @@ static void nbd_trip(void *opaque) done: nbd_request_put(req); + nbd_client_put(client); return; out: nbd_request_put(req); client_close(client); + nbd_client_put(client); } -static void nbd_read(void *opaque) +static void nbd_client_receive_next_request(NBDClient *client) { - NBDClient *client = opaque; - - if (client->recv_coroutine) { - qemu_coroutine_enter(client->recv_coroutine); - } else { - qemu_coroutine_enter(qemu_coroutine_create(nbd_trip, client)); - } -} - -static void nbd_restart_write(void *opaque) -{ - NBDClient *client = opaque; - - qemu_coroutine_enter(client->send_coroutine); -} - -static void nbd_set_handlers(NBDClient *client) -{ - if (client->exp && client->exp->ctx) { - aio_set_fd_handler(client->exp->ctx, client->sioc->fd, true, - client->can_read ? nbd_read : NULL, - client->send_coroutine ? nbd_restart_write : NULL, - NULL, client); - } -} - -static void nbd_unset_handlers(NBDClient *client) -{ - if (client->exp && client->exp->ctx) { - aio_set_fd_handler(client->exp->ctx, client->sioc->fd, true, NULL, - NULL, NULL, NULL); - } -} - -static void nbd_update_can_read(NBDClient *client) -{ - bool can_read = client->recv_coroutine || - client->nb_requests < MAX_NBD_REQUESTS; - - if (can_read != client->can_read) { - client->can_read = can_read; - nbd_set_handlers(client); - - /* There is no need to invoke aio_notify(), since aio_set_fd_handler() - * in nbd_set_handlers() will have taken care of that */ + if (!client->recv_coroutine && client->nb_requests < MAX_NBD_REQUESTS) { + nbd_client_get(client); + client->recv_coroutine = qemu_coroutine_create(nbd_trip, client); + aio_co_schedule(client->exp->ctx, client->recv_coroutine); } } @@ -XXX,XX +XXX,XX @@ static coroutine_fn void nbd_co_client_start(void *opaque) goto out; } qemu_co_mutex_init(&client->send_lock); - nbd_set_handlers(client); if (exp) { QTAILQ_INSERT_TAIL(&exp->clients, client, next); } + + nbd_client_receive_next_request(client); + out: g_free(data); } @@ -XXX,XX +XXX,XX @@ void nbd_client_new(NBDExport *exp, object_ref(OBJECT(client->sioc)); client->ioc = QIO_CHANNEL(sioc); object_ref(OBJECT(client->ioc)); - client->can_read = true; client->close = close_fn; data->client = client; -- 2.9.3 From: Paolo Bonzini <pbonzini@redhat.com> As a small step towards the introduction of multiqueue, we want coroutines to remain on the same AioContext that started them, unless they are moved explicitly with e.g. aio_co_schedule. This patch avoids that coroutines switch AioContext when they use a CoMutex. For now it does not make much of a difference, because the CoMutex is not thread-safe and the AioContext itself is used to protect the CoMutex from concurrent access. However, this is going to change. Reviewed-by: Stefan Hajnoczi <stefanha@redhat.com> Signed-off-by: Paolo Bonzini <pbonzini@redhat.com> Reviewed-by: Fam Zheng <famz@redhat.com> Reviewed-by: Daniel P. Berrange <berrange@redhat.com> Message-id: 20170213135235.12274-9-pbonzini@redhat.com Signed-off-by: Stefan Hajnoczi <stefanha@redhat.com> --- util/qemu-coroutine-lock.c | 5 ++--- util/trace-events | 1 - 2 files changed, 2 insertions(+), 4 deletions(-) diff --git a/util/qemu-coroutine-lock.c b/util/qemu-coroutine-lock.c index XXXXXXX..XXXXXXX 100644 --- a/util/qemu-coroutine-lock.c +++ b/util/qemu-coroutine-lock.c @@ -XXX,XX +XXX,XX @@ #include "qemu/coroutine.h" #include "qemu/coroutine_int.h" #include "qemu/queue.h" +#include "block/aio.h" #include "trace.h" void qemu_co_queue_init(CoQueue *queue) @@ -XXX,XX +XXX,XX @@ void qemu_co_queue_run_restart(Coroutine *co) static bool qemu_co_queue_do_restart(CoQueue *queue, bool single) { - Coroutine *self = qemu_coroutine_self(); Coroutine *next; if (QSIMPLEQ_EMPTY(&queue->entries)) { @@ -XXX,XX +XXX,XX @@ static bool qemu_co_queue_do_restart(CoQueue *queue, bool single) while ((next = QSIMPLEQ_FIRST(&queue->entries)) != NULL) { QSIMPLEQ_REMOVE_HEAD(&queue->entries, co_queue_next); - QSIMPLEQ_INSERT_TAIL(&self->co_queue_wakeup, next, co_queue_next); - trace_qemu_co_queue_next(next); + aio_co_wake(next); if (single) { break; } diff --git a/util/trace-events b/util/trace-events index XXXXXXX..XXXXXXX 100644 --- a/util/trace-events +++ b/util/trace-events @@ -XXX,XX +XXX,XX @@ qemu_coroutine_terminate(void *co) "self %p" # util/qemu-coroutine-lock.c qemu_co_queue_run_restart(void *co) "co %p" -qemu_co_queue_next(void *nxt) "next %p" qemu_co_mutex_lock_entry(void *mutex, void *self) "mutex %p self %p" qemu_co_mutex_lock_return(void *mutex, void *self) "mutex %p self %p" qemu_co_mutex_unlock_entry(void *mutex, void *self) "mutex %p self %p" -- 2.9.3 From: Paolo Bonzini <pbonzini@redhat.com> Keep the coroutine on the same AioContext. Without this change, there would be a race between yielding the coroutine and reentering it. While the race cannot happen now, because the code only runs from a single AioContext, this will change with multiqueue support in the block layer. While doing the change, replace custom bottom half with aio_co_schedule. Signed-off-by: Paolo Bonzini <pbonzini@redhat.com> Reviewed-by: Fam Zheng <famz@redhat.com> Reviewed-by: Stefan Hajnoczi <stefanha@redhat.com> Reviewed-by: Daniel P. Berrange <berrange@redhat.com> Message-id: 20170213135235.12274-10-pbonzini@redhat.com Signed-off-by: Stefan Hajnoczi <stefanha@redhat.com> --- block/blkdebug.c | 9 +-------- 1 file changed, 1 insertion(+), 8 deletions(-) diff --git a/block/blkdebug.c b/block/blkdebug.c index XXXXXXX..XXXXXXX 100644 --- a/block/blkdebug.c +++ b/block/blkdebug.c @@ -XXX,XX +XXX,XX @@ out: return ret; } -static void error_callback_bh(void *opaque) -{ - Coroutine *co = opaque; - qemu_coroutine_enter(co); -} - static int inject_error(BlockDriverState *bs, BlkdebugRule *rule) { BDRVBlkdebugState *s = bs->opaque; @@ -XXX,XX +XXX,XX @@ static int inject_error(BlockDriverState *bs, BlkdebugRule *rule) } if (!immediately) { - aio_bh_schedule_oneshot(bdrv_get_aio_context(bs), error_callback_bh, - qemu_coroutine_self()); + aio_co_schedule(qemu_get_current_aio_context(), qemu_coroutine_self()); qemu_coroutine_yield(); } -- 2.9.3 From: Paolo Bonzini <pbonzini@redhat.com> qed_aio_start_io and qed_aio_next_io will not have to acquire/release the AioContext, while qed_aio_next_io_cb will. Split the functionality and gain a little type-safety in the process. Reviewed-by: Stefan Hajnoczi <stefanha@redhat.com> Signed-off-by: Paolo Bonzini <pbonzini@redhat.com> Reviewed-by: Fam Zheng <famz@redhat.com> Reviewed-by: Daniel P. Berrange <berrange@redhat.com> Message-id: 20170213135235.12274-11-pbonzini@redhat.com Signed-off-by: Stefan Hajnoczi <stefanha@redhat.com> --- block/qed.c | 39 +++++++++++++++++++++++++-------------- 1 file changed, 25 insertions(+), 14 deletions(-) diff --git a/block/qed.c b/block/qed.c index XXXXXXX..XXXXXXX 100644 --- a/block/qed.c +++ b/block/qed.c @@ -XXX,XX +XXX,XX @@ static CachedL2Table *qed_new_l2_table(BDRVQEDState *s) return l2_table; } -static void qed_aio_next_io(void *opaque, int ret); +static void qed_aio_next_io(QEDAIOCB *acb, int ret); + +static void qed_aio_start_io(QEDAIOCB *acb) +{ + qed_aio_next_io(acb, 0); +} + +static void qed_aio_next_io_cb(void *opaque, int ret) +{ + QEDAIOCB *acb = opaque; + + qed_aio_next_io(acb, ret); +} static void qed_plug_allocating_write_reqs(BDRVQEDState *s) { @@ -XXX,XX +XXX,XX @@ static void qed_unplug_allocating_write_reqs(BDRVQEDState *s) acb = QSIMPLEQ_FIRST(&s->allocating_write_reqs); if (acb) { - qed_aio_next_io(acb, 0); + qed_aio_start_io(acb); } } @@ -XXX,XX +XXX,XX @@ static void qed_aio_complete(QEDAIOCB *acb, int ret) QSIMPLEQ_REMOVE_HEAD(&s->allocating_write_reqs, next); acb = QSIMPLEQ_FIRST(&s->allocating_write_reqs); if (acb) { - qed_aio_next_io(acb, 0); + qed_aio_start_io(acb); } else if (s->header.features & QED_F_NEED_CHECK) { qed_start_need_check_timer(s); } @@ -XXX,XX +XXX,XX @@ static void qed_commit_l2_update(void *opaque, int ret) acb->request.l2_table = qed_find_l2_cache_entry(&s->l2_cache, l2_offset); assert(acb->request.l2_table != NULL); - qed_aio_next_io(opaque, ret); + qed_aio_next_io(acb, ret); } /** @@ -XXX,XX +XXX,XX @@ static void qed_aio_write_l2_update(QEDAIOCB *acb, int ret, uint64_t offset) if (need_alloc) { /* Write out the whole new L2 table */ qed_write_l2_table(s, &acb->request, 0, s->table_nelems, true, - qed_aio_write_l1_update, acb); + qed_aio_write_l1_update, acb); } else { /* Write out only the updated part of the L2 table */ qed_write_l2_table(s, &acb->request, index, acb->cur_nclusters, false, - qed_aio_next_io, acb); + qed_aio_next_io_cb, acb); } return; @@ -XXX,XX +XXX,XX @@ static void qed_aio_write_main(void *opaque, int ret) } if (acb->find_cluster_ret == QED_CLUSTER_FOUND) { - next_fn = qed_aio_next_io; + next_fn = qed_aio_next_io_cb; } else { if (s->bs->backing) { next_fn = qed_aio_write_flush_before_l2_update; @@ -XXX,XX +XXX,XX @@ static void qed_aio_write_alloc(QEDAIOCB *acb, size_t len) if (acb->flags & QED_AIOCB_ZERO) { /* Skip ahead if the clusters are already zero */ if (acb->find_cluster_ret == QED_CLUSTER_ZERO) { - qed_aio_next_io(acb, 0); + qed_aio_start_io(acb); return; } @@ -XXX,XX +XXX,XX @@ static void qed_aio_read_data(void *opaque, int ret, /* Handle zero cluster and backing file reads */ if (ret == QED_CLUSTER_ZERO) { qemu_iovec_memset(&acb->cur_qiov, 0, 0, acb->cur_qiov.size); - qed_aio_next_io(acb, 0); + qed_aio_start_io(acb); return; } else if (ret != QED_CLUSTER_FOUND) { qed_read_backing_file(s, acb->cur_pos, &acb->cur_qiov, - &acb->backing_qiov, qed_aio_next_io, acb); + &acb->backing_qiov, qed_aio_next_io_cb, acb); return; } BLKDBG_EVENT(bs->file, BLKDBG_READ_AIO); bdrv_aio_readv(bs->file, offset / BDRV_SECTOR_SIZE, &acb->cur_qiov, acb->cur_qiov.size / BDRV_SECTOR_SIZE, - qed_aio_next_io, acb); + qed_aio_next_io_cb, acb); return; err: @@ -XXX,XX +XXX,XX @@ err: /** * Begin next I/O or complete the request */ -static void qed_aio_next_io(void *opaque, int ret) +static void qed_aio_next_io(QEDAIOCB *acb, int ret) { - QEDAIOCB *acb = opaque; BDRVQEDState *s = acb_to_s(acb); QEDFindClusterFunc *io_fn = (acb->flags & QED_AIOCB_WRITE) ? qed_aio_write_data : qed_aio_read_data; @@ -XXX,XX +XXX,XX @@ static BlockAIOCB *qed_aio_setup(BlockDriverState *bs, qemu_iovec_init(&acb->cur_qiov, qiov->niov); /* Start request */ - qed_aio_next_io(acb, 0); + qed_aio_start_io(acb); return &acb->common; } -- 2.9.3 From: Paolo Bonzini <pbonzini@redhat.com> The AioContext data structures are now protected by list_lock and/or they are walked with FOREACH_RCU primitives. There is no need anymore to acquire the AioContext for the entire duration of aio_dispatch. Instead, just acquire it before and after invoking the callbacks. The next step is then to push it further down. Reviewed-by: Stefan Hajnoczi <stefanha@redhat.com> Signed-off-by: Paolo Bonzini <pbonzini@redhat.com> Reviewed-by: Fam Zheng <famz@redhat.com> Reviewed-by: Daniel P. Berrange <berrange@redhat.com> Message-id: 20170213135235.12274-12-pbonzini@redhat.com Signed-off-by: Stefan Hajnoczi <stefanha@redhat.com> --- util/aio-posix.c | 25 +++++++++++-------------- util/aio-win32.c | 15 +++++++-------- util/async.c | 2 ++ 3 files changed, 20 insertions(+), 22 deletions(-) diff --git a/util/aio-posix.c b/util/aio-posix.c index XXXXXXX..XXXXXXX 100644 --- a/util/aio-posix.c +++ b/util/aio-posix.c @@ -XXX,XX +XXX,XX @@ static bool aio_dispatch_handlers(AioContext *ctx) (revents & (G_IO_IN | G_IO_HUP | G_IO_ERR)) && aio_node_check(ctx, node->is_external) && node->io_read) { + aio_context_acquire(ctx); node->io_read(node->opaque); + aio_context_release(ctx); /* aio_notify() does not count as progress */ if (node->opaque != &ctx->notifier) { @@ -XXX,XX +XXX,XX @@ static bool aio_dispatch_handlers(AioContext *ctx) (revents & (G_IO_OUT | G_IO_ERR)) && aio_node_check(ctx, node->is_external) && node->io_write) { + aio_context_acquire(ctx); node->io_write(node->opaque); + aio_context_release(ctx); progress = true; } @@ -XXX,XX +XXX,XX @@ bool aio_dispatch(AioContext *ctx, bool dispatch_fds) } /* Run our timers */ + aio_context_acquire(ctx); progress |= timerlistgroup_run_timers(&ctx->tlg); + aio_context_release(ctx); return progress; } @@ -XXX,XX +XXX,XX @@ bool aio_poll(AioContext *ctx, bool blocking) int64_t timeout; int64_t start = 0; - aio_context_acquire(ctx); - progress = false; - /* aio_notify can avoid the expensive event_notifier_set if * everything (file descriptors, bottom halves, timers) will * be re-evaluated before the next blocking poll(). This is @@ -XXX,XX +XXX,XX @@ bool aio_poll(AioContext *ctx, bool blocking) start = qemu_clock_get_ns(QEMU_CLOCK_REALTIME); } - if (try_poll_mode(ctx, blocking)) { - progress = true; - } else { + aio_context_acquire(ctx); + progress = try_poll_mode(ctx, blocking); + aio_context_release(ctx); + + if (!progress) { assert(npfd == 0); /* fill pollfds */ @@ -XXX,XX +XXX,XX @@ bool aio_poll(AioContext *ctx, bool blocking) timeout = blocking ? aio_compute_timeout(ctx) : 0; /* wait until next event */ - if (timeout) { - aio_context_release(ctx); - } if (aio_epoll_check_poll(ctx, pollfds, npfd, timeout)) { AioHandler epoll_handler; @@ -XXX,XX +XXX,XX @@ bool aio_poll(AioContext *ctx, bool blocking) } else { ret = qemu_poll_ns(pollfds, npfd, timeout); } - if (timeout) { - aio_context_acquire(ctx); - } } if (blocking) { @@ -XXX,XX +XXX,XX @@ bool aio_poll(AioContext *ctx, bool blocking) progress = true; } - aio_context_release(ctx); - return progress; } diff --git a/util/aio-win32.c b/util/aio-win32.c index XXXXXXX..XXXXXXX 100644 --- a/util/aio-win32.c +++ b/util/aio-win32.c @@ -XXX,XX +XXX,XX @@ static bool aio_dispatch_handlers(AioContext *ctx, HANDLE event) (revents || event_notifier_get_handle(node->e) == event) && node->io_notify) { node->pfd.revents = 0; + aio_context_acquire(ctx); node->io_notify(node->e); + aio_context_release(ctx); /* aio_notify() does not count as progress */ if (node->e != &ctx->notifier) { @@ -XXX,XX +XXX,XX @@ static bool aio_dispatch_handlers(AioContext *ctx, HANDLE event) (node->io_read || node->io_write)) { node->pfd.revents = 0; if ((revents & G_IO_IN) && node->io_read) { + aio_context_acquire(ctx); node->io_read(node->opaque); + aio_context_release(ctx); progress = true; } if ((revents & G_IO_OUT) && node->io_write) { + aio_context_acquire(ctx); node->io_write(node->opaque); + aio_context_release(ctx); progress = true; } @@ -XXX,XX +XXX,XX @@ bool aio_poll(AioContext *ctx, bool blocking) int count; int timeout; - aio_context_acquire(ctx); progress = false; /* aio_notify can avoid the expensive event_notifier_set if @@ -XXX,XX +XXX,XX @@ bool aio_poll(AioContext *ctx, bool blocking) timeout = blocking && !have_select_revents ? qemu_timeout_ns_to_ms(aio_compute_timeout(ctx)) : 0; - if (timeout) { - aio_context_release(ctx); - } ret = WaitForMultipleObjects(count, events, FALSE, timeout); if (blocking) { assert(first); atomic_sub(&ctx->notify_me, 2); } - if (timeout) { - aio_context_acquire(ctx); - } if (first) { aio_notify_accept(ctx); @@ -XXX,XX +XXX,XX @@ bool aio_poll(AioContext *ctx, bool blocking) progress |= aio_dispatch_handlers(ctx, event); } while (count > 0); + aio_context_acquire(ctx); progress |= timerlistgroup_run_timers(&ctx->tlg); - aio_context_release(ctx); return progress; } diff --git a/util/async.c b/util/async.c index XXXXXXX..XXXXXXX 100644 --- a/util/async.c +++ b/util/async.c @@ -XXX,XX +XXX,XX @@ int aio_bh_poll(AioContext *ctx) ret = 1; } bh->idle = 0; + aio_context_acquire(ctx); aio_bh_call(bh); + aio_context_release(ctx); } if (bh->deleted) { deleted = true; -- 2.9.3 From: Paolo Bonzini <pbonzini@redhat.com> Reviewed-by: Stefan Hajnoczi <stefanha@redhat.com> Signed-off-by: Paolo Bonzini <pbonzini@redhat.com> Reviewed-by: Fam Zheng <famz@redhat.com> Reviewed-by: Daniel P. Berrange <berrange@redhat.com> Message-id: 20170213135235.12274-13-pbonzini@redhat.com Signed-off-by: Stefan Hajnoczi <stefanha@redhat.com> --- block/qed.h | 3 +++ block/curl.c | 2 ++ block/io.c | 5 +++++ block/iscsi.c | 8 ++++++-- block/null.c | 4 ++++ block/qed.c | 12 ++++++++++++ block/throttle-groups.c | 2 ++ util/aio-posix.c | 2 -- util/aio-win32.c | 2 -- util/qemu-coroutine-sleep.c | 2 +- 10 files changed, 35 insertions(+), 7 deletions(-) diff --git a/block/qed.h b/block/qed.h index XXXXXXX..XXXXXXX 100644 --- a/block/qed.h +++ b/block/qed.h @@ -XXX,XX +XXX,XX @@ enum { */ typedef void QEDFindClusterFunc(void *opaque, int ret, uint64_t offset, size_t len); +void qed_acquire(BDRVQEDState *s); +void qed_release(BDRVQEDState *s); + /** * Generic callback for chaining async callbacks */ diff --git a/block/curl.c b/block/curl.c index XXXXXXX..XXXXXXX 100644 --- a/block/curl.c +++ b/block/curl.c @@ -XXX,XX +XXX,XX @@ static void curl_multi_timeout_do(void *arg) return; } + aio_context_acquire(s->aio_context); curl_multi_socket_action(s->multi, CURL_SOCKET_TIMEOUT, 0, &running); curl_multi_check_completion(s); + aio_context_release(s->aio_context); #else abort(); #endif diff --git a/block/io.c b/block/io.c index XXXXXXX..XXXXXXX 100644 --- a/block/io.c +++ b/block/io.c @@ -XXX,XX +XXX,XX @@ void bdrv_aio_cancel(BlockAIOCB *acb) if (acb->aiocb_info->get_aio_context) { aio_poll(acb->aiocb_info->get_aio_context(acb), true); } else if (acb->bs) { + /* qemu_aio_ref and qemu_aio_unref are not thread-safe, so + * assert that we're not using an I/O thread. Thread-safe + * code should use bdrv_aio_cancel_async exclusively. + */ + assert(bdrv_get_aio_context(acb->bs) == qemu_get_aio_context()); aio_poll(bdrv_get_aio_context(acb->bs), true); } else { abort(); diff --git a/block/iscsi.c b/block/iscsi.c index XXXXXXX..XXXXXXX 100644 --- a/block/iscsi.c +++ b/block/iscsi.c @@ -XXX,XX +XXX,XX @@ static void iscsi_retry_timer_expired(void *opaque) struct IscsiTask *iTask = opaque; iTask->complete = 1; if (iTask->co) { - qemu_coroutine_enter(iTask->co); + aio_co_wake(iTask->co); } } @@ -XXX,XX +XXX,XX @@ static void iscsi_nop_timed_event(void *opaque) { IscsiLun *iscsilun = opaque; + aio_context_acquire(iscsilun->aio_context); if (iscsi_get_nops_in_flight(iscsilun->iscsi) >= MAX_NOP_FAILURES) { error_report("iSCSI: NOP timeout. Reconnecting..."); iscsilun->request_timed_out = true; } else if (iscsi_nop_out_async(iscsilun->iscsi, NULL, NULL, 0, NULL) != 0) { error_report("iSCSI: failed to sent NOP-Out. Disabling NOP messages."); - return; + goto out; } timer_mod(iscsilun->nop_timer, qemu_clock_get_ms(QEMU_CLOCK_REALTIME) + NOP_INTERVAL); iscsi_set_events(iscsilun); + +out: + aio_context_release(iscsilun->aio_context); } static void iscsi_readcapacity_sync(IscsiLun *iscsilun, Error **errp) diff --git a/block/null.c b/block/null.c index XXXXXXX..XXXXXXX 100644 --- a/block/null.c +++ b/block/null.c @@ -XXX,XX +XXX,XX @@ static void null_bh_cb(void *opaque) static void null_timer_cb(void *opaque) { NullAIOCB *acb = opaque; + AioContext *ctx = bdrv_get_aio_context(acb->common.bs); + + aio_context_acquire(ctx); acb->common.cb(acb->common.opaque, 0); + aio_context_release(ctx); timer_deinit(&acb->timer); qemu_aio_unref(acb); } diff --git a/block/qed.c b/block/qed.c index XXXXXXX..XXXXXXX 100644 --- a/block/qed.c +++ b/block/qed.c @@ -XXX,XX +XXX,XX @@ static void qed_need_check_timer_cb(void *opaque) trace_qed_need_check_timer_cb(s); + qed_acquire(s); qed_plug_allocating_write_reqs(s); /* Ensure writes are on disk before clearing flag */ bdrv_aio_flush(s->bs->file->bs, qed_clear_need_check, s); + qed_release(s); +} + +void qed_acquire(BDRVQEDState *s) +{ + aio_context_acquire(bdrv_get_aio_context(s->bs)); +} + +void qed_release(BDRVQEDState *s) +{ + aio_context_release(bdrv_get_aio_context(s->bs)); } static void qed_start_need_check_timer(BDRVQEDState *s) diff --git a/block/throttle-groups.c b/block/throttle-groups.c index XXXXXXX..XXXXXXX 100644 --- a/block/throttle-groups.c +++ b/block/throttle-groups.c @@ -XXX,XX +XXX,XX @@ static void timer_cb(BlockBackend *blk, bool is_write) qemu_mutex_unlock(&tg->lock); /* Run the request that was waiting for this timer */ + aio_context_acquire(blk_get_aio_context(blk)); empty_queue = !qemu_co_enter_next(&blkp->throttled_reqs[is_write]); + aio_context_release(blk_get_aio_context(blk)); /* If the request queue was empty then we have to take care of * scheduling the next one */ diff --git a/util/aio-posix.c b/util/aio-posix.c index XXXXXXX..XXXXXXX 100644 --- a/util/aio-posix.c +++ b/util/aio-posix.c @@ -XXX,XX +XXX,XX @@ bool aio_dispatch(AioContext *ctx, bool dispatch_fds) } /* Run our timers */ - aio_context_acquire(ctx); progress |= timerlistgroup_run_timers(&ctx->tlg); - aio_context_release(ctx); return progress; } diff --git a/util/aio-win32.c b/util/aio-win32.c index XXXXXXX..XXXXXXX 100644 --- a/util/aio-win32.c +++ b/util/aio-win32.c @@ -XXX,XX +XXX,XX @@ bool aio_poll(AioContext *ctx, bool blocking) progress |= aio_dispatch_handlers(ctx, event); } while (count > 0); - aio_context_acquire(ctx); progress |= timerlistgroup_run_timers(&ctx->tlg); - aio_context_release(ctx); return progress; } diff --git a/util/qemu-coroutine-sleep.c b/util/qemu-coroutine-sleep.c index XXXXXXX..XXXXXXX 100644 --- a/util/qemu-coroutine-sleep.c +++ b/util/qemu-coroutine-sleep.c @@ -XXX,XX +XXX,XX @@ static void co_sleep_cb(void *opaque) { CoSleepCB *sleep_cb = opaque; - qemu_coroutine_enter(sleep_cb->co); + aio_co_wake(sleep_cb->co); } void coroutine_fn co_aio_sleep_ns(AioContext *ctx, QEMUClockType type, -- 2.9.3 From: Paolo Bonzini <pbonzini@redhat.com> This covers both file descriptor callbacks and polling callbacks, since they execute related code. Reviewed-by: Stefan Hajnoczi <stefanha@redhat.com> Signed-off-by: Paolo Bonzini <pbonzini@redhat.com> Reviewed-by: Fam Zheng <famz@redhat.com> Reviewed-by: Daniel P. Berrange <berrange@redhat.com> Message-id: 20170213135235.12274-14-pbonzini@redhat.com Signed-off-by: Stefan Hajnoczi <stefanha@redhat.com> --- block/curl.c | 16 +++++++++++++--- block/iscsi.c | 4 ++++ block/linux-aio.c | 4 ++++ block/nfs.c | 6 ++++++ block/sheepdog.c | 29 +++++++++++++++-------------- block/ssh.c | 29 +++++++++-------------------- block/win32-aio.c | 10 ++++++---- hw/block/virtio-blk.c | 5 ++++- hw/scsi/virtio-scsi.c | 7 +++++++ util/aio-posix.c | 7 ------- util/aio-win32.c | 6 ------ 11 files changed, 68 insertions(+), 55 deletions(-) diff --git a/block/curl.c b/block/curl.c index XXXXXXX..XXXXXXX 100644 --- a/block/curl.c +++ b/block/curl.c @@ -XXX,XX +XXX,XX @@ static void curl_multi_check_completion(BDRVCURLState *s) } } -static void curl_multi_do(void *arg) +static void curl_multi_do_locked(CURLState *s) { - CURLState *s = (CURLState *)arg; CURLSocket *socket, *next_socket; int running; int r; @@ -XXX,XX +XXX,XX @@ static void curl_multi_do(void *arg) } } +static void curl_multi_do(void *arg) +{ + CURLState *s = (CURLState *)arg; + + aio_context_acquire(s->s->aio_context); + curl_multi_do_locked(s); + aio_context_release(s->s->aio_context); +} + static void curl_multi_read(void *arg) { CURLState *s = (CURLState *)arg; - curl_multi_do(arg); + aio_context_acquire(s->s->aio_context); + curl_multi_do_locked(s); curl_multi_check_completion(s->s); + aio_context_release(s->s->aio_context); } static void curl_multi_timeout_do(void *arg) diff --git a/block/iscsi.c b/block/iscsi.c index XXXXXXX..XXXXXXX 100644 --- a/block/iscsi.c +++ b/block/iscsi.c @@ -XXX,XX +XXX,XX @@ iscsi_process_read(void *arg) IscsiLun *iscsilun = arg; struct iscsi_context *iscsi = iscsilun->iscsi; + aio_context_acquire(iscsilun->aio_context); iscsi_service(iscsi, POLLIN); iscsi_set_events(iscsilun); + aio_context_release(iscsilun->aio_context); } static void @@ -XXX,XX +XXX,XX @@ iscsi_process_write(void *arg) IscsiLun *iscsilun = arg; struct iscsi_context *iscsi = iscsilun->iscsi; + aio_context_acquire(iscsilun->aio_context); iscsi_service(iscsi, POLLOUT); iscsi_set_events(iscsilun); + aio_context_release(iscsilun->aio_context); } static int64_t sector_lun2qemu(int64_t sector, IscsiLun *iscsilun) diff --git a/block/linux-aio.c b/block/linux-aio.c index XXXXXXX..XXXXXXX 100644 --- a/block/linux-aio.c +++ b/block/linux-aio.c @@ -XXX,XX +XXX,XX @@ static void qemu_laio_completion_cb(EventNotifier *e) LinuxAioState *s = container_of(e, LinuxAioState, e); if (event_notifier_test_and_clear(&s->e)) { + aio_context_acquire(s->aio_context); qemu_laio_process_completions_and_submit(s); + aio_context_release(s->aio_context); } } @@ -XXX,XX +XXX,XX @@ static bool qemu_laio_poll_cb(void *opaque) return false; } + aio_context_acquire(s->aio_context); qemu_laio_process_completions_and_submit(s); + aio_context_release(s->aio_context); return true; } diff --git a/block/nfs.c b/block/nfs.c index XXXXXXX..XXXXXXX 100644 --- a/block/nfs.c +++ b/block/nfs.c @@ -XXX,XX +XXX,XX @@ static void nfs_set_events(NFSClient *client) static void nfs_process_read(void *arg) { NFSClient *client = arg; + + aio_context_acquire(client->aio_context); nfs_service(client->context, POLLIN); nfs_set_events(client); + aio_context_release(client->aio_context); } static void nfs_process_write(void *arg) { NFSClient *client = arg; + + aio_context_acquire(client->aio_context); nfs_service(client->context, POLLOUT); nfs_set_events(client); + aio_context_release(client->aio_context); } static void nfs_co_init_task(BlockDriverState *bs, NFSRPC *task) diff --git a/block/sheepdog.c b/block/sheepdog.c index XXXXXXX..XXXXXXX 100644 --- a/block/sheepdog.c +++ b/block/sheepdog.c @@ -XXX,XX +XXX,XX @@ static coroutine_fn int send_co_req(int sockfd, SheepdogReq *hdr, void *data, return ret; } -static void restart_co_req(void *opaque) -{ - Coroutine *co = opaque; - - qemu_coroutine_enter(co); -} - typedef struct SheepdogReqCo { int sockfd; BlockDriverState *bs; @@ -XXX,XX +XXX,XX @@ typedef struct SheepdogReqCo { unsigned int *rlen; int ret; bool finished; + Coroutine *co; } SheepdogReqCo; +static void restart_co_req(void *opaque) +{ + SheepdogReqCo *srco = opaque; + + aio_co_wake(srco->co); +} + static coroutine_fn void do_co_req(void *opaque) { int ret; - Coroutine *co; SheepdogReqCo *srco = opaque; int sockfd = srco->sockfd; SheepdogReq *hdr = srco->hdr; @@ -XXX,XX +XXX,XX @@ static coroutine_fn void do_co_req(void *opaque) unsigned int *wlen = srco->wlen; unsigned int *rlen = srco->rlen; - co = qemu_coroutine_self(); + srco->co = qemu_coroutine_self(); aio_set_fd_handler(srco->aio_context, sockfd, false, - NULL, restart_co_req, NULL, co); + NULL, restart_co_req, NULL, srco); ret = send_co_req(sockfd, hdr, data, wlen); if (ret < 0) { @@ -XXX,XX +XXX,XX @@ static coroutine_fn void do_co_req(void *opaque) } aio_set_fd_handler(srco->aio_context, sockfd, false, - restart_co_req, NULL, NULL, co); + restart_co_req, NULL, NULL, srco); ret = qemu_co_recv(sockfd, hdr, sizeof(*hdr)); if (ret != sizeof(*hdr)) { @@ -XXX,XX +XXX,XX @@ out: aio_set_fd_handler(srco->aio_context, sockfd, false, NULL, NULL, NULL, NULL); + srco->co = NULL; srco->ret = ret; srco->finished = true; if (srco->bs) { @@ -XXX,XX +XXX,XX @@ static void coroutine_fn aio_read_response(void *opaque) * We've finished all requests which belong to the AIOCB, so * we can switch back to sd_co_readv/writev now. */ - qemu_coroutine_enter(acb->coroutine); + aio_co_wake(acb->coroutine); } return; @@ -XXX,XX +XXX,XX @@ static void co_read_response(void *opaque) s->co_recv = qemu_coroutine_create(aio_read_response, opaque); } - qemu_coroutine_enter(s->co_recv); + aio_co_wake(s->co_recv); } static void co_write_request(void *opaque) { BDRVSheepdogState *s = opaque; - qemu_coroutine_enter(s->co_send); + aio_co_wake(s->co_send); } /* diff --git a/block/ssh.c b/block/ssh.c index XXXXXXX..XXXXXXX 100644 --- a/block/ssh.c +++ b/block/ssh.c @@ -XXX,XX +XXX,XX @@ static void restart_coroutine(void *opaque) DPRINTF("co=%p", co); - qemu_coroutine_enter(co); + aio_co_wake(co); } -static coroutine_fn void set_fd_handler(BDRVSSHState *s, BlockDriverState *bs) +/* A non-blocking call returned EAGAIN, so yield, ensuring the + * handlers are set up so that we'll be rescheduled when there is an + * interesting event on the socket. + */ +static coroutine_fn void co_yield(BDRVSSHState *s, BlockDriverState *bs) { int r; IOHandler *rd_handler = NULL, *wr_handler = NULL; @@ -XXX,XX +XXX,XX @@ static coroutine_fn void set_fd_handler(BDRVSSHState *s, BlockDriverState *bs) aio_set_fd_handler(bdrv_get_aio_context(bs), s->sock, false, rd_handler, wr_handler, NULL, co); -} - -static coroutine_fn void clear_fd_handler(BDRVSSHState *s, - BlockDriverState *bs) -{ - DPRINTF("s->sock=%d", s->sock); - aio_set_fd_handler(bdrv_get_aio_context(bs), s->sock, - false, NULL, NULL, NULL, NULL); -} - -/* A non-blocking call returned EAGAIN, so yield, ensuring the - * handlers are set up so that we'll be rescheduled when there is an - * interesting event on the socket. - */ -static coroutine_fn void co_yield(BDRVSSHState *s, BlockDriverState *bs) -{ - set_fd_handler(s, bs); qemu_coroutine_yield(); - clear_fd_handler(s, bs); + DPRINTF("s->sock=%d - back", s->sock); + aio_set_fd_handler(bdrv_get_aio_context(bs), s->sock, false, + NULL, NULL, NULL, NULL); } /* SFTP has a function `libssh2_sftp_seek64' which seeks to a position diff --git a/block/win32-aio.c b/block/win32-aio.c index XXXXXXX..XXXXXXX 100644 --- a/block/win32-aio.c +++ b/block/win32-aio.c @@ -XXX,XX +XXX,XX @@ struct QEMUWin32AIOState { HANDLE hIOCP; EventNotifier e; int count; - bool is_aio_context_attached; + AioContext *aio_ctx; }; typedef struct QEMUWin32AIOCB { @@ -XXX,XX +XXX,XX @@ static void win32_aio_process_completion(QEMUWin32AIOState *s, } + aio_context_acquire(s->aio_ctx); waiocb->common.cb(waiocb->common.opaque, ret); + aio_context_release(s->aio_ctx); qemu_aio_unref(waiocb); } @@ -XXX,XX +XXX,XX @@ void win32_aio_detach_aio_context(QEMUWin32AIOState *aio, AioContext *old_context) { aio_set_event_notifier(old_context, &aio->e, false, NULL, NULL); - aio->is_aio_context_attached = false; + aio->aio_ctx = NULL; } void win32_aio_attach_aio_context(QEMUWin32AIOState *aio, AioContext *new_context) { - aio->is_aio_context_attached = true; + aio->aio_ctx = new_context; aio_set_event_notifier(new_context, &aio->e, false, win32_aio_completion_cb, NULL); } @@ -XXX,XX +XXX,XX @@ out_free_state: void win32_aio_cleanup(QEMUWin32AIOState *aio) { - assert(!aio->is_aio_context_attached); + assert(!aio->aio_ctx); CloseHandle(aio->hIOCP); event_notifier_cleanup(&aio->e); g_free(aio); diff --git a/hw/block/virtio-blk.c b/hw/block/virtio-blk.c index XXXXXXX..XXXXXXX 100644 --- a/hw/block/virtio-blk.c +++ b/hw/block/virtio-blk.c @@ -XXX,XX +XXX,XX @@ static void virtio_blk_ioctl_complete(void *opaque, int status) { VirtIOBlockIoctlReq *ioctl_req = opaque; VirtIOBlockReq *req = ioctl_req->req; - VirtIODevice *vdev = VIRTIO_DEVICE(req->dev); + VirtIOBlock *s = req->dev; + VirtIODevice *vdev = VIRTIO_DEVICE(s); struct virtio_scsi_inhdr *scsi; struct sg_io_hdr *hdr; @@ -XXX,XX +XXX,XX @@ bool virtio_blk_handle_vq(VirtIOBlock *s, VirtQueue *vq) MultiReqBuffer mrb = {}; bool progress = false; + aio_context_acquire(blk_get_aio_context(s->blk)); blk_io_plug(s->blk); do { @@ -XXX,XX +XXX,XX @@ bool virtio_blk_handle_vq(VirtIOBlock *s, VirtQueue *vq) } blk_io_unplug(s->blk); + aio_context_release(blk_get_aio_context(s->blk)); return progress; } diff --git a/hw/scsi/virtio-scsi.c b/hw/scsi/virtio-scsi.c index XXXXXXX..XXXXXXX 100644 --- a/hw/scsi/virtio-scsi.c +++ b/hw/scsi/virtio-scsi.c @@ -XXX,XX +XXX,XX @@ bool virtio_scsi_handle_ctrl_vq(VirtIOSCSI *s, VirtQueue *vq) VirtIOSCSIReq *req; bool progress = false; + virtio_scsi_acquire(s); while ((req = virtio_scsi_pop_req(s, vq))) { progress = true; virtio_scsi_handle_ctrl_req(s, req); } + virtio_scsi_release(s); return progress; } @@ -XXX,XX +XXX,XX @@ bool virtio_scsi_handle_cmd_vq(VirtIOSCSI *s, VirtQueue *vq) QTAILQ_HEAD(, VirtIOSCSIReq) reqs = QTAILQ_HEAD_INITIALIZER(reqs); + virtio_scsi_acquire(s); do { virtio_queue_set_notification(vq, 0); @@ -XXX,XX +XXX,XX @@ bool virtio_scsi_handle_cmd_vq(VirtIOSCSI *s, VirtQueue *vq) QTAILQ_FOREACH_SAFE(req, &reqs, next, next) { virtio_scsi_handle_cmd_req_submit(s, req); } + virtio_scsi_release(s); return progress; } @@ -XXX,XX +XXX,XX @@ out: bool virtio_scsi_handle_event_vq(VirtIOSCSI *s, VirtQueue *vq) { + virtio_scsi_acquire(s); if (s->events_dropped) { virtio_scsi_push_event(s, NULL, VIRTIO_SCSI_T_NO_EVENT, 0); + virtio_scsi_release(s); return true; } + virtio_scsi_release(s); return false; } diff --git a/util/aio-posix.c b/util/aio-posix.c index XXXXXXX..XXXXXXX 100644 --- a/util/aio-posix.c +++ b/util/aio-posix.c @@ -XXX,XX +XXX,XX @@ static bool aio_dispatch_handlers(AioContext *ctx) (revents & (G_IO_IN | G_IO_HUP | G_IO_ERR)) && aio_node_check(ctx, node->is_external) && node->io_read) { - aio_context_acquire(ctx); node->io_read(node->opaque); - aio_context_release(ctx); /* aio_notify() does not count as progress */ if (node->opaque != &ctx->notifier) { @@ -XXX,XX +XXX,XX @@ static bool aio_dispatch_handlers(AioContext *ctx) (revents & (G_IO_OUT | G_IO_ERR)) && aio_node_check(ctx, node->is_external) && node->io_write) { - aio_context_acquire(ctx); node->io_write(node->opaque); - aio_context_release(ctx); progress = true; } @@ -XXX,XX +XXX,XX @@ bool aio_poll(AioContext *ctx, bool blocking) start = qemu_clock_get_ns(QEMU_CLOCK_REALTIME); } - aio_context_acquire(ctx); progress = try_poll_mode(ctx, blocking); - aio_context_release(ctx); - if (!progress) { assert(npfd == 0); diff --git a/util/aio-win32.c b/util/aio-win32.c index XXXXXXX..XXXXXXX 100644 --- a/util/aio-win32.c +++ b/util/aio-win32.c @@ -XXX,XX +XXX,XX @@ static bool aio_dispatch_handlers(AioContext *ctx, HANDLE event) (revents || event_notifier_get_handle(node->e) == event) && node->io_notify) { node->pfd.revents = 0; - aio_context_acquire(ctx); node->io_notify(node->e); - aio_context_release(ctx); /* aio_notify() does not count as progress */ if (node->e != &ctx->notifier) { @@ -XXX,XX +XXX,XX @@ static bool aio_dispatch_handlers(AioContext *ctx, HANDLE event) (node->io_read || node->io_write)) { node->pfd.revents = 0; if ((revents & G_IO_IN) && node->io_read) { - aio_context_acquire(ctx); node->io_read(node->opaque); - aio_context_release(ctx); progress = true; } if ((revents & G_IO_OUT) && node->io_write) { - aio_context_acquire(ctx); node->io_write(node->opaque); - aio_context_release(ctx); progress = true; } -- 2.9.3 From: Paolo Bonzini <pbonzini@redhat.com> Reviewed-by: Stefan Hajnoczi <stefanha@redhat.com> Signed-off-by: Paolo Bonzini <pbonzini@redhat.com> Reviewed-by: Fam Zheng <famz@redhat.com> Reviewed-by: Daniel P. Berrange <berrange@redhat.com> Message-id: 20170213135235.12274-15-pbonzini@redhat.com Signed-off-by: Stefan Hajnoczi <stefanha@redhat.com> --- block/archipelago.c | 3 +++ block/blkreplay.c | 2 +- block/block-backend.c | 6 ++++++ block/curl.c | 26 ++++++++++++++++++-------- block/gluster.c | 9 +-------- block/io.c | 6 +++++- block/iscsi.c | 6 +++++- block/linux-aio.c | 15 +++++++++------ block/nfs.c | 3 ++- block/null.c | 4 ++++ block/qed.c | 3 +++ block/rbd.c | 4 ++++ dma-helpers.c | 2 ++ hw/block/virtio-blk.c | 2 ++ hw/scsi/scsi-bus.c | 2 ++ util/async.c | 4 ++-- util/thread-pool.c | 2 ++ 17 files changed, 71 insertions(+), 28 deletions(-) diff --git a/block/archipelago.c b/block/archipelago.c index XXXXXXX..XXXXXXX 100644 --- a/block/archipelago.c +++ b/block/archipelago.c @@ -XXX,XX +XXX,XX @@ static void qemu_archipelago_complete_aio(void *opaque) { AIORequestData *reqdata = (AIORequestData *) opaque; ArchipelagoAIOCB *aio_cb = (ArchipelagoAIOCB *) reqdata->aio_cb; + AioContext *ctx = bdrv_get_aio_context(aio_cb->common.bs); + aio_context_acquire(ctx); aio_cb->common.cb(aio_cb->common.opaque, aio_cb->ret); + aio_context_release(ctx); aio_cb->status = 0; qemu_aio_unref(aio_cb); diff --git a/block/blkreplay.c b/block/blkreplay.c index XXXXXXX..XXXXXXX 100755 --- a/block/blkreplay.c +++ b/block/blkreplay.c @@ -XXX,XX +XXX,XX @@ static int64_t blkreplay_getlength(BlockDriverState *bs) static void blkreplay_bh_cb(void *opaque) { Request *req = opaque; - qemu_coroutine_enter(req->co); + aio_co_wake(req->co); qemu_bh_delete(req->bh); g_free(req); } diff --git a/block/block-backend.c b/block/block-backend.c index XXXXXXX..XXXXXXX 100644 --- a/block/block-backend.c +++ b/block/block-backend.c @@ -XXX,XX +XXX,XX @@ int blk_make_zero(BlockBackend *blk, BdrvRequestFlags flags) static void error_callback_bh(void *opaque) { struct BlockBackendAIOCB *acb = opaque; + AioContext *ctx = bdrv_get_aio_context(acb->common.bs); bdrv_dec_in_flight(acb->common.bs); + aio_context_acquire(ctx); acb->common.cb(acb->common.opaque, acb->ret); + aio_context_release(ctx); qemu_aio_unref(acb); } @@ -XXX,XX +XXX,XX @@ static void blk_aio_complete(BlkAioEmAIOCB *acb) static void blk_aio_complete_bh(void *opaque) { BlkAioEmAIOCB *acb = opaque; + AioContext *ctx = bdrv_get_aio_context(acb->common.bs); assert(acb->has_returned); + aio_context_acquire(ctx); blk_aio_complete(acb); + aio_context_release(ctx); } static BlockAIOCB *blk_aio_prwv(BlockBackend *blk, int64_t offset, int bytes, diff --git a/block/curl.c b/block/curl.c index XXXXXXX..XXXXXXX 100644 --- a/block/curl.c +++ b/block/curl.c @@ -XXX,XX +XXX,XX @@ static void curl_readv_bh_cb(void *p) { CURLState *state; int running; + int ret = -EINPROGRESS; CURLAIOCB *acb = p; - BDRVCURLState *s = acb->common.bs->opaque; + BlockDriverState *bs = acb->common.bs; + BDRVCURLState *s = bs->opaque; + AioContext *ctx = bdrv_get_aio_context(bs); size_t start = acb->sector_num * BDRV_SECTOR_SIZE; size_t end; + aio_context_acquire(ctx); + // In case we have the requested data already (e.g. read-ahead), // we can just call the callback and be done. switch (curl_find_buf(s, start, acb->nb_sectors * BDRV_SECTOR_SIZE, acb)) { @@ -XXX,XX +XXX,XX @@ static void curl_readv_bh_cb(void *p) qemu_aio_unref(acb); // fall through case FIND_RET_WAIT: - return; + goto out; default: break; } @@ -XXX,XX +XXX,XX @@ static void curl_readv_bh_cb(void *p) // No cache found, so let's start a new request state = curl_init_state(acb->common.bs, s); if (!state) { - acb->common.cb(acb->common.opaque, -EIO); - qemu_aio_unref(acb); - return; + ret = -EIO; + goto out; } acb->start = 0; @@ -XXX,XX +XXX,XX @@ static void curl_readv_bh_cb(void *p) state->orig_buf = g_try_malloc(state->buf_len); if (state->buf_len && state->orig_buf == NULL) { curl_clean_state(state); - acb->common.cb(acb->common.opaque, -ENOMEM); - qemu_aio_unref(acb); - return; + ret = -ENOMEM; + goto out; } state->acb[0] = acb; @@ -XXX,XX +XXX,XX @@ static void curl_readv_bh_cb(void *p) /* Tell curl it needs to kick things off */ curl_multi_socket_action(s->multi, CURL_SOCKET_TIMEOUT, 0, &running); + +out: + if (ret != -EINPROGRESS) { + acb->common.cb(acb->common.opaque, ret); + qemu_aio_unref(acb); + } + aio_context_release(ctx); } static BlockAIOCB *curl_aio_readv(BlockDriverState *bs, diff --git a/block/gluster.c b/block/gluster.c index XXXXXXX..XXXXXXX 100644 --- a/block/gluster.c +++ b/block/gluster.c @@ -XXX,XX +XXX,XX @@ static struct glfs *qemu_gluster_init(BlockdevOptionsGluster *gconf, return qemu_gluster_glfs_init(gconf, errp); } -static void qemu_gluster_complete_aio(void *opaque) -{ - GlusterAIOCB *acb = (GlusterAIOCB *)opaque; - - qemu_coroutine_enter(acb->coroutine); -} - /* * AIO callback routine called from GlusterFS thread. */ @@ -XXX,XX +XXX,XX @@ static void gluster_finish_aiocb(struct glfs_fd *fd, ssize_t ret, void *arg) acb->ret = -EIO; /* Partial read/write - fail it */ } - aio_bh_schedule_oneshot(acb->aio_context, qemu_gluster_complete_aio, acb); + aio_co_schedule(acb->aio_context, acb->coroutine); } static void qemu_gluster_parse_flags(int bdrv_flags, int *open_flags) diff --git a/block/io.c b/block/io.c index XXXXXXX..XXXXXXX 100644 --- a/block/io.c +++ b/block/io.c @@ -XXX,XX +XXX,XX @@ static void bdrv_co_drain_bh_cb(void *opaque) bdrv_dec_in_flight(bs); bdrv_drained_begin(bs); data->done = true; - qemu_coroutine_enter(co); + aio_co_wake(co); } static void coroutine_fn bdrv_co_yield_to_drain(BlockDriverState *bs) @@ -XXX,XX +XXX,XX @@ static void bdrv_co_complete(BlockAIOCBCoroutine *acb) static void bdrv_co_em_bh(void *opaque) { BlockAIOCBCoroutine *acb = opaque; + BlockDriverState *bs = acb->common.bs; + AioContext *ctx = bdrv_get_aio_context(bs); assert(!acb->need_bh); + aio_context_acquire(ctx); bdrv_co_complete(acb); + aio_context_release(ctx); } static void bdrv_co_maybe_schedule_bh(BlockAIOCBCoroutine *acb) diff --git a/block/iscsi.c b/block/iscsi.c index XXXXXXX..XXXXXXX 100644 --- a/block/iscsi.c +++ b/block/iscsi.c @@ -XXX,XX +XXX,XX @@ static void iscsi_bh_cb(void *p) { IscsiAIOCB *acb = p; + AioContext *ctx = bdrv_get_aio_context(acb->common.bs); qemu_bh_delete(acb->bh); g_free(acb->buf); acb->buf = NULL; + aio_context_acquire(ctx); acb->common.cb(acb->common.opaque, acb->status); + aio_context_release(ctx); if (acb->task != NULL) { scsi_free_scsi_task(acb->task); @@ -XXX,XX +XXX,XX @@ iscsi_schedule_bh(IscsiAIOCB *acb) static void iscsi_co_generic_bh_cb(void *opaque) { struct IscsiTask *iTask = opaque; + iTask->complete = 1; - qemu_coroutine_enter(iTask->co); + aio_co_wake(iTask->co); } static void iscsi_retry_timer_expired(void *opaque) diff --git a/block/linux-aio.c b/block/linux-aio.c index XXXXXXX..XXXXXXX 100644 --- a/block/linux-aio.c +++ b/block/linux-aio.c @@ -XXX,XX +XXX,XX @@ struct LinuxAioState { io_context_t ctx; EventNotifier e; - /* io queue for submit at batch */ + /* io queue for submit at batch. Protected by AioContext lock. */ LaioQueue io_q; - /* I/O completion processing */ + /* I/O completion processing. Only runs in I/O thread. */ QEMUBH *completion_bh; int event_idx; int event_max; @@ -XXX,XX +XXX,XX @@ static inline ssize_t io_event_ret(struct io_event *ev) */ static void qemu_laio_process_completion(struct qemu_laiocb *laiocb) { + LinuxAioState *s = laiocb->ctx; int ret; ret = laiocb->ret; @@ -XXX,XX +XXX,XX @@ static void qemu_laio_process_completion(struct qemu_laiocb *laiocb) } laiocb->ret = ret; + aio_context_acquire(s->aio_context); if (laiocb->co) { /* If the coroutine is already entered it must be in ioq_submit() and * will notice laio->ret has been filled in when it eventually runs @@ -XXX,XX +XXX,XX @@ static void qemu_laio_process_completion(struct qemu_laiocb *laiocb) laiocb->common.cb(laiocb->common.opaque, ret); qemu_aio_unref(laiocb); } + aio_context_release(s->aio_context); } /** @@ -XXX,XX +XXX,XX @@ static void qemu_laio_process_completions(LinuxAioState *s) static void qemu_laio_process_completions_and_submit(LinuxAioState *s) { qemu_laio_process_completions(s); + + aio_context_acquire(s->aio_context); if (!s->io_q.plugged && !QSIMPLEQ_EMPTY(&s->io_q.pending)) { ioq_submit(s); } + aio_context_release(s->aio_context); } static void qemu_laio_completion_bh(void *opaque) @@ -XXX,XX +XXX,XX @@ static void qemu_laio_completion_cb(EventNotifier *e) LinuxAioState *s = container_of(e, LinuxAioState, e); if (event_notifier_test_and_clear(&s->e)) { - aio_context_acquire(s->aio_context); qemu_laio_process_completions_and_submit(s); - aio_context_release(s->aio_context); } } @@ -XXX,XX +XXX,XX @@ static bool qemu_laio_poll_cb(void *opaque) return false; } - aio_context_acquire(s->aio_context); qemu_laio_process_completions_and_submit(s); - aio_context_release(s->aio_context); return true; } @@ -XXX,XX +XXX,XX @@ void laio_detach_aio_context(LinuxAioState *s, AioContext *old_context) { aio_set_event_notifier(old_context, &s->e, false, NULL, NULL); qemu_bh_delete(s->completion_bh); + s->aio_context = NULL; } void laio_attach_aio_context(LinuxAioState *s, AioContext *new_context) diff --git a/block/nfs.c b/block/nfs.c index XXXXXXX..XXXXXXX 100644 --- a/block/nfs.c +++ b/block/nfs.c @@ -XXX,XX +XXX,XX @@ static void nfs_co_init_task(BlockDriverState *bs, NFSRPC *task) static void nfs_co_generic_bh_cb(void *opaque) { NFSRPC *task = opaque; + task->complete = 1; - qemu_coroutine_enter(task->co); + aio_co_wake(task->co); } static void diff --git a/block/null.c b/block/null.c index XXXXXXX..XXXXXXX 100644 --- a/block/null.c +++ b/block/null.c @@ -XXX,XX +XXX,XX @@ static const AIOCBInfo null_aiocb_info = { static void null_bh_cb(void *opaque) { NullAIOCB *acb = opaque; + AioContext *ctx = bdrv_get_aio_context(acb->common.bs); + + aio_context_acquire(ctx); acb->common.cb(acb->common.opaque, 0); + aio_context_release(ctx); qemu_aio_unref(acb); } diff --git a/block/qed.c b/block/qed.c index XXXXXXX..XXXXXXX 100644 --- a/block/qed.c +++ b/block/qed.c @@ -XXX,XX +XXX,XX @@ static void qed_update_l2_table(BDRVQEDState *s, QEDTable *table, int index, static void qed_aio_complete_bh(void *opaque) { QEDAIOCB *acb = opaque; + BDRVQEDState *s = acb_to_s(acb); BlockCompletionFunc *cb = acb->common.cb; void *user_opaque = acb->common.opaque; int ret = acb->bh_ret; @@ -XXX,XX +XXX,XX @@ static void qed_aio_complete_bh(void *opaque) qemu_aio_unref(acb); /* Invoke callback */ + qed_acquire(s); cb(user_opaque, ret); + qed_release(s); } static void qed_aio_complete(QEDAIOCB *acb, int ret) diff --git a/block/rbd.c b/block/rbd.c index XXXXXXX..XXXXXXX 100644 --- a/block/rbd.c +++ b/block/rbd.c @@ -XXX,XX +XXX,XX @@ shutdown: static void qemu_rbd_complete_aio(RADOSCB *rcb) { RBDAIOCB *acb = rcb->acb; + AioContext *ctx = bdrv_get_aio_context(acb->common.bs); int64_t r; r = rcb->ret; @@ -XXX,XX +XXX,XX @@ static void qemu_rbd_complete_aio(RADOSCB *rcb) qemu_iovec_from_buf(acb->qiov, 0, acb->bounce, acb->qiov->size); } qemu_vfree(acb->bounce); + + aio_context_acquire(ctx); acb->common.cb(acb->common.opaque, (acb->ret > 0 ? 0 : acb->ret)); + aio_context_release(ctx); qemu_aio_unref(acb); } diff --git a/dma-helpers.c b/dma-helpers.c index XXXXXXX..XXXXXXX 100644 --- a/dma-helpers.c +++ b/dma-helpers.c @@ -XXX,XX +XXX,XX @@ static void dma_blk_cb(void *opaque, int ret) QEMU_ALIGN_DOWN(dbs->iov.size, dbs->align)); } + aio_context_acquire(dbs->ctx); dbs->acb = dbs->io_func(dbs->offset, &dbs->iov, dma_blk_cb, dbs, dbs->io_func_opaque); + aio_context_release(dbs->ctx); assert(dbs->acb); } diff --git a/hw/block/virtio-blk.c b/hw/block/virtio-blk.c index XXXXXXX..XXXXXXX 100644 --- a/hw/block/virtio-blk.c +++ b/hw/block/virtio-blk.c @@ -XXX,XX +XXX,XX @@ static void virtio_blk_dma_restart_bh(void *opaque) s->rq = NULL; + aio_context_acquire(blk_get_aio_context(s->conf.conf.blk)); while (req) { VirtIOBlockReq *next = req->next; if (virtio_blk_handle_request(req, &mrb)) { @@ -XXX,XX +XXX,XX @@ static void virtio_blk_dma_restart_bh(void *opaque) if (mrb.num_reqs) { virtio_blk_submit_multireq(s->blk, &mrb); } + aio_context_release(blk_get_aio_context(s->conf.conf.blk)); } static void virtio_blk_dma_restart_cb(void *opaque, int running, diff --git a/hw/scsi/scsi-bus.c b/hw/scsi/scsi-bus.c index XXXXXXX..XXXXXXX 100644 --- a/hw/scsi/scsi-bus.c +++ b/hw/scsi/scsi-bus.c @@ -XXX,XX +XXX,XX @@ static void scsi_dma_restart_bh(void *opaque) qemu_bh_delete(s->bh); s->bh = NULL; + aio_context_acquire(blk_get_aio_context(s->conf.blk)); QTAILQ_FOREACH_SAFE(req, &s->requests, next, next) { scsi_req_ref(req); if (req->retry) { @@ -XXX,XX +XXX,XX @@ static void scsi_dma_restart_bh(void *opaque) } scsi_req_unref(req); } + aio_context_release(blk_get_aio_context(s->conf.blk)); } void scsi_req_retry(SCSIRequest *req) diff --git a/util/async.c b/util/async.c index XXXXXXX..XXXXXXX 100644 --- a/util/async.c +++ b/util/async.c @@ -XXX,XX +XXX,XX @@ int aio_bh_poll(AioContext *ctx) ret = 1; } bh->idle = 0; - aio_context_acquire(ctx); aio_bh_call(bh); - aio_context_release(ctx); } if (bh->deleted) { deleted = true; @@ -XXX,XX +XXX,XX @@ static void co_schedule_bh_cb(void *opaque) Coroutine *co = QSLIST_FIRST(&straight); QSLIST_REMOVE_HEAD(&straight, co_scheduled_next); trace_aio_co_schedule_bh_cb(ctx, co); + aio_context_acquire(ctx); qemu_coroutine_enter(co); + aio_context_release(ctx); } } diff --git a/util/thread-pool.c b/util/thread-pool.c index XXXXXXX..XXXXXXX 100644 --- a/util/thread-pool.c +++ b/util/thread-pool.c @@ -XXX,XX +XXX,XX @@ static void thread_pool_completion_bh(void *opaque) ThreadPool *pool = opaque; ThreadPoolElement *elem, *next; + aio_context_acquire(pool->ctx); restart: QLIST_FOREACH_SAFE(elem, &pool->head, all, next) { if (elem->state != THREAD_DONE) { @@ -XXX,XX +XXX,XX @@ restart: qemu_aio_unref(elem); } } + aio_context_release(pool->ctx); } static void thread_pool_cancel(BlockAIOCB *acb) -- 2.9.3 From: Paolo Bonzini <pbonzini@redhat.com> Reviewed-by: Stefan Hajnoczi <stefanha@redhat.com> Signed-off-by: Paolo Bonzini <pbonzini@redhat.com> Reviewed-by: Fam Zheng <famz@redhat.com> Reviewed-by: Daniel P. Berrange <berrange@redhat.com> Message-id: 20170213135235.12274-16-pbonzini@redhat.com Signed-off-by: Stefan Hajnoczi <stefanha@redhat.com> --- block/archipelago.c | 3 --- block/block-backend.c | 7 ------- block/curl.c | 2 +- block/io.c | 6 +----- block/iscsi.c | 3 --- block/linux-aio.c | 5 +---- block/mirror.c | 12 +++++++++--- block/null.c | 8 -------- block/qed-cluster.c | 2 ++ block/qed-table.c | 12 ++++++++++-- block/qed.c | 4 ++-- block/rbd.c | 4 ---- block/win32-aio.c | 3 --- hw/block/virtio-blk.c | 12 +++++++++++- hw/scsi/scsi-disk.c | 15 +++++++++++++++ hw/scsi/scsi-generic.c | 20 +++++++++++++++++--- util/thread-pool.c | 4 +++- 17 files changed, 72 insertions(+), 50 deletions(-) diff --git a/block/archipelago.c b/block/archipelago.c index XXXXXXX..XXXXXXX 100644 --- a/block/archipelago.c +++ b/block/archipelago.c @@ -XXX,XX +XXX,XX @@ static void qemu_archipelago_complete_aio(void *opaque) { AIORequestData *reqdata = (AIORequestData *) opaque; ArchipelagoAIOCB *aio_cb = (ArchipelagoAIOCB *) reqdata->aio_cb; - AioContext *ctx = bdrv_get_aio_context(aio_cb->common.bs); - aio_context_acquire(ctx); aio_cb->common.cb(aio_cb->common.opaque, aio_cb->ret); - aio_context_release(ctx); aio_cb->status = 0; qemu_aio_unref(aio_cb); diff --git a/block/block-backend.c b/block/block-backend.c index XXXXXXX..XXXXXXX 100644 --- a/block/block-backend.c +++ b/block/block-backend.c @@ -XXX,XX +XXX,XX @@ int blk_make_zero(BlockBackend *blk, BdrvRequestFlags flags) static void error_callback_bh(void *opaque) { struct BlockBackendAIOCB *acb = opaque; - AioContext *ctx = bdrv_get_aio_context(acb->common.bs); bdrv_dec_in_flight(acb->common.bs); - aio_context_acquire(ctx); acb->common.cb(acb->common.opaque, acb->ret); - aio_context_release(ctx); qemu_aio_unref(acb); } @@ -XXX,XX +XXX,XX @@ static void blk_aio_complete(BlkAioEmAIOCB *acb) static void blk_aio_complete_bh(void *opaque) { BlkAioEmAIOCB *acb = opaque; - AioContext *ctx = bdrv_get_aio_context(acb->common.bs); - assert(acb->has_returned); - aio_context_acquire(ctx); blk_aio_complete(acb); - aio_context_release(ctx); } static BlockAIOCB *blk_aio_prwv(BlockBackend *blk, int64_t offset, int bytes, diff --git a/block/curl.c b/block/curl.c index XXXXXXX..XXXXXXX 100644 --- a/block/curl.c +++ b/block/curl.c @@ -XXX,XX +XXX,XX @@ static void curl_readv_bh_cb(void *p) curl_multi_socket_action(s->multi, CURL_SOCKET_TIMEOUT, 0, &running); out: + aio_context_release(ctx); if (ret != -EINPROGRESS) { acb->common.cb(acb->common.opaque, ret); qemu_aio_unref(acb); } - aio_context_release(ctx); } static BlockAIOCB *curl_aio_readv(BlockDriverState *bs, diff --git a/block/io.c b/block/io.c index XXXXXXX..XXXXXXX 100644 --- a/block/io.c +++ b/block/io.c @@ -XXX,XX +XXX,XX @@ static void bdrv_co_io_em_complete(void *opaque, int ret) CoroutineIOCompletion *co = opaque; co->ret = ret; - qemu_coroutine_enter(co->coroutine); + aio_co_wake(co->coroutine); } static int coroutine_fn bdrv_driver_preadv(BlockDriverState *bs, @@ -XXX,XX +XXX,XX @@ static void bdrv_co_complete(BlockAIOCBCoroutine *acb) static void bdrv_co_em_bh(void *opaque) { BlockAIOCBCoroutine *acb = opaque; - BlockDriverState *bs = acb->common.bs; - AioContext *ctx = bdrv_get_aio_context(bs); assert(!acb->need_bh); - aio_context_acquire(ctx); bdrv_co_complete(acb); - aio_context_release(ctx); } static void bdrv_co_maybe_schedule_bh(BlockAIOCBCoroutine *acb) diff --git a/block/iscsi.c b/block/iscsi.c index XXXXXXX..XXXXXXX 100644 --- a/block/iscsi.c +++ b/block/iscsi.c @@ -XXX,XX +XXX,XX @@ static void iscsi_bh_cb(void *p) { IscsiAIOCB *acb = p; - AioContext *ctx = bdrv_get_aio_context(acb->common.bs); qemu_bh_delete(acb->bh); g_free(acb->buf); acb->buf = NULL; - aio_context_acquire(ctx); acb->common.cb(acb->common.opaque, acb->status); - aio_context_release(ctx); if (acb->task != NULL) { scsi_free_scsi_task(acb->task); diff --git a/block/linux-aio.c b/block/linux-aio.c index XXXXXXX..XXXXXXX 100644 --- a/block/linux-aio.c +++ b/block/linux-aio.c @@ -XXX,XX +XXX,XX @@ static inline ssize_t io_event_ret(struct io_event *ev) */ static void qemu_laio_process_completion(struct qemu_laiocb *laiocb) { - LinuxAioState *s = laiocb->ctx; int ret; ret = laiocb->ret; @@ -XXX,XX +XXX,XX @@ static void qemu_laio_process_completion(struct qemu_laiocb *laiocb) } laiocb->ret = ret; - aio_context_acquire(s->aio_context); if (laiocb->co) { /* If the coroutine is already entered it must be in ioq_submit() and * will notice laio->ret has been filled in when it eventually runs @@ -XXX,XX +XXX,XX @@ static void qemu_laio_process_completion(struct qemu_laiocb *laiocb) * that! */ if (!qemu_coroutine_entered(laiocb->co)) { - qemu_coroutine_enter(laiocb->co); + aio_co_wake(laiocb->co); } } else { laiocb->common.cb(laiocb->common.opaque, ret); qemu_aio_unref(laiocb); } - aio_context_release(s->aio_context); } /** diff --git a/block/mirror.c b/block/mirror.c index XXXXXXX..XXXXXXX 100644 --- a/block/mirror.c +++ b/block/mirror.c @@ -XXX,XX +XXX,XX @@ static void mirror_write_complete(void *opaque, int ret) { MirrorOp *op = opaque; MirrorBlockJob *s = op->s; + + aio_context_acquire(blk_get_aio_context(s->common.blk)); if (ret < 0) { BlockErrorAction action; @@ -XXX,XX +XXX,XX @@ static void mirror_write_complete(void *opaque, int ret) } } mirror_iteration_done(op, ret); + aio_context_release(blk_get_aio_context(s->common.blk)); } static void mirror_read_complete(void *opaque, int ret) { MirrorOp *op = opaque; MirrorBlockJob *s = op->s; + + aio_context_acquire(blk_get_aio_context(s->common.blk)); if (ret < 0) { BlockErrorAction action; @@ -XXX,XX +XXX,XX @@ static void mirror_read_complete(void *opaque, int ret) } mirror_iteration_done(op, ret); - return; + } else { + blk_aio_pwritev(s->target, op->sector_num * BDRV_SECTOR_SIZE, &op->qiov, + 0, mirror_write_complete, op); } - blk_aio_pwritev(s->target, op->sector_num * BDRV_SECTOR_SIZE, &op->qiov, - 0, mirror_write_complete, op); + aio_context_release(blk_get_aio_context(s->common.blk)); } static inline void mirror_clip_sectors(MirrorBlockJob *s, diff --git a/block/null.c b/block/null.c index XXXXXXX..XXXXXXX 100644 --- a/block/null.c +++ b/block/null.c @@ -XXX,XX +XXX,XX @@ static const AIOCBInfo null_aiocb_info = { static void null_bh_cb(void *opaque) { NullAIOCB *acb = opaque; - AioContext *ctx = bdrv_get_aio_context(acb->common.bs); - - aio_context_acquire(ctx); acb->common.cb(acb->common.opaque, 0); - aio_context_release(ctx); qemu_aio_unref(acb); } static void null_timer_cb(void *opaque) { NullAIOCB *acb = opaque; - AioContext *ctx = bdrv_get_aio_context(acb->common.bs); - - aio_context_acquire(ctx); acb->common.cb(acb->common.opaque, 0); - aio_context_release(ctx); timer_deinit(&acb->timer); qemu_aio_unref(acb); } diff --git a/block/qed-cluster.c b/block/qed-cluster.c index XXXXXXX..XXXXXXX 100644 --- a/block/qed-cluster.c +++ b/block/qed-cluster.c @@ -XXX,XX +XXX,XX @@ static void qed_find_cluster_cb(void *opaque, int ret) unsigned int index; unsigned int n; + qed_acquire(s); if (ret) { goto out; } @@ -XXX,XX +XXX,XX @@ static void qed_find_cluster_cb(void *opaque, int ret) out: find_cluster_cb->cb(find_cluster_cb->opaque, ret, offset, len); + qed_release(s); g_free(find_cluster_cb); } diff --git a/block/qed-table.c b/block/qed-table.c index XXXXXXX..XXXXXXX 100644 --- a/block/qed-table.c +++ b/block/qed-table.c @@ -XXX,XX +XXX,XX @@ static void qed_read_table_cb(void *opaque, int ret) { QEDReadTableCB *read_table_cb = opaque; QEDTable *table = read_table_cb->table; + BDRVQEDState *s = read_table_cb->s; int noffsets = read_table_cb->qiov.size / sizeof(uint64_t); int i; @@ -XXX,XX +XXX,XX @@ static void qed_read_table_cb(void *opaque, int ret) } /* Byteswap offsets */ + qed_acquire(s); for (i = 0; i < noffsets; i++) { table->offsets[i] = le64_to_cpu(table->offsets[i]); } + qed_release(s); out: /* Completion */ - trace_qed_read_table_cb(read_table_cb->s, read_table_cb->table, ret); + trace_qed_read_table_cb(s, read_table_cb->table, ret); gencb_complete(&read_table_cb->gencb, ret); } @@ -XXX,XX +XXX,XX @@ typedef struct { static void qed_write_table_cb(void *opaque, int ret) { QEDWriteTableCB *write_table_cb = opaque; + BDRVQEDState *s = write_table_cb->s; - trace_qed_write_table_cb(write_table_cb->s, + trace_qed_write_table_cb(s, write_table_cb->orig_table, write_table_cb->flush, ret); @@ -XXX,XX +XXX,XX @@ static void qed_write_table_cb(void *opaque, int ret) if (write_table_cb->flush) { /* We still need to flush first */ write_table_cb->flush = false; + qed_acquire(s); bdrv_aio_flush(write_table_cb->s->bs, qed_write_table_cb, write_table_cb); + qed_release(s); return; } @@ -XXX,XX +XXX,XX @@ static void qed_read_l2_table_cb(void *opaque, int ret) CachedL2Table *l2_table = request->l2_table; uint64_t l2_offset = read_l2_table_cb->l2_offset; + qed_acquire(s); if (ret) { /* can't trust loaded L2 table anymore */ qed_unref_l2_cache_entry(l2_table); @@ -XXX,XX +XXX,XX @@ static void qed_read_l2_table_cb(void *opaque, int ret) request->l2_table = qed_find_l2_cache_entry(&s->l2_cache, l2_offset); assert(request->l2_table != NULL); } + qed_release(s); gencb_complete(&read_l2_table_cb->gencb, ret); } diff --git a/block/qed.c b/block/qed.c index XXXXXXX..XXXXXXX 100644 --- a/block/qed.c +++ b/block/qed.c @@ -XXX,XX +XXX,XX @@ static void qed_is_allocated_cb(void *opaque, int ret, uint64_t offset, size_t l } if (cb->co) { - qemu_coroutine_enter(cb->co); + aio_co_wake(cb->co); } } @@ -XXX,XX +XXX,XX @@ static void coroutine_fn qed_co_pwrite_zeroes_cb(void *opaque, int ret) cb->done = true; cb->ret = ret; if (cb->co) { - qemu_coroutine_enter(cb->co); + aio_co_wake(cb->co); } } diff --git a/block/rbd.c b/block/rbd.c index XXXXXXX..XXXXXXX 100644 --- a/block/rbd.c +++ b/block/rbd.c @@ -XXX,XX +XXX,XX @@ shutdown: static void qemu_rbd_complete_aio(RADOSCB *rcb) { RBDAIOCB *acb = rcb->acb; - AioContext *ctx = bdrv_get_aio_context(acb->common.bs); int64_t r; r = rcb->ret; @@ -XXX,XX +XXX,XX @@ static void qemu_rbd_complete_aio(RADOSCB *rcb) qemu_iovec_from_buf(acb->qiov, 0, acb->bounce, acb->qiov->size); } qemu_vfree(acb->bounce); - - aio_context_acquire(ctx); acb->common.cb(acb->common.opaque, (acb->ret > 0 ? 0 : acb->ret)); - aio_context_release(ctx); qemu_aio_unref(acb); } diff --git a/block/win32-aio.c b/block/win32-aio.c index XXXXXXX..XXXXXXX 100644 --- a/block/win32-aio.c +++ b/block/win32-aio.c @@ -XXX,XX +XXX,XX @@ static void win32_aio_process_completion(QEMUWin32AIOState *s, qemu_vfree(waiocb->buf); } - - aio_context_acquire(s->aio_ctx); waiocb->common.cb(waiocb->common.opaque, ret); - aio_context_release(s->aio_ctx); qemu_aio_unref(waiocb); } diff --git a/hw/block/virtio-blk.c b/hw/block/virtio-blk.c index XXXXXXX..XXXXXXX 100644 --- a/hw/block/virtio-blk.c +++ b/hw/block/virtio-blk.c @@ -XXX,XX +XXX,XX @@ static int virtio_blk_handle_rw_error(VirtIOBlockReq *req, int error, static void virtio_blk_rw_complete(void *opaque, int ret) { VirtIOBlockReq *next = opaque; + VirtIOBlock *s = next->dev; + aio_context_acquire(blk_get_aio_context(s->conf.conf.blk)); while (next) { VirtIOBlockReq *req = next; next = req->mr_next; @@ -XXX,XX +XXX,XX @@ static void virtio_blk_rw_complete(void *opaque, int ret) block_acct_done(blk_get_stats(req->dev->blk), &req->acct); virtio_blk_free_request(req); } + aio_context_release(blk_get_aio_context(s->conf.conf.blk)); } static void virtio_blk_flush_complete(void *opaque, int ret) { VirtIOBlockReq *req = opaque; + VirtIOBlock *s = req->dev; + aio_context_acquire(blk_get_aio_context(s->conf.conf.blk)); if (ret) { if (virtio_blk_handle_rw_error(req, -ret, 0)) { - return; + goto out; } } virtio_blk_req_complete(req, VIRTIO_BLK_S_OK); block_acct_done(blk_get_stats(req->dev->blk), &req->acct); virtio_blk_free_request(req); + +out: + aio_context_release(blk_get_aio_context(s->conf.conf.blk)); } #ifdef __linux__ @@ -XXX,XX +XXX,XX @@ static void virtio_blk_ioctl_complete(void *opaque, int status) virtio_stl_p(vdev, &scsi->data_len, hdr->dxfer_len); out: + aio_context_acquire(blk_get_aio_context(s->conf.conf.blk)); virtio_blk_req_complete(req, status); virtio_blk_free_request(req); + aio_context_release(blk_get_aio_context(s->conf.conf.blk)); g_free(ioctl_req); } diff --git a/hw/scsi/scsi-disk.c b/hw/scsi/scsi-disk.c index XXXXXXX..XXXXXXX 100644 --- a/hw/scsi/scsi-disk.c +++ b/hw/scsi/scsi-disk.c @@ -XXX,XX +XXX,XX @@ static void scsi_aio_complete(void *opaque, int ret) assert(r->req.aiocb != NULL); r->req.aiocb = NULL; + aio_context_acquire(blk_get_aio_context(s->qdev.conf.blk)); if (scsi_disk_req_check_error(r, ret, true)) { goto done; } @@ -XXX,XX +XXX,XX @@ static void scsi_aio_complete(void *opaque, int ret) scsi_req_complete(&r->req, GOOD); done: + aio_context_release(blk_get_aio_context(s->qdev.conf.blk)); scsi_req_unref(&r->req); } @@ -XXX,XX +XXX,XX @@ static void scsi_dma_complete(void *opaque, int ret) assert(r->req.aiocb != NULL); r->req.aiocb = NULL; + aio_context_acquire(blk_get_aio_context(s->qdev.conf.blk)); if (ret < 0) { block_acct_failed(blk_get_stats(s->qdev.conf.blk), &r->acct); } else { block_acct_done(blk_get_stats(s->qdev.conf.blk), &r->acct); } scsi_dma_complete_noio(r, ret); + aio_context_release(blk_get_aio_context(s->qdev.conf.blk)); } static void scsi_read_complete(void * opaque, int ret) @@ -XXX,XX +XXX,XX @@ static void scsi_read_complete(void * opaque, int ret) assert(r->req.aiocb != NULL); r->req.aiocb = NULL; + aio_context_acquire(blk_get_aio_context(s->qdev.conf.blk)); if (scsi_disk_req_check_error(r, ret, true)) { goto done; } @@ -XXX,XX +XXX,XX @@ static void scsi_read_complete(void * opaque, int ret) done: scsi_req_unref(&r->req); + aio_context_release(blk_get_aio_context(s->qdev.conf.blk)); } /* Actually issue a read to the block device. */ @@ -XXX,XX +XXX,XX @@ static void scsi_do_read_cb(void *opaque, int ret) assert (r->req.aiocb != NULL); r->req.aiocb = NULL; + aio_context_acquire(blk_get_aio_context(s->qdev.conf.blk)); if (ret < 0) { block_acct_failed(blk_get_stats(s->qdev.conf.blk), &r->acct); } else { block_acct_done(blk_get_stats(s->qdev.conf.blk), &r->acct); } scsi_do_read(opaque, ret); + aio_context_release(blk_get_aio_context(s->qdev.conf.blk)); } /* Read more data from scsi device into buffer. */ @@ -XXX,XX +XXX,XX @@ static void scsi_write_complete(void * opaque, int ret) assert (r->req.aiocb != NULL); r->req.aiocb = NULL; + aio_context_acquire(blk_get_aio_context(s->qdev.conf.blk)); if (ret < 0) { block_acct_failed(blk_get_stats(s->qdev.conf.blk), &r->acct); } else { block_acct_done(blk_get_stats(s->qdev.conf.blk), &r->acct); } scsi_write_complete_noio(r, ret); + aio_context_release(blk_get_aio_context(s->qdev.conf.blk)); } static void scsi_write_data(SCSIRequest *req) @@ -XXX,XX +XXX,XX @@ static void scsi_unmap_complete(void *opaque, int ret) { UnmapCBData *data = opaque; SCSIDiskReq *r = data->r; + SCSIDiskState *s = DO_UPCAST(SCSIDiskState, qdev, r->req.dev); assert(r->req.aiocb != NULL); r->req.aiocb = NULL; + aio_context_acquire(blk_get_aio_context(s->qdev.conf.blk)); scsi_unmap_complete_noio(data, ret); + aio_context_release(blk_get_aio_context(s->qdev.conf.blk)); } static void scsi_disk_emulate_unmap(SCSIDiskReq *r, uint8_t *inbuf) @@ -XXX,XX +XXX,XX @@ static void scsi_write_same_complete(void *opaque, int ret) assert(r->req.aiocb != NULL); r->req.aiocb = NULL; + aio_context_acquire(blk_get_aio_context(s->qdev.conf.blk)); if (scsi_disk_req_check_error(r, ret, true)) { goto done; } @@ -XXX,XX +XXX,XX @@ done: scsi_req_unref(&r->req); qemu_vfree(data->iov.iov_base); g_free(data); + aio_context_release(blk_get_aio_context(s->qdev.conf.blk)); } static void scsi_disk_emulate_write_same(SCSIDiskReq *r, uint8_t *inbuf) diff --git a/hw/scsi/scsi-generic.c b/hw/scsi/scsi-generic.c index XXXXXXX..XXXXXXX 100644 --- a/hw/scsi/scsi-generic.c +++ b/hw/scsi/scsi-generic.c @@ -XXX,XX +XXX,XX @@ done: static void scsi_command_complete(void *opaque, int ret) { SCSIGenericReq *r = (SCSIGenericReq *)opaque; + SCSIDevice *s = r->req.dev; assert(r->req.aiocb != NULL); r->req.aiocb = NULL; + + aio_context_acquire(blk_get_aio_context(s->conf.blk)); scsi_command_complete_noio(r, ret); + aio_context_release(blk_get_aio_context(s->conf.blk)); } static int execute_command(BlockBackend *blk, @@ -XXX,XX +XXX,XX @@ static void scsi_read_complete(void * opaque, int ret) assert(r->req.aiocb != NULL); r->req.aiocb = NULL; + aio_context_acquire(blk_get_aio_context(s->conf.blk)); + if (ret || r->req.io_canceled) { scsi_command_complete_noio(r, ret); - return; + goto done; } len = r->io_header.dxfer_len - r->io_header.resid; @@ -XXX,XX +XXX,XX @@ static void scsi_read_complete(void * opaque, int ret) r->len = -1; if (len == 0) { scsi_command_complete_noio(r, 0); - return; + goto done; } /* Snoop READ CAPACITY output to set the blocksize. */ @@ -XXX,XX +XXX,XX @@ static void scsi_read_complete(void * opaque, int ret) } scsi_req_data(&r->req, len); scsi_req_unref(&r->req); + +done: + aio_context_release(blk_get_aio_context(s->conf.blk)); } /* Read more data from scsi device into buffer. */ @@ -XXX,XX +XXX,XX @@ static void scsi_write_complete(void * opaque, int ret) assert(r->req.aiocb != NULL); r->req.aiocb = NULL; + aio_context_acquire(blk_get_aio_context(s->conf.blk)); + if (ret || r->req.io_canceled) { scsi_command_complete_noio(r, ret); - return; + goto done; } if (r->req.cmd.buf[0] == MODE_SELECT && r->req.cmd.buf[4] == 12 && @@ -XXX,XX +XXX,XX @@ static void scsi_write_complete(void * opaque, int ret) } scsi_command_complete_noio(r, ret); + +done: + aio_context_release(blk_get_aio_context(s->conf.blk)); } /* Write data to a scsi device. Returns nonzero on failure. diff --git a/util/thread-pool.c b/util/thread-pool.c index XXXXXXX..XXXXXXX 100644 --- a/util/thread-pool.c +++ b/util/thread-pool.c @@ -XXX,XX +XXX,XX @@ restart: */ qemu_bh_schedule(pool->completion_bh); + aio_context_release(pool->ctx); elem->common.cb(elem->common.opaque, elem->ret); + aio_context_acquire(pool->ctx); qemu_aio_unref(elem); goto restart; } else { @@ -XXX,XX +XXX,XX @@ static void thread_pool_co_cb(void *opaque, int ret) ThreadPoolCo *co = opaque; co->ret = ret; - qemu_coroutine_enter(co->co); + aio_co_wake(co->co); } int coroutine_fn thread_pool_submit_co(ThreadPool *pool, ThreadPoolFunc *func, -- 2.9.3 From: Paolo Bonzini <pbonzini@redhat.com> This patch prepares for the removal of unnecessary lockcnt inc/dec pairs. Extract the dispatching loop for file descriptor handlers into a new function aio_dispatch_handlers, and then inline aio_dispatch into aio_poll. aio_dispatch can now become void. Reviewed-by: Stefan Hajnoczi <stefanha@redhat.com> Signed-off-by: Paolo Bonzini <pbonzini@redhat.com> Reviewed-by: Fam Zheng <famz@redhat.com> Reviewed-by: Daniel P. Berrange <berrange@redhat.com> Message-id: 20170213135235.12274-17-pbonzini@redhat.com Signed-off-by: Stefan Hajnoczi <stefanha@redhat.com> --- include/block/aio.h | 6 +----- util/aio-posix.c | 44 ++++++++++++++------------------------------ util/aio-win32.c | 13 ++++--------- util/async.c | 2 +- 4 files changed, 20 insertions(+), 45 deletions(-) diff --git a/include/block/aio.h b/include/block/aio.h index XXXXXXX..XXXXXXX 100644 --- a/include/block/aio.h +++ b/include/block/aio.h @@ -XXX,XX +XXX,XX @@ bool aio_pending(AioContext *ctx); /* Dispatch any pending callbacks from the GSource attached to the AioContext. * * This is used internally in the implementation of the GSource. - * - * @dispatch_fds: true to process fds, false to skip them - * (can be used as an optimization by callers that know there - * are no fds ready) */ -bool aio_dispatch(AioContext *ctx, bool dispatch_fds); +void aio_dispatch(AioContext *ctx); /* Progress in completing AIO work to occur. This can issue new pending * aio as a result of executing I/O completion or bh callbacks. diff --git a/util/aio-posix.c b/util/aio-posix.c index XXXXXXX..XXXXXXX 100644 --- a/util/aio-posix.c +++ b/util/aio-posix.c @@ -XXX,XX +XXX,XX @@ static bool aio_dispatch_handlers(AioContext *ctx) AioHandler *node, *tmp; bool progress = false; - /* - * We have to walk very carefully in case aio_set_fd_handler is - * called while we're walking. - */ - qemu_lockcnt_inc(&ctx->list_lock); - QLIST_FOREACH_SAFE_RCU(node, &ctx->aio_handlers, node, tmp) { int revents; @@ -XXX,XX +XXX,XX @@ static bool aio_dispatch_handlers(AioContext *ctx) } } - qemu_lockcnt_dec(&ctx->list_lock); return progress; } -/* - * Note that dispatch_fds == false has the side-effect of post-poning the - * freeing of deleted handlers. - */ -bool aio_dispatch(AioContext *ctx, bool dispatch_fds) +void aio_dispatch(AioContext *ctx) { - bool progress; + aio_bh_poll(ctx); - /* - * If there are callbacks left that have been queued, we need to call them. - * Do not call select in this case, because it is possible that the caller - * does not need a complete flush (as is the case for aio_poll loops). - */ - progress = aio_bh_poll(ctx); + qemu_lockcnt_inc(&ctx->list_lock); + aio_dispatch_handlers(ctx); + qemu_lockcnt_dec(&ctx->list_lock); - if (dispatch_fds) { - progress |= aio_dispatch_handlers(ctx); - } - - /* Run our timers */ - progress |= timerlistgroup_run_timers(&ctx->tlg); - - return progress; + timerlistgroup_run_timers(&ctx->tlg); } /* These thread-local variables are used only in a small part of aio_poll @@ -XXX,XX +XXX,XX @@ bool aio_poll(AioContext *ctx, bool blocking) npfd = 0; qemu_lockcnt_dec(&ctx->list_lock); - /* Run dispatch even if there were no readable fds to run timers */ - if (aio_dispatch(ctx, ret > 0)) { - progress = true; + progress |= aio_bh_poll(ctx); + + if (ret > 0) { + qemu_lockcnt_inc(&ctx->list_lock); + progress |= aio_dispatch_handlers(ctx); + qemu_lockcnt_dec(&ctx->list_lock); } + progress |= timerlistgroup_run_timers(&ctx->tlg); + return progress; } diff --git a/util/aio-win32.c b/util/aio-win32.c index XXXXXXX..XXXXXXX 100644 --- a/util/aio-win32.c +++ b/util/aio-win32.c @@ -XXX,XX +XXX,XX @@ static bool aio_dispatch_handlers(AioContext *ctx, HANDLE event) return progress; } -bool aio_dispatch(AioContext *ctx, bool dispatch_fds) +void aio_dispatch(AioContext *ctx) { - bool progress; - - progress = aio_bh_poll(ctx); - if (dispatch_fds) { - progress |= aio_dispatch_handlers(ctx, INVALID_HANDLE_VALUE); - } - progress |= timerlistgroup_run_timers(&ctx->tlg); - return progress; + aio_bh_poll(ctx); + aio_dispatch_handlers(ctx, INVALID_HANDLE_VALUE); + timerlistgroup_run_timers(&ctx->tlg); } bool aio_poll(AioContext *ctx, bool blocking) diff --git a/util/async.c b/util/async.c index XXXXXXX..XXXXXXX 100644 --- a/util/async.c +++ b/util/async.c @@ -XXX,XX +XXX,XX @@ aio_ctx_dispatch(GSource *source, AioContext *ctx = (AioContext *) source; assert(callback == NULL); - aio_dispatch(ctx, true); + aio_dispatch(ctx); return true; } -- 2.9.3 From: Paolo Bonzini <pbonzini@redhat.com> Pull the increment/decrement pair out of aio_bh_poll and into the callers. Reviewed-by: Stefan Hajnoczi <stefanha@redhat.com> Signed-off-by: Paolo Bonzini <pbonzini@redhat.com> Reviewed-by: Fam Zheng <famz@redhat.com> Reviewed-by: Daniel P. Berrange <berrange@redhat.com> Message-id: 20170213135235.12274-18-pbonzini@redhat.com Signed-off-by: Stefan Hajnoczi <stefanha@redhat.com> --- util/aio-posix.c | 8 +++----- util/aio-win32.c | 8 ++++---- util/async.c | 12 ++++++------ 3 files changed, 13 insertions(+), 15 deletions(-) diff --git a/util/aio-posix.c b/util/aio-posix.c index XXXXXXX..XXXXXXX 100644 --- a/util/aio-posix.c +++ b/util/aio-posix.c @@ -XXX,XX +XXX,XX @@ static bool aio_dispatch_handlers(AioContext *ctx) void aio_dispatch(AioContext *ctx) { + qemu_lockcnt_inc(&ctx->list_lock); aio_bh_poll(ctx); - - qemu_lockcnt_inc(&ctx->list_lock); aio_dispatch_handlers(ctx); qemu_lockcnt_dec(&ctx->list_lock); @@ -XXX,XX +XXX,XX @@ bool aio_poll(AioContext *ctx, bool blocking) } npfd = 0; - qemu_lockcnt_dec(&ctx->list_lock); progress |= aio_bh_poll(ctx); if (ret > 0) { - qemu_lockcnt_inc(&ctx->list_lock); progress |= aio_dispatch_handlers(ctx); - qemu_lockcnt_dec(&ctx->list_lock); } + qemu_lockcnt_dec(&ctx->list_lock); + progress |= timerlistgroup_run_timers(&ctx->tlg); return progress; diff --git a/util/aio-win32.c b/util/aio-win32.c index XXXXXXX..XXXXXXX 100644 --- a/util/aio-win32.c +++ b/util/aio-win32.c @@ -XXX,XX +XXX,XX @@ static bool aio_dispatch_handlers(AioContext *ctx, HANDLE event) bool progress = false; AioHandler *tmp; - qemu_lockcnt_inc(&ctx->list_lock); - /* * We have to walk very carefully in case aio_set_fd_handler is * called while we're walking. @@ -XXX,XX +XXX,XX @@ static bool aio_dispatch_handlers(AioContext *ctx, HANDLE event) } } - qemu_lockcnt_dec(&ctx->list_lock); return progress; } void aio_dispatch(AioContext *ctx) { + qemu_lockcnt_inc(&ctx->list_lock); aio_bh_poll(ctx); aio_dispatch_handlers(ctx, INVALID_HANDLE_VALUE); + qemu_lockcnt_dec(&ctx->list_lock); timerlistgroup_run_timers(&ctx->tlg); } @@ -XXX,XX +XXX,XX @@ bool aio_poll(AioContext *ctx, bool blocking) } } - qemu_lockcnt_dec(&ctx->list_lock); first = true; /* ctx->notifier is always registered. */ @@ -XXX,XX +XXX,XX @@ bool aio_poll(AioContext *ctx, bool blocking) progress |= aio_dispatch_handlers(ctx, event); } while (count > 0); + qemu_lockcnt_dec(&ctx->list_lock); + progress |= timerlistgroup_run_timers(&ctx->tlg); return progress; } diff --git a/util/async.c b/util/async.c index XXXXXXX..XXXXXXX 100644 --- a/util/async.c +++ b/util/async.c @@ -XXX,XX +XXX,XX @@ void aio_bh_call(QEMUBH *bh) bh->cb(bh->opaque); } -/* Multiple occurrences of aio_bh_poll cannot be called concurrently */ +/* Multiple occurrences of aio_bh_poll cannot be called concurrently. + * The count in ctx->list_lock is incremented before the call, and is + * not affected by the call. + */ int aio_bh_poll(AioContext *ctx) { QEMUBH *bh, **bhp, *next; int ret; bool deleted = false; - qemu_lockcnt_inc(&ctx->list_lock); - ret = 0; for (bh = atomic_rcu_read(&ctx->first_bh); bh; bh = next) { next = atomic_rcu_read(&bh->next); @@ -XXX,XX +XXX,XX @@ int aio_bh_poll(AioContext *ctx) /* remove deleted bhs */ if (!deleted) { - qemu_lockcnt_dec(&ctx->list_lock); return ret; } - if (qemu_lockcnt_dec_and_lock(&ctx->list_lock)) { + if (qemu_lockcnt_dec_if_lock(&ctx->list_lock)) { bhp = &ctx->first_bh; while (*bhp) { bh = *bhp; @@ -XXX,XX +XXX,XX @@ int aio_bh_poll(AioContext *ctx) bhp = &bh->next; } } - qemu_lockcnt_unlock(&ctx->list_lock); + qemu_lockcnt_inc_and_unlock(&ctx->list_lock); } return ret; } -- 2.9.3 From: Paolo Bonzini <pbonzini@redhat.com> Reviewed-by: Stefan Hajnoczi <stefanha@redhat.com> Signed-off-by: Paolo Bonzini <pbonzini@redhat.com> Reviewed-by: Fam Zheng <famz@redhat.com> Reviewed-by: Daniel P. Berrange <berrange@redhat.com> Message-id: 20170213135235.12274-19-pbonzini@redhat.com Signed-off-by: Stefan Hajnoczi <stefanha@redhat.com> --- include/block/block_int.h | 64 +++++++++++++++++++++++++----------------- include/sysemu/block-backend.h | 14 ++++++--- 2 files changed, 49 insertions(+), 29 deletions(-) diff --git a/include/block/block_int.h b/include/block/block_int.h index XXXXXXX..XXXXXXX 100644 --- a/include/block/block_int.h +++ b/include/block/block_int.h @@ -XXX,XX +XXX,XX @@ struct BdrvChild { * copied as well. */ struct BlockDriverState { - int64_t total_sectors; /* if we are reading a disk image, give its - size in sectors */ + /* Protected by big QEMU lock or read-only after opening. No special + * locking needed during I/O... + */ int open_flags; /* flags used to open the file, re-used for re-open */ bool read_only; /* if true, the media is read only */ bool encrypted; /* if true, the media is encrypted */ @@ -XXX,XX +XXX,XX @@ struct BlockDriverState { bool sg; /* if true, the device is a /dev/sg* */ bool probed; /* if true, format was probed rather than specified */ - int copy_on_read; /* if nonzero, copy read backing sectors into image. - note this is a reference count */ - - CoQueue flush_queue; /* Serializing flush queue */ - bool active_flush_req; /* Flush request in flight? */ - unsigned int write_gen; /* Current data generation */ - unsigned int flushed_gen; /* Flushed write generation */ - BlockDriver *drv; /* NULL means no media */ void *opaque; @@ -XXX,XX +XXX,XX @@ struct BlockDriverState { BdrvChild *backing; BdrvChild *file; - /* Callback before write request is processed */ - NotifierWithReturnList before_write_notifiers; - - /* number of in-flight requests; overall and serialising */ - unsigned int in_flight; - unsigned int serialising_in_flight; - - bool wakeup; - - /* Offset after the highest byte written to */ - uint64_t wr_highest_offset; - /* I/O Limits */ BlockLimits bl; @@ -XXX,XX +XXX,XX @@ struct BlockDriverState { QTAILQ_ENTRY(BlockDriverState) bs_list; /* element of the list of monitor-owned BDS */ QTAILQ_ENTRY(BlockDriverState) monitor_list; - QLIST_HEAD(, BdrvDirtyBitmap) dirty_bitmaps; int refcnt; - QLIST_HEAD(, BdrvTrackedRequest) tracked_requests; - /* operation blockers */ QLIST_HEAD(, BdrvOpBlocker) op_blockers[BLOCK_OP_TYPE_MAX]; @@ -XXX,XX +XXX,XX @@ struct BlockDriverState { /* The error object in use for blocking operations on backing_hd */ Error *backing_blocker; + /* Protected by AioContext lock */ + + /* If true, copy read backing sectors into image. Can be >1 if more + * than one client has requested copy-on-read. + */ + int copy_on_read; + + /* If we are reading a disk image, give its size in sectors. + * Generally read-only; it is written to by load_vmstate and save_vmstate, + * but the block layer is quiescent during those. + */ + int64_t total_sectors; + + /* Callback before write request is processed */ + NotifierWithReturnList before_write_notifiers; + + /* number of in-flight requests; overall and serialising */ + unsigned int in_flight; + unsigned int serialising_in_flight; + + bool wakeup; + + /* Offset after the highest byte written to */ + uint64_t wr_highest_offset; + /* threshold limit for writes, in bytes. "High water mark". */ uint64_t write_threshold_offset; NotifierWithReturn write_threshold_notifier; @@ -XXX,XX +XXX,XX @@ struct BlockDriverState { /* counter for nested bdrv_io_plug */ unsigned io_plugged; + QLIST_HEAD(, BdrvTrackedRequest) tracked_requests; + CoQueue flush_queue; /* Serializing flush queue */ + bool active_flush_req; /* Flush request in flight? */ + unsigned int write_gen; /* Current data generation */ + unsigned int flushed_gen; /* Flushed write generation */ + + QLIST_HEAD(, BdrvDirtyBitmap) dirty_bitmaps; + + /* do we need to tell the quest if we have a volatile write cache? */ + int enable_write_cache; + int quiesce_counter; }; diff --git a/include/sysemu/block-backend.h b/include/sysemu/block-backend.h index XXXXXXX..XXXXXXX 100644 --- a/include/sysemu/block-backend.h +++ b/include/sysemu/block-backend.h @@ -XXX,XX +XXX,XX @@ typedef struct BlockDevOps { * fields that must be public. This is in particular for QLIST_ENTRY() and * friends so that BlockBackends can be kept in lists outside block-backend.c */ typedef struct BlockBackendPublic { - /* I/O throttling. - * throttle_state tells us if this BlockBackend has I/O limits configured. - * io_limits_disabled tells us if they are currently being enforced */ + /* I/O throttling has its own locking, but also some fields are + * protected by the AioContext lock. + */ + + /* Protected by AioContext lock. */ CoQueue throttled_reqs[2]; + + /* Nonzero if the I/O limits are currently being ignored; generally + * it is zero. */ unsigned int io_limits_disabled; /* The following fields are protected by the ThrottleGroup lock. - * See the ThrottleGroup documentation for details. */ + * See the ThrottleGroup documentation for details. + * throttle_state tells us if I/O limits are configured. */ ThrottleState *throttle_state; ThrottleTimers throttle_timers; unsigned pending_reqs[2]; -- 2.9.3 From: Paolo Bonzini <pbonzini@redhat.com> This uses the lock-free mutex described in the paper '"Blocking without Locking", or LFTHREADS: A lock-free thread library' by Gidenstam and Papatriantafilou. The same technique is used in OSv, and in fact the code is essentially a conversion to C of OSv's code. [Added missing coroutine_fn in tests/test-aio-multithread.c. --Stefan] Signed-off-by: Paolo Bonzini <pbonzini@redhat.com> Reviewed-by: Fam Zheng <famz@redhat.com> Message-id: 20170213181244.16297-2-pbonzini@redhat.com Signed-off-by: Stefan Hajnoczi <stefanha@redhat.com> --- include/qemu/coroutine.h | 17 ++++- tests/test-aio-multithread.c | 86 ++++++++++++++++++++++++ util/qemu-coroutine-lock.c | 155 ++++++++++++++++++++++++++++++++++++++++--- util/trace-events | 1 + 4 files changed, 246 insertions(+), 13 deletions(-) diff --git a/include/qemu/coroutine.h b/include/qemu/coroutine.h index XXXXXXX..XXXXXXX 100644 --- a/include/qemu/coroutine.h +++ b/include/qemu/coroutine.h @@ -XXX,XX +XXX,XX @@ bool qemu_co_queue_empty(CoQueue *queue); /** * Provides a mutex that can be used to synchronise coroutines */ +struct CoWaitRecord; typedef struct CoMutex { - bool locked; + /* Count of pending lockers; 0 for a free mutex, 1 for an + * uncontended mutex. + */ + unsigned locked; + + /* A queue of waiters. Elements are added atomically in front of + * from_push. to_pop is only populated, and popped from, by whoever + * is in charge of the next wakeup. This can be an unlocker or, + * through the handoff protocol, a locker that is about to go to sleep. + */ + QSLIST_HEAD(, CoWaitRecord) from_push, to_pop; + + unsigned handoff, sequence; + Coroutine *holder; - CoQueue queue; } CoMutex; /** diff --git a/tests/test-aio-multithread.c b/tests/test-aio-multithread.c index XXXXXXX..XXXXXXX 100644 --- a/tests/test-aio-multithread.c +++ b/tests/test-aio-multithread.c @@ -XXX,XX +XXX,XX @@ static void test_multi_co_schedule_10(void) test_multi_co_schedule(10); } +/* CoMutex thread-safety. */ + +static uint32_t atomic_counter; +static uint32_t running; +static uint32_t counter; +static CoMutex comutex; + +static void coroutine_fn test_multi_co_mutex_entry(void *opaque) +{ + while (!atomic_mb_read(&now_stopping)) { + qemu_co_mutex_lock(&comutex); + counter++; + qemu_co_mutex_unlock(&comutex); + + /* Increase atomic_counter *after* releasing the mutex. Otherwise + * there is a chance (it happens about 1 in 3 runs) that the iothread + * exits before the coroutine is woken up, causing a spurious + * assertion failure. + */ + atomic_inc(&atomic_counter); + } + atomic_dec(&running); +} + +static void test_multi_co_mutex(int threads, int seconds) +{ + int i; + + qemu_co_mutex_init(&comutex); + counter = 0; + atomic_counter = 0; + now_stopping = false; + + create_aio_contexts(); + assert(threads <= NUM_CONTEXTS); + running = threads; + for (i = 0; i < threads; i++) { + Coroutine *co1 = qemu_coroutine_create(test_multi_co_mutex_entry, NULL); + aio_co_schedule(ctx[i], co1); + } + + g_usleep(seconds * 1000000); + + atomic_mb_set(&now_stopping, true); + while (running > 0) { + g_usleep(100000); + } + + join_aio_contexts(); + g_test_message("%d iterations/second\n", counter / seconds); + g_assert_cmpint(counter, ==, atomic_counter); +} + +/* Testing with NUM_CONTEXTS threads focuses on the queue. The mutex however + * is too contended (and the threads spend too much time in aio_poll) + * to actually stress the handoff protocol. + */ +static void test_multi_co_mutex_1(void) +{ + test_multi_co_mutex(NUM_CONTEXTS, 1); +} + +static void test_multi_co_mutex_10(void) +{ + test_multi_co_mutex(NUM_CONTEXTS, 10); +} + +/* Testing with fewer threads stresses the handoff protocol too. Still, the + * case where the locker _can_ pick up a handoff is very rare, happening + * about 10 times in 1 million, so increase the runtime a bit compared to + * other "quick" testcases that only run for 1 second. + */ +static void test_multi_co_mutex_2_3(void) +{ + test_multi_co_mutex(2, 3); +} + +static void test_multi_co_mutex_2_30(void) +{ + test_multi_co_mutex(2, 30); +} + /* End of tests. */ int main(int argc, char **argv) @@ -XXX,XX +XXX,XX @@ int main(int argc, char **argv) g_test_add_func("/aio/multi/lifecycle", test_lifecycle); if (g_test_quick()) { g_test_add_func("/aio/multi/schedule", test_multi_co_schedule_1); + g_test_add_func("/aio/multi/mutex/contended", test_multi_co_mutex_1); + g_test_add_func("/aio/multi/mutex/handoff", test_multi_co_mutex_2_3); } else { g_test_add_func("/aio/multi/schedule", test_multi_co_schedule_10); + g_test_add_func("/aio/multi/mutex/contended", test_multi_co_mutex_10); + g_test_add_func("/aio/multi/mutex/handoff", test_multi_co_mutex_2_30); } return g_test_run(); } diff --git a/util/qemu-coroutine-lock.c b/util/qemu-coroutine-lock.c index XXXXXXX..XXXXXXX 100644 --- a/util/qemu-coroutine-lock.c +++ b/util/qemu-coroutine-lock.c @@ -XXX,XX +XXX,XX @@ * LIABILITY, WHETHER IN AN ACTION OF CONTRACT, TORT OR OTHERWISE, ARISING FROM, * OUT OF OR IN CONNECTION WITH THE SOFTWARE OR THE USE OR OTHER DEALINGS IN * THE SOFTWARE. + * + * The lock-free mutex implementation is based on OSv + * (core/lfmutex.cc, include/lockfree/mutex.hh). + * Copyright (C) 2013 Cloudius Systems, Ltd. */ #include "qemu/osdep.h" @@ -XXX,XX +XXX,XX @@ bool qemu_co_queue_empty(CoQueue *queue) return QSIMPLEQ_FIRST(&queue->entries) == NULL; } +/* The wait records are handled with a multiple-producer, single-consumer + * lock-free queue. There cannot be two concurrent pop_waiter() calls + * because pop_waiter() can only be called while mutex->handoff is zero. + * This can happen in three cases: + * - in qemu_co_mutex_unlock, before the hand-off protocol has started. + * In this case, qemu_co_mutex_lock will see mutex->handoff == 0 and + * not take part in the handoff. + * - in qemu_co_mutex_lock, if it steals the hand-off responsibility from + * qemu_co_mutex_unlock. In this case, qemu_co_mutex_unlock will fail + * the cmpxchg (it will see either 0 or the next sequence value) and + * exit. The next hand-off cannot begin until qemu_co_mutex_lock has + * woken up someone. + * - in qemu_co_mutex_unlock, if it takes the hand-off token itself. + * In this case another iteration starts with mutex->handoff == 0; + * a concurrent qemu_co_mutex_lock will fail the cmpxchg, and + * qemu_co_mutex_unlock will go back to case (1). + * + * The following functions manage this queue. + */ +typedef struct CoWaitRecord { + Coroutine *co; + QSLIST_ENTRY(CoWaitRecord) next; +} CoWaitRecord; + +static void push_waiter(CoMutex *mutex, CoWaitRecord *w) +{ + w->co = qemu_coroutine_self(); + QSLIST_INSERT_HEAD_ATOMIC(&mutex->from_push, w, next); +} + +static void move_waiters(CoMutex *mutex) +{ + QSLIST_HEAD(, CoWaitRecord) reversed; + QSLIST_MOVE_ATOMIC(&reversed, &mutex->from_push); + while (!QSLIST_EMPTY(&reversed)) { + CoWaitRecord *w = QSLIST_FIRST(&reversed); + QSLIST_REMOVE_HEAD(&reversed, next); + QSLIST_INSERT_HEAD(&mutex->to_pop, w, next); + } +} + +static CoWaitRecord *pop_waiter(CoMutex *mutex) +{ + CoWaitRecord *w; + + if (QSLIST_EMPTY(&mutex->to_pop)) { + move_waiters(mutex); + if (QSLIST_EMPTY(&mutex->to_pop)) { + return NULL; + } + } + w = QSLIST_FIRST(&mutex->to_pop); + QSLIST_REMOVE_HEAD(&mutex->to_pop, next); + return w; +} + +static bool has_waiters(CoMutex *mutex) +{ + return QSLIST_EMPTY(&mutex->to_pop) || QSLIST_EMPTY(&mutex->from_push); +} + void qemu_co_mutex_init(CoMutex *mutex) { memset(mutex, 0, sizeof(*mutex)); - qemu_co_queue_init(&mutex->queue); } -void coroutine_fn qemu_co_mutex_lock(CoMutex *mutex) +static void coroutine_fn qemu_co_mutex_lock_slowpath(CoMutex *mutex) { Coroutine *self = qemu_coroutine_self(); + CoWaitRecord w; + unsigned old_handoff; trace_qemu_co_mutex_lock_entry(mutex, self); + w.co = self; + push_waiter(mutex, &w); - while (mutex->locked) { - qemu_co_queue_wait(&mutex->queue); + /* This is the "Responsibility Hand-Off" protocol; a lock() picks from + * a concurrent unlock() the responsibility of waking somebody up. + */ + old_handoff = atomic_mb_read(&mutex->handoff); + if (old_handoff && + has_waiters(mutex) && + atomic_cmpxchg(&mutex->handoff, old_handoff, 0) == old_handoff) { + /* There can be no concurrent pops, because there can be only + * one active handoff at a time. + */ + CoWaitRecord *to_wake = pop_waiter(mutex); + Coroutine *co = to_wake->co; + if (co == self) { + /* We got the lock ourselves! */ + assert(to_wake == &w); + return; + } + + aio_co_wake(co); } - mutex->locked = true; - mutex->holder = self; - self->locks_held++; - + qemu_coroutine_yield(); trace_qemu_co_mutex_lock_return(mutex, self); } +void coroutine_fn qemu_co_mutex_lock(CoMutex *mutex) +{ + Coroutine *self = qemu_coroutine_self(); + + if (atomic_fetch_inc(&mutex->locked) == 0) { + /* Uncontended. */ + trace_qemu_co_mutex_lock_uncontended(mutex, self); + } else { + qemu_co_mutex_lock_slowpath(mutex); + } + mutex->holder = self; + self->locks_held++; +} + void coroutine_fn qemu_co_mutex_unlock(CoMutex *mutex) { Coroutine *self = qemu_coroutine_self(); trace_qemu_co_mutex_unlock_entry(mutex, self); - assert(mutex->locked == true); + assert(mutex->locked); assert(mutex->holder == self); assert(qemu_in_coroutine()); - mutex->locked = false; mutex->holder = NULL; self->locks_held--; - qemu_co_queue_next(&mutex->queue); + if (atomic_fetch_dec(&mutex->locked) == 1) { + /* No waiting qemu_co_mutex_lock(). Pfew, that was easy! */ + return; + } + + for (;;) { + CoWaitRecord *to_wake = pop_waiter(mutex); + unsigned our_handoff; + + if (to_wake) { + Coroutine *co = to_wake->co; + aio_co_wake(co); + break; + } + + /* Some concurrent lock() is in progress (we know this because + * mutex->locked was >1) but it hasn't yet put itself on the wait + * queue. Pick a sequence number for the handoff protocol (not 0). + */ + if (++mutex->sequence == 0) { + mutex->sequence = 1; + } + + our_handoff = mutex->sequence; + atomic_mb_set(&mutex->handoff, our_handoff); + if (!has_waiters(mutex)) { + /* The concurrent lock has not added itself yet, so it + * will be able to pick our handoff. + */ + break; + } + + /* Try to do the handoff protocol ourselves; if somebody else has + * already taken it, however, we're done and they're responsible. + */ + if (atomic_cmpxchg(&mutex->handoff, our_handoff, 0) != our_handoff) { + break; + } + } trace_qemu_co_mutex_unlock_return(mutex, self); } diff --git a/util/trace-events b/util/trace-events index XXXXXXX..XXXXXXX 100644 --- a/util/trace-events +++ b/util/trace-events @@ -XXX,XX +XXX,XX @@ qemu_coroutine_terminate(void *co) "self %p" # util/qemu-coroutine-lock.c qemu_co_queue_run_restart(void *co) "co %p" +qemu_co_mutex_lock_uncontended(void *mutex, void *self) "mutex %p self %p" qemu_co_mutex_lock_entry(void *mutex, void *self) "mutex %p self %p" qemu_co_mutex_lock_return(void *mutex, void *self) "mutex %p self %p" qemu_co_mutex_unlock_entry(void *mutex, void *self) "mutex %p self %p" -- 2.9.3 From: Paolo Bonzini <pbonzini@redhat.com> Running a very small critical section on pthread_mutex_t and CoMutex shows that pthread_mutex_t is much faster because it doesn't actually go to sleep. What happens is that the critical section is shorter than the latency of entering the kernel and thus FUTEX_WAIT always fails. With CoMutex there is no such latency but you still want to avoid wait and wakeup. So introduce it artificially. This only works with one waiters; because CoMutex is fair, it will always have more waits and wakeups than a pthread_mutex_t. Signed-off-by: Paolo Bonzini <pbonzini@redhat.com> Reviewed-by: Fam Zheng <famz@redhat.com> Message-id: 20170213181244.16297-3-pbonzini@redhat.com Signed-off-by: Stefan Hajnoczi <stefanha@redhat.com> --- include/qemu/coroutine.h | 5 +++++ util/qemu-coroutine-lock.c | 51 ++++++++++++++++++++++++++++++++++++++++------ util/qemu-coroutine.c | 2 +- 3 files changed, 51 insertions(+), 7 deletions(-) diff --git a/include/qemu/coroutine.h b/include/qemu/coroutine.h index XXXXXXX..XXXXXXX 100644 --- a/include/qemu/coroutine.h +++ b/include/qemu/coroutine.h @@ -XXX,XX +XXX,XX @@ typedef struct CoMutex { */ unsigned locked; + /* Context that is holding the lock. Useful to avoid spinning + * when two coroutines on the same AioContext try to get the lock. :) + */ + AioContext *ctx; + /* A queue of waiters. Elements are added atomically in front of * from_push. to_pop is only populated, and popped from, by whoever * is in charge of the next wakeup. This can be an unlocker or, diff --git a/util/qemu-coroutine-lock.c b/util/qemu-coroutine-lock.c index XXXXXXX..XXXXXXX 100644 --- a/util/qemu-coroutine-lock.c +++ b/util/qemu-coroutine-lock.c @@ -XXX,XX +XXX,XX @@ #include "qemu-common.h" #include "qemu/coroutine.h" #include "qemu/coroutine_int.h" +#include "qemu/processor.h" #include "qemu/queue.h" #include "block/aio.h" #include "trace.h" @@ -XXX,XX +XXX,XX @@ void qemu_co_mutex_init(CoMutex *mutex) memset(mutex, 0, sizeof(*mutex)); } -static void coroutine_fn qemu_co_mutex_lock_slowpath(CoMutex *mutex) +static void coroutine_fn qemu_co_mutex_wake(CoMutex *mutex, Coroutine *co) +{ + /* Read co before co->ctx; pairs with smp_wmb() in + * qemu_coroutine_enter(). + */ + smp_read_barrier_depends(); + mutex->ctx = co->ctx; + aio_co_wake(co); +} + +static void coroutine_fn qemu_co_mutex_lock_slowpath(AioContext *ctx, + CoMutex *mutex) { Coroutine *self = qemu_coroutine_self(); CoWaitRecord w; @@ -XXX,XX +XXX,XX @@ static void coroutine_fn qemu_co_mutex_lock_slowpath(CoMutex *mutex) if (co == self) { /* We got the lock ourselves! */ assert(to_wake == &w); + mutex->ctx = ctx; return; } - aio_co_wake(co); + qemu_co_mutex_wake(mutex, co); } qemu_coroutine_yield(); @@ -XXX,XX +XXX,XX @@ static void coroutine_fn qemu_co_mutex_lock_slowpath(CoMutex *mutex) void coroutine_fn qemu_co_mutex_lock(CoMutex *mutex) { + AioContext *ctx = qemu_get_current_aio_context(); Coroutine *self = qemu_coroutine_self(); + int waiters, i; - if (atomic_fetch_inc(&mutex->locked) == 0) { + /* Running a very small critical section on pthread_mutex_t and CoMutex + * shows that pthread_mutex_t is much faster because it doesn't actually + * go to sleep. What happens is that the critical section is shorter + * than the latency of entering the kernel and thus FUTEX_WAIT always + * fails. With CoMutex there is no such latency but you still want to + * avoid wait and wakeup. So introduce it artificially. + */ + i = 0; +retry_fast_path: + waiters = atomic_cmpxchg(&mutex->locked, 0, 1); + if (waiters != 0) { + while (waiters == 1 && ++i < 1000) { + if (atomic_read(&mutex->ctx) == ctx) { + break; + } + if (atomic_read(&mutex->locked) == 0) { + goto retry_fast_path; + } + cpu_relax(); + } + waiters = atomic_fetch_inc(&mutex->locked); + } + + if (waiters == 0) { /* Uncontended. */ trace_qemu_co_mutex_lock_uncontended(mutex, self); + mutex->ctx = ctx; } else { - qemu_co_mutex_lock_slowpath(mutex); + qemu_co_mutex_lock_slowpath(ctx, mutex); } mutex->holder = self; self->locks_held++; @@ -XXX,XX +XXX,XX @@ void coroutine_fn qemu_co_mutex_unlock(CoMutex *mutex) assert(mutex->holder == self); assert(qemu_in_coroutine()); + mutex->ctx = NULL; mutex->holder = NULL; self->locks_held--; if (atomic_fetch_dec(&mutex->locked) == 1) { @@ -XXX,XX +XXX,XX @@ void coroutine_fn qemu_co_mutex_unlock(CoMutex *mutex) unsigned our_handoff; if (to_wake) { - Coroutine *co = to_wake->co; - aio_co_wake(co); + qemu_co_mutex_wake(mutex, to_wake->co); break; } diff --git a/util/qemu-coroutine.c b/util/qemu-coroutine.c index XXXXXXX..XXXXXXX 100644 --- a/util/qemu-coroutine.c +++ b/util/qemu-coroutine.c @@ -XXX,XX +XXX,XX @@ void qemu_coroutine_enter(Coroutine *co) co->ctx = qemu_get_current_aio_context(); /* Store co->ctx before anything that stores co. Matches - * barrier in aio_co_wake. + * barrier in aio_co_wake and qemu_co_mutex_wake. */ smp_wmb(); -- 2.9.3 From: Paolo Bonzini <pbonzini@redhat.com> Add two implementations of the same benchmark as the previous patch, but using pthreads. One uses a normal QemuMutex, the other is Linux only and implements a fair mutex based on MCS locks and futexes. This shows that the slower performance of the 5-thread case is due to the fairness of CoMutex, rather than to coroutines. If fairness does not matter, as is the case with two threads, CoMutex can actually be faster than pthreads. Signed-off-by: Paolo Bonzini <pbonzini@redhat.com> Reviewed-by: Fam Zheng <famz@redhat.com> Message-id: 20170213181244.16297-4-pbonzini@redhat.com Signed-off-by: Stefan Hajnoczi <stefanha@redhat.com> --- tests/test-aio-multithread.c | 164 +++++++++++++++++++++++++++++++++++++++++++ 1 file changed, 164 insertions(+) diff --git a/tests/test-aio-multithread.c b/tests/test-aio-multithread.c index XXXXXXX..XXXXXXX 100644 --- a/tests/test-aio-multithread.c +++ b/tests/test-aio-multithread.c @@ -XXX,XX +XXX,XX @@ static void test_multi_co_mutex_2_30(void) test_multi_co_mutex(2, 30); } +/* Same test with fair mutexes, for performance comparison. */ + +#ifdef CONFIG_LINUX +#include "qemu/futex.h" + +/* The nodes for the mutex reside in this structure (on which we try to avoid + * false sharing). The head of the mutex is in the "mutex_head" variable. + */ +static struct { + int next, locked; + int padding[14]; +} nodes[NUM_CONTEXTS] __attribute__((__aligned__(64))); + +static int mutex_head = -1; + +static void mcs_mutex_lock(void) +{ + int prev; + + nodes[id].next = -1; + nodes[id].locked = 1; + prev = atomic_xchg(&mutex_head, id); + if (prev != -1) { + atomic_set(&nodes[prev].next, id); + qemu_futex_wait(&nodes[id].locked, 1); + } +} + +static void mcs_mutex_unlock(void) +{ + int next; + if (nodes[id].next == -1) { + if (atomic_read(&mutex_head) == id && + atomic_cmpxchg(&mutex_head, id, -1) == id) { + /* Last item in the list, exit. */ + return; + } + while (atomic_read(&nodes[id].next) == -1) { + /* mcs_mutex_lock did the xchg, but has not updated + * nodes[prev].next yet. + */ + } + } + + /* Wake up the next in line. */ + next = nodes[id].next; + nodes[next].locked = 0; + qemu_futex_wake(&nodes[next].locked, 1); +} + +static void test_multi_fair_mutex_entry(void *opaque) +{ + while (!atomic_mb_read(&now_stopping)) { + mcs_mutex_lock(); + counter++; + mcs_mutex_unlock(); + atomic_inc(&atomic_counter); + } + atomic_dec(&running); +} + +static void test_multi_fair_mutex(int threads, int seconds) +{ + int i; + + assert(mutex_head == -1); + counter = 0; + atomic_counter = 0; + now_stopping = false; + + create_aio_contexts(); + assert(threads <= NUM_CONTEXTS); + running = threads; + for (i = 0; i < threads; i++) { + Coroutine *co1 = qemu_coroutine_create(test_multi_fair_mutex_entry, NULL); + aio_co_schedule(ctx[i], co1); + } + + g_usleep(seconds * 1000000); + + atomic_mb_set(&now_stopping, true); + while (running > 0) { + g_usleep(100000); + } + + join_aio_contexts(); + g_test_message("%d iterations/second\n", counter / seconds); + g_assert_cmpint(counter, ==, atomic_counter); +} + +static void test_multi_fair_mutex_1(void) +{ + test_multi_fair_mutex(NUM_CONTEXTS, 1); +} + +static void test_multi_fair_mutex_10(void) +{ + test_multi_fair_mutex(NUM_CONTEXTS, 10); +} +#endif + +/* Same test with pthread mutexes, for performance comparison and + * portability. */ + +static QemuMutex mutex; + +static void test_multi_mutex_entry(void *opaque) +{ + while (!atomic_mb_read(&now_stopping)) { + qemu_mutex_lock(&mutex); + counter++; + qemu_mutex_unlock(&mutex); + atomic_inc(&atomic_counter); + } + atomic_dec(&running); +} + +static void test_multi_mutex(int threads, int seconds) +{ + int i; + + qemu_mutex_init(&mutex); + counter = 0; + atomic_counter = 0; + now_stopping = false; + + create_aio_contexts(); + assert(threads <= NUM_CONTEXTS); + running = threads; + for (i = 0; i < threads; i++) { + Coroutine *co1 = qemu_coroutine_create(test_multi_mutex_entry, NULL); + aio_co_schedule(ctx[i], co1); + } + + g_usleep(seconds * 1000000); + + atomic_mb_set(&now_stopping, true); + while (running > 0) { + g_usleep(100000); + } + + join_aio_contexts(); + g_test_message("%d iterations/second\n", counter / seconds); + g_assert_cmpint(counter, ==, atomic_counter); +} + +static void test_multi_mutex_1(void) +{ + test_multi_mutex(NUM_CONTEXTS, 1); +} + +static void test_multi_mutex_10(void) +{ + test_multi_mutex(NUM_CONTEXTS, 10); +} + /* End of tests. */ int main(int argc, char **argv) @@ -XXX,XX +XXX,XX @@ int main(int argc, char **argv) g_test_add_func("/aio/multi/schedule", test_multi_co_schedule_1); g_test_add_func("/aio/multi/mutex/contended", test_multi_co_mutex_1); g_test_add_func("/aio/multi/mutex/handoff", test_multi_co_mutex_2_3); +#ifdef CONFIG_LINUX + g_test_add_func("/aio/multi/mutex/mcs", test_multi_fair_mutex_1); +#endif + g_test_add_func("/aio/multi/mutex/pthread", test_multi_mutex_1); } else { g_test_add_func("/aio/multi/schedule", test_multi_co_schedule_10); g_test_add_func("/aio/multi/mutex/contended", test_multi_co_mutex_10); g_test_add_func("/aio/multi/mutex/handoff", test_multi_co_mutex_2_30); +#ifdef CONFIG_LINUX + g_test_add_func("/aio/multi/mutex/mcs", test_multi_fair_mutex_10); +#endif + g_test_add_func("/aio/multi/mutex/pthread", test_multi_mutex_10); } return g_test_run(); } -- 2.9.3 From: Paolo Bonzini <pbonzini@redhat.com> This will avoid forward references in the next patch. It is also more logical because CoQueue is not anymore the basic primitive. Signed-off-by: Paolo Bonzini <pbonzini@redhat.com> Reviewed-by: Fam Zheng <famz@redhat.com> Message-id: 20170213181244.16297-5-pbonzini@redhat.com Signed-off-by: Stefan Hajnoczi <stefanha@redhat.com> --- include/qemu/coroutine.h | 89 ++++++++++++++++++++++++------------------------ 1 file changed, 44 insertions(+), 45 deletions(-) diff --git a/include/qemu/coroutine.h b/include/qemu/coroutine.h index XXXXXXX..XXXXXXX 100644 --- a/include/qemu/coroutine.h +++ b/include/qemu/coroutine.h @@ -XXX,XX +XXX,XX @@ bool qemu_in_coroutine(void); */ bool qemu_coroutine_entered(Coroutine *co); - -/** - * CoQueues are a mechanism to queue coroutines in order to continue executing - * them later. They provide the fundamental primitives on which coroutine locks - * are built. - */ -typedef struct CoQueue { - QSIMPLEQ_HEAD(, Coroutine) entries; -} CoQueue; - -/** - * Initialise a CoQueue. This must be called before any other operation is used - * on the CoQueue. - */ -void qemu_co_queue_init(CoQueue *queue); - -/** - * Adds the current coroutine to the CoQueue and transfers control to the - * caller of the coroutine. - */ -void coroutine_fn qemu_co_queue_wait(CoQueue *queue); - -/** - * Restarts the next coroutine in the CoQueue and removes it from the queue. - * - * Returns true if a coroutine was restarted, false if the queue is empty. - */ -bool coroutine_fn qemu_co_queue_next(CoQueue *queue); - -/** - * Restarts all coroutines in the CoQueue and leaves the queue empty. - */ -void coroutine_fn qemu_co_queue_restart_all(CoQueue *queue); - -/** - * Enter the next coroutine in the queue - */ -bool qemu_co_enter_next(CoQueue *queue); - -/** - * Checks if the CoQueue is empty. - */ -bool qemu_co_queue_empty(CoQueue *queue); - - /** * Provides a mutex that can be used to synchronise coroutines */ @@ -XXX,XX +XXX,XX @@ void coroutine_fn qemu_co_mutex_lock(CoMutex *mutex); */ void coroutine_fn qemu_co_mutex_unlock(CoMutex *mutex); + +/** + * CoQueues are a mechanism to queue coroutines in order to continue executing + * them later. + */ +typedef struct CoQueue { + QSIMPLEQ_HEAD(, Coroutine) entries; +} CoQueue; + +/** + * Initialise a CoQueue. This must be called before any other operation is used + * on the CoQueue. + */ +void qemu_co_queue_init(CoQueue *queue); + +/** + * Adds the current coroutine to the CoQueue and transfers control to the + * caller of the coroutine. + */ +void coroutine_fn qemu_co_queue_wait(CoQueue *queue); + +/** + * Restarts the next coroutine in the CoQueue and removes it from the queue. + * + * Returns true if a coroutine was restarted, false if the queue is empty. + */ +bool coroutine_fn qemu_co_queue_next(CoQueue *queue); + +/** + * Restarts all coroutines in the CoQueue and leaves the queue empty. + */ +void coroutine_fn qemu_co_queue_restart_all(CoQueue *queue); + +/** + * Enter the next coroutine in the queue + */ +bool qemu_co_enter_next(CoQueue *queue); + +/** + * Checks if the CoQueue is empty. + */ +bool qemu_co_queue_empty(CoQueue *queue); + + typedef struct CoRwlock { bool writer; int reader; -- 2.9.3 From: Paolo Bonzini <pbonzini@redhat.com> All that CoQueue needs in order to become thread-safe is help from an external mutex. Add this to the API. Signed-off-by: Paolo Bonzini <pbonzini@redhat.com> Reviewed-by: Fam Zheng <famz@redhat.com> Message-id: 20170213181244.16297-6-pbonzini@redhat.com Signed-off-by: Stefan Hajnoczi <stefanha@redhat.com> --- include/qemu/coroutine.h | 8 +++++--- block/backup.c | 2 +- block/io.c | 4 ++-- block/nbd-client.c | 2 +- block/qcow2-cluster.c | 4 +--- block/sheepdog.c | 2 +- block/throttle-groups.c | 2 +- hw/9pfs/9p.c | 2 +- util/qemu-coroutine-lock.c | 24 +++++++++++++++++++++--- 9 files changed, 34 insertions(+), 16 deletions(-) diff --git a/include/qemu/coroutine.h b/include/qemu/coroutine.h index XXXXXXX..XXXXXXX 100644 --- a/include/qemu/coroutine.h +++ b/include/qemu/coroutine.h @@ -XXX,XX +XXX,XX @@ void coroutine_fn qemu_co_mutex_unlock(CoMutex *mutex); /** * CoQueues are a mechanism to queue coroutines in order to continue executing - * them later. + * them later. They are similar to condition variables, but they need help + * from an external mutex in order to maintain thread-safety. */ typedef struct CoQueue { QSIMPLEQ_HEAD(, Coroutine) entries; @@ -XXX,XX +XXX,XX @@ void qemu_co_queue_init(CoQueue *queue); /** * Adds the current coroutine to the CoQueue and transfers control to the - * caller of the coroutine. + * caller of the coroutine. The mutex is unlocked during the wait and + * locked again afterwards. */ -void coroutine_fn qemu_co_queue_wait(CoQueue *queue); +void coroutine_fn qemu_co_queue_wait(CoQueue *queue, CoMutex *mutex); /** * Restarts the next coroutine in the CoQueue and removes it from the queue. diff --git a/block/backup.c b/block/backup.c index XXXXXXX..XXXXXXX 100644 --- a/block/backup.c +++ b/block/backup.c @@ -XXX,XX +XXX,XX @@ static void coroutine_fn wait_for_overlapping_requests(BackupBlockJob *job, retry = false; QLIST_FOREACH(req, &job->inflight_reqs, list) { if (end > req->start && start < req->end) { - qemu_co_queue_wait(&req->wait_queue); + qemu_co_queue_wait(&req->wait_queue, NULL); retry = true; break; } diff --git a/block/io.c b/block/io.c index XXXXXXX..XXXXXXX 100644 --- a/block/io.c +++ b/block/io.c @@ -XXX,XX +XXX,XX @@ static bool coroutine_fn wait_serialising_requests(BdrvTrackedRequest *self) * (instead of producing a deadlock in the former case). */ if (!req->waiting_for) { self->waiting_for = req; - qemu_co_queue_wait(&req->wait_queue); + qemu_co_queue_wait(&req->wait_queue, NULL); self->waiting_for = NULL; retry = true; waited = true; @@ -XXX,XX +XXX,XX @@ int coroutine_fn bdrv_co_flush(BlockDriverState *bs) /* Wait until any previous flushes are completed */ while (bs->active_flush_req) { - qemu_co_queue_wait(&bs->flush_queue); + qemu_co_queue_wait(&bs->flush_queue, NULL); } bs->active_flush_req = true; diff --git a/block/nbd-client.c b/block/nbd-client.c index XXXXXXX..XXXXXXX 100644 --- a/block/nbd-client.c +++ b/block/nbd-client.c @@ -XXX,XX +XXX,XX @@ static void nbd_coroutine_start(NBDClientSession *s, /* Poor man semaphore. The free_sema is locked when no other request * can be accepted, and unlocked after receiving one reply. */ if (s->in_flight == MAX_NBD_REQUESTS) { - qemu_co_queue_wait(&s->free_sema); + qemu_co_queue_wait(&s->free_sema, NULL); assert(s->in_flight < MAX_NBD_REQUESTS); } s->in_flight++; diff --git a/block/qcow2-cluster.c b/block/qcow2-cluster.c index XXXXXXX..XXXXXXX 100644 --- a/block/qcow2-cluster.c +++ b/block/qcow2-cluster.c @@ -XXX,XX +XXX,XX @@ static int handle_dependencies(BlockDriverState *bs, uint64_t guest_offset, if (bytes == 0) { /* Wait for the dependency to complete. We need to recheck * the free/allocated clusters when we continue. */ - qemu_co_mutex_unlock(&s->lock); - qemu_co_queue_wait(&old_alloc->dependent_requests); - qemu_co_mutex_lock(&s->lock); + qemu_co_queue_wait(&old_alloc->dependent_requests, &s->lock); return -EAGAIN; } } diff --git a/block/sheepdog.c b/block/sheepdog.c index XXXXXXX..XXXXXXX 100644 --- a/block/sheepdog.c +++ b/block/sheepdog.c @@ -XXX,XX +XXX,XX @@ static void wait_for_overlapping_aiocb(BDRVSheepdogState *s, SheepdogAIOCB *acb) retry: QLIST_FOREACH(cb, &s->inflight_aiocb_head, aiocb_siblings) { if (AIOCBOverlapping(acb, cb)) { - qemu_co_queue_wait(&s->overlapping_queue); + qemu_co_queue_wait(&s->overlapping_queue, NULL); goto retry; } } diff --git a/block/throttle-groups.c b/block/throttle-groups.c index XXXXXXX..XXXXXXX 100644 --- a/block/throttle-groups.c +++ b/block/throttle-groups.c @@ -XXX,XX +XXX,XX @@ void coroutine_fn throttle_group_co_io_limits_intercept(BlockBackend *blk, if (must_wait || blkp->pending_reqs[is_write]) { blkp->pending_reqs[is_write]++; qemu_mutex_unlock(&tg->lock); - qemu_co_queue_wait(&blkp->throttled_reqs[is_write]); + qemu_co_queue_wait(&blkp->throttled_reqs[is_write], NULL); qemu_mutex_lock(&tg->lock); blkp->pending_reqs[is_write]--; } diff --git a/hw/9pfs/9p.c b/hw/9pfs/9p.c index XXXXXXX..XXXXXXX 100644 --- a/hw/9pfs/9p.c +++ b/hw/9pfs/9p.c @@ -XXX,XX +XXX,XX @@ static void coroutine_fn v9fs_flush(void *opaque) /* * Wait for pdu to complete. */ - qemu_co_queue_wait(&cancel_pdu->complete); + qemu_co_queue_wait(&cancel_pdu->complete, NULL); cancel_pdu->cancelled = 0; pdu_free(cancel_pdu); } diff --git a/util/qemu-coroutine-lock.c b/util/qemu-coroutine-lock.c index XXXXXXX..XXXXXXX 100644 --- a/util/qemu-coroutine-lock.c +++ b/util/qemu-coroutine-lock.c @@ -XXX,XX +XXX,XX @@ void qemu_co_queue_init(CoQueue *queue) QSIMPLEQ_INIT(&queue->entries); } -void coroutine_fn qemu_co_queue_wait(CoQueue *queue) +void coroutine_fn qemu_co_queue_wait(CoQueue *queue, CoMutex *mutex) { Coroutine *self = qemu_coroutine_self(); QSIMPLEQ_INSERT_TAIL(&queue->entries, self, co_queue_next); + + if (mutex) { + qemu_co_mutex_unlock(mutex); + } + + /* There is no race condition here. Other threads will call + * aio_co_schedule on our AioContext, which can reenter this + * coroutine but only after this yield and after the main loop + * has gone through the next iteration. + */ qemu_coroutine_yield(); assert(qemu_in_coroutine()); + + /* TODO: OSv implements wait morphing here, where the wakeup + * primitive automatically places the woken coroutine on the + * mutex's queue. This avoids the thundering herd effect. + */ + if (mutex) { + qemu_co_mutex_lock(mutex); + } } /** @@ -XXX,XX +XXX,XX @@ void qemu_co_rwlock_rdlock(CoRwlock *lock) Coroutine *self = qemu_coroutine_self(); while (lock->writer) { - qemu_co_queue_wait(&lock->queue); + qemu_co_queue_wait(&lock->queue, NULL); } lock->reader++; self->locks_held++; @@ -XXX,XX +XXX,XX @@ void qemu_co_rwlock_wrlock(CoRwlock *lock) Coroutine *self = qemu_coroutine_self(); while (lock->writer || lock->reader) { - qemu_co_queue_wait(&lock->queue); + qemu_co_queue_wait(&lock->queue, NULL); } lock->writer = true; self->locks_held++; -- 2.9.3 From: Paolo Bonzini <pbonzini@redhat.com> This adds a CoMutex around the existing CoQueue. Because the write-side can just take CoMutex, the old "writer" field is not necessary anymore. Instead of removing it altogether, count the number of pending writers during a read-side critical section and forbid further readers from entering. Signed-off-by: Paolo Bonzini <pbonzini@redhat.com> Reviewed-by: Fam Zheng <famz@redhat.com> Message-id: 20170213181244.16297-7-pbonzini@redhat.com Signed-off-by: Stefan Hajnoczi <stefanha@redhat.com> --- include/qemu/coroutine.h | 3 ++- util/qemu-coroutine-lock.c | 35 ++++++++++++++++++++++++----------- 2 files changed, 26 insertions(+), 12 deletions(-) diff --git a/include/qemu/coroutine.h b/include/qemu/coroutine.h index XXXXXXX..XXXXXXX 100644 --- a/include/qemu/coroutine.h +++ b/include/qemu/coroutine.h @@ -XXX,XX +XXX,XX @@ bool qemu_co_queue_empty(CoQueue *queue); typedef struct CoRwlock { - bool writer; + int pending_writer; int reader; + CoMutex mutex; CoQueue queue; } CoRwlock; diff --git a/util/qemu-coroutine-lock.c b/util/qemu-coroutine-lock.c index XXXXXXX..XXXXXXX 100644 --- a/util/qemu-coroutine-lock.c +++ b/util/qemu-coroutine-lock.c @@ -XXX,XX +XXX,XX @@ void qemu_co_rwlock_init(CoRwlock *lock) { memset(lock, 0, sizeof(*lock)); qemu_co_queue_init(&lock->queue); + qemu_co_mutex_init(&lock->mutex); } void qemu_co_rwlock_rdlock(CoRwlock *lock) { Coroutine *self = qemu_coroutine_self(); - while (lock->writer) { - qemu_co_queue_wait(&lock->queue, NULL); + qemu_co_mutex_lock(&lock->mutex); + /* For fairness, wait if a writer is in line. */ + while (lock->pending_writer) { + qemu_co_queue_wait(&lock->queue, &lock->mutex); } lock->reader++; + qemu_co_mutex_unlock(&lock->mutex); + + /* The rest of the read-side critical section is run without the mutex. */ self->locks_held++; } @@ -XXX,XX +XXX,XX @@ void qemu_co_rwlock_unlock(CoRwlock *lock) Coroutine *self = qemu_coroutine_self(); assert(qemu_in_coroutine()); - if (lock->writer) { - lock->writer = false; + if (!lock->reader) { + /* The critical section started in qemu_co_rwlock_wrlock. */ qemu_co_queue_restart_all(&lock->queue); } else { + self->locks_held--; + + qemu_co_mutex_lock(&lock->mutex); lock->reader--; assert(lock->reader >= 0); /* Wakeup only one waiting writer */ @@ -XXX,XX +XXX,XX @@ void qemu_co_rwlock_unlock(CoRwlock *lock) qemu_co_queue_next(&lock->queue); } } - self->locks_held--; + qemu_co_mutex_unlock(&lock->mutex); } void qemu_co_rwlock_wrlock(CoRwlock *lock) { - Coroutine *self = qemu_coroutine_self(); - - while (lock->writer || lock->reader) { - qemu_co_queue_wait(&lock->queue, NULL); + qemu_co_mutex_lock(&lock->mutex); + lock->pending_writer++; + while (lock->reader) { + qemu_co_queue_wait(&lock->queue, &lock->mutex); } - lock->writer = true; - self->locks_held++; + lock->pending_writer--; + + /* The rest of the write-side critical section is run with + * the mutex taken, so that lock->reader remains zero. + * There is no need to update self->locks_held. + */ } -- 2.9.3