The following changes since commit 75ee62ac606bfc9eb59310b9446df3434bf6e8c2: Merge remote-tracking branch 'remotes/ehabkost-gl/tags/x86-next-pull-request' into staging (2020-12-17 18:53:36 +0000) are available in the Git repository at: https://github.com/XanClic/qemu.git tags/pull-block-2020-12-18 for you to fetch changes up to 0e72078128229bf9efb542e396ab44bf91b91340: iotests: Fix _send_qemu_cmd with bash 5.1 (2020-12-18 12:47:38 +0100) ---------------------------------------------------------------- Block patches: - New block filter: preallocate (which, on writes beyond an image file's end, allocates big chunks of data so that such post-EOF writes will occur less frequently) - write-zeroes and block-status support for Quorum - Implementation of truncate for the nvme block driver similarly to the existing implementations for host block devices and iscsi devices - Block layer refactoring: Drop the tighten_restrictions concept in the block permission functions - iotest fixes ---------------------------------------------------------------- Alberto Garcia (2): quorum: Implement bdrv_co_block_status() quorum: Implement bdrv_co_pwrite_zeroes() Max Reitz (2): iotests/102: Pass $QEMU_HANDLE to _send_qemu_cmd iotests: Fix _send_qemu_cmd with bash 5.1 Philippe Mathieu-Daudé (1): block/nvme: Implement fake truncate() coroutine Vladimir Sementsov-Ogievskiy (25): block: add bdrv_refresh_perms() helper block: bdrv_set_perm() drop redundant parameters. block: bdrv_child_set_perm() drop redundant parameters. block: drop tighten_restrictions block: simplify comment to BDRV_REQ_SERIALISING block/io.c: drop assertion on double waiting for request serialisation block/io: split out bdrv_find_conflicting_request block/io: bdrv_wait_serialising_requests_locked: drop extra bs arg block: bdrv_mark_request_serialising: split non-waiting function block: introduce BDRV_REQ_NO_WAIT flag block: bdrv_check_perm(): process children anyway block: introduce preallocate filter qemu-io: add preallocate mode parameter for truncate command iotests: qemu_io_silent: support --image-opts iotests.py: execute_setup_common(): add required_fmts argument iotests: add 298 to test new preallocate filter driver scripts/simplebench: fix grammar: s/successed/succeeded/ scripts/simplebench: support iops scripts/simplebench: use standard deviation for +- error simplebench: rename ascii() to results_to_text() simplebench: move results_to_text() into separate file simplebench/results_to_text: improve view of the table simplebench/results_to_text: add difference line to the table simplebench/results_to_text: make executable scripts/simplebench: add bench_prealloc.py docs/system/qemu-block-drivers.rst.inc | 26 ++ qapi/block-core.json | 20 +- include/block/block.h | 20 +- include/block/block_int.h | 3 +- block.c | 185 +++----- block/file-posix.c | 2 +- block/io.c | 130 +++--- block/nvme.c | 24 ++ block/preallocate.c | 559 +++++++++++++++++++++++++ block/quorum.c | 88 +++- qemu-io-cmds.c | 46 +- block/meson.build | 1 + scripts/simplebench/bench-example.py | 3 +- scripts/simplebench/bench_prealloc.py | 132 ++++++ scripts/simplebench/bench_write_req.py | 3 +- scripts/simplebench/results_to_text.py | 126 ++++++ scripts/simplebench/simplebench.py | 66 ++- tests/qemu-iotests/085.out | 167 ++++++-- tests/qemu-iotests/094.out | 10 +- tests/qemu-iotests/095.out | 4 +- tests/qemu-iotests/102 | 2 +- tests/qemu-iotests/102.out | 2 +- tests/qemu-iotests/109.out | 88 +++- tests/qemu-iotests/117.out | 13 +- tests/qemu-iotests/127.out | 12 +- tests/qemu-iotests/140.out | 10 +- tests/qemu-iotests/141.out | 128 ++++-- tests/qemu-iotests/143.out | 4 +- tests/qemu-iotests/144.out | 28 +- tests/qemu-iotests/153.out | 18 +- tests/qemu-iotests/156.out | 39 +- tests/qemu-iotests/161.out | 18 +- tests/qemu-iotests/173.out | 25 +- tests/qemu-iotests/182.out | 42 +- tests/qemu-iotests/183.out | 19 +- tests/qemu-iotests/185.out | 45 +- tests/qemu-iotests/191.out | 12 +- tests/qemu-iotests/223.out | 92 ++-- tests/qemu-iotests/229.out | 13 +- tests/qemu-iotests/249.out | 16 +- tests/qemu-iotests/298 | 186 ++++++++ tests/qemu-iotests/298.out | 5 + tests/qemu-iotests/308.out | 103 ++++- tests/qemu-iotests/312 | 159 +++++++ tests/qemu-iotests/312.out | 81 ++++ tests/qemu-iotests/common.qemu | 11 +- tests/qemu-iotests/group | 2 + tests/qemu-iotests/iotests.py | 16 +- 48 files changed, 2357 insertions(+), 447 deletions(-) create mode 100644 block/preallocate.c create mode 100755 scripts/simplebench/bench_prealloc.py create mode 100755 scripts/simplebench/results_to_text.py create mode 100644 tests/qemu-iotests/298 create mode 100644 tests/qemu-iotests/298.out create mode 100755 tests/qemu-iotests/312 create mode 100644 tests/qemu-iotests/312.out -- 2.29.2 From: Vladimir Sementsov-Ogievskiy <vsementsov@virtuozzo.com> Make separate function for common pattern. Signed-off-by: Vladimir Sementsov-Ogievskiy <vsementsov@virtuozzo.com> Message-Id: <20201106124241.16950-5-vsementsov@virtuozzo.com> [mreitz: Squashed in https://lists.nongnu.org/archive/html/qemu-block/2020-11/msg00299.html] Signed-off-by: Max Reitz <mreitz@redhat.com> --- block.c | 61 +++++++++++++++++++++++++++++---------------------------- 1 file changed, 31 insertions(+), 30 deletions(-) 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_child_abort_perm_update(BdrvChild *c) bdrv_abort_perm_update(c->bs); } +static int bdrv_refresh_perms(BlockDriverState *bs, bool *tighten_restrictions, + Error **errp) +{ + int ret; + uint64_t perm, shared_perm; + + bdrv_get_cumulative_perm(bs, &perm, &shared_perm); + ret = bdrv_check_perm(bs, NULL, perm, shared_perm, NULL, + tighten_restrictions, errp); + if (ret < 0) { + bdrv_abort_perm_update(bs); + return ret; + } + bdrv_set_perm(bs, perm, shared_perm); + + return 0; +} + int bdrv_child_try_set_perm(BdrvChild *c, uint64_t perm, uint64_t shared, Error **errp) { @@ -XXX,XX +XXX,XX @@ static void bdrv_replace_child(BdrvChild *child, BlockDriverState *new_bs) } if (old_bs) { - /* Update permissions for old node. This is guaranteed to succeed - * because we're just taking a parent away, so we're loosening - * restrictions. */ bool tighten_restrictions; - int ret; - bdrv_get_cumulative_perm(old_bs, &perm, &shared_perm); - ret = bdrv_check_perm(old_bs, NULL, perm, shared_perm, NULL, - &tighten_restrictions, NULL); + /* + * Update permissions for old node. We're just taking a parent away, so + * we're loosening restrictions. Errors of permission update are not + * fatal in this case, ignore them. + */ + bdrv_refresh_perms(old_bs, &tighten_restrictions, NULL); assert(tighten_restrictions == false); - if (ret < 0) { - /* We only tried to loosen restrictions, so errors are not fatal */ - bdrv_abort_perm_update(old_bs); - } else { - bdrv_set_perm(old_bs, perm, shared_perm); - } /* When the parent requiring a non-default AioContext is removed, the * node moves back to the main AioContext */ @@ -XXX,XX +XXX,XX @@ void bdrv_init_with_whitelist(void) int coroutine_fn bdrv_co_invalidate_cache(BlockDriverState *bs, Error **errp) { BdrvChild *child, *parent; - uint64_t perm, shared_perm; Error *local_err = NULL; int ret; BdrvDirtyBitmap *bm; @@ -XXX,XX +XXX,XX @@ int coroutine_fn bdrv_co_invalidate_cache(BlockDriverState *bs, Error **errp) */ if (bs->open_flags & BDRV_O_INACTIVE) { bs->open_flags &= ~BDRV_O_INACTIVE; - bdrv_get_cumulative_perm(bs, &perm, &shared_perm); - ret = bdrv_check_perm(bs, NULL, perm, shared_perm, NULL, NULL, errp); + ret = bdrv_refresh_perms(bs, NULL, errp); if (ret < 0) { - bdrv_abort_perm_update(bs); bs->open_flags |= BDRV_O_INACTIVE; return ret; } - bdrv_set_perm(bs, perm, shared_perm); if (bs->drv->bdrv_co_invalidate_cache) { bs->drv->bdrv_co_invalidate_cache(bs, &local_err); @@ -XXX,XX +XXX,XX @@ static int bdrv_inactivate_recurse(BlockDriverState *bs) { BdrvChild *child, *parent; bool tighten_restrictions; - uint64_t perm, shared_perm; int ret; if (!bs->drv) { @@ -XXX,XX +XXX,XX @@ static int bdrv_inactivate_recurse(BlockDriverState *bs) bs->open_flags |= BDRV_O_INACTIVE; - /* Update permissions, they may differ for inactive nodes */ - bdrv_get_cumulative_perm(bs, &perm, &shared_perm); - ret = bdrv_check_perm(bs, NULL, perm, shared_perm, NULL, - &tighten_restrictions, NULL); + /* + * Update permissions, they may differ for inactive nodes. + * We only tried to loosen restrictions, so errors are not fatal, ignore + * them. + */ + bdrv_refresh_perms(bs, &tighten_restrictions, NULL); assert(tighten_restrictions == false); - if (ret < 0) { - /* We only tried to loosen restrictions, so errors are not fatal */ - bdrv_abort_perm_update(bs); - } else { - bdrv_set_perm(bs, perm, shared_perm); - } - /* Recursively inactivate children */ QLIST_FOREACH(child, &bs->children, next) { -- 2.29.2 From: Vladimir Sementsov-Ogievskiy <vsementsov@virtuozzo.com> We should never set permissions other than cumulative permissions of parents. During bdrv_reopen_multiple() we _check_ for synthetic permissions but when we do _set_ the graph is already updated. Add an assertion to bdrv_reopen_multiple(), other cases are more obvious. Signed-off-by: Vladimir Sementsov-Ogievskiy <vsementsov@virtuozzo.com> Message-Id: <20201106124241.16950-6-vsementsov@virtuozzo.com> Reviewed-by: Max Reitz <mreitz@redhat.com> Signed-off-by: Max Reitz <mreitz@redhat.com> --- block.c | 29 +++++++++++++++-------------- 1 file changed, 15 insertions(+), 14 deletions(-) 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_abort_perm_update(BlockDriverState *bs) } } -static void bdrv_set_perm(BlockDriverState *bs, uint64_t cumulative_perms, - uint64_t cumulative_shared_perms) +static void bdrv_set_perm(BlockDriverState *bs) { + uint64_t cumulative_perms, cumulative_shared_perms; BlockDriver *drv = bs->drv; BdrvChild *c; @@ -XXX,XX +XXX,XX @@ static void bdrv_set_perm(BlockDriverState *bs, uint64_t cumulative_perms, return; } + bdrv_get_cumulative_perm(bs, &cumulative_perms, &cumulative_shared_perms); + /* Update this node */ if (drv->bdrv_set_perm) { drv->bdrv_set_perm(bs, cumulative_perms, cumulative_shared_perms); @@ -XXX,XX +XXX,XX @@ static int bdrv_child_check_perm(BdrvChild *c, BlockReopenQueue *q, static void bdrv_child_set_perm(BdrvChild *c, uint64_t perm, uint64_t shared) { - uint64_t cumulative_perms, cumulative_shared_perms; - c->has_backup_perm = false; c->perm = perm; c->shared_perm = shared; - bdrv_get_cumulative_perm(c->bs, &cumulative_perms, - &cumulative_shared_perms); - bdrv_set_perm(c->bs, cumulative_perms, cumulative_shared_perms); + bdrv_set_perm(c->bs); } static void bdrv_child_abort_perm_update(BdrvChild *c) @@ -XXX,XX +XXX,XX @@ static int bdrv_refresh_perms(BlockDriverState *bs, bool *tighten_restrictions, bdrv_abort_perm_update(bs); return ret; } - bdrv_set_perm(bs, perm, shared_perm); + bdrv_set_perm(bs); return 0; } @@ -XXX,XX +XXX,XX @@ static void bdrv_replace_child_noperm(BdrvChild *child, static void bdrv_replace_child(BdrvChild *child, BlockDriverState *new_bs) { BlockDriverState *old_bs = child->bs; - uint64_t perm, shared_perm; /* Asserts that child->frozen == false */ bdrv_replace_child_noperm(child, new_bs); @@ -XXX,XX +XXX,XX @@ static void bdrv_replace_child(BdrvChild *child, BlockDriverState *new_bs) * restrictions. */ if (new_bs) { - bdrv_get_cumulative_perm(new_bs, &perm, &shared_perm); - bdrv_set_perm(new_bs, perm, shared_perm); + bdrv_set_perm(new_bs); } if (old_bs) { @@ -XXX,XX +XXX,XX @@ cleanup_perm: } if (ret == 0) { - bdrv_set_perm(state->bs, state->perm, state->shared_perm); + uint64_t perm, shared; + + bdrv_get_cumulative_perm(state->bs, &perm, &shared); + assert(perm == state->perm); + assert(shared == state->shared_perm); + + bdrv_set_perm(state->bs); } else { bdrv_abort_perm_update(state->bs); if (state->replace_backing_bs && state->new_backing_bs) { @@ -XXX,XX +XXX,XX @@ static void bdrv_replace_node_common(BlockDriverState *from, bdrv_unref(from); } - bdrv_get_cumulative_perm(to, &perm, &shared); - bdrv_set_perm(to, perm, shared); + bdrv_set_perm(to); out: g_slist_free(list); -- 2.29.2 From: Vladimir Sementsov-Ogievskiy <vsementsov@virtuozzo.com> We must set the permission used for _check_. Assert that we have backup and drop extra arguments. Signed-off-by: Vladimir Sementsov-Ogievskiy <vsementsov@virtuozzo.com> Message-Id: <20201106124241.16950-7-vsementsov@virtuozzo.com> Reviewed-by: Max Reitz <mreitz@redhat.com> Signed-off-by: Max Reitz <mreitz@redhat.com> --- block.c | 15 ++++----------- 1 file changed, 4 insertions(+), 11 deletions(-) diff --git a/block.c b/block.c index XXXXXXX..XXXXXXX 100644 --- a/block.c +++ b/block.c @@ -XXX,XX +XXX,XX @@ static int bdrv_child_check_perm(BdrvChild *c, BlockReopenQueue *q, GSList *ignore_children, bool *tighten_restrictions, Error **errp); static void bdrv_child_abort_perm_update(BdrvChild *c); -static void bdrv_child_set_perm(BdrvChild *c, uint64_t perm, uint64_t shared); +static void bdrv_child_set_perm(BdrvChild *c); typedef struct BlockReopenQueueEntry { bool prepared; @@ -XXX,XX +XXX,XX @@ static void bdrv_set_perm(BlockDriverState *bs) /* Update all children */ QLIST_FOREACH(c, &bs->children, next) { - uint64_t cur_perm, cur_shared; - bdrv_child_perm(bs, c->bs, c, c->role, NULL, - cumulative_perms, cumulative_shared_perms, - &cur_perm, &cur_shared); - bdrv_child_set_perm(c, cur_perm, cur_shared); + bdrv_child_set_perm(c); } } @@ -XXX,XX +XXX,XX @@ static int bdrv_child_check_perm(BdrvChild *c, BlockReopenQueue *q, return 0; } -static void bdrv_child_set_perm(BdrvChild *c, uint64_t perm, uint64_t shared) +static void bdrv_child_set_perm(BdrvChild *c) { c->has_backup_perm = false; - c->perm = perm; - c->shared_perm = shared; - bdrv_set_perm(c->bs); } @@ -XXX,XX +XXX,XX @@ int bdrv_child_try_set_perm(BdrvChild *c, uint64_t perm, uint64_t shared, return ret; } - bdrv_child_set_perm(c, perm, shared); + bdrv_child_set_perm(c); return 0; } -- 2.29.2 From: Vladimir Sementsov-Ogievskiy <vsementsov@virtuozzo.com> The only users of this thing are: 1. bdrv_child_try_set_perm, to ignore failures on loosen restrictions 2. assertion in bdrv_replace_child 3. assertion in bdrv_inactivate_recurse Assertions are not enough reason for overcomplication the permission update system. So, look at bdrv_child_try_set_perm. We are interested in tighten_restrictions only on failure. But on failure this field is not reliable: we may fail in the middle of permission update, some nodes are not touched and we don't know should their permissions be tighten or not. So, we rely on the fact that if we loose restrictions on some node (or BdrvChild), we'll not tighten restriction in the whole subtree as part of this update (assertions 2 and 3 rely on this fact as well). And, if we rely on this fact anyway, we can just check it on top, and don't pass additional pointer through the whole recursive infrastructure. Note also, that further patches will fix real bugs in permission update system, so now is good time to simplify it, as a help for further refactorings. Signed-off-by: Vladimir Sementsov-Ogievskiy <vsementsov@virtuozzo.com> Message-Id: <20201106124241.16950-8-vsementsov@virtuozzo.com> [mreitz: Fixed rebase conflict] Signed-off-by: Max Reitz <mreitz@redhat.com> --- block.c | 89 +++++++++++---------------------------------------------- 1 file changed, 17 insertions(+), 72 deletions(-) diff --git a/block.c b/block.c index XXXXXXX..XXXXXXX 100644 --- a/block.c +++ b/block.c @@ -XXX,XX +XXX,XX @@ static int bdrv_fill_options(QDict **options, const char *filename, static int bdrv_child_check_perm(BdrvChild *c, BlockReopenQueue *q, uint64_t perm, uint64_t shared, - GSList *ignore_children, - bool *tighten_restrictions, Error **errp); + GSList *ignore_children, Error **errp); static void bdrv_child_abort_perm_update(BdrvChild *c); static void bdrv_child_set_perm(BdrvChild *c); @@ -XXX,XX +XXX,XX @@ static void bdrv_child_perm(BlockDriverState *bs, BlockDriverState *child_bs, * permissions of all its parents. This involves checking whether all necessary * permission changes to child nodes can be performed. * - * Will set *tighten_restrictions to true if and only if new permissions have to - * be taken or currently shared permissions are to be unshared. Otherwise, - * errors are not fatal as long as the caller accepts that the restrictions - * remain tighter than they need to be. The caller still has to abort the - * transaction. - * @tighten_restrictions cannot be used together with @q: When reopening, we may - * encounter fatal errors even though no restrictions are to be tightened. For - * example, changing a node from RW to RO will fail if the WRITE permission is - * to be kept. - * * A call to this function must always be followed by a call to bdrv_set_perm() * or bdrv_abort_perm_update(). */ static int bdrv_check_perm(BlockDriverState *bs, BlockReopenQueue *q, uint64_t cumulative_perms, uint64_t cumulative_shared_perms, - GSList *ignore_children, - bool *tighten_restrictions, Error **errp) + GSList *ignore_children, Error **errp) { BlockDriver *drv = bs->drv; BdrvChild *c; int ret; - assert(!q || !tighten_restrictions); - - if (tighten_restrictions) { - uint64_t current_perms, current_shared; - uint64_t added_perms, removed_shared_perms; - - bdrv_get_cumulative_perm(bs, &current_perms, &current_shared); - - added_perms = cumulative_perms & ~current_perms; - removed_shared_perms = current_shared & ~cumulative_shared_perms; - - *tighten_restrictions = added_perms || removed_shared_perms; - } - /* Write permissions never work with read-only images */ if ((cumulative_perms & (BLK_PERM_WRITE | BLK_PERM_WRITE_UNCHANGED)) && !bdrv_is_writable_after_reopen(bs, q)) @@ -XXX,XX +XXX,XX @@ static int bdrv_check_perm(BlockDriverState *bs, BlockReopenQueue *q, /* Check all children */ QLIST_FOREACH(c, &bs->children, next) { uint64_t cur_perm, cur_shared; - bool child_tighten_restr; bdrv_child_perm(bs, c->bs, c, c->role, q, cumulative_perms, cumulative_shared_perms, &cur_perm, &cur_shared); ret = bdrv_child_check_perm(c, q, cur_perm, cur_shared, ignore_children, - tighten_restrictions ? &child_tighten_restr - : NULL, errp); - if (tighten_restrictions) { - *tighten_restrictions |= child_tighten_restr; - } if (ret < 0) { return ret; } @@ -XXX,XX +XXX,XX @@ char *bdrv_perm_names(uint64_t perm) * set, the BdrvChild objects in this list are ignored in the calculations; * this allows checking permission updates for an existing reference. * - * See bdrv_check_perm() for the semantics of @tighten_restrictions. - * * Needs to be followed by a call to either bdrv_set_perm() or * bdrv_abort_perm_update(). */ static int bdrv_check_update_perm(BlockDriverState *bs, BlockReopenQueue *q, uint64_t new_used_perm, uint64_t new_shared_perm, GSList *ignore_children, - bool *tighten_restrictions, Error **errp) { BdrvChild *c; uint64_t cumulative_perms = new_used_perm; uint64_t cumulative_shared_perms = new_shared_perm; - assert(!q || !tighten_restrictions); /* There is no reason why anyone couldn't tolerate write_unchanged */ assert(new_shared_perm & BLK_PERM_WRITE_UNCHANGED); @@ -XXX,XX +XXX,XX @@ static int bdrv_check_update_perm(BlockDriverState *bs, BlockReopenQueue *q, char *user = bdrv_child_user_desc(c); char *perm_names = bdrv_perm_names(new_used_perm & ~c->shared_perm); - if (tighten_restrictions) { - *tighten_restrictions = true; - } - error_setg(errp, "Conflicts with use by %s as '%s', which does not " "allow '%s' on %s", user, c->name, perm_names, bdrv_get_node_name(c->bs)); @@ -XXX,XX +XXX,XX @@ static int bdrv_check_update_perm(BlockDriverState *bs, BlockReopenQueue *q, char *user = bdrv_child_user_desc(c); char *perm_names = bdrv_perm_names(c->perm & ~new_shared_perm); - if (tighten_restrictions) { - *tighten_restrictions = true; - } - error_setg(errp, "Conflicts with use by %s as '%s', which uses " "'%s' on %s", user, c->name, perm_names, bdrv_get_node_name(c->bs)); @@ -XXX,XX +XXX,XX @@ static int bdrv_check_update_perm(BlockDriverState *bs, BlockReopenQueue *q, } return bdrv_check_perm(bs, q, cumulative_perms, cumulative_shared_perms, - ignore_children, tighten_restrictions, errp); + ignore_children, errp); } /* Needs to be followed by a call to either bdrv_child_set_perm() or * bdrv_child_abort_perm_update(). */ static int bdrv_child_check_perm(BdrvChild *c, BlockReopenQueue *q, uint64_t perm, uint64_t shared, - GSList *ignore_children, - bool *tighten_restrictions, Error **errp) + GSList *ignore_children, Error **errp) { int ret; ignore_children = g_slist_prepend(g_slist_copy(ignore_children), c); - ret = bdrv_check_update_perm(c->bs, q, perm, shared, ignore_children, - tighten_restrictions, errp); + ret = bdrv_check_update_perm(c->bs, q, perm, shared, ignore_children, errp); g_slist_free(ignore_children); if (ret < 0) { @@ -XXX,XX +XXX,XX @@ static void bdrv_child_abort_perm_update(BdrvChild *c) bdrv_abort_perm_update(c->bs); } -static int bdrv_refresh_perms(BlockDriverState *bs, bool *tighten_restrictions, - Error **errp) +static int bdrv_refresh_perms(BlockDriverState *bs, Error **errp) { int ret; uint64_t perm, shared_perm; bdrv_get_cumulative_perm(bs, &perm, &shared_perm); - ret = bdrv_check_perm(bs, NULL, perm, shared_perm, NULL, - tighten_restrictions, errp); + ret = bdrv_check_perm(bs, NULL, perm, shared_perm, NULL, errp); if (ret < 0) { bdrv_abort_perm_update(bs); return ret; @@ -XXX,XX +XXX,XX @@ int bdrv_child_try_set_perm(BdrvChild *c, uint64_t perm, uint64_t shared, { Error *local_err = NULL; int ret; - bool tighten_restrictions; - ret = bdrv_child_check_perm(c, NULL, perm, shared, NULL, - &tighten_restrictions, &local_err); + ret = bdrv_child_check_perm(c, NULL, perm, shared, NULL, &local_err); if (ret < 0) { bdrv_child_abort_perm_update(c); - if (tighten_restrictions) { + if ((perm & ~c->perm) || (c->shared_perm & ~shared)) { + /* tighten permissions */ error_propagate(errp, local_err); } else { /* @@ -XXX,XX +XXX,XX @@ static void bdrv_replace_child(BdrvChild *child, BlockDriverState *new_bs) } if (old_bs) { - bool tighten_restrictions; - /* * Update permissions for old node. We're just taking a parent away, so * we're loosening restrictions. Errors of permission update are not * fatal in this case, ignore them. */ - bdrv_refresh_perms(old_bs, &tighten_restrictions, NULL); - assert(tighten_restrictions == false); + bdrv_refresh_perms(old_bs, NULL); /* When the parent requiring a non-default AioContext is removed, the * node moves back to the main AioContext */ @@ -XXX,XX +XXX,XX @@ BdrvChild *bdrv_root_attach_child(BlockDriverState *child_bs, Error *local_err = NULL; int ret; - ret = bdrv_check_update_perm(child_bs, NULL, perm, shared_perm, NULL, NULL, - errp); + ret = bdrv_check_update_perm(child_bs, NULL, perm, shared_perm, NULL, errp); if (ret < 0) { bdrv_abort_perm_update(child_bs); bdrv_unref(child_bs); @@ -XXX,XX +XXX,XX @@ int bdrv_reopen_multiple(BlockReopenQueue *bs_queue, Error **errp) QTAILQ_FOREACH(bs_entry, bs_queue, entry) { BDRVReopenState *state = &bs_entry->state; ret = bdrv_check_perm(state->bs, bs_queue, state->perm, - state->shared_perm, NULL, NULL, errp); + state->shared_perm, NULL, errp); if (ret < 0) { goto cleanup_perm; } @@ -XXX,XX +XXX,XX @@ int bdrv_reopen_multiple(BlockReopenQueue *bs_queue, Error **errp) bs_queue, state->perm, state->shared_perm, &nperm, &nshared); ret = bdrv_check_update_perm(state->new_backing_bs, NULL, - nperm, nshared, NULL, NULL, errp); + nperm, nshared, NULL, errp); if (ret < 0) { goto cleanup_perm; } @@ -XXX,XX +XXX,XX @@ static void bdrv_replace_node_common(BlockDriverState *from, /* Check whether the required permissions can be granted on @to, ignoring * all BdrvChild in @list so that they can't block themselves. */ - ret = bdrv_check_update_perm(to, NULL, perm, shared, list, NULL, errp); + ret = bdrv_check_update_perm(to, NULL, perm, shared, list, errp); if (ret < 0) { bdrv_abort_perm_update(to); goto out; @@ -XXX,XX +XXX,XX @@ int coroutine_fn bdrv_co_invalidate_cache(BlockDriverState *bs, Error **errp) */ if (bs->open_flags & BDRV_O_INACTIVE) { bs->open_flags &= ~BDRV_O_INACTIVE; - ret = bdrv_refresh_perms(bs, NULL, errp); + ret = bdrv_refresh_perms(bs, errp); if (ret < 0) { bs->open_flags |= BDRV_O_INACTIVE; return ret; @@ -XXX,XX +XXX,XX @@ static bool bdrv_has_bds_parent(BlockDriverState *bs, bool only_active) static int bdrv_inactivate_recurse(BlockDriverState *bs) { BdrvChild *child, *parent; - bool tighten_restrictions; int ret; if (!bs->drv) { @@ -XXX,XX +XXX,XX @@ static int bdrv_inactivate_recurse(BlockDriverState *bs) * We only tried to loosen restrictions, so errors are not fatal, ignore * them. */ - bdrv_refresh_perms(bs, &tighten_restrictions, NULL); - assert(tighten_restrictions == false); + bdrv_refresh_perms(bs, NULL); /* Recursively inactivate children */ QLIST_FOREACH(child, &bs->children, next) { -- 2.29.2 From: Vladimir Sementsov-Ogievskiy <vsementsov@virtuozzo.com> 1. BDRV_REQ_NO_SERIALISING doesn't exist already, don't mention it. 2. We are going to add one more user of BDRV_REQ_SERIALISING, so comment about backup becomes a bit confusing here. The use case in backup is documented in block/backup.c, so let's just drop duplication here. 3. The fact that BDRV_REQ_SERIALISING is only for write requests is omitted. Add a note. Signed-off-by: Vladimir Sementsov-Ogievskiy <vsementsov@virtuozzo.com> Reviewed-by: Stefan Hajnoczi <stefanha@redhat.com> Reviewed-by: Alberto Garcia <berto@igalia.com> Message-Id: <20201021145859.11201-2-vsementsov@virtuozzo.com> Signed-off-by: Max Reitz <mreitz@redhat.com> --- include/block/block.h | 11 +---------- 1 file changed, 1 insertion(+), 10 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 { * content. */ BDRV_REQ_WRITE_UNCHANGED = 0x40, - /* - * BDRV_REQ_SERIALISING forces request serialisation for writes. - * It is used to ensure that writes to the backing file of a backup process - * target cannot race with a read of the backup target that defers to the - * backing file. - * - * Note, that BDRV_REQ_SERIALISING is _not_ opposite in meaning to - * BDRV_REQ_NO_SERIALISING. A more descriptive name for the latter might be - * _DO_NOT_WAIT_FOR_SERIALISING, except that is too long. - */ + /* Forces request serialisation. Use only with write requests. */ BDRV_REQ_SERIALISING = 0x80, /* Execute the request only if the operation can be offloaded or otherwise -- 2.29.2 From: Vladimir Sementsov-Ogievskiy <vsementsov@virtuozzo.com> The comments states, that on misaligned request we should have already been waiting. But for bdrv_padding_rmw_read, we called bdrv_mark_request_serialising with align = request_alignment, and now we serialise with align = cluster_size. So we may have to wait again with larger alignment. Note, that the only user of BDRV_REQ_SERIALISING is backup which issues cluster-aligned requests, so seems the assertion should not fire for now. But it's wrong anyway. Signed-off-by: Vladimir Sementsov-Ogievskiy <vsementsov@virtuozzo.com> Reviewed-by: Paolo Bonzini <pbonzini@redhat.com> Message-Id: <20201021145859.11201-3-vsementsov@virtuozzo.com> Signed-off-by: Max Reitz <mreitz@redhat.com> --- block/io.c | 11 +---------- 1 file changed, 1 insertion(+), 10 deletions(-) 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 @@ bdrv_co_write_req_prepare(BdrvChild *child, int64_t offset, uint64_t bytes, BdrvTrackedRequest *req, int flags) { BlockDriverState *bs = child->bs; - bool waited; int64_t end_sector = DIV_ROUND_UP(offset + bytes, BDRV_SECTOR_SIZE); if (bs->read_only) { @@ -XXX,XX +XXX,XX @@ bdrv_co_write_req_prepare(BdrvChild *child, int64_t offset, uint64_t bytes, assert(!(flags & ~BDRV_REQ_MASK)); if (flags & BDRV_REQ_SERIALISING) { - waited = bdrv_mark_request_serialising(req, bdrv_get_cluster_size(bs)); - /* - * For a misaligned request we should have already waited earlier, - * because we come after bdrv_padding_rmw_read which must be called - * with the request already marked as serialising. - */ - assert(!waited || - (req->offset == req->overlap_offset && - req->bytes == req->overlap_bytes)); + bdrv_mark_request_serialising(req, bdrv_get_cluster_size(bs)); } else { bdrv_wait_serialising_requests(req); } -- 2.29.2 From: Vladimir Sementsov-Ogievskiy <vsementsov@virtuozzo.com> To be reused in separate. Signed-off-by: Vladimir Sementsov-Ogievskiy <vsementsov@virtuozzo.com> Reviewed-by: Stefan Hajnoczi <stefanha@redhat.com> Message-Id: <20201021145859.11201-4-vsementsov@virtuozzo.com> Signed-off-by: Max Reitz <mreitz@redhat.com> --- block/io.c | 71 +++++++++++++++++++++++++++++++----------------------- 1 file changed, 41 insertions(+), 30 deletions(-) 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 tracked_request_overlaps(BdrvTrackedRequest *req, return true; } +/* Called with self->bs->reqs_lock held */ +static BdrvTrackedRequest * +bdrv_find_conflicting_request(BdrvTrackedRequest *self) +{ + BdrvTrackedRequest *req; + + QLIST_FOREACH(req, &self->bs->tracked_requests, list) { + if (req == self || (!req->serialising && !self->serialising)) { + continue; + } + if (tracked_request_overlaps(req, self->overlap_offset, + self->overlap_bytes)) + { + /* + * Hitting this means there was a reentrant request, for + * example, a block driver issuing nested requests. This must + * never happen since it means deadlock. + */ + assert(qemu_coroutine_self() != req->co); + + /* + * If the request is already (indirectly) waiting for us, or + * will wait for us as soon as it wakes up, then just go on + * (instead of producing a deadlock in the former case). + */ + if (!req->waiting_for) { + return req; + } + } + } + + return NULL; +} + static bool coroutine_fn bdrv_wait_serialising_requests_locked(BlockDriverState *bs, BdrvTrackedRequest *self) { BdrvTrackedRequest *req; - bool retry; bool waited = false; - do { - retry = false; - QLIST_FOREACH(req, &bs->tracked_requests, list) { - if (req == self || (!req->serialising && !self->serialising)) { - continue; - } - if (tracked_request_overlaps(req, self->overlap_offset, - self->overlap_bytes)) - { - /* Hitting this means there was a reentrant request, for - * example, a block driver issuing nested requests. This must - * never happen since it means deadlock. - */ - assert(qemu_coroutine_self() != req->co); - - /* If the request is already (indirectly) waiting for us, or - * will wait for us as soon as it wakes up, then just go on - * (instead of producing a deadlock in the former case). */ - if (!req->waiting_for) { - self->waiting_for = req; - qemu_co_queue_wait(&req->wait_queue, &bs->reqs_lock); - self->waiting_for = NULL; - retry = true; - waited = true; - break; - } - } - } - } while (retry); + while ((req = bdrv_find_conflicting_request(self))) { + self->waiting_for = req; + qemu_co_queue_wait(&req->wait_queue, &bs->reqs_lock); + self->waiting_for = NULL; + waited = true; + } + return waited; } -- 2.29.2 From: Vladimir Sementsov-Ogievskiy <vsementsov@virtuozzo.com> bs is linked in req, so no needs to pass it separately. Most of tracked-requests API doesn't have bs argument. Actually, after this patch only tracked_request_begin has it, but it's for purpose. While being here, also add a comment about what "_locked" is. Signed-off-by: Vladimir Sementsov-Ogievskiy <vsementsov@virtuozzo.com> Reviewed-by: Stefan Hajnoczi <stefanha@redhat.com> Message-Id: <20201021145859.11201-5-vsementsov@virtuozzo.com> Signed-off-by: Max Reitz <mreitz@redhat.com> --- block/io.c | 10 +++++----- 1 file changed, 5 insertions(+), 5 deletions(-) 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 @@ bdrv_find_conflicting_request(BdrvTrackedRequest *self) return NULL; } +/* Called with self->bs->reqs_lock held */ static bool coroutine_fn -bdrv_wait_serialising_requests_locked(BlockDriverState *bs, - BdrvTrackedRequest *self) +bdrv_wait_serialising_requests_locked(BdrvTrackedRequest *self) { BdrvTrackedRequest *req; bool waited = false; while ((req = bdrv_find_conflicting_request(self))) { self->waiting_for = req; - qemu_co_queue_wait(&req->wait_queue, &bs->reqs_lock); + qemu_co_queue_wait(&req->wait_queue, &self->bs->reqs_lock); self->waiting_for = NULL; waited = true; } @@ -XXX,XX +XXX,XX @@ bool bdrv_mark_request_serialising(BdrvTrackedRequest *req, uint64_t align) req->overlap_offset = MIN(req->overlap_offset, overlap_offset); req->overlap_bytes = MAX(req->overlap_bytes, overlap_bytes); - waited = bdrv_wait_serialising_requests_locked(bs, req); + waited = bdrv_wait_serialising_requests_locked(req); qemu_co_mutex_unlock(&bs->reqs_lock); return waited; } @@ -XXX,XX +XXX,XX @@ static bool coroutine_fn bdrv_wait_serialising_requests(BdrvTrackedRequest *self } qemu_co_mutex_lock(&bs->reqs_lock); - waited = bdrv_wait_serialising_requests_locked(bs, self); + waited = bdrv_wait_serialising_requests_locked(self); qemu_co_mutex_unlock(&bs->reqs_lock); return waited; -- 2.29.2 From: Vladimir Sementsov-Ogievskiy <vsementsov@virtuozzo.com> We'll need a separate function, which will only "mark" request serialising with specified align but not wait for conflicting requests. So, it will be like old bdrv_mark_request_serialising(), before merging bdrv_wait_serialising_requests_locked() into it. To reduce the possible mess, let's do the following: Public function that does both marking and waiting will be called bdrv_make_request_serialising, and private function which will only "mark" will be called tracked_request_set_serialising(). Signed-off-by: Vladimir Sementsov-Ogievskiy <vsementsov@virtuozzo.com> Reviewed-by: Max Reitz <mreitz@redhat.com> Message-Id: <20201021145859.11201-6-vsementsov@virtuozzo.com> Signed-off-by: Max Reitz <mreitz@redhat.com> --- include/block/block_int.h | 3 ++- block/file-posix.c | 2 +- block/io.c | 35 +++++++++++++++++++++++------------ 3 files changed, 26 insertions(+), 14 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 @@ extern unsigned int bdrv_drain_all_count; void bdrv_apply_subtree_drain(BdrvChild *child, BlockDriverState *new_parent); void bdrv_unapply_subtree_drain(BdrvChild *child, BlockDriverState *old_parent); -bool coroutine_fn bdrv_mark_request_serialising(BdrvTrackedRequest *req, uint64_t align); +bool coroutine_fn bdrv_make_request_serialising(BdrvTrackedRequest *req, + uint64_t align); BdrvTrackedRequest *coroutine_fn bdrv_co_get_self_request(BlockDriverState *bs); int get_tmp_filename(char *filename, int size); 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 @@ raw_do_pwrite_zeroes(BlockDriverState *bs, int64_t offset, int bytes, assert(bdrv_check_request(req->offset, req->bytes) == 0); - bdrv_mark_request_serialising(req, bs->bl.request_alignment); + bdrv_make_request_serialising(req, bs->bl.request_alignment); } #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 @@ bdrv_wait_serialising_requests_locked(BdrvTrackedRequest *self) return waited; } -bool bdrv_mark_request_serialising(BdrvTrackedRequest *req, uint64_t align) +/* Called with req->bs->reqs_lock held */ +static void tracked_request_set_serialising(BdrvTrackedRequest *req, + uint64_t align) { - BlockDriverState *bs = req->bs; int64_t overlap_offset = req->offset & ~(align - 1); uint64_t overlap_bytes = ROUND_UP(req->offset + req->bytes, align) - overlap_offset; - bool waited; - qemu_co_mutex_lock(&bs->reqs_lock); if (!req->serialising) { qatomic_inc(&req->bs->serialising_in_flight); req->serialising = true; @@ -XXX,XX +XXX,XX @@ bool bdrv_mark_request_serialising(BdrvTrackedRequest *req, uint64_t align) req->overlap_offset = MIN(req->overlap_offset, overlap_offset); req->overlap_bytes = MAX(req->overlap_bytes, overlap_bytes); - waited = bdrv_wait_serialising_requests_locked(req); - qemu_co_mutex_unlock(&bs->reqs_lock); - return waited; } /** @@ -XXX,XX +XXX,XX @@ static bool coroutine_fn bdrv_wait_serialising_requests(BdrvTrackedRequest *self return waited; } +bool coroutine_fn bdrv_make_request_serialising(BdrvTrackedRequest *req, + uint64_t align) +{ + bool waited; + + qemu_co_mutex_lock(&req->bs->reqs_lock); + + tracked_request_set_serialising(req, align); + waited = bdrv_wait_serialising_requests_locked(req); + + qemu_co_mutex_unlock(&req->bs->reqs_lock); + + return waited; +} + int bdrv_check_request(int64_t offset, int64_t bytes) { if (offset < 0 || bytes < 0) { @@ -XXX,XX +XXX,XX @@ static int coroutine_fn bdrv_aligned_preadv(BdrvChild *child, * with each other for the same cluster. For example, in copy-on-read * it ensures that the CoR read and write operations are atomic and * guest writes cannot interleave between them. */ - bdrv_mark_request_serialising(req, bdrv_get_cluster_size(bs)); + bdrv_make_request_serialising(req, bdrv_get_cluster_size(bs)); } else { bdrv_wait_serialising_requests(req); } @@ -XXX,XX +XXX,XX @@ bdrv_co_write_req_prepare(BdrvChild *child, int64_t offset, uint64_t bytes, assert(!(flags & ~BDRV_REQ_MASK)); if (flags & BDRV_REQ_SERIALISING) { - bdrv_mark_request_serialising(req, bdrv_get_cluster_size(bs)); + bdrv_make_request_serialising(req, bdrv_get_cluster_size(bs)); } else { bdrv_wait_serialising_requests(req); } @@ -XXX,XX +XXX,XX @@ static int coroutine_fn bdrv_co_do_zero_pwritev(BdrvChild *child, padding = bdrv_init_padding(bs, offset, bytes, &pad); if (padding) { - bdrv_mark_request_serialising(req, align); + bdrv_make_request_serialising(req, align); bdrv_padding_rmw_read(child, req, &pad, true); @@ -XXX,XX +XXX,XX @@ int coroutine_fn bdrv_co_pwritev_part(BdrvChild *child, } if (bdrv_pad_request(bs, &qiov, &qiov_offset, &offset, &bytes, &pad)) { - bdrv_mark_request_serialising(&req, align); + bdrv_make_request_serialising(&req, align); bdrv_padding_rmw_read(child, &req, &pad, false); } @@ -XXX,XX +XXX,XX @@ int coroutine_fn bdrv_co_truncate(BdrvChild *child, int64_t offset, bool exact, * new area, we need to make sure that no write requests are made to it * concurrently or they might be overwritten by preallocation. */ if (new_bytes) { - bdrv_mark_request_serialising(&req, 1); + bdrv_make_request_serialising(&req, 1); } if (bs->read_only) { error_setg(errp, "Image is read-only"); -- 2.29.2 From: Vladimir Sementsov-Ogievskiy <vsementsov@virtuozzo.com> Add flag to make serialising request no wait: if there are conflicting requests, just return error immediately. It's will be used in upcoming preallocate filter. Signed-off-by: Vladimir Sementsov-Ogievskiy <vsementsov@virtuozzo.com> Reviewed-by: Max Reitz <mreitz@redhat.com> Message-Id: <20201021145859.11201-7-vsementsov@virtuozzo.com> Signed-off-by: Max Reitz <mreitz@redhat.com> --- include/block/block.h | 9 ++++++++- block/io.c | 11 ++++++++++- 2 files changed, 18 insertions(+), 2 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 { * written to qiov parameter which may be NULL. */ BDRV_REQ_PREFETCH = 0x200, + + /* + * If we need to wait for other requests, just fail immediately. Used + * only together with BDRV_REQ_SERIALISING. + */ + BDRV_REQ_NO_WAIT = 0x400, + /* Mask of valid flags */ - BDRV_REQ_MASK = 0x3ff, + BDRV_REQ_MASK = 0x7ff, } BdrvRequestFlags; typedef struct BlockSizes { 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 @@ bdrv_co_write_req_prepare(BdrvChild *child, int64_t offset, uint64_t bytes, assert(!(bs->open_flags & BDRV_O_INACTIVE)); assert((bs->open_flags & BDRV_O_NO_IO) == 0); assert(!(flags & ~BDRV_REQ_MASK)); + assert(!((flags & BDRV_REQ_NO_WAIT) && !(flags & BDRV_REQ_SERIALISING))); if (flags & BDRV_REQ_SERIALISING) { - bdrv_make_request_serialising(req, bdrv_get_cluster_size(bs)); + QEMU_LOCK_GUARD(&bs->reqs_lock); + + tracked_request_set_serialising(req, bdrv_get_cluster_size(bs)); + + if ((flags & BDRV_REQ_NO_WAIT) && bdrv_find_conflicting_request(req)) { + return -EBUSY; + } + + bdrv_wait_serialising_requests_locked(req); } else { bdrv_wait_serialising_requests(req); } -- 2.29.2 From: Vladimir Sementsov-Ogievskiy <vsementsov@virtuozzo.com> Do generic processing even for drivers which define .bdrv_check_perm handler. It's needed for further preallocate filter: it will need to do additional action on bdrv_check_perm, but don't want to reimplement generic logic. The patch doesn't change existing behaviour: the only driver that implements bdrv_check_perm is file-posix, but it never has any children. Also, bdrv_set_perm() don't stop processing if driver has .bdrv_set_perm handler as well. Signed-off-by: Vladimir Sementsov-Ogievskiy <vsementsov@virtuozzo.com> Message-Id: <20201021145859.11201-8-vsementsov@virtuozzo.com> Reviewed-by: Max Reitz <mreitz@redhat.com> Signed-off-by: Max Reitz <mreitz@redhat.com> --- block.c | 7 +++++-- 1 file changed, 5 insertions(+), 2 deletions(-) diff --git a/block.c b/block.c index XXXXXXX..XXXXXXX 100644 --- a/block.c +++ b/block.c @@ -XXX,XX +XXX,XX @@ static int bdrv_check_perm(BlockDriverState *bs, BlockReopenQueue *q, } if (drv->bdrv_check_perm) { - return drv->bdrv_check_perm(bs, cumulative_perms, - cumulative_shared_perms, errp); + ret = drv->bdrv_check_perm(bs, cumulative_perms, + cumulative_shared_perms, errp); + if (ret < 0) { + return ret; + } } /* Drivers that never have children can omit .bdrv_child_perm() */ -- 2.29.2 From: Vladimir Sementsov-Ogievskiy <vsementsov@virtuozzo.com> It's intended to be inserted between format and protocol nodes to preallocate additional space (expanding protocol file) on writes crossing EOF. It improves performance for file-systems with slow allocation. Signed-off-by: Vladimir Sementsov-Ogievskiy <vsementsov@virtuozzo.com> Message-Id: <20201021145859.11201-9-vsementsov@virtuozzo.com> Reviewed-by: Max Reitz <mreitz@redhat.com> [mreitz: Two comment fixes, and bumped the version from 5.2 to 6.0] Signed-off-by: Max Reitz <mreitz@redhat.com> --- docs/system/qemu-block-drivers.rst.inc | 26 ++ qapi/block-core.json | 20 +- block/preallocate.c | 559 +++++++++++++++++++++++++ block/meson.build | 1 + 4 files changed, 605 insertions(+), 1 deletion(-) create mode 100644 block/preallocate.c diff --git a/docs/system/qemu-block-drivers.rst.inc b/docs/system/qemu-block-drivers.rst.inc index XXXXXXX..XXXXXXX 100644 --- a/docs/system/qemu-block-drivers.rst.inc +++ b/docs/system/qemu-block-drivers.rst.inc @@ -XXX,XX +XXX,XX @@ on host and see if there are locks held by the QEMU process on the image file. More than one byte could be locked by the QEMU instance, each byte of which reflects a particular permission that is acquired or protected by the running block driver. + +Filter drivers +~~~~~~~~~~~~~~ + +QEMU supports several filter drivers, which don't store any data, but perform +some additional tasks, hooking io requests. + +.. program:: filter-drivers +.. option:: preallocate + + The preallocate filter driver is intended to be inserted between format + and protocol nodes and preallocates some additional space + (expanding the protocol file) when writing past the file’s end. This can be + useful for file-systems with slow allocation. + + Supported options: + + .. program:: preallocate + .. option:: prealloc-align + + On preallocation, align the file length to this value (in bytes), default 1M. + + .. program:: preallocate + .. option:: prealloc-size + + How much to preallocate (in bytes), default 128M. 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 @@ 'cloop', 'compress', 'copy-on-read', 'dmg', 'file', 'ftp', 'ftps', 'gluster', 'host_cdrom', 'host_device', 'http', 'https', 'iscsi', 'luks', 'nbd', 'nfs', 'null-aio', 'null-co', 'nvme', 'parallels', - 'qcow', 'qcow2', 'qed', 'quorum', 'raw', 'rbd', + 'preallocate', 'qcow', 'qcow2', 'qed', 'quorum', 'raw', 'rbd', { 'name': 'replication', 'if': 'defined(CONFIG_REPLICATION)' }, 'sheepdog', 'ssh', 'throttle', 'vdi', 'vhdx', 'vmdk', 'vpc', 'vvfat' ] } @@ -XXX,XX +XXX,XX @@ 'data': { 'aes': 'QCryptoBlockOptionsQCow', 'luks': 'QCryptoBlockOptionsLUKS'} } +## +# @BlockdevOptionsPreallocate: +# +# Filter driver intended to be inserted between format and protocol node +# and do preallocation in protocol node on write. +# +# @prealloc-align: on preallocation, align file length to this number, +# default 1048576 (1M) +# +# @prealloc-size: how much to preallocate, default 134217728 (128M) +# +# Since: 6.0 +## +{ 'struct': 'BlockdevOptionsPreallocate', + 'base': 'BlockdevOptionsGenericFormat', + 'data': { '*prealloc-align': 'int', '*prealloc-size': 'int' } } + ## # @BlockdevOptionsQcow2: # @@ -XXX,XX +XXX,XX @@ 'null-co': 'BlockdevOptionsNull', 'nvme': 'BlockdevOptionsNVMe', 'parallels': 'BlockdevOptionsGenericFormat', + 'preallocate':'BlockdevOptionsPreallocate', 'qcow2': 'BlockdevOptionsQcow2', 'qcow': 'BlockdevOptionsQcow', 'qed': 'BlockdevOptionsGenericCOWFormat', diff --git a/block/preallocate.c b/block/preallocate.c new file mode 100644 index XXXXXXX..XXXXXXX --- /dev/null +++ b/block/preallocate.c @@ -XXX,XX +XXX,XX @@ +/* + * preallocate filter driver + * + * The driver performs preallocate operation: it is injected above + * some node, and before each write over EOF it does additional preallocating + * write-zeroes request. + * + * Copyright (c) 2020 Virtuozzo International GmbH. + * + * Author: + * Sementsov-Ogievskiy Vladimir <vsementsov@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/>. + */ + +#include "qemu/osdep.h" + +#include "qapi/error.h" +#include "qemu/module.h" +#include "qemu/option.h" +#include "qemu/units.h" +#include "block/block_int.h" + + +typedef struct PreallocateOpts { + int64_t prealloc_size; + int64_t prealloc_align; +} PreallocateOpts; + +typedef struct BDRVPreallocateState { + PreallocateOpts opts; + + /* + * Track real data end, to crop preallocation on close. If < 0 the status is + * unknown. + * + * @data_end is a maximum of file size on open (or when we get write/resize + * permissions) and all write request ends after it. So it's safe to + * truncate to data_end if it is valid. + */ + int64_t data_end; + + /* + * Start of trailing preallocated area which reads as zero. May be smaller + * than data_end, if user does over-EOF write zero operation. If < 0 the + * status is unknown. + * + * If both @zero_start and @file_end are valid, the region + * [@zero_start, @file_end) is known to be preallocated zeroes. If @file_end + * is not valid, @zero_start doesn't make much sense. + */ + int64_t zero_start; + + /* + * Real end of file. Actually the cache for bdrv_getlength(bs->file->bs), + * to avoid extra lseek() calls on each write operation. If < 0 the status + * is unknown. + */ + int64_t file_end; + + /* + * All three states @data_end, @zero_start and @file_end are guaranteed to + * be invalid (< 0) when we don't have both exclusive BLK_PERM_RESIZE and + * BLK_PERM_WRITE permissions on file child. + */ +} BDRVPreallocateState; + +#define PREALLOCATE_OPT_PREALLOC_ALIGN "prealloc-align" +#define PREALLOCATE_OPT_PREALLOC_SIZE "prealloc-size" +static QemuOptsList runtime_opts = { + .name = "preallocate", + .head = QTAILQ_HEAD_INITIALIZER(runtime_opts.head), + .desc = { + { + .name = PREALLOCATE_OPT_PREALLOC_ALIGN, + .type = QEMU_OPT_SIZE, + .help = "on preallocation, align file length to this number, " + "default 1M", + }, + { + .name = PREALLOCATE_OPT_PREALLOC_SIZE, + .type = QEMU_OPT_SIZE, + .help = "how much to preallocate, default 128M", + }, + { /* end of list */ } + }, +}; + +static bool preallocate_absorb_opts(PreallocateOpts *dest, QDict *options, + BlockDriverState *child_bs, Error **errp) +{ + QemuOpts *opts = qemu_opts_create(&runtime_opts, NULL, 0, &error_abort); + + if (!qemu_opts_absorb_qdict(opts, options, errp)) { + return false; + } + + dest->prealloc_align = + qemu_opt_get_size(opts, PREALLOCATE_OPT_PREALLOC_ALIGN, 1 * MiB); + dest->prealloc_size = + qemu_opt_get_size(opts, PREALLOCATE_OPT_PREALLOC_SIZE, 128 * MiB); + + qemu_opts_del(opts); + + if (!QEMU_IS_ALIGNED(dest->prealloc_align, BDRV_SECTOR_SIZE)) { + error_setg(errp, "prealloc-align parameter of preallocate filter " + "is not aligned to %llu", BDRV_SECTOR_SIZE); + return false; + } + + if (!QEMU_IS_ALIGNED(dest->prealloc_align, + child_bs->bl.request_alignment)) { + error_setg(errp, "prealloc-align parameter of preallocate filter " + "is not aligned to underlying node request alignment " + "(%" PRIi32 ")", child_bs->bl.request_alignment); + return false; + } + + return true; +} + +static int preallocate_open(BlockDriverState *bs, QDict *options, int flags, + Error **errp) +{ + BDRVPreallocateState *s = bs->opaque; + + /* + * s->data_end and friends should be initialized on permission update. + * For this to work, mark them invalid. + */ + s->file_end = s->zero_start = s->data_end = -EINVAL; + + bs->file = bdrv_open_child(NULL, options, "file", bs, &child_of_bds, + BDRV_CHILD_FILTERED | BDRV_CHILD_PRIMARY, + false, errp); + if (!bs->file) { + return -EINVAL; + } + + if (!preallocate_absorb_opts(&s->opts, options, bs->file->bs, errp)) { + return -EINVAL; + } + + bs->supported_write_flags = BDRV_REQ_WRITE_UNCHANGED | + (BDRV_REQ_FUA & bs->file->bs->supported_write_flags); + + bs->supported_zero_flags = BDRV_REQ_WRITE_UNCHANGED | + ((BDRV_REQ_FUA | BDRV_REQ_MAY_UNMAP | BDRV_REQ_NO_FALLBACK) & + bs->file->bs->supported_zero_flags); + + return 0; +} + +static void preallocate_close(BlockDriverState *bs) +{ + int ret; + BDRVPreallocateState *s = bs->opaque; + + if (s->data_end < 0) { + return; + } + + if (s->file_end < 0) { + s->file_end = bdrv_getlength(bs->file->bs); + if (s->file_end < 0) { + return; + } + } + + if (s->data_end < s->file_end) { + ret = bdrv_truncate(bs->file, s->data_end, true, PREALLOC_MODE_OFF, 0, + NULL); + s->file_end = ret < 0 ? ret : s->data_end; + } +} + + +/* + * Handle reopen. + * + * We must implement reopen handlers, otherwise reopen just don't work. Handle + * new options and don't care about preallocation state, as it is handled in + * set/check permission handlers. + */ + +static int preallocate_reopen_prepare(BDRVReopenState *reopen_state, + BlockReopenQueue *queue, Error **errp) +{ + PreallocateOpts *opts = g_new0(PreallocateOpts, 1); + + if (!preallocate_absorb_opts(opts, reopen_state->options, + reopen_state->bs->file->bs, errp)) { + g_free(opts); + return -EINVAL; + } + + reopen_state->opaque = opts; + + return 0; +} + +static void preallocate_reopen_commit(BDRVReopenState *state) +{ + BDRVPreallocateState *s = state->bs->opaque; + + s->opts = *(PreallocateOpts *)state->opaque; + + g_free(state->opaque); + state->opaque = NULL; +} + +static void preallocate_reopen_abort(BDRVReopenState *state) +{ + g_free(state->opaque); + state->opaque = NULL; +} + +static coroutine_fn int preallocate_co_preadv_part( + BlockDriverState *bs, uint64_t offset, uint64_t bytes, + QEMUIOVector *qiov, size_t qiov_offset, int flags) +{ + return bdrv_co_preadv_part(bs->file, offset, bytes, qiov, qiov_offset, + flags); +} + +static int coroutine_fn preallocate_co_pdiscard(BlockDriverState *bs, + int64_t offset, int bytes) +{ + return bdrv_co_pdiscard(bs->file, offset, bytes); +} + +static bool can_write_resize(uint64_t perm) +{ + return (perm & BLK_PERM_WRITE) && (perm & BLK_PERM_RESIZE); +} + +static bool has_prealloc_perms(BlockDriverState *bs) +{ + BDRVPreallocateState *s = bs->opaque; + + if (can_write_resize(bs->file->perm)) { + assert(!(bs->file->shared_perm & BLK_PERM_WRITE)); + assert(!(bs->file->shared_perm & BLK_PERM_RESIZE)); + return true; + } + + assert(s->data_end < 0); + assert(s->zero_start < 0); + assert(s->file_end < 0); + return false; +} + +/* + * Call on each write. Returns true if @want_merge_zero is true and the region + * [offset, offset + bytes) is zeroed (as a result of this call or earlier + * preallocation). + * + * want_merge_zero is used to merge write-zero request with preallocation in + * one bdrv_co_pwrite_zeroes() call. + */ +static bool coroutine_fn handle_write(BlockDriverState *bs, int64_t offset, + int64_t bytes, bool want_merge_zero) +{ + BDRVPreallocateState *s = bs->opaque; + int64_t end = offset + bytes; + int64_t prealloc_start, prealloc_end; + int ret; + + if (!has_prealloc_perms(bs)) { + /* We don't have state neither should try to recover it */ + return false; + } + + if (s->data_end < 0) { + s->data_end = bdrv_getlength(bs->file->bs); + if (s->data_end < 0) { + return false; + } + + if (s->file_end < 0) { + s->file_end = s->data_end; + } + } + + if (end <= s->data_end) { + return false; + } + + /* We have valid s->data_end, and request writes beyond it. */ + + s->data_end = end; + if (s->zero_start < 0 || !want_merge_zero) { + s->zero_start = end; + } + + if (s->file_end < 0) { + s->file_end = bdrv_getlength(bs->file->bs); + if (s->file_end < 0) { + return false; + } + } + + /* Now s->data_end, s->zero_start and s->file_end are valid. */ + + if (end <= s->file_end) { + /* No preallocation needed. */ + return want_merge_zero && offset >= s->zero_start; + } + + /* Now we want new preallocation, as request writes beyond s->file_end. */ + + prealloc_start = want_merge_zero ? MIN(offset, s->file_end) : s->file_end; + prealloc_end = QEMU_ALIGN_UP(end + s->opts.prealloc_size, + s->opts.prealloc_align); + + ret = bdrv_co_pwrite_zeroes( + bs->file, prealloc_start, prealloc_end - prealloc_start, + BDRV_REQ_NO_FALLBACK | BDRV_REQ_SERIALISING | BDRV_REQ_NO_WAIT); + if (ret < 0) { + s->file_end = ret; + return false; + } + + s->file_end = prealloc_end; + return want_merge_zero; +} + +static int coroutine_fn preallocate_co_pwrite_zeroes(BlockDriverState *bs, + int64_t offset, int bytes, BdrvRequestFlags flags) +{ + bool want_merge_zero = + !(flags & ~(BDRV_REQ_ZERO_WRITE | BDRV_REQ_NO_FALLBACK)); + if (handle_write(bs, offset, bytes, want_merge_zero)) { + return 0; + } + + return bdrv_co_pwrite_zeroes(bs->file, offset, bytes, flags); +} + +static coroutine_fn int preallocate_co_pwritev_part(BlockDriverState *bs, + uint64_t offset, + uint64_t bytes, + QEMUIOVector *qiov, + size_t qiov_offset, + int flags) +{ + handle_write(bs, offset, bytes, false); + + return bdrv_co_pwritev_part(bs->file, offset, bytes, qiov, qiov_offset, + flags); +} + +static int coroutine_fn +preallocate_co_truncate(BlockDriverState *bs, int64_t offset, + bool exact, PreallocMode prealloc, + BdrvRequestFlags flags, Error **errp) +{ + ERRP_GUARD(); + BDRVPreallocateState *s = bs->opaque; + int ret; + + if (s->data_end >= 0 && offset > s->data_end) { + if (s->file_end < 0) { + s->file_end = bdrv_getlength(bs->file->bs); + if (s->file_end < 0) { + error_setg(errp, "failed to get file length"); + return s->file_end; + } + } + + if (prealloc == PREALLOC_MODE_FALLOC) { + /* + * If offset <= s->file_end, the task is already done, just + * update s->data_end, to move part of "filter preallocation" + * to "preallocation requested by user". + * Otherwise just proceed to preallocate missing part. + */ + if (offset <= s->file_end) { + s->data_end = offset; + return 0; + } + } else { + /* + * We have to drop our preallocation, to + * - avoid "Cannot use preallocation for shrinking files" in + * case of offset < file_end + * - give PREALLOC_MODE_OFF a chance to keep small disk + * usage + * - give PREALLOC_MODE_FULL a chance to actually write the + * whole region as user expects + */ + if (s->file_end > s->data_end) { + ret = bdrv_co_truncate(bs->file, s->data_end, true, + PREALLOC_MODE_OFF, 0, errp); + if (ret < 0) { + s->file_end = ret; + error_prepend(errp, "preallocate-filter: failed to drop " + "write-zero preallocation: "); + return ret; + } + s->file_end = s->data_end; + } + } + + s->data_end = offset; + } + + ret = bdrv_co_truncate(bs->file, offset, exact, prealloc, flags, errp); + if (ret < 0) { + s->file_end = s->zero_start = s->data_end = ret; + return ret; + } + + if (has_prealloc_perms(bs)) { + s->file_end = s->zero_start = s->data_end = offset; + } + return 0; +} + +static int coroutine_fn preallocate_co_flush(BlockDriverState *bs) +{ + return bdrv_co_flush(bs->file->bs); +} + +static int64_t preallocate_getlength(BlockDriverState *bs) +{ + int64_t ret; + BDRVPreallocateState *s = bs->opaque; + + if (s->data_end >= 0) { + return s->data_end; + } + + ret = bdrv_getlength(bs->file->bs); + + if (has_prealloc_perms(bs)) { + s->file_end = s->zero_start = s->data_end = ret; + } + + return ret; +} + +static int preallocate_check_perm(BlockDriverState *bs, + uint64_t perm, uint64_t shared, Error **errp) +{ + BDRVPreallocateState *s = bs->opaque; + + if (s->data_end >= 0 && !can_write_resize(perm)) { + /* + * Lose permissions. + * We should truncate in check_perm, as in set_perm bs->file->perm will + * be already changed, and we should not violate it. + */ + if (s->file_end < 0) { + s->file_end = bdrv_getlength(bs->file->bs); + if (s->file_end < 0) { + error_setg(errp, "Failed to get file length"); + return s->file_end; + } + } + + if (s->data_end < s->file_end) { + int ret = bdrv_truncate(bs->file, s->data_end, true, + PREALLOC_MODE_OFF, 0, NULL); + if (ret < 0) { + error_setg(errp, "Failed to drop preallocation"); + s->file_end = ret; + return ret; + } + s->file_end = s->data_end; + } + } + + return 0; +} + +static void preallocate_set_perm(BlockDriverState *bs, + uint64_t perm, uint64_t shared) +{ + BDRVPreallocateState *s = bs->opaque; + + if (can_write_resize(perm)) { + if (s->data_end < 0) { + s->data_end = s->file_end = s->zero_start = + bdrv_getlength(bs->file->bs); + } + } else { + /* + * We drop our permissions, as well as allow shared + * permissions (see preallocate_child_perm), anyone will be able to + * change the child, so mark all states invalid. We'll regain control if + * get good permissions back. + */ + s->data_end = s->file_end = s->zero_start = -EINVAL; + } +} + +static void preallocate_child_perm(BlockDriverState *bs, BdrvChild *c, + BdrvChildRole role, BlockReopenQueue *reopen_queue, + uint64_t perm, uint64_t shared, uint64_t *nperm, uint64_t *nshared) +{ + bdrv_default_perms(bs, c, role, reopen_queue, perm, shared, nperm, nshared); + + if (can_write_resize(perm)) { + /* This should come by default, but let's enforce: */ + *nperm |= BLK_PERM_WRITE | BLK_PERM_RESIZE; + + /* + * Don't share, to keep our states s->file_end, s->data_end and + * s->zero_start valid. + */ + *nshared &= ~(BLK_PERM_WRITE | BLK_PERM_RESIZE); + } +} + +BlockDriver bdrv_preallocate_filter = { + .format_name = "preallocate", + .instance_size = sizeof(BDRVPreallocateState), + + .bdrv_getlength = preallocate_getlength, + .bdrv_open = preallocate_open, + .bdrv_close = preallocate_close, + + .bdrv_reopen_prepare = preallocate_reopen_prepare, + .bdrv_reopen_commit = preallocate_reopen_commit, + .bdrv_reopen_abort = preallocate_reopen_abort, + + .bdrv_co_preadv_part = preallocate_co_preadv_part, + .bdrv_co_pwritev_part = preallocate_co_pwritev_part, + .bdrv_co_pwrite_zeroes = preallocate_co_pwrite_zeroes, + .bdrv_co_pdiscard = preallocate_co_pdiscard, + .bdrv_co_flush = preallocate_co_flush, + .bdrv_co_truncate = preallocate_co_truncate, + + .bdrv_check_perm = preallocate_check_perm, + .bdrv_set_perm = preallocate_set_perm, + .bdrv_child_perm = preallocate_child_perm, + + .has_variable_length = true, + .is_filter = true, +}; + +static void bdrv_preallocate_init(void) +{ + bdrv_register(&bdrv_preallocate_filter); +} + +block_init(bdrv_preallocate_init); diff --git a/block/meson.build b/block/meson.build index XXXXXXX..XXXXXXX 100644 --- a/block/meson.build +++ b/block/meson.build @@ -XXX,XX +XXX,XX @@ block_ss.add(files( 'block-copy.c', 'commit.c', 'copy-on-read.c', + 'preallocate.c', 'create.c', 'crypto.c', 'dirty-bitmap.c', -- 2.29.2 From: Vladimir Sementsov-Ogievskiy <vsementsov@virtuozzo.com> This will be used in further test. Signed-off-by: Vladimir Sementsov-Ogievskiy <vsementsov@virtuozzo.com> Reviewed-by: Max Reitz <mreitz@redhat.com> Message-Id: <20201021145859.11201-10-vsementsov@virtuozzo.com> Signed-off-by: Max Reitz <mreitz@redhat.com> --- qemu-io-cmds.c | 46 ++++++++++++++++++++++++++++++++-------------- 1 file changed, 32 insertions(+), 14 deletions(-) diff --git a/qemu-io-cmds.c b/qemu-io-cmds.c index XXXXXXX..XXXXXXX 100644 --- a/qemu-io-cmds.c +++ b/qemu-io-cmds.c @@ -XXX,XX +XXX,XX @@ static const cmdinfo_t flush_cmd = { .oneline = "flush all in-core file state to disk", }; +static int truncate_f(BlockBackend *blk, int argc, char **argv); +static const cmdinfo_t truncate_cmd = { + .name = "truncate", + .altname = "t", + .cfunc = truncate_f, + .perm = BLK_PERM_WRITE | BLK_PERM_RESIZE, + .argmin = 1, + .argmax = 3, + .args = "[-m prealloc_mode] off", + .oneline = "truncates the current file at the given offset", +}; + static int truncate_f(BlockBackend *blk, int argc, char **argv) { Error *local_err = NULL; int64_t offset; - int ret; + int c, ret; + PreallocMode prealloc = PREALLOC_MODE_OFF; - offset = cvtnum(argv[1]); + while ((c = getopt(argc, argv, "m:")) != -1) { + switch (c) { + case 'm': + prealloc = qapi_enum_parse(&PreallocMode_lookup, optarg, + PREALLOC_MODE__MAX, NULL); + if (prealloc == PREALLOC_MODE__MAX) { + error_report("Invalid preallocation mode '%s'", optarg); + return -EINVAL; + } + break; + default: + qemuio_command_usage(&truncate_cmd); + return -EINVAL; + } + } + + offset = cvtnum(argv[optind]); if (offset < 0) { print_cvtnum_err(offset, argv[1]); return offset; @@ -XXX,XX +XXX,XX @@ static int truncate_f(BlockBackend *blk, int argc, char **argv) * exact=true. It is better to err on the "emit more errors" side * than to be overly permissive. */ - ret = blk_truncate(blk, offset, false, PREALLOC_MODE_OFF, 0, &local_err); + ret = blk_truncate(blk, offset, false, prealloc, 0, &local_err); if (ret < 0) { error_report_err(local_err); return ret; @@ -XXX,XX +XXX,XX @@ static int truncate_f(BlockBackend *blk, int argc, char **argv) return 0; } -static const cmdinfo_t truncate_cmd = { - .name = "truncate", - .altname = "t", - .cfunc = truncate_f, - .perm = BLK_PERM_WRITE | BLK_PERM_RESIZE, - .argmin = 1, - .argmax = 1, - .args = "off", - .oneline = "truncates the current file at the given offset", -}; - static int length_f(BlockBackend *blk, int argc, char **argv) { int64_t size; -- 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: <20201021145859.11201-11-vsementsov@virtuozzo.com> Signed-off-by: Max Reitz <mreitz@redhat.com> --- tests/qemu-iotests/iotests.py | 7 ++++++- 1 file changed, 6 insertions(+), 1 deletion(-) 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 @@ def qemu_io_log(*args): def qemu_io_silent(*args): '''Run qemu-io and return the exit code, suppressing stdout''' - args = qemu_io_args + list(args) + if '-f' in args or '--image-opts' in args: + default_args = qemu_io_args_no_fmt + else: + default_args = qemu_io_args + + args = default_args + list(args) exitcode = subprocess.call(args, stdout=open('/dev/null', 'w')) if exitcode < 0: sys.stderr.write('qemu-io received signal %i: %s\n' % -- 2.29.2 From: Vladimir Sementsov-Ogievskiy <vsementsov@virtuozzo.com> Add a parameter to skip test if some needed additional formats are not supported (for example filter drivers). Signed-off-by: Vladimir Sementsov-Ogievskiy <vsementsov@virtuozzo.com> Message-Id: <20201021145859.11201-12-vsementsov@virtuozzo.com> Reviewed-by: Max Reitz <mreitz@redhat.com> Signed-off-by: Max Reitz <mreitz@redhat.com> --- tests/qemu-iotests/iotests.py | 9 ++++++++- 1 file changed, 8 insertions(+), 1 deletion(-) 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 @@ def _verify_aio_mode(supported_aio_modes: Sequence[str] = ()) -> None: if supported_aio_modes and (aiomode not in supported_aio_modes): notrun('not suitable for this aio mode: %s' % aiomode) +def _verify_formats(required_formats: Sequence[str] = ()) -> None: + usf_list = list(set(required_formats) - set(supported_formats())) + if usf_list: + notrun(f'formats {usf_list} are not whitelisted') + def supports_quorum(): return 'quorum' in qemu_img_pipe('--help') @@ -XXX,XX +XXX,XX @@ def execute_setup_common(supported_fmts: Sequence[str] = (), supported_aio_modes: Sequence[str] = (), unsupported_fmts: Sequence[str] = (), supported_protocols: Sequence[str] = (), - unsupported_protocols: Sequence[str] = ()) -> bool: + unsupported_protocols: Sequence[str] = (), + required_fmts: Sequence[str] = ()) -> bool: """ Perform necessary setup for either script-style or unittest-style tests. @@ -XXX,XX +XXX,XX @@ def execute_setup_common(supported_fmts: Sequence[str] = (), _verify_platform(supported=supported_platforms) _verify_cache_mode(supported_cache_modes) _verify_aio_mode(supported_aio_modes) + _verify_formats(required_fmts) return debug -- 2.29.2 From: Vladimir Sementsov-Ogievskiy <vsementsov@virtuozzo.com> Signed-off-by: Vladimir Sementsov-Ogievskiy <vsementsov@virtuozzo.com> Message-Id: <20201021145859.11201-13-vsementsov@virtuozzo.com> Reviewed-by: Max Reitz <mreitz@redhat.com> Signed-off-by: Max Reitz <mreitz@redhat.com> --- tests/qemu-iotests/298 | 186 +++++++++++++++++++++++++++++++++++++ tests/qemu-iotests/298.out | 5 + tests/qemu-iotests/group | 1 + 3 files changed, 192 insertions(+) create mode 100644 tests/qemu-iotests/298 create mode 100644 tests/qemu-iotests/298.out diff --git a/tests/qemu-iotests/298 b/tests/qemu-iotests/298 new file mode 100644 index XXXXXXX..XXXXXXX --- /dev/null +++ b/tests/qemu-iotests/298 @@ -XXX,XX +XXX,XX @@ +#!/usr/bin/env python3 +# +# Test for preallocate filter +# +# 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 os +import iotests + +MiB = 1024 * 1024 +disk = os.path.join(iotests.test_dir, 'disk') +overlay = os.path.join(iotests.test_dir, 'overlay') +refdisk = os.path.join(iotests.test_dir, 'refdisk') +drive_opts = f'node-name=disk,driver={iotests.imgfmt},' \ + f'file.node-name=filter,file.driver=preallocate,' \ + f'file.file.node-name=file,file.file.filename={disk}' + + +class TestPreallocateBase(iotests.QMPTestCase): + def setUp(self): + iotests.qemu_img_create('-f', iotests.imgfmt, disk, str(10 * MiB)) + + def tearDown(self): + try: + self.check_small() + check = iotests.qemu_img_check(disk) + self.assertFalse('leaks' in check) + self.assertFalse('corruptions' in check) + self.assertEqual(check['check-errors'], 0) + finally: + os.remove(disk) + + def check_big(self): + self.assertTrue(os.path.getsize(disk) > 100 * MiB) + + def check_small(self): + self.assertTrue(os.path.getsize(disk) < 10 * MiB) + + +class TestQemuImg(TestPreallocateBase): + def test_qemu_img(self): + p = iotests.QemuIoInteractive('--image-opts', drive_opts) + + p.cmd('write 0 1M') + p.cmd('flush') + + self.check_big() + + p.close() + + +class TestPreallocateFilter(TestPreallocateBase): + def setUp(self): + super().setUp() + self.vm = iotests.VM().add_drive(path=None, opts=drive_opts) + self.vm.launch() + + def tearDown(self): + self.vm.shutdown() + super().tearDown() + + def test_prealloc(self): + self.vm.hmp_qemu_io('drive0', 'write 0 1M') + self.check_big() + + def test_external_snapshot(self): + self.test_prealloc() + + result = self.vm.qmp('blockdev-snapshot-sync', node_name='disk', + snapshot_file=overlay, + snapshot_node_name='overlay') + self.assert_qmp(result, 'return', {}) + + # on reopen to r-o base preallocation should be dropped + self.check_small() + + self.vm.hmp_qemu_io('drive0', 'write 1M 1M') + + result = self.vm.qmp('block-commit', device='overlay') + self.assert_qmp(result, 'return', {}) + self.complete_and_wait() + + # commit of new megabyte should trigger preallocation + self.check_big() + + def test_reopen_opts(self): + result = self.vm.qmp('x-blockdev-reopen', **{ + 'node-name': 'disk', + 'driver': iotests.imgfmt, + 'file': { + 'node-name': 'filter', + 'driver': 'preallocate', + 'prealloc-size': 20 * MiB, + 'prealloc-align': 5 * MiB, + 'file': { + 'node-name': 'file', + 'driver': 'file', + 'filename': disk + } + } + }) + self.assert_qmp(result, 'return', {}) + + self.vm.hmp_qemu_io('drive0', 'write 0 1M') + self.assertTrue(os.path.getsize(disk) == 25 * MiB) + + +class TestTruncate(iotests.QMPTestCase): + def setUp(self): + iotests.qemu_img_create('-f', iotests.imgfmt, disk, str(10 * MiB)) + iotests.qemu_img_create('-f', iotests.imgfmt, refdisk, str(10 * MiB)) + + def tearDown(self): + os.remove(disk) + os.remove(refdisk) + + def do_test(self, prealloc_mode, new_size): + ret = iotests.qemu_io_silent('--image-opts', '-c', 'write 0 10M', '-c', + f'truncate -m {prealloc_mode} {new_size}', + drive_opts) + self.assertEqual(ret, 0) + + ret = iotests.qemu_io_silent('-f', iotests.imgfmt, '-c', 'write 0 10M', + '-c', + f'truncate -m {prealloc_mode} {new_size}', + refdisk) + self.assertEqual(ret, 0) + + stat = os.stat(disk) + refstat = os.stat(refdisk) + + # Probably we'll want preallocate filter to keep align to cluster when + # shrink preallocation, so, ignore small differece + self.assertLess(abs(stat.st_size - refstat.st_size), 64 * 1024) + + # Preallocate filter may leak some internal clusters (for example, if + # guest write far over EOF, skipping some clusters - they will remain + # fallocated, preallocate filter don't care about such leaks, it drops + # only trailing preallocation. + self.assertLess(abs(stat.st_blocks - refstat.st_blocks) * 512, + 1024 * 1024) + + def test_real_shrink(self): + self.do_test('off', '5M') + + def test_truncate_inside_preallocated_area__falloc(self): + self.do_test('falloc', '50M') + + def test_truncate_inside_preallocated_area__metadata(self): + self.do_test('metadata', '50M') + + def test_truncate_inside_preallocated_area__full(self): + self.do_test('full', '50M') + + def test_truncate_inside_preallocated_area__off(self): + self.do_test('off', '50M') + + def test_truncate_over_preallocated_area__falloc(self): + self.do_test('falloc', '150M') + + def test_truncate_over_preallocated_area__metadata(self): + self.do_test('metadata', '150M') + + def test_truncate_over_preallocated_area__full(self): + self.do_test('full', '150M') + + def test_truncate_over_preallocated_area__off(self): + self.do_test('off', '150M') + + +if __name__ == '__main__': + iotests.main(supported_fmts=['qcow2'], required_fmts=['preallocate']) diff --git a/tests/qemu-iotests/298.out b/tests/qemu-iotests/298.out new file mode 100644 index XXXXXXX..XXXXXXX --- /dev/null +++ b/tests/qemu-iotests/298.out @@ -XXX,XX +XXX,XX @@ +............. +---------------------------------------------------------------------- +Ran 13 tests + +OK 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 @@ 295 rw 296 rw 297 meta +298 299 auto quick 300 migration 301 backing quick -- 2.29.2 From: Vladimir Sementsov-Ogievskiy <vsementsov@virtuozzo.com> Signed-off-by: Vladimir Sementsov-Ogievskiy <vsementsov@virtuozzo.com> Message-Id: <20201021145859.11201-14-vsementsov@virtuozzo.com> Reviewed-by: Max Reitz <mreitz@redhat.com> Signed-off-by: Max Reitz <mreitz@redhat.com> --- scripts/simplebench/simplebench.py | 12 ++++++------ 1 file changed, 6 insertions(+), 6 deletions(-) diff --git a/scripts/simplebench/simplebench.py b/scripts/simplebench/simplebench.py index XXXXXXX..XXXXXXX 100644 --- a/scripts/simplebench/simplebench.py +++ b/scripts/simplebench/simplebench.py @@ -XXX,XX +XXX,XX @@ def bench_one(test_func, test_env, test_case, count=5, initial_run=True): result = {'runs': runs} - successed = [r for r in runs if ('seconds' in r)] - if successed: - avg = sum(r['seconds'] for r in successed) / len(successed) + succeeded = [r for r in runs if ('seconds' in r)] + if succeeded: + avg = sum(r['seconds'] for r in succeeded) / len(succeeded) result['average'] = avg - result['delta'] = max(abs(r['seconds'] - avg) for r in successed) + result['delta'] = max(abs(r['seconds'] - avg) for r in succeeded) - if len(successed) < count: - result['n-failed'] = count - len(successed) + if len(succeeded) < count: + result['n-failed'] = count - len(succeeded) return result -- 2.29.2 From: Vladimir Sementsov-Ogievskiy <vsementsov@virtuozzo.com> Support benchmarks returning not seconds but iops. We'll use it for further new test. Signed-off-by: Vladimir Sementsov-Ogievskiy <vsementsov@virtuozzo.com> Message-Id: <20201021145859.11201-15-vsementsov@virtuozzo.com> Reviewed-by: Max Reitz <mreitz@redhat.com> Signed-off-by: Max Reitz <mreitz@redhat.com> --- scripts/simplebench/simplebench.py | 38 ++++++++++++++++++++++-------- 1 file changed, 28 insertions(+), 10 deletions(-) diff --git a/scripts/simplebench/simplebench.py b/scripts/simplebench/simplebench.py index XXXXXXX..XXXXXXX 100644 --- a/scripts/simplebench/simplebench.py +++ b/scripts/simplebench/simplebench.py @@ -XXX,XX +XXX,XX @@ def bench_one(test_func, test_env, test_case, count=5, initial_run=True): test_func -- benchmarking function with prototype test_func(env, case), which takes test_env and test_case - arguments and returns {'seconds': int} (which is benchmark - result) on success and {'error': str} on error. Returned - dict may contain any other additional fields. + arguments and on success returns dict with 'seconds' or + 'iops' (or both) fields, specifying the benchmark result. + If both 'iops' and 'seconds' provided, the 'iops' is + considered the main, and 'seconds' is just an additional + info. On failure test_func should return {'error': str}. + Returned dict may contain any other additional fields. test_env -- test environment - opaque first argument for test_func test_case -- test case - opaque second argument for test_func count -- how many times to call test_func, to calculate average @@ -XXX,XX +XXX,XX @@ def bench_one(test_func, test_env, test_case, count=5, initial_run=True): Returns dict with the following fields: 'runs': list of test_func results - 'average': average seconds per run (exists only if at least one run - succeeded) + 'dimension': dimension of results, may be 'seconds' or 'iops' + 'average': average value (iops or seconds) per run (exists only if at + least one run succeeded) 'delta': maximum delta between test_func result and the average (exists only if at least one run succeeded) 'n-failed': number of failed runs (exists only if at least one run @@ -XXX,XX +XXX,XX @@ def bench_one(test_func, test_env, test_case, count=5, initial_run=True): result = {'runs': runs} - succeeded = [r for r in runs if ('seconds' in r)] + succeeded = [r for r in runs if ('seconds' in r or 'iops' in r)] if succeeded: - avg = sum(r['seconds'] for r in succeeded) / len(succeeded) + if 'iops' in succeeded[0]: + assert all('iops' in r for r in succeeded) + dim = 'iops' + else: + assert all('seconds' in r for r in succeeded) + assert all('iops' not in r for r in succeeded) + dim = 'seconds' + avg = sum(r[dim] for r in succeeded) / len(succeeded) + result['dimension'] = dim result['average'] = avg - result['delta'] = max(abs(r['seconds'] - avg) for r in succeeded) + result['delta'] = max(abs(r[dim] - avg) for r in succeeded) if len(succeeded) < count: result['n-failed'] = count - len(succeeded) @@ -XXX,XX +XXX,XX @@ def ascii(results): """Return ASCII representation of bench() returned dict.""" from tabulate import tabulate + dim = None tab = [[""] + [c['id'] for c in results['envs']]] for case in results['cases']: row = [case['id']] for env in results['envs']: - row.append(ascii_one(results['tab'][case['id']][env['id']])) + res = results['tab'][case['id']][env['id']] + if dim is None: + dim = res['dimension'] + else: + assert dim == res['dimension'] + row.append(ascii_one(res)) tab.append(row) - return tabulate(tab) + return f'All results are in {dim}\n\n' + tabulate(tab) -- 2.29.2 From: Vladimir Sementsov-Ogievskiy <vsementsov@virtuozzo.com> Standard deviation is more usual to see after +- than current maximum of deviations. Signed-off-by: Vladimir Sementsov-Ogievskiy <vsementsov@virtuozzo.com> Message-Id: <20201021145859.11201-16-vsementsov@virtuozzo.com> Reviewed-by: Max Reitz <mreitz@redhat.com> Signed-off-by: Max Reitz <mreitz@redhat.com> --- scripts/simplebench/simplebench.py | 11 ++++++----- 1 file changed, 6 insertions(+), 5 deletions(-) diff --git a/scripts/simplebench/simplebench.py b/scripts/simplebench/simplebench.py index XXXXXXX..XXXXXXX 100644 --- a/scripts/simplebench/simplebench.py +++ b/scripts/simplebench/simplebench.py @@ -XXX,XX +XXX,XX @@ # along with this program. If not, see <http://www.gnu.org/licenses/>. # +import statistics + def bench_one(test_func, test_env, test_case, count=5, initial_run=True): """Benchmark one test-case @@ -XXX,XX +XXX,XX @@ def bench_one(test_func, test_env, test_case, count=5, initial_run=True): 'dimension': dimension of results, may be 'seconds' or 'iops' 'average': average value (iops or seconds) per run (exists only if at least one run succeeded) - 'delta': maximum delta between test_func result and the average + 'stdev': standard deviation of results (exists only if at least one run succeeded) 'n-failed': number of failed runs (exists only if at least one run failed) @@ -XXX,XX +XXX,XX @@ def bench_one(test_func, test_env, test_case, count=5, initial_run=True): assert all('seconds' in r for r in succeeded) assert all('iops' not in r for r in succeeded) dim = 'seconds' - avg = sum(r[dim] for r in succeeded) / len(succeeded) result['dimension'] = dim - result['average'] = avg - result['delta'] = max(abs(r[dim] - avg) for r in succeeded) + result['average'] = statistics.mean(r[dim] for r in succeeded) + result['stdev'] = statistics.stdev(r[dim] for r in succeeded) if len(succeeded) < count: result['n-failed'] = count - len(succeeded) @@ -XXX,XX +XXX,XX @@ def bench_one(test_func, test_env, test_case, count=5, initial_run=True): def ascii_one(result): """Return ASCII representation of bench_one() returned dict.""" if 'average' in result: - s = '{:.2f} +- {:.2f}'.format(result['average'], result['delta']) + s = '{:.2f} +- {:.2f}'.format(result['average'], result['stdev']) if 'n-failed' in result: s += '\n({} failed)'.format(result['n-failed']) return s -- 2.29.2 From: Vladimir Sementsov-Ogievskiy <vsementsov@virtuozzo.com> Next patch will use utf8 plus-minus symbol, let's use more generic (and more readable) name. Signed-off-by: Vladimir Sementsov-Ogievskiy <vsementsov@virtuozzo.com> Message-Id: <20201021145859.11201-17-vsementsov@virtuozzo.com> Reviewed-by: Max Reitz <mreitz@redhat.com> Signed-off-by: Max Reitz <mreitz@redhat.com> --- scripts/simplebench/bench-example.py | 2 +- scripts/simplebench/bench_write_req.py | 2 +- scripts/simplebench/simplebench.py | 10 +++++----- 3 files changed, 7 insertions(+), 7 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 @@ test_envs = [ ] result = simplebench.bench(bench_func, test_envs, test_cases, count=3) -print(simplebench.ascii(result)) +print(simplebench.results_to_text(result)) diff --git a/scripts/simplebench/bench_write_req.py b/scripts/simplebench/bench_write_req.py index XXXXXXX..XXXXXXX 100755 --- a/scripts/simplebench/bench_write_req.py +++ b/scripts/simplebench/bench_write_req.py @@ -XXX,XX +XXX,XX @@ if __name__ == '__main__': result = simplebench.bench(bench_func, test_envs, test_cases, count=3, initial_run=False) - print(simplebench.ascii(result)) + print(simplebench.results_to_text(result)) diff --git a/scripts/simplebench/simplebench.py b/scripts/simplebench/simplebench.py index XXXXXXX..XXXXXXX 100644 --- a/scripts/simplebench/simplebench.py +++ b/scripts/simplebench/simplebench.py @@ -XXX,XX +XXX,XX @@ def bench_one(test_func, test_env, test_case, count=5, initial_run=True): return result -def ascii_one(result): - """Return ASCII representation of bench_one() returned dict.""" +def result_to_text(result): + """Return text representation of bench_one() returned dict.""" if 'average' in result: s = '{:.2f} +- {:.2f}'.format(result['average'], result['stdev']) if 'n-failed' in result: @@ -XXX,XX +XXX,XX @@ def bench(test_func, test_envs, test_cases, *args, **vargs): return results -def ascii(results): - """Return ASCII representation of bench() returned dict.""" +def results_to_text(results): + """Return text representation of bench() returned dict.""" from tabulate import tabulate dim = None @@ -XXX,XX +XXX,XX @@ def ascii(results): dim = res['dimension'] else: assert dim == res['dimension'] - row.append(ascii_one(res)) + row.append(result_to_text(res)) tab.append(row) return f'All results are in {dim}\n\n' + tabulate(tab) -- 2.29.2 From: Vladimir Sementsov-Ogievskiy <vsementsov@virtuozzo.com> Let's keep view part in separate: this way it's better to improve it in the following commits. Signed-off-by: Vladimir Sementsov-Ogievskiy <vsementsov@virtuozzo.com> Message-Id: <20201021145859.11201-18-vsementsov@virtuozzo.com> Reviewed-by: Max Reitz <mreitz@redhat.com> Signed-off-by: Max Reitz <mreitz@redhat.com> --- scripts/simplebench/bench-example.py | 3 +- scripts/simplebench/bench_write_req.py | 3 +- scripts/simplebench/results_to_text.py | 48 ++++++++++++++++++++++++++ scripts/simplebench/simplebench.py | 31 ----------------- 4 files changed, 52 insertions(+), 33 deletions(-) create mode 100644 scripts/simplebench/results_to_text.py 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 @@ # import simplebench +from results_to_text import results_to_text from bench_block_job import bench_block_copy, drv_file, drv_nbd @@ -XXX,XX +XXX,XX @@ test_envs = [ ] result = simplebench.bench(bench_func, test_envs, test_cases, count=3) -print(simplebench.results_to_text(result)) +print(results_to_text(result)) diff --git a/scripts/simplebench/bench_write_req.py b/scripts/simplebench/bench_write_req.py index XXXXXXX..XXXXXXX 100755 --- a/scripts/simplebench/bench_write_req.py +++ b/scripts/simplebench/bench_write_req.py @@ -XXX,XX +XXX,XX @@ import sys import os import subprocess import simplebench +from results_to_text import results_to_text def bench_func(env, case): @@ -XXX,XX +XXX,XX @@ if __name__ == '__main__': result = simplebench.bench(bench_func, test_envs, test_cases, count=3, initial_run=False) - print(simplebench.results_to_text(result)) + print(results_to_text(result)) diff --git a/scripts/simplebench/results_to_text.py b/scripts/simplebench/results_to_text.py new file mode 100644 index XXXXXXX..XXXXXXX --- /dev/null +++ b/scripts/simplebench/results_to_text.py @@ -XXX,XX +XXX,XX @@ +# Simple benchmarking framework +# +# Copyright (c) 2019 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/>. +# + + +def result_to_text(result): + """Return text representation of bench_one() returned dict.""" + if 'average' in result: + s = '{:.2f} +- {:.2f}'.format(result['average'], result['stdev']) + if 'n-failed' in result: + s += '\n({} failed)'.format(result['n-failed']) + return s + else: + return 'FAILED' + + +def results_to_text(results): + """Return text representation of bench() returned dict.""" + from tabulate import tabulate + + dim = None + tab = [[""] + [c['id'] for c in results['envs']]] + for case in results['cases']: + row = [case['id']] + for env in results['envs']: + res = results['tab'][case['id']][env['id']] + if dim is None: + dim = res['dimension'] + else: + assert dim == res['dimension'] + row.append(result_to_text(res)) + tab.append(row) + + return f'All results are in {dim}\n\n' + tabulate(tab) diff --git a/scripts/simplebench/simplebench.py b/scripts/simplebench/simplebench.py index XXXXXXX..XXXXXXX 100644 --- a/scripts/simplebench/simplebench.py +++ b/scripts/simplebench/simplebench.py @@ -XXX,XX +XXX,XX @@ def bench_one(test_func, test_env, test_case, count=5, initial_run=True): return result -def result_to_text(result): - """Return text representation of bench_one() returned dict.""" - if 'average' in result: - s = '{:.2f} +- {:.2f}'.format(result['average'], result['stdev']) - if 'n-failed' in result: - s += '\n({} failed)'.format(result['n-failed']) - return s - else: - return 'FAILED' - - def bench(test_func, test_envs, test_cases, *args, **vargs): """Fill benchmark table @@ -XXX,XX +XXX,XX @@ def bench(test_func, test_envs, test_cases, *args, **vargs): print('Done') return results - - -def results_to_text(results): - """Return text representation of bench() returned dict.""" - from tabulate import tabulate - - dim = None - tab = [[""] + [c['id'] for c in results['envs']]] - for case in results['cases']: - row = [case['id']] - for env in results['envs']: - res = results['tab'][case['id']][env['id']] - if dim is None: - dim = res['dimension'] - else: - assert dim == res['dimension'] - row.append(result_to_text(res)) - tab.append(row) - - return f'All results are in {dim}\n\n' + tabulate(tab) -- 2.29.2 From: Vladimir Sementsov-Ogievskiy <vsementsov@virtuozzo.com> Move to generic format for floats and percentage for error. Signed-off-by: Vladimir Sementsov-Ogievskiy <vsementsov@virtuozzo.com> Message-Id: <20201021145859.11201-19-vsementsov@virtuozzo.com> Acked-by: Max Reitz <mreitz@redhat.com> Signed-off-by: Max Reitz <mreitz@redhat.com> --- scripts/simplebench/results_to_text.py | 13 ++++++++++++- 1 file changed, 12 insertions(+), 1 deletion(-) diff --git a/scripts/simplebench/results_to_text.py b/scripts/simplebench/results_to_text.py index XXXXXXX..XXXXXXX 100644 --- a/scripts/simplebench/results_to_text.py +++ b/scripts/simplebench/results_to_text.py @@ -XXX,XX +XXX,XX @@ # along with this program. If not, see <http://www.gnu.org/licenses/>. # +import math + + +def format_value(x, stdev): + stdev_pr = stdev / x * 100 + if stdev_pr < 1.5: + # don't care too much + return f'{x:.2g}' + else: + return f'{x:.2g} ± {math.ceil(stdev_pr)}%' + def result_to_text(result): """Return text representation of bench_one() returned dict.""" if 'average' in result: - s = '{:.2f} +- {:.2f}'.format(result['average'], result['stdev']) + s = format_value(result['average'], result['stdev']) if 'n-failed' in result: s += '\n({} failed)'.format(result['n-failed']) return s -- 2.29.2 From: Vladimir Sementsov-Ogievskiy <vsementsov@virtuozzo.com> Performance improvements / degradations are usually discussed in percentage. Let's make the script calculate it for us. Signed-off-by: Vladimir Sementsov-Ogievskiy <vsementsov@virtuozzo.com> Message-Id: <20201021145859.11201-20-vsementsov@virtuozzo.com> Reviewed-by: Max Reitz <mreitz@redhat.com> [mreitz: 'seconds' instead of 'secs'] Signed-off-by: Max Reitz <mreitz@redhat.com> --- scripts/simplebench/results_to_text.py | 67 +++++++++++++++++++++++--- 1 file changed, 60 insertions(+), 7 deletions(-) diff --git a/scripts/simplebench/results_to_text.py b/scripts/simplebench/results_to_text.py index XXXXXXX..XXXXXXX 100644 --- a/scripts/simplebench/results_to_text.py +++ b/scripts/simplebench/results_to_text.py @@ -XXX,XX +XXX,XX @@ # import math +import tabulate + +# We want leading whitespace for difference row cells (see below) +tabulate.PRESERVE_WHITESPACE = True def format_value(x, stdev): @@ -XXX,XX +XXX,XX @@ def result_to_text(result): return 'FAILED' -def results_to_text(results): - """Return text representation of bench() returned dict.""" - from tabulate import tabulate - +def results_dimension(results): dim = None - tab = [[""] + [c['id'] for c in results['envs']]] for case in results['cases']: - row = [case['id']] for env in results['envs']: res = results['tab'][case['id']][env['id']] if dim is None: dim = res['dimension'] else: assert dim == res['dimension'] + + assert dim in ('iops', 'seconds') + + return dim + + +def results_to_text(results): + """Return text representation of bench() returned dict.""" + n_columns = len(results['envs']) + named_columns = n_columns > 2 + dim = results_dimension(results) + tab = [] + + if named_columns: + # Environment columns are named A, B, ... + tab.append([''] + [chr(ord('A') + i) for i in range(n_columns)]) + + tab.append([''] + [c['id'] for c in results['envs']]) + + for case in results['cases']: + row = [case['id']] + case_results = results['tab'][case['id']] + for env in results['envs']: + res = case_results[env['id']] row.append(result_to_text(res)) tab.append(row) - return f'All results are in {dim}\n\n' + tabulate(tab) + # Add row of difference between columns. For each column starting from + # B we calculate difference with all previous columns. + row = ['', ''] # case name and first column + for i in range(1, n_columns): + cell = '' + env = results['envs'][i] + res = case_results[env['id']] + + if 'average' not in res: + # Failed result + row.append(cell) + continue + + for j in range(0, i): + env_j = results['envs'][j] + res_j = case_results[env_j['id']] + cell += ' ' + + if 'average' not in res_j: + # Failed result + cell += '--' + continue + + col_j = tab[0][j + 1] if named_columns else '' + diff_pr = round((res['average'] - res_j['average']) / + res_j['average'] * 100) + cell += f' {col_j}{diff_pr:+}%' + row.append(cell) + tab.append(row) + + return f'All results are in {dim}\n\n' + tabulate.tabulate(tab) -- 2.29.2 From: Vladimir Sementsov-Ogievskiy <vsementsov@virtuozzo.com> Make results_to_text a tool to dump results saved in JSON file. Signed-off-by: Vladimir Sementsov-Ogievskiy <vsementsov@virtuozzo.com> Message-Id: <20201021145859.11201-21-vsementsov@virtuozzo.com> Reviewed-by: Max Reitz <mreitz@redhat.com> Signed-off-by: Max Reitz <mreitz@redhat.com> --- scripts/simplebench/results_to_text.py | 14 ++++++++++++++ 1 file changed, 14 insertions(+) mode change 100644 => 100755 scripts/simplebench/results_to_text.py diff --git a/scripts/simplebench/results_to_text.py b/scripts/simplebench/results_to_text.py old mode 100644 new mode 100755 index XXXXXXX..XXXXXXX --- a/scripts/simplebench/results_to_text.py +++ b/scripts/simplebench/results_to_text.py @@ -XXX,XX +XXX,XX @@ +#!/usr/bin/env python3 +# # Simple benchmarking framework # # Copyright (c) 2019 Virtuozzo International GmbH. @@ -XXX,XX +XXX,XX @@ def results_to_text(results): tab.append(row) return f'All results are in {dim}\n\n' + tabulate.tabulate(tab) + + +if __name__ == '__main__': + import sys + import json + + if len(sys.argv) < 2: + print(f'USAGE: {sys.argv[0]} results.json') + exit(1) + + with open(sys.argv[1]) as f: + print(results_to_text(json.load(f))) -- 2.29.2 From: Vladimir Sementsov-Ogievskiy <vsementsov@virtuozzo.com> Benchmark for new preallocate filter. Example usage: ./bench_prealloc.py ../../build/qemu-img \ ssd-ext4:/path/to/mount/point \ ssd-xfs:/path2 hdd-ext4:/path3 hdd-xfs:/path4 The benchmark shows performance improvement (or degradation) when use new preallocate filter with qcow2 image. Signed-off-by: Vladimir Sementsov-Ogievskiy <vsementsov@virtuozzo.com> Message-Id: <20201021145859.11201-22-vsementsov@virtuozzo.com> Reviewed-by: Max Reitz <mreitz@redhat.com> Signed-off-by: Max Reitz <mreitz@redhat.com> --- scripts/simplebench/bench_prealloc.py | 132 ++++++++++++++++++++++++++ 1 file changed, 132 insertions(+) create mode 100755 scripts/simplebench/bench_prealloc.py diff --git a/scripts/simplebench/bench_prealloc.py b/scripts/simplebench/bench_prealloc.py new file mode 100755 index XXXXXXX..XXXXXXX --- /dev/null +++ b/scripts/simplebench/bench_prealloc.py @@ -XXX,XX +XXX,XX @@ +#!/usr/bin/env python3 +# +# Benchmark preallocate filter +# +# 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 sys +import os +import subprocess +import re +import json + +import simplebench +from results_to_text import results_to_text + + +def qemu_img_bench(args): + p = subprocess.run(args, stdout=subprocess.PIPE, stderr=subprocess.STDOUT, + universal_newlines=True) + + if p.returncode == 0: + try: + m = re.search(r'Run completed in (\d+.\d+) seconds.', p.stdout) + return {'seconds': float(m.group(1))} + except Exception: + return {'error': f'failed to parse qemu-img output: {p.stdout}'} + else: + return {'error': f'qemu-img failed: {p.returncode}: {p.stdout}'} + + +def bench_func(env, case): + fname = f"{case['dir']}/prealloc-test.qcow2" + try: + os.remove(fname) + except OSError: + pass + + subprocess.run([env['qemu-img-binary'], 'create', '-f', 'qcow2', fname, + '16G'], stdout=subprocess.DEVNULL, + stderr=subprocess.DEVNULL, check=True) + + args = [env['qemu-img-binary'], 'bench', '-c', str(case['count']), + '-d', '64', '-s', case['block-size'], '-t', 'none', '-n', '-w'] + if env['prealloc']: + args += ['--image-opts', + 'driver=qcow2,file.driver=preallocate,file.file.driver=file,' + f'file.file.filename={fname}'] + else: + args += ['-f', 'qcow2', fname] + + return qemu_img_bench(args) + + +def auto_count_bench_func(env, case): + case['count'] = 100 + while True: + res = bench_func(env, case) + if 'error' in res: + return res + + if res['seconds'] >= 1: + break + + case['count'] *= 10 + + if res['seconds'] < 5: + case['count'] = round(case['count'] * 5 / res['seconds']) + res = bench_func(env, case) + if 'error' in res: + return res + + res['iops'] = case['count'] / res['seconds'] + return res + + +if __name__ == '__main__': + if len(sys.argv) < 2: + print(f'USAGE: {sys.argv[0]} <qemu-img binary> ' + 'DISK_NAME:DIR_PATH ...') + exit(1) + + qemu_img = sys.argv[1] + + envs = [ + { + 'id': 'no-prealloc', + 'qemu-img-binary': qemu_img, + 'prealloc': False + }, + { + 'id': 'prealloc', + 'qemu-img-binary': qemu_img, + 'prealloc': True + } + ] + + aligned_cases = [] + unaligned_cases = [] + + for disk in sys.argv[2:]: + name, path = disk.split(':') + aligned_cases.append({ + 'id': f'{name}, aligned sequential 16k', + 'block-size': '16k', + 'dir': path + }) + unaligned_cases.append({ + 'id': f'{name}, unaligned sequential 64k', + 'block-size': '16k', + 'dir': path + }) + + result = simplebench.bench(auto_count_bench_func, envs, + aligned_cases + unaligned_cases, count=5) + print(results_to_text(result)) + with open('results.json', 'w') as f: + json.dump(result, f, indent=4) -- 2.29.2 From: Alberto Garcia <berto@igalia.com> The quorum driver does not implement bdrv_co_block_status() and because of that it always reports to contain data even if all its children are known to be empty. One consequence of this is that if we for example create a quorum with a size of 10GB and we mirror it to a new image the operation will write 10GB of actual zeroes to the destination image wasting a lot of time and disk space. Since a quorum has an arbitrary number of children of potentially different formats there is no way to report all possible allocation status flags in a way that makes sense, so this implementation only reports when a given region is known to contain zeroes (BDRV_BLOCK_ZERO) or not (BDRV_BLOCK_DATA). If all children agree that a region contains zeroes then we can return BDRV_BLOCK_ZERO using the smallest size reported by the children (because all agree that a region of at least that size contains zeroes). If at least one child disagrees we have to return BDRV_BLOCK_DATA. In this case we use the largest of the sizes reported by the children that didn't return BDRV_BLOCK_ZERO (because we know that there won't be an agreement for at least that size). Signed-off-by: Alberto Garcia <berto@igalia.com> Tested-by: Tao Xu <tao3.xu@intel.com> Reviewed-by: Max Reitz <mreitz@redhat.com> Message-Id: <db83149afcf0f793effc8878089d29af4c46ffe1.1605286097.git.berto@igalia.com> Signed-off-by: Max Reitz <mreitz@redhat.com> --- block/quorum.c | 52 +++++++++++++ tests/qemu-iotests/312 | 148 +++++++++++++++++++++++++++++++++++++ tests/qemu-iotests/312.out | 67 +++++++++++++++++ tests/qemu-iotests/group | 1 + 4 files changed, 268 insertions(+) create mode 100755 tests/qemu-iotests/312 create mode 100644 tests/qemu-iotests/312.out diff --git a/block/quorum.c b/block/quorum.c index XXXXXXX..XXXXXXX 100644 --- a/block/quorum.c +++ b/block/quorum.c @@ -XXX,XX +XXX,XX @@ #include "qemu/module.h" #include "qemu/option.h" #include "block/block_int.h" +#include "block/coroutines.h" #include "block/qdict.h" #include "qapi/error.h" #include "qapi/qapi-events-block.h" @@ -XXX,XX +XXX,XX @@ static void quorum_child_perm(BlockDriverState *bs, BdrvChild *c, | DEFAULT_PERM_UNCHANGED; } +/* + * Each one of the children can report different status flags even + * when they contain the same data, so what this function does is + * return BDRV_BLOCK_ZERO if *all* children agree that a certain + * region contains zeroes, and BDRV_BLOCK_DATA otherwise. + */ +static int coroutine_fn quorum_co_block_status(BlockDriverState *bs, + bool want_zero, + int64_t offset, int64_t count, + int64_t *pnum, int64_t *map, + BlockDriverState **file) +{ + BDRVQuorumState *s = bs->opaque; + int i, ret; + int64_t pnum_zero = count; + int64_t pnum_data = 0; + + for (i = 0; i < s->num_children; i++) { + int64_t bytes; + ret = bdrv_co_common_block_status_above(s->children[i]->bs, NULL, false, + want_zero, offset, count, + &bytes, NULL, NULL, NULL); + if (ret < 0) { + quorum_report_bad(QUORUM_OP_TYPE_READ, offset, count, + s->children[i]->bs->node_name, ret); + pnum_data = count; + break; + } + /* + * Even if all children agree about whether there are zeroes + * or not at @offset they might disagree on the size, so use + * the smallest when reporting BDRV_BLOCK_ZERO and the largest + * when reporting BDRV_BLOCK_DATA. + */ + if (ret & BDRV_BLOCK_ZERO) { + pnum_zero = MIN(pnum_zero, bytes); + } else { + pnum_data = MAX(pnum_data, bytes); + } + } + + if (pnum_data) { + *pnum = pnum_data; + return BDRV_BLOCK_DATA; + } else { + *pnum = pnum_zero; + return BDRV_BLOCK_ZERO; + } +} + static const char *const quorum_strong_runtime_opts[] = { QUORUM_OPT_VOTE_THRESHOLD, QUORUM_OPT_BLKVERIFY, @@ -XXX,XX +XXX,XX @@ static BlockDriver bdrv_quorum = { .bdrv_close = quorum_close, .bdrv_gather_child_options = quorum_gather_child_options, .bdrv_dirname = quorum_dirname, + .bdrv_co_block_status = quorum_co_block_status, .bdrv_co_flush_to_disk = quorum_co_flush, diff --git a/tests/qemu-iotests/312 b/tests/qemu-iotests/312 new file mode 100755 index XXXXXXX..XXXXXXX --- /dev/null +++ b/tests/qemu-iotests/312 @@ -XXX,XX +XXX,XX @@ +#!/usr/bin/env bash +# +# Test drive-mirror with quorum +# +# The goal of this test is to check how the quorum driver reports +# regions that are known to read as zeroes (BDRV_BLOCK_ZERO). The idea +# is that drive-mirror will try the efficient representation of zeroes +# in the destination image instead of writing actual zeroes. +# +# Copyright (C) 2020 Igalia, S.L. +# Author: Alberto Garcia <berto@igalia.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 $seq" + +status=1 # failure is the default! + +_cleanup() +{ + _rm_test_img "$TEST_IMG.0" + _rm_test_img "$TEST_IMG.1" + _rm_test_img "$TEST_IMG.2" + _rm_test_img "$TEST_IMG.3" + _cleanup_qemu +} +trap "_cleanup; exit \$status" 0 1 2 3 15 + +# get standard environment, filters and checks +. ./common.rc +. ./common.filter +. ./common.qemu + +_supported_fmt qcow2 +_supported_proto file +_supported_os Linux +_unsupported_imgopts cluster_size data_file + +echo +echo '### Create all images' # three source (quorum), one destination +echo +TEST_IMG="$TEST_IMG.0" _make_test_img -o cluster_size=64k 10M +TEST_IMG="$TEST_IMG.1" _make_test_img -o cluster_size=64k 10M +TEST_IMG="$TEST_IMG.2" _make_test_img -o cluster_size=64k 10M +TEST_IMG="$TEST_IMG.3" _make_test_img -o cluster_size=64k 10M + +quorum="driver=raw,file.driver=quorum,file.vote-threshold=2" +quorum="$quorum,file.children.0.file.filename=$TEST_IMG.0" +quorum="$quorum,file.children.1.file.filename=$TEST_IMG.1" +quorum="$quorum,file.children.2.file.filename=$TEST_IMG.2" +quorum="$quorum,file.children.0.driver=$IMGFMT" +quorum="$quorum,file.children.1.driver=$IMGFMT" +quorum="$quorum,file.children.2.driver=$IMGFMT" + +echo +echo '### Output of qemu-img map (empty quorum)' +echo +$QEMU_IMG map --image-opts $quorum | _filter_qemu_img_map + +# Now we write data to the quorum. All three images will read as +# zeroes in all cases, but with different ways to represent them +# (unallocated clusters, zero clusters, data clusters with zeroes) +# that will have an effect on how the data will be mirrored and the +# output of qemu-img map on the resulting image. +echo +echo '### Write data to the quorum' +echo +# Test 1: data regions surrounded by unallocated clusters. +# Three data regions, the largest one (0x30000) will be picked, end result: +# offset 0x10000, length 0x30000 -> data +$QEMU_IO -c "write -P 0 $((0x10000)) $((0x10000))" "$TEST_IMG.0" | _filter_qemu_io +$QEMU_IO -c "write -P 0 $((0x10000)) $((0x30000))" "$TEST_IMG.1" | _filter_qemu_io +$QEMU_IO -c "write -P 0 $((0x10000)) $((0x20000))" "$TEST_IMG.2" | _filter_qemu_io + +# Test 2: zero regions surrounded by data clusters. +# First we allocate the data clusters. +$QEMU_IO -c "open -o $quorum" -c "write -P 0 $((0x100000)) $((0x40000))" | _filter_qemu_io + +# Three zero regions, the smallest one (0x10000) will be picked, end result: +# offset 0x100000, length 0x10000 -> data +# offset 0x110000, length 0x10000 -> zeroes +# offset 0x120000, length 0x20000 -> data +$QEMU_IO -c "write -z $((0x110000)) $((0x10000))" "$TEST_IMG.0" | _filter_qemu_io +$QEMU_IO -c "write -z $((0x110000)) $((0x30000))" "$TEST_IMG.1" | _filter_qemu_io +$QEMU_IO -c "write -z $((0x110000)) $((0x20000))" "$TEST_IMG.2" | _filter_qemu_io + +# Test 3: zero clusters surrounded by unallocated clusters. +# Everything reads as zeroes, no effect on the end result. +$QEMU_IO -c "write -z $((0x150000)) $((0x10000))" "$TEST_IMG.0" | _filter_qemu_io +$QEMU_IO -c "write -z $((0x150000)) $((0x30000))" "$TEST_IMG.1" | _filter_qemu_io +$QEMU_IO -c "write -z $((0x150000)) $((0x20000))" "$TEST_IMG.2" | _filter_qemu_io + +# Test 4: mix of data and zero clusters. +# The zero region will be ignored in favor of the largest data region +# (0x20000), end result: +# offset 0x200000, length 0x20000 -> data +$QEMU_IO -c "write -P 0 $((0x200000)) $((0x10000))" "$TEST_IMG.0" | _filter_qemu_io +$QEMU_IO -c "write -z $((0x200000)) $((0x30000))" "$TEST_IMG.1" | _filter_qemu_io +$QEMU_IO -c "write -P 0 $((0x200000)) $((0x20000))" "$TEST_IMG.2" | _filter_qemu_io + +echo +echo '### Launch the drive-mirror job' +echo +qemu_comm_method="qmp" _launch_qemu -drive if=virtio,"$quorum" +h=$QEMU_HANDLE +_send_qemu_cmd $h "{ 'execute': 'qmp_capabilities' }" 'return' + +_send_qemu_cmd $h \ + "{'execute': 'drive-mirror', + 'arguments': {'device': 'virtio0', + 'format': '$IMGFMT', + 'target': '$TEST_IMG.3', + 'sync': 'full', + 'mode': 'existing' }}" \ + "BLOCK_JOB_READY.*virtio0" + +_send_qemu_cmd $h \ + "{ 'execute': 'block-job-complete', + 'arguments': { 'device': 'virtio0' } }" \ + 'BLOCK_JOB_COMPLETED' + +_send_qemu_cmd $h "{ 'execute': 'quit' }" '' + +echo +echo '### Output of qemu-img map (destination image)' +echo +$QEMU_IMG map "$TEST_IMG.3" | _filter_qemu_img_map + +# success, all done +echo "*** done" +rm -f $seq.full +status=0 diff --git a/tests/qemu-iotests/312.out b/tests/qemu-iotests/312.out new file mode 100644 index XXXXXXX..XXXXXXX --- /dev/null +++ b/tests/qemu-iotests/312.out @@ -XXX,XX +XXX,XX @@ +QA output created by 312 + +### Create all images + +Formatting 'TEST_DIR/t.IMGFMT.0', fmt=IMGFMT size=10485760 +Formatting 'TEST_DIR/t.IMGFMT.1', fmt=IMGFMT size=10485760 +Formatting 'TEST_DIR/t.IMGFMT.2', fmt=IMGFMT size=10485760 +Formatting 'TEST_DIR/t.IMGFMT.3', fmt=IMGFMT size=10485760 + +### Output of qemu-img map (empty quorum) + +Offset Length File + +### Write data to the quorum + +wrote 65536/65536 bytes at offset 65536 +64 KiB, X ops; XX:XX:XX.X (XXX YYY/sec and XXX ops/sec) +wrote 196608/196608 bytes at offset 65536 +192 KiB, X ops; XX:XX:XX.X (XXX YYY/sec and XXX ops/sec) +wrote 131072/131072 bytes at offset 65536 +128 KiB, X ops; XX:XX:XX.X (XXX YYY/sec and XXX ops/sec) +wrote 262144/262144 bytes at offset 1048576 +256 KiB, X ops; XX:XX:XX.X (XXX YYY/sec and XXX ops/sec) +wrote 65536/65536 bytes at offset 1114112 +64 KiB, X ops; XX:XX:XX.X (XXX YYY/sec and XXX ops/sec) +wrote 196608/196608 bytes at offset 1114112 +192 KiB, X ops; XX:XX:XX.X (XXX YYY/sec and XXX ops/sec) +wrote 131072/131072 bytes at offset 1114112 +128 KiB, X ops; XX:XX:XX.X (XXX YYY/sec and XXX ops/sec) +wrote 65536/65536 bytes at offset 1376256 +64 KiB, X ops; XX:XX:XX.X (XXX YYY/sec and XXX ops/sec) +wrote 196608/196608 bytes at offset 1376256 +192 KiB, X ops; XX:XX:XX.X (XXX YYY/sec and XXX ops/sec) +wrote 131072/131072 bytes at offset 1376256 +128 KiB, X ops; XX:XX:XX.X (XXX YYY/sec and XXX ops/sec) +wrote 65536/65536 bytes at offset 2097152 +64 KiB, X ops; XX:XX:XX.X (XXX YYY/sec and XXX ops/sec) +wrote 196608/196608 bytes at offset 2097152 +192 KiB, X ops; XX:XX:XX.X (XXX YYY/sec and XXX ops/sec) +wrote 131072/131072 bytes at offset 2097152 +128 KiB, X ops; XX:XX:XX.X (XXX YYY/sec and XXX ops/sec) + +### Launch the drive-mirror job + +{ 'execute': 'qmp_capabilities' } +{"return": {}} +{'execute': 'drive-mirror', 'arguments': {'device': 'virtio0', 'format': 'IMGFMT', 'target': 'TEST_DIR/t.IMGFMT.3', 'sync': 'full', 'mode': 'existing' }} +{"timestamp": {"seconds": TIMESTAMP, "microseconds": TIMESTAMP}, "event": "JOB_STATUS_CHANGE", "data": {"status": "created", "id": "virtio0"}} +{"timestamp": {"seconds": TIMESTAMP, "microseconds": TIMESTAMP}, "event": "JOB_STATUS_CHANGE", "data": {"status": "running", "id": "virtio0"}} +{"return": {}} +{"timestamp": {"seconds": TIMESTAMP, "microseconds": TIMESTAMP}, "event": "JOB_STATUS_CHANGE", "data": {"status": "ready", "id": "virtio0"}} +{"timestamp": {"seconds": TIMESTAMP, "microseconds": TIMESTAMP}, "event": "BLOCK_JOB_READY", "data": {"device": "virtio0", "len": 10485760, "offset": 10485760, "speed": 0, "type": "mirror"}} +{ 'execute': 'block-job-complete', 'arguments': { 'device': 'virtio0' } } +{"return": {}} +{"timestamp": {"seconds": TIMESTAMP, "microseconds": TIMESTAMP}, "event": "JOB_STATUS_CHANGE", "data": {"status": "waiting", "id": "virtio0"}} +{"timestamp": {"seconds": TIMESTAMP, "microseconds": TIMESTAMP}, "event": "JOB_STATUS_CHANGE", "data": {"status": "pending", "id": "virtio0"}} +{"timestamp": {"seconds": TIMESTAMP, "microseconds": TIMESTAMP}, "event": "BLOCK_JOB_COMPLETED", "data": {"device": "virtio0", "len": 10485760, "offset": 10485760, "speed": 0, "type": "mirror"}} +{ 'execute': 'quit' } + +### Output of qemu-img map (destination image) + +Offset Length File +0x10000 0x30000 TEST_DIR/t.IMGFMT.3 +0x100000 0x10000 TEST_DIR/t.IMGFMT.3 +0x120000 0x20000 TEST_DIR/t.IMGFMT.3 +0x200000 0x20000 TEST_DIR/t.IMGFMT.3 +*** 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 +312 rw auto quick -- 2.29.2 From: Alberto Garcia <berto@igalia.com> This simply calls bdrv_co_pwrite_zeroes() in all children. bs->supported_zero_flags is also set to the flags that are supported by all children. Signed-off-by: Alberto Garcia <berto@igalia.com> Message-Id: <2f09c842781fe336b4c2e40036bba577b7430190.1605286097.git.berto@igalia.com> Reviewed-by: Max Reitz <mreitz@redhat.com> Signed-off-by: Max Reitz <mreitz@redhat.com> --- block/quorum.c | 36 ++++++++++++++++++++++++++++++++++-- tests/qemu-iotests/312 | 11 +++++++++++ tests/qemu-iotests/312.out | 8 ++++++++ 3 files changed, 53 insertions(+), 2 deletions(-) diff --git a/block/quorum.c b/block/quorum.c index XXXXXXX..XXXXXXX 100644 --- a/block/quorum.c +++ b/block/quorum.c @@ -XXX,XX +XXX,XX @@ static void write_quorum_entry(void *opaque) QuorumChildRequest *sacb = &acb->qcrs[i]; sacb->bs = s->children[i]->bs; - sacb->ret = bdrv_co_pwritev(s->children[i], acb->offset, acb->bytes, - acb->qiov, acb->flags); + if (acb->flags & BDRV_REQ_ZERO_WRITE) { + sacb->ret = bdrv_co_pwrite_zeroes(s->children[i], acb->offset, + acb->bytes, acb->flags); + } else { + sacb->ret = bdrv_co_pwritev(s->children[i], acb->offset, acb->bytes, + acb->qiov, acb->flags); + } if (sacb->ret == 0) { acb->success_count++; } else { @@ -XXX,XX +XXX,XX @@ static int quorum_co_pwritev(BlockDriverState *bs, uint64_t offset, return ret; } +static int quorum_co_pwrite_zeroes(BlockDriverState *bs, int64_t offset, + int bytes, BdrvRequestFlags flags) + +{ + return quorum_co_pwritev(bs, offset, bytes, NULL, + flags | BDRV_REQ_ZERO_WRITE); +} + static int64_t quorum_getlength(BlockDriverState *bs) { BDRVQuorumState *s = bs->opaque; @@ -XXX,XX +XXX,XX @@ static QemuOptsList quorum_runtime_opts = { }, }; +static void quorum_refresh_flags(BlockDriverState *bs) +{ + BDRVQuorumState *s = bs->opaque; + int i; + + bs->supported_zero_flags = + BDRV_REQ_FUA | BDRV_REQ_MAY_UNMAP | BDRV_REQ_NO_FALLBACK; + + for (i = 0; i < s->num_children; i++) { + bs->supported_zero_flags &= s->children[i]->bs->supported_zero_flags; + } + + bs->supported_zero_flags |= BDRV_REQ_WRITE_UNCHANGED; +} + static int quorum_open(BlockDriverState *bs, QDict *options, int flags, Error **errp) { @@ -XXX,XX +XXX,XX @@ static int quorum_open(BlockDriverState *bs, QDict *options, int flags, s->next_child_index = s->num_children; bs->supported_write_flags = BDRV_REQ_WRITE_UNCHANGED; + quorum_refresh_flags(bs); g_free(opened); goto exit; @@ -XXX,XX +XXX,XX @@ static void quorum_add_child(BlockDriverState *bs, BlockDriverState *child_bs, } s->children = g_renew(BdrvChild *, s->children, s->num_children + 1); s->children[s->num_children++] = child; + quorum_refresh_flags(bs); out: bdrv_drained_end(bs); @@ -XXX,XX +XXX,XX @@ static void quorum_del_child(BlockDriverState *bs, BdrvChild *child, s->children = g_renew(BdrvChild *, s->children, --s->num_children); bdrv_unref_child(bs, child); + quorum_refresh_flags(bs); bdrv_drained_end(bs); } @@ -XXX,XX +XXX,XX @@ static BlockDriver bdrv_quorum = { .bdrv_co_preadv = quorum_co_preadv, .bdrv_co_pwritev = quorum_co_pwritev, + .bdrv_co_pwrite_zeroes = quorum_co_pwrite_zeroes, .bdrv_add_child = quorum_add_child, .bdrv_del_child = quorum_del_child, diff --git a/tests/qemu-iotests/312 b/tests/qemu-iotests/312 index XXXXXXX..XXXXXXX 100755 --- a/tests/qemu-iotests/312 +++ b/tests/qemu-iotests/312 @@ -XXX,XX +XXX,XX @@ $QEMU_IO -c "write -P 0 $((0x200000)) $((0x10000))" "$TEST_IMG.0" | _filter_qemu $QEMU_IO -c "write -z $((0x200000)) $((0x30000))" "$TEST_IMG.1" | _filter_qemu_io $QEMU_IO -c "write -P 0 $((0x200000)) $((0x20000))" "$TEST_IMG.2" | _filter_qemu_io +# Test 5: write data to a region and then zeroize it, doing it +# directly on the quorum device instead of the individual images. +# This has no effect on the end result but proves that the quorum driver +# supports 'write -z'. +$QEMU_IO -c "open -o $quorum" -c "write -P 1 $((0x250000)) $((0x10000))" | _filter_qemu_io +# Verify the data that we just wrote +$QEMU_IO -c "open -o $quorum" -c "read -P 1 $((0x250000)) $((0x10000))" | _filter_qemu_io +$QEMU_IO -c "open -o $quorum" -c "write -z $((0x250000)) $((0x10000))" | _filter_qemu_io +# Now it should read back as zeroes +$QEMU_IO -c "open -o $quorum" -c "read -P 0 $((0x250000)) $((0x10000))" | _filter_qemu_io + echo echo '### Launch the drive-mirror job' echo diff --git a/tests/qemu-iotests/312.out b/tests/qemu-iotests/312.out index XXXXXXX..XXXXXXX 100644 --- a/tests/qemu-iotests/312.out +++ b/tests/qemu-iotests/312.out @@ -XXX,XX +XXX,XX @@ wrote 196608/196608 bytes at offset 2097152 192 KiB, X ops; XX:XX:XX.X (XXX YYY/sec and XXX ops/sec) wrote 131072/131072 bytes at offset 2097152 128 KiB, X ops; XX:XX:XX.X (XXX YYY/sec and XXX ops/sec) +wrote 65536/65536 bytes at offset 2424832 +64 KiB, X ops; XX:XX:XX.X (XXX YYY/sec and XXX ops/sec) +read 65536/65536 bytes at offset 2424832 +64 KiB, X ops; XX:XX:XX.X (XXX YYY/sec and XXX ops/sec) +wrote 65536/65536 bytes at offset 2424832 +64 KiB, X ops; XX:XX:XX.X (XXX YYY/sec and XXX ops/sec) +read 65536/65536 bytes at offset 2424832 +64 KiB, X ops; XX:XX:XX.X (XXX YYY/sec and XXX ops/sec) ### Launch the drive-mirror job -- 2.29.2 From: Philippe Mathieu-Daudé <philmd@redhat.com> NVMe drive cannot be shrunk. Since commit c80d8b06cfa we can use the @exact parameter (set to false) to return success if the block device is larger than the requested offset (even if we can not be shrunk). Use this parameter to implement the NVMe truncate() coroutine, similarly how it is done for the iscsi and file-posix drivers (see commit 82325ae5f2f "Evaluate @exact in protocol drivers"). Reported-by: Xueqiang Wei <xuwei@redhat.com> Suggested-by: Max Reitz <mreitz@redhat.com> Signed-off-by: Philippe Mathieu-Daudé <philmd@redhat.com> Message-Id: <20201210125202.858656-1-philmd@redhat.com> Signed-off-by: Max Reitz <mreitz@redhat.com> --- block/nvme.c | 24 ++++++++++++++++++++++++ 1 file changed, 24 insertions(+) diff --git a/block/nvme.c b/block/nvme.c index XXXXXXX..XXXXXXX 100644 --- a/block/nvme.c +++ b/block/nvme.c @@ -XXX,XX +XXX,XX @@ out: } +static int coroutine_fn nvme_co_truncate(BlockDriverState *bs, int64_t offset, + bool exact, PreallocMode prealloc, + BdrvRequestFlags flags, Error **errp) +{ + int64_t cur_length; + + if (prealloc != PREALLOC_MODE_OFF) { + error_setg(errp, "Unsupported preallocation mode '%s'", + PreallocMode_str(prealloc)); + return -ENOTSUP; + } + + cur_length = nvme_getlength(bs); + if (offset != cur_length && exact) { + error_setg(errp, "Cannot resize NVMe devices"); + return -ENOTSUP; + } else if (offset > cur_length) { + error_setg(errp, "Cannot grow NVMe devices"); + return -EINVAL; + } + + return 0; +} static int nvme_reopen_prepare(BDRVReopenState *reopen_state, BlockReopenQueue *queue, Error **errp) @@ -XXX,XX +XXX,XX @@ static BlockDriver bdrv_nvme = { .bdrv_close = nvme_close, .bdrv_getlength = nvme_getlength, .bdrv_probe_blocksizes = nvme_probe_blocksizes, + .bdrv_co_truncate = nvme_co_truncate, .bdrv_co_preadv = nvme_co_preadv, .bdrv_co_pwritev = nvme_co_pwritev, -- 2.29.2 The first parameter passed to _send_qemu_cmd is supposed to be the $QEMU_HANDLE. 102 does not do so here, fix it. As a result, the output changes: Now we see the prompt this command is supposedly waiting for before the resize message - as it should be. Signed-off-by: Max Reitz <mreitz@redhat.com> Message-Id: <20201217153803.101231-2-mreitz@redhat.com> Reviewed-by: Kevin Wolf <kwolf@redhat.com> --- tests/qemu-iotests/102 | 2 +- tests/qemu-iotests/102.out | 2 +- 2 files changed, 2 insertions(+), 2 deletions(-) diff --git a/tests/qemu-iotests/102 b/tests/qemu-iotests/102 index XXXXXXX..XXXXXXX 100755 --- a/tests/qemu-iotests/102 +++ b/tests/qemu-iotests/102 @@ -XXX,XX +XXX,XX @@ $QEMU_IO -c 'write 0 64k' "$TEST_IMG" | _filter_qemu_io qemu_comm_method=monitor _launch_qemu -drive if=none,file="$TEST_IMG",id=drv0 # Wait for a prompt to appear (so we know qemu has opened the image) -_send_qemu_cmd '' '(qemu)' +_send_qemu_cmd $QEMU_HANDLE '' '(qemu)' $QEMU_IMG resize --shrink --image-opts \ "driver=raw,file.driver=file,file.filename=$TEST_IMG,file.locking=off" \ diff --git a/tests/qemu-iotests/102.out b/tests/qemu-iotests/102.out index XXXXXXX..XXXXXXX 100644 --- a/tests/qemu-iotests/102.out +++ b/tests/qemu-iotests/102.out @@ -XXX,XX +XXX,XX @@ Formatting 'TEST_DIR/t.IMGFMT', fmt=IMGFMT size=65536 wrote 65536/65536 bytes at offset 0 64 KiB, X ops; XX:XX:XX.X (XXX YYY/sec and XXX ops/sec) QEMU X.Y.Z monitor - type 'help' for more information -Image resized. (qemu) +Image resized. (qemu) qemu-io drv0 map 64 KiB (0x10000) bytes allocated at offset 0 bytes (0x0) *** done -- 2.29.2 With bash 5.1, the output of the following script changes: a=("double space") a=${a[@]:0:1} echo "$a" from "double space" to "double space", i.e. all white space is preserved as-is. This is probably what we actually want here (judging from the "...to accommodate pathnames with spaces" comment), but before 5.1, we would have to quote the ${} slice to get the same behavior. In any case, without quoting, the reference output of many iotests is different between bash 5.1 and pre-5.1, which is not very good. The output of 5.1 is what we want, so whatever we do to get pre-5.1 to the same result, it means we have to fix the reference output of basically all tests that invoke _send_qemu_cmd (except the ones that only use single spaces in the commands they invoke). Instead of quoting the ${} slice (cmd="${$@: 1:...}"), we can also just not use array slicing and replace the whole thing with a simple "cmd=$1; shift", which works because all callers quote the whole $cmd argument anyway. Signed-off-by: Max Reitz <mreitz@redhat.com> Message-Id: <20201217153803.101231-3-mreitz@redhat.com> Reviewed-by: Kevin Wolf <kwolf@redhat.com> --- tests/qemu-iotests/085.out | 167 ++++++++++++++++++++++++++++----- tests/qemu-iotests/094.out | 10 +- tests/qemu-iotests/095.out | 4 +- tests/qemu-iotests/109.out | 88 ++++++++++++----- tests/qemu-iotests/117.out | 13 ++- tests/qemu-iotests/127.out | 12 ++- tests/qemu-iotests/140.out | 10 +- tests/qemu-iotests/141.out | 128 +++++++++++++++++++------ tests/qemu-iotests/143.out | 4 +- tests/qemu-iotests/144.out | 28 +++++- tests/qemu-iotests/153.out | 18 ++-- tests/qemu-iotests/156.out | 39 ++++++-- tests/qemu-iotests/161.out | 18 +++- tests/qemu-iotests/173.out | 25 ++++- tests/qemu-iotests/182.out | 42 +++++++-- tests/qemu-iotests/183.out | 19 +++- tests/qemu-iotests/185.out | 45 +++++++-- tests/qemu-iotests/191.out | 12 ++- tests/qemu-iotests/223.out | 92 ++++++++++++------ tests/qemu-iotests/229.out | 13 ++- tests/qemu-iotests/249.out | 16 +++- tests/qemu-iotests/308.out | 103 +++++++++++++++++--- tests/qemu-iotests/312.out | 10 +- tests/qemu-iotests/common.qemu | 11 +-- 24 files changed, 728 insertions(+), 199 deletions(-) diff --git a/tests/qemu-iotests/085.out b/tests/qemu-iotests/085.out index XXXXXXX..XXXXXXX 100644 --- a/tests/qemu-iotests/085.out +++ b/tests/qemu-iotests/085.out @@ -XXX,XX +XXX,XX @@ Formatting 'TEST_DIR/t.IMGFMT.2', fmt=IMGFMT size=134217728 === Create a single snapshot on virtio0 === -{ 'execute': 'blockdev-snapshot-sync', 'arguments': { 'device': 'virtio0', 'snapshot-file':'TEST_DIR/1-snapshot-v0.IMGFMT', 'format': 'IMGFMT' } } +{ 'execute': 'blockdev-snapshot-sync', + 'arguments': { 'device': 'virtio0', + 'snapshot-file':'TEST_DIR/1-snapshot-v0.IMGFMT', + 'format': 'IMGFMT' } } Formatting 'TEST_DIR/1-snapshot-v0.qcow2', fmt=qcow2 cluster_size=65536 extended_l2=off compression_type=zlib size=134217728 backing_file=TEST_DIR/t.qcow2.1 backing_fmt=qcow2 lazy_refcounts=off refcount_bits=16 {"return": {}} === Invalid command - missing device and nodename === -{ 'execute': 'blockdev-snapshot-sync', 'arguments': { 'snapshot-file':'TEST_DIR/1-snapshot-v0.IMGFMT', 'format': 'IMGFMT' } } +{ 'execute': 'blockdev-snapshot-sync', + 'arguments': { 'snapshot-file':'TEST_DIR/1-snapshot-v0.IMGFMT', + 'format': 'IMGFMT' } } {"error": {"class": "GenericError", "desc": "Cannot find device= nor node_name="}} === Invalid command - missing snapshot-file === -{ 'execute': 'blockdev-snapshot-sync', 'arguments': { 'device': 'virtio0', 'format': 'IMGFMT' } } +{ 'execute': 'blockdev-snapshot-sync', + 'arguments': { 'device': 'virtio0', + 'format': 'IMGFMT' } } {"error": {"class": "GenericError", "desc": "Parameter 'snapshot-file' is missing"}} === Create several transactional group snapshots === -{ 'execute': 'transaction', 'arguments': {'actions': [ { 'type': 'blockdev-snapshot-sync', 'data' : { 'device': 'virtio0', 'snapshot-file': 'TEST_DIR/2-snapshot-v0.IMGFMT' } }, { 'type': 'blockdev-snapshot-sync', 'data' : { 'device': 'virtio1', 'snapshot-file': 'TEST_DIR/2-snapshot-v1.IMGFMT' } } ] } } +{ 'execute': 'transaction', 'arguments': + {'actions': [ + { 'type': 'blockdev-snapshot-sync', 'data' : + { 'device': 'virtio0', + 'snapshot-file': 'TEST_DIR/2-snapshot-v0.IMGFMT' } }, + { 'type': 'blockdev-snapshot-sync', 'data' : + { 'device': 'virtio1', + 'snapshot-file': 'TEST_DIR/2-snapshot-v1.IMGFMT' } } ] + } } Formatting 'TEST_DIR/2-snapshot-v0.qcow2', fmt=qcow2 cluster_size=65536 extended_l2=off compression_type=zlib size=134217728 backing_file=TEST_DIR/1-snapshot-v0.qcow2 backing_fmt=qcow2 lazy_refcounts=off refcount_bits=16 Formatting 'TEST_DIR/2-snapshot-v1.qcow2', fmt=qcow2 cluster_size=65536 extended_l2=off compression_type=zlib size=134217728 backing_file=TEST_DIR/t.qcow2.2 backing_fmt=qcow2 lazy_refcounts=off refcount_bits=16 {"return": {}} -{ 'execute': 'transaction', 'arguments': {'actions': [ { 'type': 'blockdev-snapshot-sync', 'data' : { 'device': 'virtio0', 'snapshot-file': 'TEST_DIR/3-snapshot-v0.IMGFMT' } }, { 'type': 'blockdev-snapshot-sync', 'data' : { 'device': 'virtio1', 'snapshot-file': 'TEST_DIR/3-snapshot-v1.IMGFMT' } } ] } } +{ 'execute': 'transaction', 'arguments': + {'actions': [ + { 'type': 'blockdev-snapshot-sync', 'data' : + { 'device': 'virtio0', + 'snapshot-file': 'TEST_DIR/3-snapshot-v0.IMGFMT' } }, + { 'type': 'blockdev-snapshot-sync', 'data' : + { 'device': 'virtio1', + 'snapshot-file': 'TEST_DIR/3-snapshot-v1.IMGFMT' } } ] + } } Formatting 'TEST_DIR/3-snapshot-v0.qcow2', fmt=qcow2 cluster_size=65536 extended_l2=off compression_type=zlib size=134217728 backing_file=TEST_DIR/2-snapshot-v0.qcow2 backing_fmt=qcow2 lazy_refcounts=off refcount_bits=16 Formatting 'TEST_DIR/3-snapshot-v1.qcow2', fmt=qcow2 cluster_size=65536 extended_l2=off compression_type=zlib size=134217728 backing_file=TEST_DIR/2-snapshot-v1.qcow2 backing_fmt=qcow2 lazy_refcounts=off refcount_bits=16 {"return": {}} -{ 'execute': 'transaction', 'arguments': {'actions': [ { 'type': 'blockdev-snapshot-sync', 'data' : { 'device': 'virtio0', 'snapshot-file': 'TEST_DIR/4-snapshot-v0.IMGFMT' } }, { 'type': 'blockdev-snapshot-sync', 'data' : { 'device': 'virtio1', 'snapshot-file': 'TEST_DIR/4-snapshot-v1.IMGFMT' } } ] } } +{ 'execute': 'transaction', 'arguments': + {'actions': [ + { 'type': 'blockdev-snapshot-sync', 'data' : + { 'device': 'virtio0', + 'snapshot-file': 'TEST_DIR/4-snapshot-v0.IMGFMT' } }, + { 'type': 'blockdev-snapshot-sync', 'data' : + { 'device': 'virtio1', + 'snapshot-file': 'TEST_DIR/4-snapshot-v1.IMGFMT' } } ] + } } Formatting 'TEST_DIR/4-snapshot-v0.qcow2', fmt=qcow2 cluster_size=65536 extended_l2=off compression_type=zlib size=134217728 backing_file=TEST_DIR/3-snapshot-v0.qcow2 backing_fmt=qcow2 lazy_refcounts=off refcount_bits=16 Formatting 'TEST_DIR/4-snapshot-v1.qcow2', fmt=qcow2 cluster_size=65536 extended_l2=off compression_type=zlib size=134217728 backing_file=TEST_DIR/3-snapshot-v1.qcow2 backing_fmt=qcow2 lazy_refcounts=off refcount_bits=16 {"return": {}} -{ 'execute': 'transaction', 'arguments': {'actions': [ { 'type': 'blockdev-snapshot-sync', 'data' : { 'device': 'virtio0', 'snapshot-file': 'TEST_DIR/5-snapshot-v0.IMGFMT' } }, { 'type': 'blockdev-snapshot-sync', 'data' : { 'device': 'virtio1', 'snapshot-file': 'TEST_DIR/5-snapshot-v1.IMGFMT' } } ] } } +{ 'execute': 'transaction', 'arguments': + {'actions': [ + { 'type': 'blockdev-snapshot-sync', 'data' : + { 'device': 'virtio0', + 'snapshot-file': 'TEST_DIR/5-snapshot-v0.IMGFMT' } }, + { 'type': 'blockdev-snapshot-sync', 'data' : + { 'device': 'virtio1', + 'snapshot-file': 'TEST_DIR/5-snapshot-v1.IMGFMT' } } ] + } } Formatting 'TEST_DIR/5-snapshot-v0.qcow2', fmt=qcow2 cluster_size=65536 extended_l2=off compression_type=zlib size=134217728 backing_file=TEST_DIR/4-snapshot-v0.qcow2 backing_fmt=qcow2 lazy_refcounts=off refcount_bits=16 Formatting 'TEST_DIR/5-snapshot-v1.qcow2', fmt=qcow2 cluster_size=65536 extended_l2=off compression_type=zlib size=134217728 backing_file=TEST_DIR/4-snapshot-v1.qcow2 backing_fmt=qcow2 lazy_refcounts=off refcount_bits=16 {"return": {}} -{ 'execute': 'transaction', 'arguments': {'actions': [ { 'type': 'blockdev-snapshot-sync', 'data' : { 'device': 'virtio0', 'snapshot-file': 'TEST_DIR/6-snapshot-v0.IMGFMT' } }, { 'type': 'blockdev-snapshot-sync', 'data' : { 'device': 'virtio1', 'snapshot-file': 'TEST_DIR/6-snapshot-v1.IMGFMT' } } ] } } +{ 'execute': 'transaction', 'arguments': + {'actions': [ + { 'type': 'blockdev-snapshot-sync', 'data' : + { 'device': 'virtio0', + 'snapshot-file': 'TEST_DIR/6-snapshot-v0.IMGFMT' } }, + { 'type': 'blockdev-snapshot-sync', 'data' : + { 'device': 'virtio1', + 'snapshot-file': 'TEST_DIR/6-snapshot-v1.IMGFMT' } } ] + } } Formatting 'TEST_DIR/6-snapshot-v0.qcow2', fmt=qcow2 cluster_size=65536 extended_l2=off compression_type=zlib size=134217728 backing_file=TEST_DIR/5-snapshot-v0.qcow2 backing_fmt=qcow2 lazy_refcounts=off refcount_bits=16 Formatting 'TEST_DIR/6-snapshot-v1.qcow2', fmt=qcow2 cluster_size=65536 extended_l2=off compression_type=zlib size=134217728 backing_file=TEST_DIR/5-snapshot-v1.qcow2 backing_fmt=qcow2 lazy_refcounts=off refcount_bits=16 {"return": {}} -{ 'execute': 'transaction', 'arguments': {'actions': [ { 'type': 'blockdev-snapshot-sync', 'data' : { 'device': 'virtio0', 'snapshot-file': 'TEST_DIR/7-snapshot-v0.IMGFMT' } }, { 'type': 'blockdev-snapshot-sync', 'data' : { 'device': 'virtio1', 'snapshot-file': 'TEST_DIR/7-snapshot-v1.IMGFMT' } } ] } } +{ 'execute': 'transaction', 'arguments': + {'actions': [ + { 'type': 'blockdev-snapshot-sync', 'data' : + { 'device': 'virtio0', + 'snapshot-file': 'TEST_DIR/7-snapshot-v0.IMGFMT' } }, + { 'type': 'blockdev-snapshot-sync', 'data' : + { 'device': 'virtio1', + 'snapshot-file': 'TEST_DIR/7-snapshot-v1.IMGFMT' } } ] + } } Formatting 'TEST_DIR/7-snapshot-v0.qcow2', fmt=qcow2 cluster_size=65536 extended_l2=off compression_type=zlib size=134217728 backing_file=TEST_DIR/6-snapshot-v0.qcow2 backing_fmt=qcow2 lazy_refcounts=off refcount_bits=16 Formatting 'TEST_DIR/7-snapshot-v1.qcow2', fmt=qcow2 cluster_size=65536 extended_l2=off compression_type=zlib size=134217728 backing_file=TEST_DIR/6-snapshot-v1.qcow2 backing_fmt=qcow2 lazy_refcounts=off refcount_bits=16 {"return": {}} -{ 'execute': 'transaction', 'arguments': {'actions': [ { 'type': 'blockdev-snapshot-sync', 'data' : { 'device': 'virtio0', 'snapshot-file': 'TEST_DIR/8-snapshot-v0.IMGFMT' } }, { 'type': 'blockdev-snapshot-sync', 'data' : { 'device': 'virtio1', 'snapshot-file': 'TEST_DIR/8-snapshot-v1.IMGFMT' } } ] } } +{ 'execute': 'transaction', 'arguments': + {'actions': [ + { 'type': 'blockdev-snapshot-sync', 'data' : + { 'device': 'virtio0', + 'snapshot-file': 'TEST_DIR/8-snapshot-v0.IMGFMT' } }, + { 'type': 'blockdev-snapshot-sync', 'data' : + { 'device': 'virtio1', + 'snapshot-file': 'TEST_DIR/8-snapshot-v1.IMGFMT' } } ] + } } Formatting 'TEST_DIR/8-snapshot-v0.qcow2', fmt=qcow2 cluster_size=65536 extended_l2=off compression_type=zlib size=134217728 backing_file=TEST_DIR/7-snapshot-v0.qcow2 backing_fmt=qcow2 lazy_refcounts=off refcount_bits=16 Formatting 'TEST_DIR/8-snapshot-v1.qcow2', fmt=qcow2 cluster_size=65536 extended_l2=off compression_type=zlib size=134217728 backing_file=TEST_DIR/7-snapshot-v1.qcow2 backing_fmt=qcow2 lazy_refcounts=off refcount_bits=16 {"return": {}} -{ 'execute': 'transaction', 'arguments': {'actions': [ { 'type': 'blockdev-snapshot-sync', 'data' : { 'device': 'virtio0', 'snapshot-file': 'TEST_DIR/9-snapshot-v0.IMGFMT' } }, { 'type': 'blockdev-snapshot-sync', 'data' : { 'device': 'virtio1', 'snapshot-file': 'TEST_DIR/9-snapshot-v1.IMGFMT' } } ] } } +{ 'execute': 'transaction', 'arguments': + {'actions': [ + { 'type': 'blockdev-snapshot-sync', 'data' : + { 'device': 'virtio0', + 'snapshot-file': 'TEST_DIR/9-snapshot-v0.IMGFMT' } }, + { 'type': 'blockdev-snapshot-sync', 'data' : + { 'device': 'virtio1', + 'snapshot-file': 'TEST_DIR/9-snapshot-v1.IMGFMT' } } ] + } } Formatting 'TEST_DIR/9-snapshot-v0.qcow2', fmt=qcow2 cluster_size=65536 extended_l2=off compression_type=zlib size=134217728 backing_file=TEST_DIR/8-snapshot-v0.qcow2 backing_fmt=qcow2 lazy_refcounts=off refcount_bits=16 Formatting 'TEST_DIR/9-snapshot-v1.qcow2', fmt=qcow2 cluster_size=65536 extended_l2=off compression_type=zlib size=134217728 backing_file=TEST_DIR/8-snapshot-v1.qcow2 backing_fmt=qcow2 lazy_refcounts=off refcount_bits=16 {"return": {}} -{ 'execute': 'transaction', 'arguments': {'actions': [ { 'type': 'blockdev-snapshot-sync', 'data' : { 'device': 'virtio0', 'snapshot-file': 'TEST_DIR/10-snapshot-v0.IMGFMT' } }, { 'type': 'blockdev-snapshot-sync', 'data' : { 'device': 'virtio1', 'snapshot-file': 'TEST_DIR/10-snapshot-v1.IMGFMT' } } ] } } +{ 'execute': 'transaction', 'arguments': + {'actions': [ + { 'type': 'blockdev-snapshot-sync', 'data' : + { 'device': 'virtio0', + 'snapshot-file': 'TEST_DIR/10-snapshot-v0.IMGFMT' } }, + { 'type': 'blockdev-snapshot-sync', 'data' : + { 'device': 'virtio1', + 'snapshot-file': 'TEST_DIR/10-snapshot-v1.IMGFMT' } } ] + } } Formatting 'TEST_DIR/10-snapshot-v0.qcow2', fmt=qcow2 cluster_size=65536 extended_l2=off compression_type=zlib size=134217728 backing_file=TEST_DIR/9-snapshot-v0.qcow2 backing_fmt=qcow2 lazy_refcounts=off refcount_bits=16 Formatting 'TEST_DIR/10-snapshot-v1.qcow2', fmt=qcow2 cluster_size=65536 extended_l2=off compression_type=zlib size=134217728 backing_file=TEST_DIR/9-snapshot-v1.qcow2 backing_fmt=qcow2 lazy_refcounts=off refcount_bits=16 {"return": {}} @@ -XXX,XX +XXX,XX @@ Formatting 'TEST_DIR/10-snapshot-v1.qcow2', fmt=qcow2 cluster_size=65536 extende === Create a couple of snapshots using blockdev-snapshot === Formatting 'TEST_DIR/11-snapshot-v0.IMGFMT', fmt=IMGFMT size=134217728 backing_file=TEST_DIR/10-snapshot-v0.IMGFMT backing_fmt=IMGFMT -{ 'execute': 'blockdev-add', 'arguments': { 'driver': 'IMGFMT', 'node-name': 'snap_11', 'backing': null, 'file': { 'driver': 'file', 'filename': 'TEST_DIR/11-snapshot-v0.IMGFMT', 'node-name': 'file_11' } } } +{ 'execute': 'blockdev-add', 'arguments': + { 'driver': 'IMGFMT', 'node-name': 'snap_11', 'backing': null, + 'file': + { 'driver': 'file', 'filename': 'TEST_DIR/11-snapshot-v0.IMGFMT', + 'node-name': 'file_11' } } } {"return": {}} -{ 'execute': 'blockdev-snapshot', 'arguments': { 'node': 'virtio0', 'overlay':'snap_11' } } +{ 'execute': 'blockdev-snapshot', + 'arguments': { 'node': 'virtio0', + 'overlay':'snap_11' } } {"return": {}} Formatting 'TEST_DIR/12-snapshot-v0.IMGFMT', fmt=IMGFMT size=134217728 backing_file=TEST_DIR/11-snapshot-v0.IMGFMT backing_fmt=IMGFMT -{ 'execute': 'blockdev-add', 'arguments': { 'driver': 'IMGFMT', 'node-name': 'snap_12', 'backing': null, 'file': { 'driver': 'file', 'filename': 'TEST_DIR/12-snapshot-v0.IMGFMT', 'node-name': 'file_12' } } } +{ 'execute': 'blockdev-add', 'arguments': + { 'driver': 'IMGFMT', 'node-name': 'snap_12', 'backing': null, + 'file': + { 'driver': 'file', 'filename': 'TEST_DIR/12-snapshot-v0.IMGFMT', + 'node-name': 'file_12' } } } {"return": {}} -{ 'execute': 'blockdev-snapshot', 'arguments': { 'node': 'virtio0', 'overlay':'snap_12' } } +{ 'execute': 'blockdev-snapshot', + 'arguments': { 'node': 'virtio0', + 'overlay':'snap_12' } } {"return": {}} === Invalid command - cannot create a snapshot using a file BDS === -{ 'execute': 'blockdev-snapshot', 'arguments': { 'node':'virtio0', 'overlay':'file_12' } } +{ 'execute': 'blockdev-snapshot', + 'arguments': { 'node':'virtio0', + 'overlay':'file_12' } + } {"error": {"class": "GenericError", "desc": "The overlay is already in use"}} === Invalid command - snapshot node used as active layer === -{ 'execute': 'blockdev-snapshot', 'arguments': { 'node': 'virtio0', 'overlay':'snap_12' } } +{ 'execute': 'blockdev-snapshot', + 'arguments': { 'node': 'virtio0', + 'overlay':'snap_12' } } {"error": {"class": "GenericError", "desc": "The overlay is already in use"}} -{ 'execute': 'blockdev-snapshot', 'arguments': { 'node':'virtio0', 'overlay':'virtio0' } } +{ 'execute': 'blockdev-snapshot', + 'arguments': { 'node':'virtio0', + 'overlay':'virtio0' } + } {"error": {"class": "GenericError", "desc": "The overlay is already in use"}} -{ 'execute': 'blockdev-snapshot', 'arguments': { 'node':'virtio0', 'overlay':'virtio1' } } +{ 'execute': 'blockdev-snapshot', + 'arguments': { 'node':'virtio0', + 'overlay':'virtio1' } + } {"error": {"class": "GenericError", "desc": "The overlay is already in use"}} === Invalid command - snapshot node used as backing hd === -{ 'execute': 'blockdev-snapshot', 'arguments': { 'node': 'virtio0', 'overlay':'snap_11' } } +{ 'execute': 'blockdev-snapshot', + 'arguments': { 'node': 'virtio0', + 'overlay':'snap_11' } } {"error": {"class": "GenericError", "desc": "The overlay is already in use"}} === Invalid command - snapshot node has a backing image === Formatting 'TEST_DIR/t.IMGFMT.base', fmt=IMGFMT size=134217728 Formatting 'TEST_DIR/t.IMGFMT', fmt=IMGFMT size=134217728 backing_file=TEST_DIR/t.IMGFMT.base backing_fmt=IMGFMT -{ 'execute': 'blockdev-add', 'arguments': { 'driver': 'IMGFMT', 'node-name': 'snap_13', 'file': { 'driver': 'file', 'filename': 'TEST_DIR/t.IMGFMT', 'node-name': 'file_13' } } } -{"return": {}} -{ 'execute': 'blockdev-snapshot', 'arguments': { 'node': 'virtio0', 'overlay':'snap_13' } } +{ 'execute': 'blockdev-add', 'arguments': + { 'driver': 'IMGFMT', 'node-name': 'snap_13', + 'file': + { 'driver': 'file', 'filename': 'TEST_DIR/t.IMGFMT', + 'node-name': 'file_13' } } } +{"return": {}} +{ 'execute': 'blockdev-snapshot', + 'arguments': { 'node': 'virtio0', + 'overlay':'snap_13' } } {"error": {"class": "GenericError", "desc": "The overlay already has a backing image"}} === Invalid command - The node does not exist === -{ 'execute': 'blockdev-snapshot', 'arguments': { 'node': 'virtio0', 'overlay':'snap_14' } } +{ 'execute': 'blockdev-snapshot', + 'arguments': { 'node': 'virtio0', + 'overlay':'snap_14' } } {"error": {"class": "GenericError", "desc": "Cannot find device=snap_14 nor node_name=snap_14"}} -{ 'execute': 'blockdev-snapshot', 'arguments': { 'node':'nodevice', 'overlay':'snap_13' } } +{ 'execute': 'blockdev-snapshot', + 'arguments': { 'node':'nodevice', + 'overlay':'snap_13' } + } {"error": {"class": "GenericError", "desc": "Cannot find device=nodevice nor node_name=nodevice"}} *** done diff --git a/tests/qemu-iotests/094.out b/tests/qemu-iotests/094.out index XXXXXXX..XXXXXXX 100644 --- a/tests/qemu-iotests/094.out +++ b/tests/qemu-iotests/094.out @@ -XXX,XX +XXX,XX @@ Formatting 'TEST_DIR/t.IMGFMT', fmt=IMGFMT size=67108864 Formatting 'TEST_DIR/source.IMGFMT', fmt=IMGFMT size=67108864 {'execute': 'qmp_capabilities'} {"return": {}} -{'execute': 'drive-mirror', 'arguments': {'device': 'src', 'target': 'nbd+unix:///?socket=SOCK_DIR/nbd', 'format': 'nbd', 'sync':'full', 'mode':'existing'}} +{'execute': 'drive-mirror', + 'arguments': {'device': 'src', + 'target': 'nbd+unix:///?socket=SOCK_DIR/nbd', + 'format': 'nbd', + 'sync':'full', + 'mode':'existing'}} {"timestamp": {"seconds": TIMESTAMP, "microseconds": TIMESTAMP}, "event": "JOB_STATUS_CHANGE", "data": {"status": "created", "id": "src"}} {"timestamp": {"seconds": TIMESTAMP, "microseconds": TIMESTAMP}, "event": "JOB_STATUS_CHANGE", "data": {"status": "running", "id": "src"}} {"return": {}} {"timestamp": {"seconds": TIMESTAMP, "microseconds": TIMESTAMP}, "event": "JOB_STATUS_CHANGE", "data": {"status": "ready", "id": "src"}} {"timestamp": {"seconds": TIMESTAMP, "microseconds": TIMESTAMP}, "event": "BLOCK_JOB_READY", "data": {"device": "src", "len": 67108864, "offset": 67108864, "speed": 0, "type": "mirror"}} -{'execute': 'block-job-complete', 'arguments': {'device': 'src'}} +{'execute': 'block-job-complete', + 'arguments': {'device': 'src'}} {"return": {}} {"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"}} diff --git a/tests/qemu-iotests/095.out b/tests/qemu-iotests/095.out index XXXXXXX..XXXXXXX 100644 --- a/tests/qemu-iotests/095.out +++ b/tests/qemu-iotests/095.out @@ -XXX,XX +XXX,XX @@ virtual size: 5 MiB (5242880 bytes) { 'execute': 'qmp_capabilities' } {"return": {}} -{ 'execute': 'block-commit', 'arguments': { 'device': 'test', 'top': 'TEST_DIR/t.IMGFMT.snp1' } } +{ 'execute': 'block-commit', + 'arguments': { 'device': 'test', + 'top': 'TEST_DIR/t.IMGFMT.snp1' } } {"timestamp": {"seconds": TIMESTAMP, "microseconds": TIMESTAMP}, "event": "JOB_STATUS_CHANGE", "data": {"status": "created", "id": "test"}} {"timestamp": {"seconds": TIMESTAMP, "microseconds": TIMESTAMP}, "event": "JOB_STATUS_CHANGE", "data": {"status": "running", "id": "test"}} {"return": {}} 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 @@ Formatting 'TEST_DIR/t.raw.src', fmt=IMGFMT size=67108864 Formatting 'TEST_DIR/t.IMGFMT', fmt=IMGFMT size=SIZE { 'execute': 'qmp_capabilities' } {"return": {}} -{'execute':'drive-mirror', 'arguments':{ 'device': 'src', 'target': 'TEST_DIR/t.IMGFMT', 'mode': 'existing', 'sync': 'full'}} +{'execute':'drive-mirror', 'arguments':{ + 'device': 'src', 'target': 'TEST_DIR/t.IMGFMT', + 'mode': 'existing', 'sync': 'full'}} WARNING: Image format was not specified for 'TEST_DIR/t.raw' and probing guessed raw. Automatically detecting the format is dangerous for raw images, write operations on block 0 will be restricted. Specify the 'raw' format explicitly to remove the restrictions. @@ -XXX,XX +XXX,XX @@ read 512/512 bytes at offset 0 512 bytes, X ops; XX:XX:XX.X (XXX YYY/sec and XXX ops/sec) { 'execute': 'qmp_capabilities' } {"return": {}} -{'execute':'drive-mirror', 'arguments':{ 'device': 'src', 'target': 'TEST_DIR/t.IMGFMT', 'format': 'IMGFMT', 'mode': 'existing', 'sync': 'full'}} +{'execute':'drive-mirror', 'arguments':{ + 'device': 'src', 'target': 'TEST_DIR/t.IMGFMT', 'format': 'IMGFMT', + 'mode': 'existing', 'sync': 'full'}} {"timestamp": {"seconds": TIMESTAMP, "microseconds": TIMESTAMP}, "event": "JOB_STATUS_CHANGE", "data": {"status": "created", "id": "src"}} {"timestamp": {"seconds": TIMESTAMP, "microseconds": TIMESTAMP}, "event": "JOB_STATUS_CHANGE", "data": {"status": "running", "id": "src"}} {"return": {}} @@ -XXX,XX +XXX,XX @@ Formatting 'TEST_DIR/t.raw.src', fmt=IMGFMT size=67108864 Formatting 'TEST_DIR/t.IMGFMT', fmt=IMGFMT size=SIZE { 'execute': 'qmp_capabilities' } {"return": {}} -{'execute':'drive-mirror', 'arguments':{ 'device': 'src', 'target': 'TEST_DIR/t.IMGFMT', 'mode': 'existing', 'sync': 'full'}} +{'execute':'drive-mirror', 'arguments':{ + 'device': 'src', 'target': 'TEST_DIR/t.IMGFMT', + 'mode': 'existing', 'sync': 'full'}} WARNING: Image format was not specified for 'TEST_DIR/t.raw' and probing guessed raw. Automatically detecting the format is dangerous for raw images, write operations on block 0 will be restricted. Specify the 'raw' format explicitly to remove the restrictions. @@ -XXX,XX +XXX,XX @@ read 512/512 bytes at offset 0 512 bytes, X ops; XX:XX:XX.X (XXX YYY/sec and XXX ops/sec) { 'execute': 'qmp_capabilities' } {"return": {}} -{'execute':'drive-mirror', 'arguments':{ 'device': 'src', 'target': 'TEST_DIR/t.IMGFMT', 'format': 'IMGFMT', 'mode': 'existing', 'sync': 'full'}} +{'execute':'drive-mirror', 'arguments':{ + 'device': 'src', 'target': 'TEST_DIR/t.IMGFMT', 'format': 'IMGFMT', + 'mode': 'existing', 'sync': 'full'}} {"timestamp": {"seconds": TIMESTAMP, "microseconds": TIMESTAMP}, "event": "JOB_STATUS_CHANGE", "data": {"status": "created", "id": "src"}} {"timestamp": {"seconds": TIMESTAMP, "microseconds": TIMESTAMP}, "event": "JOB_STATUS_CHANGE", "data": {"status": "running", "id": "src"}} {"return": {}} @@ -XXX,XX +XXX,XX @@ Formatting 'TEST_DIR/t.raw.src', fmt=IMGFMT size=67108864 Formatting 'TEST_DIR/t.IMGFMT', fmt=IMGFMT size=SIZE { 'execute': 'qmp_capabilities' } {"return": {}} -{'execute':'drive-mirror', 'arguments':{ 'device': 'src', 'target': 'TEST_DIR/t.IMGFMT', 'mode': 'existing', 'sync': 'full'}} +{'execute':'drive-mirror', 'arguments':{ + 'device': 'src', 'target': 'TEST_DIR/t.IMGFMT', + 'mode': 'existing', 'sync': 'full'}} WARNING: Image format was not specified for 'TEST_DIR/t.raw' and probing guessed raw. Automatically detecting the format is dangerous for raw images, write operations on block 0 will be restricted. Specify the 'raw' format explicitly to remove the restrictions. @@ -XXX,XX +XXX,XX @@ read 512/512 bytes at offset 0 512 bytes, X ops; XX:XX:XX.X (XXX YYY/sec and XXX ops/sec) { 'execute': 'qmp_capabilities' } {"return": {}} -{'execute':'drive-mirror', 'arguments':{ 'device': 'src', 'target': 'TEST_DIR/t.IMGFMT', 'format': 'IMGFMT', 'mode': 'existing', 'sync': 'full'}} +{'execute':'drive-mirror', 'arguments':{ + 'device': 'src', 'target': 'TEST_DIR/t.IMGFMT', 'format': 'IMGFMT', + 'mode': 'existing', 'sync': 'full'}} {"timestamp": {"seconds": TIMESTAMP, "microseconds": TIMESTAMP}, "event": "JOB_STATUS_CHANGE", "data": {"status": "created", "id": "src"}} {"timestamp": {"seconds": TIMESTAMP, "microseconds": TIMESTAMP}, "event": "JOB_STATUS_CHANGE", "data": {"status": "running", "id": "src"}} {"return": {}} @@ -XXX,XX +XXX,XX @@ Formatting 'TEST_DIR/t.raw.src', fmt=IMGFMT size=67108864 Formatting 'TEST_DIR/t.IMGFMT', fmt=IMGFMT size=SIZE { 'execute': 'qmp_capabilities' } {"return": {}} -{'execute':'drive-mirror', 'arguments':{ 'device': 'src', 'target': 'TEST_DIR/t.IMGFMT', 'mode': 'existing', 'sync': 'full'}} +{'execute':'drive-mirror', 'arguments':{ + 'device': 'src', 'target': 'TEST_DIR/t.IMGFMT', + 'mode': 'existing', 'sync': 'full'}} WARNING: Image format was not specified for 'TEST_DIR/t.raw' and probing guessed raw. Automatically detecting the format is dangerous for raw images, write operations on block 0 will be restricted. Specify the 'raw' format explicitly to remove the restrictions. @@ -XXX,XX +XXX,XX @@ read 512/512 bytes at offset 0 512 bytes, X ops; XX:XX:XX.X (XXX YYY/sec and XXX ops/sec) { 'execute': 'qmp_capabilities' } {"return": {}} -{'execute':'drive-mirror', 'arguments':{ 'device': 'src', 'target': 'TEST_DIR/t.IMGFMT', 'format': 'IMGFMT', 'mode': 'existing', 'sync': 'full'}} +{'execute':'drive-mirror', 'arguments':{ + 'device': 'src', 'target': 'TEST_DIR/t.IMGFMT', 'format': 'IMGFMT', + 'mode': 'existing', 'sync': 'full'}} {"timestamp": {"seconds": TIMESTAMP, "microseconds": TIMESTAMP}, "event": "JOB_STATUS_CHANGE", "data": {"status": "created", "id": "src"}} {"timestamp": {"seconds": TIMESTAMP, "microseconds": TIMESTAMP}, "event": "JOB_STATUS_CHANGE", "data": {"status": "running", "id": "src"}} {"return": {}} @@ -XXX,XX +XXX,XX @@ Formatting 'TEST_DIR/t.raw.src', fmt=IMGFMT size=67108864 Formatting 'TEST_DIR/t.IMGFMT', fmt=IMGFMT size=SIZE { 'execute': 'qmp_capabilities' } {"return": {}} -{'execute':'drive-mirror', 'arguments':{ 'device': 'src', 'target': 'TEST_DIR/t.IMGFMT', 'mode': 'existing', 'sync': 'full'}} +{'execute':'drive-mirror', 'arguments':{ + 'device': 'src', 'target': 'TEST_DIR/t.IMGFMT', + 'mode': 'existing', 'sync': 'full'}} WARNING: Image format was not specified for 'TEST_DIR/t.raw' and probing guessed raw. Automatically detecting the format is dangerous for raw images, write operations on block 0 will be restricted. Specify the 'raw' format explicitly to remove the restrictions. @@ -XXX,XX +XXX,XX @@ read 512/512 bytes at offset 0 512 bytes, X ops; XX:XX:XX.X (XXX YYY/sec and XXX ops/sec) { 'execute': 'qmp_capabilities' } {"return": {}} -{'execute':'drive-mirror', 'arguments':{ 'device': 'src', 'target': 'TEST_DIR/t.IMGFMT', 'format': 'IMGFMT', 'mode': 'existing', 'sync': 'full'}} +{'execute':'drive-mirror', 'arguments':{ + 'device': 'src', 'target': 'TEST_DIR/t.IMGFMT', 'format': 'IMGFMT', + 'mode': 'existing', 'sync': 'full'}} {"timestamp": {"seconds": TIMESTAMP, "microseconds": TIMESTAMP}, "event": "JOB_STATUS_CHANGE", "data": {"status": "created", "id": "src"}} {"timestamp": {"seconds": TIMESTAMP, "microseconds": TIMESTAMP}, "event": "JOB_STATUS_CHANGE", "data": {"status": "running", "id": "src"}} {"return": {}} @@ -XXX,XX +XXX,XX @@ Formatting 'TEST_DIR/t.raw.src', fmt=IMGFMT size=67108864 Formatting 'TEST_DIR/t.IMGFMT', fmt=IMGFMT size=SIZE { 'execute': 'qmp_capabilities' } {"return": {}} -{'execute':'drive-mirror', 'arguments':{ 'device': 'src', 'target': 'TEST_DIR/t.IMGFMT', 'mode': 'existing', 'sync': 'full'}} +{'execute':'drive-mirror', 'arguments':{ + 'device': 'src', 'target': 'TEST_DIR/t.IMGFMT', + 'mode': 'existing', 'sync': 'full'}} WARNING: Image format was not specified for 'TEST_DIR/t.raw' and probing guessed raw. Automatically detecting the format is dangerous for raw images, write operations on block 0 will be restricted. Specify the 'raw' format explicitly to remove the restrictions. @@ -XXX,XX +XXX,XX @@ read 512/512 bytes at offset 0 512 bytes, X ops; XX:XX:XX.X (XXX YYY/sec and XXX ops/sec) { 'execute': 'qmp_capabilities' } {"return": {}} -{'execute':'drive-mirror', 'arguments':{ 'device': 'src', 'target': 'TEST_DIR/t.IMGFMT', 'format': 'IMGFMT', 'mode': 'existing', 'sync': 'full'}} +{'execute':'drive-mirror', 'arguments':{ + 'device': 'src', 'target': 'TEST_DIR/t.IMGFMT', 'format': 'IMGFMT', + 'mode': 'existing', 'sync': 'full'}} {"timestamp": {"seconds": TIMESTAMP, "microseconds": TIMESTAMP}, "event": "JOB_STATUS_CHANGE", "data": {"status": "created", "id": "src"}} {"timestamp": {"seconds": TIMESTAMP, "microseconds": TIMESTAMP}, "event": "JOB_STATUS_CHANGE", "data": {"status": "running", "id": "src"}} {"return": {}} @@ -XXX,XX +XXX,XX @@ Images are identical. Formatting 'TEST_DIR/t.IMGFMT', fmt=IMGFMT size=SIZE { 'execute': 'qmp_capabilities' } {"return": {}} -{'execute':'drive-mirror', 'arguments':{ 'device': 'src', 'target': 'TEST_DIR/t.IMGFMT', 'mode': 'existing', 'sync': 'full'}} +{'execute':'drive-mirror', 'arguments':{ + 'device': 'src', 'target': 'TEST_DIR/t.IMGFMT', + 'mode': 'existing', 'sync': 'full'}} WARNING: Image format was not specified for 'TEST_DIR/t.raw' and probing guessed raw. Automatically detecting the format is dangerous for raw images, write operations on block 0 will be restricted. Specify the 'raw' format explicitly to remove the restrictions. @@ -XXX,XX +XXX,XX @@ read 512/512 bytes at offset 0 512 bytes, X ops; XX:XX:XX.X (XXX YYY/sec and XXX ops/sec) { 'execute': 'qmp_capabilities' } {"return": {}} -{'execute':'drive-mirror', 'arguments':{ 'device': 'src', 'target': 'TEST_DIR/t.IMGFMT', 'format': 'IMGFMT', 'mode': 'existing', 'sync': 'full'}} +{'execute':'drive-mirror', 'arguments':{ + 'device': 'src', 'target': 'TEST_DIR/t.IMGFMT', 'format': 'IMGFMT', + 'mode': 'existing', 'sync': 'full'}} {"timestamp": {"seconds": TIMESTAMP, "microseconds": TIMESTAMP}, "event": "JOB_STATUS_CHANGE", "data": {"status": "created", "id": "src"}} {"timestamp": {"seconds": TIMESTAMP, "microseconds": TIMESTAMP}, "event": "JOB_STATUS_CHANGE", "data": {"status": "running", "id": "src"}} {"return": {}} @@ -XXX,XX +XXX,XX @@ Images are identical. Formatting 'TEST_DIR/t.IMGFMT', fmt=IMGFMT size=SIZE { 'execute': 'qmp_capabilities' } {"return": {}} -{'execute':'drive-mirror', 'arguments':{ 'device': 'src', 'target': 'TEST_DIR/t.IMGFMT', 'mode': 'existing', 'sync': 'full'}} +{'execute':'drive-mirror', 'arguments':{ + 'device': 'src', 'target': 'TEST_DIR/t.IMGFMT', + 'mode': 'existing', 'sync': 'full'}} WARNING: Image format was not specified for 'TEST_DIR/t.raw' and probing guessed raw. Automatically detecting the format is dangerous for raw images, write operations on block 0 will be restricted. Specify the 'raw' format explicitly to remove the restrictions. @@ -XXX,XX +XXX,XX @@ read 512/512 bytes at offset 0 512 bytes, X ops; XX:XX:XX.X (XXX YYY/sec and XXX ops/sec) { 'execute': 'qmp_capabilities' } {"return": {}} -{'execute':'drive-mirror', 'arguments':{ 'device': 'src', 'target': 'TEST_DIR/t.IMGFMT', 'format': 'IMGFMT', 'mode': 'existing', 'sync': 'full'}} +{'execute':'drive-mirror', 'arguments':{ + 'device': 'src', 'target': 'TEST_DIR/t.IMGFMT', 'format': 'IMGFMT', + 'mode': 'existing', 'sync': 'full'}} {"timestamp": {"seconds": TIMESTAMP, "microseconds": TIMESTAMP}, "event": "JOB_STATUS_CHANGE", "data": {"status": "created", "id": "src"}} {"timestamp": {"seconds": TIMESTAMP, "microseconds": TIMESTAMP}, "event": "JOB_STATUS_CHANGE", "data": {"status": "running", "id": "src"}} {"return": {}} @@ -XXX,XX +XXX,XX @@ Images are identical. Formatting 'TEST_DIR/t.IMGFMT', fmt=IMGFMT size=SIZE { 'execute': 'qmp_capabilities' } {"return": {}} -{'execute':'drive-mirror', 'arguments':{ 'device': 'src', 'target': 'TEST_DIR/t.IMGFMT', 'mode': 'existing', 'sync': 'full'}} +{'execute':'drive-mirror', 'arguments':{ + 'device': 'src', 'target': 'TEST_DIR/t.IMGFMT', + 'mode': 'existing', 'sync': 'full'}} WARNING: Image format was not specified for 'TEST_DIR/t.raw' and probing guessed raw. Automatically detecting the format is dangerous for raw images, write operations on block 0 will be restricted. Specify the 'raw' format explicitly to remove the restrictions. @@ -XXX,XX +XXX,XX @@ read 512/512 bytes at offset 0 512 bytes, X ops; XX:XX:XX.X (XXX YYY/sec and XXX ops/sec) { 'execute': 'qmp_capabilities' } {"return": {}} -{'execute':'drive-mirror', 'arguments':{ 'device': 'src', 'target': 'TEST_DIR/t.IMGFMT', 'format': 'IMGFMT', 'mode': 'existing', 'sync': 'full'}} +{'execute':'drive-mirror', 'arguments':{ + 'device': 'src', 'target': 'TEST_DIR/t.IMGFMT', 'format': 'IMGFMT', + 'mode': 'existing', 'sync': 'full'}} {"timestamp": {"seconds": TIMESTAMP, "microseconds": TIMESTAMP}, "event": "JOB_STATUS_CHANGE", "data": {"status": "created", "id": "src"}} {"timestamp": {"seconds": TIMESTAMP, "microseconds": TIMESTAMP}, "event": "JOB_STATUS_CHANGE", "data": {"status": "running", "id": "src"}} {"return": {}} @@ -XXX,XX +XXX,XX @@ Images are identical. Formatting 'TEST_DIR/t.IMGFMT', fmt=IMGFMT size=SIZE { 'execute': 'qmp_capabilities' } {"return": {}} -{'execute':'drive-mirror', 'arguments':{ 'device': 'src', 'target': 'TEST_DIR/t.IMGFMT', 'mode': 'existing', 'sync': 'full'}} +{'execute':'drive-mirror', 'arguments':{ + 'device': 'src', 'target': 'TEST_DIR/t.IMGFMT', + 'mode': 'existing', 'sync': 'full'}} WARNING: Image format was not specified for 'TEST_DIR/t.raw' and probing guessed raw. Automatically detecting the format is dangerous for raw images, write operations on block 0 will be restricted. Specify the 'raw' format explicitly to remove the restrictions. @@ -XXX,XX +XXX,XX @@ read 512/512 bytes at offset 0 512 bytes, X ops; XX:XX:XX.X (XXX YYY/sec and XXX ops/sec) { 'execute': 'qmp_capabilities' } {"return": {}} -{'execute':'drive-mirror', 'arguments':{ 'device': 'src', 'target': 'TEST_DIR/t.IMGFMT', 'format': 'IMGFMT', 'mode': 'existing', 'sync': 'full'}} +{'execute':'drive-mirror', 'arguments':{ + 'device': 'src', 'target': 'TEST_DIR/t.IMGFMT', 'format': 'IMGFMT', + 'mode': 'existing', 'sync': 'full'}} {"timestamp": {"seconds": TIMESTAMP, "microseconds": TIMESTAMP}, "event": "JOB_STATUS_CHANGE", "data": {"status": "created", "id": "src"}} {"timestamp": {"seconds": TIMESTAMP, "microseconds": TIMESTAMP}, "event": "JOB_STATUS_CHANGE", "data": {"status": "running", "id": "src"}} {"return": {}} @@ -XXX,XX +XXX,XX @@ Images are identical. Formatting 'TEST_DIR/t.IMGFMT', fmt=IMGFMT size=SIZE { 'execute': 'qmp_capabilities' } {"return": {}} -{'execute':'drive-mirror', 'arguments':{ 'device': 'src', 'target': 'TEST_DIR/t.IMGFMT', 'mode': 'existing', 'sync': 'full'}} +{'execute':'drive-mirror', 'arguments':{ + 'device': 'src', 'target': 'TEST_DIR/t.IMGFMT', + 'mode': 'existing', 'sync': 'full'}} WARNING: Image format was not specified for 'TEST_DIR/t.raw' and probing guessed raw. Automatically detecting the format is dangerous for raw images, write operations on block 0 will be restricted. Specify the 'raw' format explicitly to remove the restrictions. @@ -XXX,XX +XXX,XX @@ WARNING: Image format was not specified for 'TEST_DIR/t.raw' and probing guessed Images are identical. { 'execute': 'qmp_capabilities' } {"return": {}} -{'execute':'drive-mirror', 'arguments':{ 'device': 'src', 'target': 'TEST_DIR/t.IMGFMT', 'format': 'IMGFMT', 'mode': 'existing', 'sync': 'full'}} +{'execute':'drive-mirror', 'arguments':{ + 'device': 'src', 'target': 'TEST_DIR/t.IMGFMT', 'format': 'IMGFMT', + 'mode': 'existing', 'sync': 'full'}} {"timestamp": {"seconds": TIMESTAMP, "microseconds": TIMESTAMP}, "event": "JOB_STATUS_CHANGE", "data": {"status": "created", "id": "src"}} {"timestamp": {"seconds": TIMESTAMP, "microseconds": TIMESTAMP}, "event": "JOB_STATUS_CHANGE", "data": {"status": "running", "id": "src"}} {"return": {}} diff --git a/tests/qemu-iotests/117.out b/tests/qemu-iotests/117.out index XXXXXXX..XXXXXXX 100644 --- a/tests/qemu-iotests/117.out +++ b/tests/qemu-iotests/117.out @@ -XXX,XX +XXX,XX @@ QA output created by 117 Formatting 'TEST_DIR/t.IMGFMT', fmt=IMGFMT size=65536 { 'execute': 'qmp_capabilities' } {"return": {}} -{ 'execute': 'blockdev-add', 'arguments': { 'node-name': 'protocol', 'driver': 'file', 'filename': 'TEST_DIR/t.IMGFMT' } } +{ 'execute': 'blockdev-add', + 'arguments': { 'node-name': 'protocol', + 'driver': 'file', + 'filename': 'TEST_DIR/t.IMGFMT' } } {"return": {}} -{ 'execute': 'blockdev-add', 'arguments': { 'node-name': 'format', 'driver': 'IMGFMT', 'file': 'protocol' } } +{ 'execute': 'blockdev-add', + 'arguments': { 'node-name': 'format', + 'driver': 'IMGFMT', + 'file': 'protocol' } } {"return": {}} -{ 'execute': 'human-monitor-command', 'arguments': { 'command-line': 'qemu-io format "write -P 42 0 64k"' } } +{ 'execute': 'human-monitor-command', + 'arguments': { 'command-line': 'qemu-io format "write -P 42 0 64k"' } } wrote 65536/65536 bytes at offset 0 64 KiB, X ops; XX:XX:XX.X (XXX YYY/sec and XXX ops/sec) {"return": ""} diff --git a/tests/qemu-iotests/127.out b/tests/qemu-iotests/127.out index XXXXXXX..XXXXXXX 100644 --- a/tests/qemu-iotests/127.out +++ b/tests/qemu-iotests/127.out @@ -XXX,XX +XXX,XX @@ wrote 42/42 bytes at offset 0 42 bytes, X ops; XX:XX:XX.X (XXX YYY/sec and XXX ops/sec) { 'execute': 'qmp_capabilities' } {"return": {}} -{ 'execute': 'drive-mirror', 'arguments': { 'job-id': 'mirror', 'device': 'source', 'target': 'TEST_DIR/t.IMGFMT.overlay1', 'mode': 'existing', 'sync': 'top' } } +{ 'execute': 'drive-mirror', + 'arguments': { + 'job-id': 'mirror', + 'device': 'source', + 'target': 'TEST_DIR/t.IMGFMT.overlay1', + 'mode': 'existing', + 'sync': 'top' + } } {"timestamp": {"seconds": TIMESTAMP, "microseconds": TIMESTAMP}, "event": "JOB_STATUS_CHANGE", "data": {"status": "created", "id": "mirror"}} {"timestamp": {"seconds": TIMESTAMP, "microseconds": TIMESTAMP}, "event": "JOB_STATUS_CHANGE", "data": {"status": "running", "id": "mirror"}} {"return": {}} {"timestamp": {"seconds": TIMESTAMP, "microseconds": TIMESTAMP}, "event": "JOB_STATUS_CHANGE", "data": {"status": "ready", "id": "mirror"}} {"timestamp": {"seconds": TIMESTAMP, "microseconds": TIMESTAMP}, "event": "BLOCK_JOB_READY", "data": {"device": "mirror", "len": 65536, "offset": 65536, "speed": 0, "type": "mirror"}} -{ 'execute': 'block-job-complete', 'arguments': { 'device': 'mirror' } } +{ 'execute': 'block-job-complete', + 'arguments': { 'device': 'mirror' } } {"return": {}} {"timestamp": {"seconds": TIMESTAMP, "microseconds": TIMESTAMP}, "event": "JOB_STATUS_CHANGE", "data": {"status": "waiting", "id": "mirror"}} {"timestamp": {"seconds": TIMESTAMP, "microseconds": TIMESTAMP}, "event": "JOB_STATUS_CHANGE", "data": {"status": "pending", "id": "mirror"}} diff --git a/tests/qemu-iotests/140.out b/tests/qemu-iotests/140.out index XXXXXXX..XXXXXXX 100644 --- a/tests/qemu-iotests/140.out +++ b/tests/qemu-iotests/140.out @@ -XXX,XX +XXX,XX @@ wrote 65536/65536 bytes at offset 0 64 KiB, X ops; XX:XX:XX.X (XXX YYY/sec and XXX ops/sec) { 'execute': 'qmp_capabilities' } {"return": {}} -{ 'execute': 'nbd-server-start', 'arguments': { 'addr': { 'type': 'unix', 'data': { 'path': 'SOCK_DIR/nbd' }}}} +{ 'execute': 'nbd-server-start', + 'arguments': { 'addr': { 'type': 'unix', + 'data': { 'path': 'SOCK_DIR/nbd' }}}} {"return": {}} -{ 'execute': 'nbd-server-add', 'arguments': { 'device': 'drv' }} +{ 'execute': 'nbd-server-add', + 'arguments': { 'device': 'drv' }} {"return": {}} read 65536/65536 bytes at offset 0 64 KiB, X ops; XX:XX:XX.X (XXX YYY/sec and XXX ops/sec) -{ 'execute': 'eject', 'arguments': { 'device': 'drv' }} +{ 'execute': 'eject', + 'arguments': { 'device': 'drv' }} {"timestamp": {"seconds": TIMESTAMP, "microseconds": TIMESTAMP}, "event": "BLOCK_EXPORT_DELETED", "data": {"id": "drv"}} qemu-io: can't open device nbd+unix:///drv?socket=SOCK_DIR/nbd: Requested export not available server reported: export 'drv' not present 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 @@ Formatting 'TEST_DIR/t.IMGFMT', fmt=IMGFMT size=1048576 backing_file=TEST_DIR/m. === Testing drive-backup === -{'execute': 'blockdev-add', 'arguments': { 'node-name': 'drv0', 'driver': 'IMGFMT', 'file': { 'driver': 'file', 'filename': 'TEST_DIR/t.IMGFMT' }}} -{"return": {}} -{'execute': 'drive-backup', 'arguments': {'job-id': 'job0', 'device': 'drv0', 'target': 'TEST_DIR/o.IMGFMT', 'format': 'IMGFMT', 'sync': 'none'}} +{'execute': 'blockdev-add', + 'arguments': { + 'node-name': 'drv0', + 'driver': 'IMGFMT', + 'file': { + 'driver': 'file', + 'filename': 'TEST_DIR/t.IMGFMT' + }}} +{"return": {}} +{'execute': 'drive-backup', +'arguments': {'job-id': 'job0', +'device': 'drv0', +'target': 'TEST_DIR/o.IMGFMT', +'format': 'IMGFMT', +'sync': 'none'}} Formatting 'TEST_DIR/o.IMGFMT', fmt=IMGFMT size=1048576 backing_file=TEST_DIR/t.IMGFMT backing_fmt=IMGFMT {"timestamp": {"seconds": TIMESTAMP, "microseconds": TIMESTAMP}, "event": "JOB_STATUS_CHANGE", "data": {"status": "created", "id": "job0"}} {"timestamp": {"seconds": TIMESTAMP, "microseconds": TIMESTAMP}, "event": "JOB_STATUS_CHANGE", "data": {"status": "running", "id": "job0"}} {"timestamp": {"seconds": TIMESTAMP, "microseconds": TIMESTAMP}, "event": "JOB_STATUS_CHANGE", "data": {"status": "paused", "id": "job0"}} {"timestamp": {"seconds": TIMESTAMP, "microseconds": TIMESTAMP}, "event": "JOB_STATUS_CHANGE", "data": {"status": "running", "id": "job0"}} -{'execute': 'blockdev-del', 'arguments': {'node-name': 'drv0'}} +{'execute': 'blockdev-del', + 'arguments': {'node-name': 'drv0'}} {"error": {"class": "GenericError", "desc": "Node 'drv0' is busy: node is used as backing hd of 'NODE_NAME'"}} -{'execute': 'block-job-cancel', 'arguments': {'device': 'job0'}} +{'execute': 'block-job-cancel', + 'arguments': {'device': 'job0'}} {"return": {}} {"timestamp": {"seconds": TIMESTAMP, "microseconds": TIMESTAMP}, "event": "JOB_STATUS_CHANGE", "data": {"status": "aborting", "id": "job0"}} {"timestamp": {"seconds": TIMESTAMP, "microseconds": TIMESTAMP}, "event": "BLOCK_JOB_CANCELLED", "data": {"device": "job0", "len": 1048576, "offset": 0, "speed": 0, "type": "backup"}} {"timestamp": {"seconds": TIMESTAMP, "microseconds": TIMESTAMP}, "event": "JOB_STATUS_CHANGE", "data": {"status": "concluded", "id": "job0"}} {"timestamp": {"seconds": TIMESTAMP, "microseconds": TIMESTAMP}, "event": "JOB_STATUS_CHANGE", "data": {"status": "null", "id": "job0"}} -{'execute': 'blockdev-del', 'arguments': {'node-name': 'drv0'}} +{'execute': 'blockdev-del', + 'arguments': {'node-name': 'drv0'}} {"return": {}} === Testing drive-mirror === -{'execute': 'blockdev-add', 'arguments': { 'node-name': 'drv0', 'driver': 'IMGFMT', 'file': { 'driver': 'file', 'filename': 'TEST_DIR/t.IMGFMT' }}} -{"return": {}} -{'execute': 'drive-mirror', 'arguments': {'job-id': 'job0', 'device': 'drv0', 'target': 'TEST_DIR/o.IMGFMT', 'format': 'IMGFMT', 'sync': 'none'}} +{'execute': 'blockdev-add', + 'arguments': { + 'node-name': 'drv0', + 'driver': 'IMGFMT', + 'file': { + 'driver': 'file', + 'filename': 'TEST_DIR/t.IMGFMT' + }}} +{"return": {}} +{'execute': 'drive-mirror', +'arguments': {'job-id': 'job0', +'device': 'drv0', +'target': 'TEST_DIR/o.IMGFMT', +'format': 'IMGFMT', +'sync': 'none'}} Formatting 'TEST_DIR/o.IMGFMT', fmt=IMGFMT size=1048576 backing_file=TEST_DIR/t.IMGFMT backing_fmt=IMGFMT {"timestamp": {"seconds": TIMESTAMP, "microseconds": TIMESTAMP}, "event": "JOB_STATUS_CHANGE", "data": {"status": "created", "id": "job0"}} {"timestamp": {"seconds": TIMESTAMP, "microseconds": TIMESTAMP}, "event": "JOB_STATUS_CHANGE", "data": {"status": "running", "id": "job0"}} {"timestamp": {"seconds": TIMESTAMP, "microseconds": TIMESTAMP}, "event": "JOB_STATUS_CHANGE", "data": {"status": "ready", "id": "job0"}} {"timestamp": {"seconds": TIMESTAMP, "microseconds": TIMESTAMP}, "event": "BLOCK_JOB_READY", "data": {"device": "job0", "len": 0, "offset": 0, "speed": 0, "type": "mirror"}} -{'execute': 'blockdev-del', 'arguments': {'node-name': 'drv0'}} +{'execute': 'blockdev-del', + 'arguments': {'node-name': 'drv0'}} {"error": {"class": "GenericError", "desc": "Node 'drv0' is busy: block device is in use by block job: mirror"}} -{'execute': 'block-job-cancel', 'arguments': {'device': 'job0'}} +{'execute': 'block-job-cancel', + 'arguments': {'device': 'job0'}} {"return": {}} {"timestamp": {"seconds": TIMESTAMP, "microseconds": TIMESTAMP}, "event": "JOB_STATUS_CHANGE", "data": {"status": "waiting", "id": "job0"}} {"timestamp": {"seconds": TIMESTAMP, "microseconds": TIMESTAMP}, "event": "JOB_STATUS_CHANGE", "data": {"status": "pending", "id": "job0"}} {"timestamp": {"seconds": TIMESTAMP, "microseconds": TIMESTAMP}, "event": "BLOCK_JOB_COMPLETED", "data": {"device": "job0", "len": 0, "offset": 0, "speed": 0, "type": "mirror"}} {"timestamp": {"seconds": TIMESTAMP, "microseconds": TIMESTAMP}, "event": "JOB_STATUS_CHANGE", "data": {"status": "concluded", "id": "job0"}} {"timestamp": {"seconds": TIMESTAMP, "microseconds": TIMESTAMP}, "event": "JOB_STATUS_CHANGE", "data": {"status": "null", "id": "job0"}} -{'execute': 'blockdev-del', 'arguments': {'node-name': 'drv0'}} +{'execute': 'blockdev-del', + 'arguments': {'node-name': 'drv0'}} {"return": {}} === Testing active block-commit === -{'execute': 'blockdev-add', 'arguments': { 'node-name': 'drv0', 'driver': 'IMGFMT', 'file': { 'driver': 'file', 'filename': 'TEST_DIR/t.IMGFMT' }}} -{"return": {}} -{'execute': 'block-commit', 'arguments': {'job-id': 'job0', 'device': 'drv0'}} +{'execute': 'blockdev-add', + 'arguments': { + 'node-name': 'drv0', + 'driver': 'IMGFMT', + 'file': { + 'driver': 'file', + 'filename': 'TEST_DIR/t.IMGFMT' + }}} +{"return": {}} +{'execute': 'block-commit', +'arguments': {'job-id': 'job0', 'device': 'drv0'}} {"timestamp": {"seconds": TIMESTAMP, "microseconds": TIMESTAMP}, "event": "JOB_STATUS_CHANGE", "data": {"status": "created", "id": "job0"}} {"timestamp": {"seconds": TIMESTAMP, "microseconds": TIMESTAMP}, "event": "JOB_STATUS_CHANGE", "data": {"status": "running", "id": "job0"}} {"timestamp": {"seconds": TIMESTAMP, "microseconds": TIMESTAMP}, "event": "JOB_STATUS_CHANGE", "data": {"status": "ready", "id": "job0"}} {"timestamp": {"seconds": TIMESTAMP, "microseconds": TIMESTAMP}, "event": "BLOCK_JOB_READY", "data": {"device": "job0", "len": 0, "offset": 0, "speed": 0, "type": "commit"}} -{'execute': 'blockdev-del', 'arguments': {'node-name': 'drv0'}} +{'execute': 'blockdev-del', + 'arguments': {'node-name': 'drv0'}} {"error": {"class": "GenericError", "desc": "Node 'drv0' is busy: block device is in use by block job: commit"}} -{'execute': 'block-job-cancel', 'arguments': {'device': 'job0'}} +{'execute': 'block-job-cancel', + 'arguments': {'device': 'job0'}} {"return": {}} {"timestamp": {"seconds": TIMESTAMP, "microseconds": TIMESTAMP}, "event": "JOB_STATUS_CHANGE", "data": {"status": "waiting", "id": "job0"}} {"timestamp": {"seconds": TIMESTAMP, "microseconds": TIMESTAMP}, "event": "JOB_STATUS_CHANGE", "data": {"status": "pending", "id": "job0"}} {"timestamp": {"seconds": TIMESTAMP, "microseconds": TIMESTAMP}, "event": "BLOCK_JOB_COMPLETED", "data": {"device": "job0", "len": 0, "offset": 0, "speed": 0, "type": "commit"}} {"timestamp": {"seconds": TIMESTAMP, "microseconds": TIMESTAMP}, "event": "JOB_STATUS_CHANGE", "data": {"status": "concluded", "id": "job0"}} {"timestamp": {"seconds": TIMESTAMP, "microseconds": TIMESTAMP}, "event": "JOB_STATUS_CHANGE", "data": {"status": "null", "id": "job0"}} -{'execute': 'blockdev-del', 'arguments': {'node-name': 'drv0'}} +{'execute': 'blockdev-del', + 'arguments': {'node-name': 'drv0'}} {"return": {}} === Testing non-active block-commit === wrote 1048576/1048576 bytes at offset 0 1 MiB, X ops; XX:XX:XX.X (XXX YYY/sec and XXX ops/sec) -{'execute': 'blockdev-add', 'arguments': { 'node-name': 'drv0', 'driver': 'IMGFMT', 'file': { 'driver': 'file', 'filename': 'TEST_DIR/t.IMGFMT' }}} -{"return": {}} -{'execute': 'block-commit', 'arguments': {'job-id': 'job0', 'device': 'drv0', 'top': 'TEST_DIR/m.IMGFMT', 'speed': 1}} +{'execute': 'blockdev-add', + 'arguments': { + 'node-name': 'drv0', + 'driver': 'IMGFMT', + 'file': { + 'driver': 'file', + 'filename': 'TEST_DIR/t.IMGFMT' + }}} +{"return": {}} +{'execute': 'block-commit', +'arguments': {'job-id': 'job0', +'device': 'drv0', +'top': 'TEST_DIR/m.IMGFMT', +'speed': 1}} {"timestamp": {"seconds": TIMESTAMP, "microseconds": TIMESTAMP}, "event": "JOB_STATUS_CHANGE", "data": {"status": "created", "id": "job0"}} {"timestamp": {"seconds": TIMESTAMP, "microseconds": TIMESTAMP}, "event": "JOB_STATUS_CHANGE", "data": {"status": "running", "id": "job0"}} -{'execute': 'blockdev-del', 'arguments': {'node-name': 'drv0'}} +{'execute': 'blockdev-del', + 'arguments': {'node-name': 'drv0'}} {"error": {"class": "GenericError", "desc": "Node drv0 is in use"}} -{'execute': 'block-job-cancel', 'arguments': {'device': 'job0'}} +{'execute': 'block-job-cancel', + 'arguments': {'device': 'job0'}} {"return": {}} {"timestamp": {"seconds": TIMESTAMP, "microseconds": TIMESTAMP}, "event": "JOB_STATUS_CHANGE", "data": {"status": "aborting", "id": "job0"}} {"timestamp": {"seconds": TIMESTAMP, "microseconds": TIMESTAMP}, "event": "BLOCK_JOB_CANCELLED", "data": {"device": "job0", "len": 1048576, "offset": 524288, "speed": 1, "type": "commit"}} {"timestamp": {"seconds": TIMESTAMP, "microseconds": TIMESTAMP}, "event": "JOB_STATUS_CHANGE", "data": {"status": "concluded", "id": "job0"}} {"timestamp": {"seconds": TIMESTAMP, "microseconds": TIMESTAMP}, "event": "JOB_STATUS_CHANGE", "data": {"status": "null", "id": "job0"}} -{'execute': 'blockdev-del', 'arguments': {'node-name': 'drv0'}} +{'execute': 'blockdev-del', + 'arguments': {'node-name': 'drv0'}} {"return": {}} === Testing block-stream === wrote 1048576/1048576 bytes at offset 0 1 MiB, X ops; XX:XX:XX.X (XXX YYY/sec and XXX ops/sec) -{'execute': 'blockdev-add', 'arguments': { 'node-name': 'drv0', 'driver': 'IMGFMT', 'file': { 'driver': 'file', 'filename': 'TEST_DIR/t.IMGFMT' }}} -{"return": {}} -{'execute': 'block-stream', 'arguments': {'job-id': 'job0', 'device': 'drv0', 'speed': 1}} +{'execute': 'blockdev-add', + 'arguments': { + 'node-name': 'drv0', + 'driver': 'IMGFMT', + 'file': { + 'driver': 'file', + 'filename': 'TEST_DIR/t.IMGFMT' + }}} +{"return": {}} +{'execute': 'block-stream', +'arguments': {'job-id': 'job0', +'device': 'drv0', +'speed': 1}} {"timestamp": {"seconds": TIMESTAMP, "microseconds": TIMESTAMP}, "event": "JOB_STATUS_CHANGE", "data": {"status": "created", "id": "job0"}} {"timestamp": {"seconds": TIMESTAMP, "microseconds": TIMESTAMP}, "event": "JOB_STATUS_CHANGE", "data": {"status": "running", "id": "job0"}} -{'execute': 'blockdev-del', 'arguments': {'node-name': 'drv0'}} +{'execute': 'blockdev-del', + 'arguments': {'node-name': 'drv0'}} {"error": {"class": "GenericError", "desc": "Node drv0 is in use"}} -{'execute': 'block-job-cancel', 'arguments': {'device': 'job0'}} +{'execute': 'block-job-cancel', + 'arguments': {'device': 'job0'}} {"return": {}} {"timestamp": {"seconds": TIMESTAMP, "microseconds": TIMESTAMP}, "event": "JOB_STATUS_CHANGE", "data": {"status": "aborting", "id": "job0"}} {"timestamp": {"seconds": TIMESTAMP, "microseconds": TIMESTAMP}, "event": "BLOCK_JOB_CANCELLED", "data": {"device": "job0", "len": 1048576, "offset": 524288, "speed": 1, "type": "stream"}} {"timestamp": {"seconds": TIMESTAMP, "microseconds": TIMESTAMP}, "event": "JOB_STATUS_CHANGE", "data": {"status": "concluded", "id": "job0"}} {"timestamp": {"seconds": TIMESTAMP, "microseconds": TIMESTAMP}, "event": "JOB_STATUS_CHANGE", "data": {"status": "null", "id": "job0"}} -{'execute': 'blockdev-del', 'arguments': {'node-name': 'drv0'}} +{'execute': 'blockdev-del', + 'arguments': {'node-name': 'drv0'}} {"return": {}} *** done diff --git a/tests/qemu-iotests/143.out b/tests/qemu-iotests/143.out index XXXXXXX..XXXXXXX 100644 --- a/tests/qemu-iotests/143.out +++ b/tests/qemu-iotests/143.out @@ -XXX,XX +XXX,XX @@ QA output created by 143 { 'execute': 'qmp_capabilities' } {"return": {}} -{ 'execute': 'nbd-server-start', 'arguments': { 'addr': { 'type': 'unix', 'data': { 'path': 'SOCK_DIR/nbd' }}}} +{ 'execute': 'nbd-server-start', + 'arguments': { 'addr': { 'type': 'unix', + 'data': { 'path': 'SOCK_DIR/nbd' }}}} {"return": {}} qemu-io: can't open device nbd+unix:///no_such_export?socket=SOCK_DIR/nbd: Requested export not available server reported: export 'no_such_export' not present diff --git a/tests/qemu-iotests/144.out b/tests/qemu-iotests/144.out index XXXXXXX..XXXXXXX 100644 --- a/tests/qemu-iotests/144.out +++ b/tests/qemu-iotests/144.out @@ -XXX,XX +XXX,XX @@ Formatting 'TEST_DIR/t.IMGFMT', fmt=IMGFMT size=536870912 { 'execute': 'qmp_capabilities' } {"return": {}} -{ 'execute': 'blockdev-snapshot-sync', 'arguments': { 'device': 'virtio0', 'snapshot-file':'TEST_DIR/tmp.IMGFMT', 'format': 'IMGFMT' } } +{ 'execute': 'blockdev-snapshot-sync', + 'arguments': { + 'device': 'virtio0', + 'snapshot-file':'TEST_DIR/tmp.IMGFMT', + 'format': 'IMGFMT' + } + } Formatting 'TEST_DIR/tmp.qcow2', fmt=qcow2 cluster_size=65536 extended_l2=off compression_type=zlib size=536870912 backing_file=TEST_DIR/t.qcow2 backing_fmt=qcow2 lazy_refcounts=off refcount_bits=16 {"return": {}} === Performing block-commit on active layer === -{ 'execute': 'block-commit', 'arguments': { 'device': 'virtio0' } } +{ 'execute': 'block-commit', + 'arguments': { + 'device': 'virtio0' + } + } {"timestamp": {"seconds": TIMESTAMP, "microseconds": TIMESTAMP}, "event": "JOB_STATUS_CHANGE", "data": {"status": "created", "id": "virtio0"}} {"timestamp": {"seconds": TIMESTAMP, "microseconds": TIMESTAMP}, "event": "JOB_STATUS_CHANGE", "data": {"status": "running", "id": "virtio0"}} {"return": {}} {"timestamp": {"seconds": TIMESTAMP, "microseconds": TIMESTAMP}, "event": "JOB_STATUS_CHANGE", "data": {"status": "ready", "id": "virtio0"}} {"timestamp": {"seconds": TIMESTAMP, "microseconds": TIMESTAMP}, "event": "BLOCK_JOB_READY", "data": {"device": "virtio0", "len": 0, "offset": 0, "speed": 0, "type": "commit"}} -{ 'execute': 'block-job-complete', 'arguments': { 'device': 'virtio0' } } +{ 'execute': 'block-job-complete', + 'arguments': { + 'device': 'virtio0' + } + } {"return": {}} {"timestamp": {"seconds": TIMESTAMP, "microseconds": TIMESTAMP}, "event": "JOB_STATUS_CHANGE", "data": {"status": "waiting", "id": "virtio0"}} {"timestamp": {"seconds": TIMESTAMP, "microseconds": TIMESTAMP}, "event": "JOB_STATUS_CHANGE", "data": {"status": "pending", "id": "virtio0"}} @@ -XXX,XX +XXX,XX @@ Formatting 'TEST_DIR/tmp.qcow2', fmt=qcow2 cluster_size=65536 extended_l2=off co === Performing Live Snapshot 2 === -{ 'execute': 'blockdev-snapshot-sync', 'arguments': { 'device': 'virtio0', 'snapshot-file':'TEST_DIR/tmp2.IMGFMT', 'format': 'IMGFMT' } } +{ 'execute': 'blockdev-snapshot-sync', + 'arguments': { + 'device': 'virtio0', + 'snapshot-file':'TEST_DIR/tmp2.IMGFMT', + 'format': 'IMGFMT' + } + } Formatting 'TEST_DIR/tmp2.qcow2', fmt=qcow2 cluster_size=65536 extended_l2=off compression_type=zlib size=536870912 backing_file=TEST_DIR/t.qcow2 backing_fmt=qcow2 lazy_refcounts=off refcount_bits=16 {"return": {}} *** done diff --git a/tests/qemu-iotests/153.out b/tests/qemu-iotests/153.out index XXXXXXX..XXXXXXX 100644 --- a/tests/qemu-iotests/153.out +++ b/tests/qemu-iotests/153.out @@ -XXX,XX +XXX,XX @@ _qemu_img_wrapper commit -b TEST_DIR/t.qcow2.b TEST_DIR/t.qcow2.c { 'execute': 'qmp_capabilities' } {"return": {}} Adding drive -{ 'execute': 'human-monitor-command', 'arguments': { 'command-line': 'drive_add 0 if=none,id=d0,file=TEST_DIR/t.IMGFMT' } } +{ 'execute': 'human-monitor-command', + 'arguments': { 'command-line': 'drive_add 0 if=none,id=d0,file=TEST_DIR/t.IMGFMT' } } {"return": "OKrn"} _qemu_io_wrapper TEST_DIR/t.qcow2 -c write 0 512 @@ -XXX,XX +XXX,XX @@ Creating overlay with qemu-img when the guest is running should be allowed _qemu_img_wrapper create -f qcow2 -b TEST_DIR/t.qcow2 -F qcow2 TEST_DIR/t.qcow2.overlay == Closing an image should unlock it == -{ 'execute': 'human-monitor-command', 'arguments': { 'command-line': 'drive_del d0' } } +{ 'execute': 'human-monitor-command', + 'arguments': { 'command-line': 'drive_del d0' } } {"return": ""} _qemu_io_wrapper TEST_DIR/t.qcow2 -c write 0 512 Adding two and closing one -{ 'execute': 'human-monitor-command', 'arguments': { 'command-line': 'drive_add 0 if=none,id=d0,file=TEST_DIR/t.IMGFMT,readonly=on' } } +{ 'execute': 'human-monitor-command', + 'arguments': { 'command-line': 'drive_add 0 if=none,id=d0,file=TEST_DIR/t.IMGFMT,readonly=on' } } {"return": "OKrn"} -{ 'execute': 'human-monitor-command', 'arguments': { 'command-line': 'drive_add 0 if=none,id=d1,file=TEST_DIR/t.IMGFMT,readonly=on' } } +{ 'execute': 'human-monitor-command', + 'arguments': { 'command-line': 'drive_add 0 if=none,id=d1,file=TEST_DIR/t.IMGFMT,readonly=on' } } {"return": "OKrn"} _qemu_img_wrapper info TEST_DIR/t.qcow2 -{ 'execute': 'human-monitor-command', 'arguments': { 'command-line': 'drive_del d0' } } +{ 'execute': 'human-monitor-command', + 'arguments': { 'command-line': 'drive_del d0' } } {"return": ""} _qemu_io_wrapper TEST_DIR/t.qcow2 -c write 0 512 qemu-io: can't open device TEST_DIR/t.qcow2: Failed to get "write" lock Is another process using the image [TEST_DIR/t.qcow2]? Closing the other -{ 'execute': 'human-monitor-command', 'arguments': { 'command-line': 'drive_del d1' } } +{ 'execute': 'human-monitor-command', + 'arguments': { 'command-line': 'drive_del d1' } } {"return": ""} _qemu_io_wrapper TEST_DIR/t.qcow2 -c write 0 512 diff --git a/tests/qemu-iotests/156.out b/tests/qemu-iotests/156.out index XXXXXXX..XXXXXXX 100644 --- a/tests/qemu-iotests/156.out +++ b/tests/qemu-iotests/156.out @@ -XXX,XX +XXX,XX @@ wrote 196608/196608 bytes at offset 65536 { 'execute': 'qmp_capabilities' } {"return": {}} Formatting 'TEST_DIR/t.IMGFMT.overlay', fmt=IMGFMT size=1048576 backing_file=TEST_DIR/t.IMGFMT backing_fmt=IMGFMT -{ 'execute': 'blockdev-snapshot-sync', 'arguments': { 'device': 'source', 'snapshot-file': 'TEST_DIR/t.IMGFMT.overlay', 'format': 'IMGFMT', 'mode': 'existing' } } +{ 'execute': 'blockdev-snapshot-sync', + 'arguments': { 'device': 'source', + 'snapshot-file': 'TEST_DIR/t.IMGFMT.overlay', + 'format': 'IMGFMT', + 'mode': 'existing' } } {"return": {}} -{ 'execute': 'human-monitor-command', 'arguments': { 'command-line': 'qemu-io source "write -P 3 128k 128k"' } } +{ 'execute': 'human-monitor-command', + 'arguments': { 'command-line': + 'qemu-io source "write -P 3 128k 128k"' } } wrote 131072/131072 bytes at offset 131072 128 KiB, X ops; XX:XX:XX.X (XXX YYY/sec and XXX ops/sec) {"return": ""} Formatting 'TEST_DIR/t.IMGFMT.target.overlay', fmt=IMGFMT size=1048576 backing_file=TEST_DIR/t.IMGFMT.target backing_fmt=IMGFMT -{ 'execute': 'drive-mirror', 'arguments': { 'device': 'source', 'target': 'TEST_DIR/t.IMGFMT.target.overlay', 'mode': 'existing', 'sync': 'top' } } +{ 'execute': 'drive-mirror', + 'arguments': { 'device': 'source', + 'target': 'TEST_DIR/t.IMGFMT.target.overlay', + 'mode': 'existing', + 'sync': 'top' } } {"timestamp": {"seconds": TIMESTAMP, "microseconds": TIMESTAMP}, "event": "JOB_STATUS_CHANGE", "data": {"status": "created", "id": "source"}} {"timestamp": {"seconds": TIMESTAMP, "microseconds": TIMESTAMP}, "event": "JOB_STATUS_CHANGE", "data": {"status": "running", "id": "source"}} {"return": {}} {"timestamp": {"seconds": TIMESTAMP, "microseconds": TIMESTAMP}, "event": "JOB_STATUS_CHANGE", "data": {"status": "ready", "id": "source"}} {"timestamp": {"seconds": TIMESTAMP, "microseconds": TIMESTAMP}, "event": "BLOCK_JOB_READY", "data": {"device": "source", "len": 131072, "offset": 131072, "speed": 0, "type": "mirror"}} -{ 'execute': 'human-monitor-command', 'arguments': { 'command-line': 'qemu-io source "write -P 4 192k 64k"' } } +{ 'execute': 'human-monitor-command', + 'arguments': { 'command-line': + 'qemu-io source "write -P 4 192k 64k"' } } wrote 65536/65536 bytes at offset 196608 64 KiB, X ops; XX:XX:XX.X (XXX YYY/sec and XXX ops/sec) {"return": ""} -{ 'execute': 'block-job-complete', 'arguments': { 'device': 'source' } } +{ 'execute': 'block-job-complete', + 'arguments': { 'device': 'source' } } {"return": {}} {"timestamp": {"seconds": TIMESTAMP, "microseconds": TIMESTAMP}, "event": "JOB_STATUS_CHANGE", "data": {"status": "waiting", "id": "source"}} {"timestamp": {"seconds": TIMESTAMP, "microseconds": TIMESTAMP}, "event": "JOB_STATUS_CHANGE", "data": {"status": "pending", "id": "source"}} @@ -XXX,XX +XXX,XX @@ wrote 65536/65536 bytes at offset 196608 {"timestamp": {"seconds": TIMESTAMP, "microseconds": TIMESTAMP}, "event": "JOB_STATUS_CHANGE", "data": {"status": "concluded", "id": "source"}} {"timestamp": {"seconds": TIMESTAMP, "microseconds": TIMESTAMP}, "event": "JOB_STATUS_CHANGE", "data": {"status": "null", "id": "source"}} -{ 'execute': 'human-monitor-command', 'arguments': { 'command-line': 'qemu-io source "read -P 1 0k 64k"' } } +{ 'execute': 'human-monitor-command', + 'arguments': { 'command-line': + 'qemu-io source "read -P 1 0k 64k"' } } read 65536/65536 bytes at offset 0 64 KiB, X ops; XX:XX:XX.X (XXX YYY/sec and XXX ops/sec) {"return": ""} -{ 'execute': 'human-monitor-command', 'arguments': { 'command-line': 'qemu-io source "read -P 2 64k 64k"' } } +{ 'execute': 'human-monitor-command', + 'arguments': { 'command-line': + 'qemu-io source "read -P 2 64k 64k"' } } read 65536/65536 bytes at offset 65536 64 KiB, X ops; XX:XX:XX.X (XXX YYY/sec and XXX ops/sec) {"return": ""} -{ 'execute': 'human-monitor-command', 'arguments': { 'command-line': 'qemu-io source "read -P 3 128k 64k"' } } +{ 'execute': 'human-monitor-command', + 'arguments': { 'command-line': + 'qemu-io source "read -P 3 128k 64k"' } } read 65536/65536 bytes at offset 131072 64 KiB, X ops; XX:XX:XX.X (XXX YYY/sec and XXX ops/sec) {"return": ""} -{ 'execute': 'human-monitor-command', 'arguments': { 'command-line': 'qemu-io source "read -P 4 192k 64k"' } } +{ 'execute': 'human-monitor-command', + 'arguments': { 'command-line': + 'qemu-io source "read -P 4 192k 64k"' } } read 65536/65536 bytes at offset 196608 64 KiB, X ops; XX:XX:XX.X (XXX YYY/sec and XXX ops/sec) {"return": ""} diff --git a/tests/qemu-iotests/161.out b/tests/qemu-iotests/161.out index XXXXXXX..XXXXXXX 100644 --- a/tests/qemu-iotests/161.out +++ b/tests/qemu-iotests/161.out @@ -XXX,XX +XXX,XX @@ Formatting 'TEST_DIR/t.IMGFMT', fmt=IMGFMT size=1048576 backing_file=TEST_DIR/t. { 'execute': 'qmp_capabilities' } {"return": {}} -{ 'execute': 'human-monitor-command', 'arguments': { 'command-line': 'qemu-io none0 "reopen -o backing.detect-zeroes=on"' } } +{ 'execute': 'human-monitor-command', + 'arguments': { 'command-line': + 'qemu-io none0 "reopen -o backing.detect-zeroes=on"' } } {"return": ""} *** Stream and then change an option on the backing file { 'execute': 'qmp_capabilities' } {"return": {}} -{ 'execute': 'block-stream', 'arguments': { 'device': 'none0', 'base': 'TEST_DIR/t.IMGFMT.base' } } +{ 'execute': 'block-stream', 'arguments': { 'device': 'none0', + 'base': 'TEST_DIR/t.IMGFMT.base' } } {"timestamp": {"seconds": TIMESTAMP, "microseconds": TIMESTAMP}, "event": "JOB_STATUS_CHANGE", "data": {"status": "created", "id": "none0"}} {"timestamp": {"seconds": TIMESTAMP, "microseconds": TIMESTAMP}, "event": "JOB_STATUS_CHANGE", "data": {"status": "running", "id": "none0"}} {"return": {}} -{ 'execute': 'human-monitor-command', 'arguments': { 'command-line': 'qemu-io none0 "reopen -o backing.detect-zeroes=on"' } } +{ 'execute': 'human-monitor-command', + 'arguments': { 'command-line': + 'qemu-io none0 "reopen -o backing.detect-zeroes=on"' } } {"timestamp": {"seconds": TIMESTAMP, "microseconds": TIMESTAMP}, "event": "JOB_STATUS_CHANGE", "data": {"status": "waiting", "id": "none0"}} {"timestamp": {"seconds": TIMESTAMP, "microseconds": TIMESTAMP}, "event": "JOB_STATUS_CHANGE", "data": {"status": "pending", "id": "none0"}} {"timestamp": {"seconds": TIMESTAMP, "microseconds": TIMESTAMP}, "event": "BLOCK_JOB_COMPLETED", "data": {"device": "none0", "len": 1048576, "offset": 1048576, "speed": 0, "type": "stream"}} @@ -XXX,XX +XXX,XX @@ Formatting 'TEST_DIR/t.IMGFMT.int', fmt=IMGFMT size=1048576 backing_file=TEST_DI Formatting 'TEST_DIR/t.IMGFMT', fmt=IMGFMT size=1048576 backing_file=TEST_DIR/t.IMGFMT.int backing_fmt=IMGFMT { 'execute': 'qmp_capabilities' } {"return": {}} -{ 'execute': 'block-commit', 'arguments': { 'device': 'none0', 'top': 'TEST_DIR/t.IMGFMT.int' } } +{ 'execute': 'block-commit', 'arguments': { 'device': 'none0', + 'top': 'TEST_DIR/t.IMGFMT.int' } } {"timestamp": {"seconds": TIMESTAMP, "microseconds": TIMESTAMP}, "event": "JOB_STATUS_CHANGE", "data": {"status": "created", "id": "none0"}} {"timestamp": {"seconds": TIMESTAMP, "microseconds": TIMESTAMP}, "event": "JOB_STATUS_CHANGE", "data": {"status": "running", "id": "none0"}} {"return": {}} -{ 'execute': 'human-monitor-command', 'arguments': { 'command-line': 'qemu-io none0 "reopen -o backing.detect-zeroes=on"' } } +{ 'execute': 'human-monitor-command', + 'arguments': { 'command-line': + 'qemu-io none0 "reopen -o backing.detect-zeroes=on"' } } {"timestamp": {"seconds": TIMESTAMP, "microseconds": TIMESTAMP}, "event": "JOB_STATUS_CHANGE", "data": {"status": "waiting", "id": "none0"}} {"timestamp": {"seconds": TIMESTAMP, "microseconds": TIMESTAMP}, "event": "JOB_STATUS_CHANGE", "data": {"status": "pending", "id": "none0"}} {"timestamp": {"seconds": TIMESTAMP, "microseconds": TIMESTAMP}, "event": "BLOCK_JOB_COMPLETED", "data": {"device": "none0", "len": 1048576, "offset": 1048576, "speed": 0, "type": "commit"}} diff --git a/tests/qemu-iotests/173.out b/tests/qemu-iotests/173.out index XXXXXXX..XXXXXXX 100644 --- a/tests/qemu-iotests/173.out +++ b/tests/qemu-iotests/173.out @@ -XXX,XX +XXX,XX @@ Formatting 'TEST_DIR/image.snp1', fmt=IMGFMT size=104857600 { 'execute': 'qmp_capabilities' } {"return": {}} -{ 'arguments': { 'device': 'disk2', 'format': 'IMGFMT', 'mode': 'existing', 'snapshot-file': 'TEST_DIR/image.snp1', 'snapshot-node-name': 'snp1' }, 'execute': 'blockdev-snapshot-sync' } +{ 'arguments': { + 'device': 'disk2', + 'format': 'IMGFMT', + 'mode': 'existing', + 'snapshot-file': 'TEST_DIR/image.snp1', + 'snapshot-node-name': 'snp1' + }, + 'execute': 'blockdev-snapshot-sync' + } {"return": {}} -{ 'arguments': { 'backing-file': 'image.base', 'device': 'disk2', 'image-node-name': 'snp1' }, 'execute': 'change-backing-file' } +{ 'arguments': { + 'backing-file': 'image.base', + 'device': 'disk2', + 'image-node-name': 'snp1' + }, + 'execute': 'change-backing-file' + } {"return": {}} -{ 'arguments': { 'base': 'TEST_DIR/image.base', 'device': 'disk2' }, 'execute': 'block-stream' } +{ 'arguments': { + 'base': 'TEST_DIR/image.base', + 'device': 'disk2' + }, + 'execute': 'block-stream' + } {"timestamp": {"seconds": TIMESTAMP, "microseconds": TIMESTAMP}, "event": "JOB_STATUS_CHANGE", "data": {"status": "created", "id": "disk2"}} {"timestamp": {"seconds": TIMESTAMP, "microseconds": TIMESTAMP}, "event": "JOB_STATUS_CHANGE", "data": {"status": "running", "id": "disk2"}} {"return": {}} diff --git a/tests/qemu-iotests/182.out b/tests/qemu-iotests/182.out index XXXXXXX..XXXXXXX 100644 --- a/tests/qemu-iotests/182.out +++ b/tests/qemu-iotests/182.out @@ -XXX,XX +XXX,XX @@ Is another process using the image [TEST_DIR/t.qcow2]? {'execute': 'qmp_capabilities'} {"return": {}} -{'execute': 'blockdev-add', 'arguments': { 'node-name': 'node0', 'driver': 'file', 'filename': 'TEST_DIR/t.IMGFMT', 'locking': 'on' } } -{"return": {}} -{'execute': 'blockdev-snapshot-sync', 'arguments': { 'node-name': 'node0', 'snapshot-file': 'TEST_DIR/t.IMGFMT.overlay', 'snapshot-node-name': 'node1' } } +{'execute': 'blockdev-add', + 'arguments': { + 'node-name': 'node0', + 'driver': 'file', + 'filename': 'TEST_DIR/t.IMGFMT', + 'locking': 'on' + } } +{"return": {}} +{'execute': 'blockdev-snapshot-sync', + 'arguments': { + 'node-name': 'node0', + 'snapshot-file': 'TEST_DIR/t.IMGFMT.overlay', + 'snapshot-node-name': 'node1' + } } Formatting 'TEST_DIR/t.qcow2.overlay', fmt=qcow2 cluster_size=65536 extended_l2=off compression_type=zlib size=197120 backing_file=TEST_DIR/t.qcow2 backing_fmt=file lazy_refcounts=off refcount_bits=16 {"return": {}} -{'execute': 'blockdev-add', 'arguments': { 'node-name': 'node1', 'driver': 'file', 'filename': 'TEST_DIR/t.IMGFMT', 'locking': 'on' } } -{"return": {}} -{'execute': 'nbd-server-start', 'arguments': { 'addr': { 'type': 'unix', 'data': { 'path': 'SOCK_DIR/nbd.socket' } } } } -{"return": {}} -{'execute': 'nbd-server-add', 'arguments': { 'device': 'node1' } } +{'execute': 'blockdev-add', + 'arguments': { + 'node-name': 'node1', + 'driver': 'file', + 'filename': 'TEST_DIR/t.IMGFMT', + 'locking': 'on' + } } +{"return": {}} +{'execute': 'nbd-server-start', + 'arguments': { + 'addr': { + 'type': 'unix', + 'data': { + 'path': 'SOCK_DIR/nbd.socket' + } } } } +{"return": {}} +{'execute': 'nbd-server-add', + 'arguments': { + 'device': 'node1' + } } {"return": {}} === Testing failure to loosen restrictions === diff --git a/tests/qemu-iotests/183.out b/tests/qemu-iotests/183.out index XXXXXXX..XXXXXXX 100644 --- a/tests/qemu-iotests/183.out +++ b/tests/qemu-iotests/183.out @@ -XXX,XX +XXX,XX @@ Formatting 'TEST_DIR/t.IMGFMT.dest', fmt=IMGFMT size=67108864 === Write something on the source === -{ 'execute': 'human-monitor-command', 'arguments': { 'command-line': 'qemu-io disk "write -P 0x55 0 64k"' } } +{ 'execute': 'human-monitor-command', + 'arguments': { 'command-line': + 'qemu-io disk "write -P 0x55 0 64k"' } } wrote 65536/65536 bytes at offset 0 64 KiB, X ops; XX:XX:XX.X (XXX YYY/sec and XXX ops/sec) {"return": ""} -{ 'execute': 'human-monitor-command', 'arguments': { 'command-line': 'qemu-io disk "read -P 0x55 0 64k"' } } +{ 'execute': 'human-monitor-command', + 'arguments': { 'command-line': + 'qemu-io disk "read -P 0x55 0 64k"' } } read 65536/65536 bytes at offset 0 64 KiB, X ops; XX:XX:XX.X (XXX YYY/sec and XXX ops/sec) {"return": ""} === Do block migration to destination === -{ 'execute': 'migrate', 'arguments': { 'uri': 'unix:SOCK_DIR/migrate', 'blk': true } } +{ 'execute': 'migrate', + 'arguments': { 'uri': 'unix:SOCK_DIR/migrate', 'blk': true } } {"return": {}} { 'execute': 'query-status' } {"return": {"status": "postmigrate", "singlestep": false, "running": false}} @@ -XXX,XX +XXX,XX @@ read 65536/65536 bytes at offset 0 { 'execute': 'query-status' } {"timestamp": {"seconds": TIMESTAMP, "microseconds": TIMESTAMP}, "event": "RESUME"} {"return": {"status": "running", "singlestep": false, "running": true}} -{ 'execute': 'human-monitor-command', 'arguments': { 'command-line': 'qemu-io disk "read -P 0x55 0 64k"' } } +{ 'execute': 'human-monitor-command', + 'arguments': { 'command-line': + 'qemu-io disk "read -P 0x55 0 64k"' } } read 65536/65536 bytes at offset 0 64 KiB, X ops; XX:XX:XX.X (XXX YYY/sec and XXX ops/sec) {"return": ""} -{ 'execute': 'human-monitor-command', 'arguments': { 'command-line': 'qemu-io disk "write -P 0x66 1M 64k"' } } +{ 'execute': 'human-monitor-command', + 'arguments': { 'command-line': + 'qemu-io disk "write -P 0x66 1M 64k"' } } wrote 65536/65536 bytes at offset 1048576 64 KiB, X ops; XX:XX:XX.X (XXX YYY/sec and XXX ops/sec) {"return": ""} 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.IMGFMT.base', fmt=IMGFMT size=67108864 === Creating backing chain === -{ 'execute': 'blockdev-snapshot-sync', 'arguments': { 'device': 'disk', 'snapshot-file': 'TEST_DIR/t.IMGFMT.mid', 'format': 'IMGFMT', 'mode': 'absolute-paths' } } +{ 'execute': 'blockdev-snapshot-sync', + 'arguments': { 'device': 'disk', + 'snapshot-file': 'TEST_DIR/t.IMGFMT.mid', + 'format': 'IMGFMT', + 'mode': 'absolute-paths' } } Formatting 'TEST_DIR/t.qcow2.mid', fmt=qcow2 cluster_size=65536 extended_l2=off compression_type=zlib size=67108864 backing_file=TEST_DIR/t.qcow2.base backing_fmt=qcow2 lazy_refcounts=off refcount_bits=16 {"return": {}} -{ 'execute': 'human-monitor-command', 'arguments': { 'command-line': 'qemu-io disk "write 0 4M"' } } +{ 'execute': 'human-monitor-command', + 'arguments': { 'command-line': + 'qemu-io disk "write 0 4M"' } } wrote 4194304/4194304 bytes at offset 0 4 MiB, X ops; XX:XX:XX.X (XXX YYY/sec and XXX ops/sec) {"return": ""} -{ 'execute': 'blockdev-snapshot-sync', 'arguments': { 'device': 'disk', 'snapshot-file': 'TEST_DIR/t.IMGFMT', 'format': 'IMGFMT', 'mode': 'absolute-paths' } } +{ 'execute': 'blockdev-snapshot-sync', + 'arguments': { 'device': 'disk', + 'snapshot-file': 'TEST_DIR/t.IMGFMT', + 'format': 'IMGFMT', + 'mode': 'absolute-paths' } } Formatting 'TEST_DIR/t.qcow2', fmt=qcow2 cluster_size=65536 extended_l2=off compression_type=zlib size=67108864 backing_file=TEST_DIR/t.qcow2.mid backing_fmt=qcow2 lazy_refcounts=off refcount_bits=16 {"return": {}} === Start commit job and exit qemu === -{ 'execute': 'block-commit', 'arguments': { 'device': 'disk', 'base':'TEST_DIR/t.IMGFMT.base', 'top': 'TEST_DIR/t.IMGFMT.mid', 'speed': 65536 } } +{ 'execute': 'block-commit', + 'arguments': { 'device': 'disk', + 'base':'TEST_DIR/t.IMGFMT.base', + 'top': 'TEST_DIR/t.IMGFMT.mid', + 'speed': 65536 } } {"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"}} {"return": {}} @@ -XXX,XX +XXX,XX @@ Formatting 'TEST_DIR/t.qcow2', fmt=qcow2 cluster_size=65536 extended_l2=off comp { 'execute': 'qmp_capabilities' } {"return": {}} -{ 'execute': 'block-commit', 'arguments': { 'device': 'disk', 'base':'TEST_DIR/t.IMGFMT.base', 'speed': 65536 } } +{ 'execute': 'block-commit', + 'arguments': { 'device': 'disk', + 'base':'TEST_DIR/t.IMGFMT.base', + 'speed': 65536 } } {"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"}} {"return": {}} @@ -XXX,XX +XXX,XX @@ Formatting 'TEST_DIR/t.qcow2', fmt=qcow2 cluster_size=65536 extended_l2=off comp { 'execute': 'qmp_capabilities' } {"return": {}} -{ 'execute': 'drive-mirror', 'arguments': { 'device': 'disk', 'target': 'TEST_DIR/t.IMGFMT.copy', 'format': 'IMGFMT', 'sync': 'full', 'speed': 65536 } } +{ 'execute': 'drive-mirror', + 'arguments': { 'device': 'disk', + 'target': 'TEST_DIR/t.IMGFMT.copy', + 'format': 'IMGFMT', + 'sync': 'full', + 'speed': 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"}} @@ -XXX,XX +XXX,XX @@ Formatting 'TEST_DIR/t.qcow2.copy', fmt=qcow2 cluster_size=65536 extended_l2=off { 'execute': 'qmp_capabilities' } {"return": {}} -{ 'execute': 'drive-backup', 'arguments': { 'device': 'disk', 'target': 'TEST_DIR/t.IMGFMT.copy', 'format': 'IMGFMT', 'sync': 'full', 'speed': 65536 } } +{ 'execute': 'drive-backup', + 'arguments': { 'device': 'disk', + 'target': 'TEST_DIR/t.IMGFMT.copy', + 'format': 'IMGFMT', + 'sync': 'full', + 'speed': 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"}} @@ -XXX,XX +XXX,XX @@ Formatting 'TEST_DIR/t.qcow2.copy', fmt=qcow2 cluster_size=65536 extended_l2=off { 'execute': 'qmp_capabilities' } {"return": {}} -{ 'execute': 'block-stream', 'arguments': { 'device': 'disk', 'speed': 65536 } } +{ 'execute': 'block-stream', + 'arguments': { 'device': 'disk', + 'speed': 65536 } } {"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"}} {"return": {}} diff --git a/tests/qemu-iotests/191.out b/tests/qemu-iotests/191.out index XXXXXXX..XXXXXXX 100644 --- a/tests/qemu-iotests/191.out +++ b/tests/qemu-iotests/191.out @@ -XXX,XX +XXX,XX @@ wrote 65536/65536 bytes at offset 1048576 === Perform commit job === -{ 'execute': 'block-commit', 'arguments': { 'job-id': 'commit0', 'device': 'top', 'base':'TEST_DIR/t.IMGFMT.base', 'top': 'TEST_DIR/t.IMGFMT.mid' } } +{ 'execute': 'block-commit', + 'arguments': { 'job-id': 'commit0', + 'device': 'top', + 'base':'TEST_DIR/t.IMGFMT.base', + 'top': 'TEST_DIR/t.IMGFMT.mid' } } { "timestamp": { "seconds": TIMESTAMP, @@ -XXX,XX +XXX,XX @@ wrote 65536/65536 bytes at offset 1048576 === Perform commit job === -{ 'execute': 'block-commit', 'arguments': { 'job-id': 'commit0', 'device': 'top', 'base':'TEST_DIR/t.IMGFMT.base', 'top': 'TEST_DIR/t.IMGFMT.mid' } } +{ 'execute': 'block-commit', + 'arguments': { 'job-id': 'commit0', + 'device': 'top', + 'base':'TEST_DIR/t.IMGFMT.base', + 'top': 'TEST_DIR/t.IMGFMT.mid' } } { "timestamp": { "seconds": TIMESTAMP, diff --git a/tests/qemu-iotests/223.out b/tests/qemu-iotests/223.out index XXXXXXX..XXXXXXX 100644 --- a/tests/qemu-iotests/223.out +++ b/tests/qemu-iotests/223.out @@ -XXX,XX +XXX,XX @@ wrote 2097152/2097152 bytes at offset 2097152 {"execute":"qmp_capabilities"} {"return": {}} -{"execute":"blockdev-add", "arguments":{"driver":"IMGFMT", "node-name":"n", "file":{"driver":"file", "filename":"TEST_DIR/t.IMGFMT"}}} +{"execute":"blockdev-add", + "arguments":{"driver":"IMGFMT", "node-name":"n", + "file":{"driver":"file", "filename":"TEST_DIR/t.IMGFMT"}}} {"return": {}} -{"execute":"block-dirty-bitmap-disable", "arguments":{"node":"n", "name":"b"}} +{"execute":"block-dirty-bitmap-disable", + "arguments":{"node":"n", "name":"b"}} {"return": {}} === Set up NBD with normal access === -{"execute":"nbd-server-add", "arguments":{"device":"n"}} +{"execute":"nbd-server-add", + "arguments":{"device":"n"}} {"error": {"class": "GenericError", "desc": "NBD server not running"}} -{"execute":"nbd-server-start", "arguments":{"addr":{"type":"unix", "data":{"path":"SOCK_DIR/nbd"}}}} +{"execute":"nbd-server-start", + "arguments":{"addr":{"type":"unix", + "data":{"path":"SOCK_DIR/nbd"}}}} {"return": {}} -{"execute":"nbd-server-start", "arguments":{"addr":{"type":"unix", "data":{"path":"SOCK_DIR/nbd1"}}}} +{"execute":"nbd-server-start", + "arguments":{"addr":{"type":"unix", + "data":{"path":"SOCK_DIR/nbd1"}}}} {"error": {"class": "GenericError", "desc": "NBD server already running"}} exports available: 0 -{"execute":"nbd-server-add", "arguments":{"device":"n", "bitmap":"b"}} +{"execute":"nbd-server-add", + "arguments":{"device":"n", "bitmap":"b"}} {"return": {}} -{"execute":"nbd-server-add", "arguments":{"device":"nosuch"}} +{"execute":"nbd-server-add", + "arguments":{"device":"nosuch"}} {"error": {"class": "GenericError", "desc": "Cannot find device=nosuch nor node_name=nosuch"}} -{"execute":"nbd-server-add", "arguments":{"device":"n"}} +{"execute":"nbd-server-add", + "arguments":{"device":"n"}} {"error": {"class": "GenericError", "desc": "Block export id 'n' is already in use"}} -{"execute":"nbd-server-add", "arguments":{"device":"n", "name":"n2", "bitmap":"b2"}} +{"execute":"nbd-server-add", + "arguments":{"device":"n", "name":"n2", + "bitmap":"b2"}} {"error": {"class": "GenericError", "desc": "Enabled bitmap 'b2' incompatible with readonly export"}} -{"execute":"nbd-server-add", "arguments":{"device":"n", "name":"n2", "bitmap":"b3"}} +{"execute":"nbd-server-add", + "arguments":{"device":"n", "name":"n2", + "bitmap":"b3"}} {"error": {"class": "GenericError", "desc": "Bitmap 'b3' is not found"}} -{"execute":"nbd-server-add", "arguments":{"device":"n", "name":"n2", "writable":true, "description":"some text", "bitmap":"b2"}} +{"execute":"nbd-server-add", + "arguments":{"device":"n", "name":"n2", "writable":true, + "description":"some text", "bitmap":"b2"}} {"return": {}} exports available: 2 export: 'n' @@ -XXX,XX +XXX,XX @@ read 2097152/2097152 bytes at offset 2097152 === End qemu NBD server === -{"execute":"nbd-server-remove", "arguments":{"name":"n"}} +{"execute":"nbd-server-remove", + "arguments":{"name":"n"}} {"return": {}} -{"execute":"nbd-server-remove", "arguments":{"name":"n2"}} +{"execute":"nbd-server-remove", + "arguments":{"name":"n2"}} {"timestamp": {"seconds": TIMESTAMP, "microseconds": TIMESTAMP}, "event": "BLOCK_EXPORT_DELETED", "data": {"id": "n"}} {"return": {}} -{"execute":"nbd-server-remove", "arguments":{"name":"n2"}} +{"execute":"nbd-server-remove", + "arguments":{"name":"n2"}} {"timestamp": {"seconds": TIMESTAMP, "microseconds": TIMESTAMP}, "event": "BLOCK_EXPORT_DELETED", "data": {"id": "n2"}} {"error": {"class": "GenericError", "desc": "Export 'n2' is not found"}} {"execute":"nbd-server-stop"} @@ -XXX,XX +XXX,XX @@ read 2097152/2097152 bytes at offset 2097152 === Set up NBD with iothread access === -{"execute":"x-blockdev-set-iothread", "arguments":{"node-name":"n", "iothread":"io0"}} +{"execute":"x-blockdev-set-iothread", + "arguments":{"node-name":"n", "iothread":"io0"}} {"return": {}} -{"execute":"nbd-server-add", "arguments":{"device":"n"}} +{"execute":"nbd-server-add", + "arguments":{"device":"n"}} {"error": {"class": "GenericError", "desc": "NBD server not running"}} -{"execute":"nbd-server-start", "arguments":{"addr":{"type":"unix", "data":{"path":"SOCK_DIR/nbd"}}}} +{"execute":"nbd-server-start", + "arguments":{"addr":{"type":"unix", + "data":{"path":"SOCK_DIR/nbd"}}}} {"return": {}} -{"execute":"nbd-server-start", "arguments":{"addr":{"type":"unix", "data":{"path":"SOCK_DIR/nbd1"}}}} +{"execute":"nbd-server-start", + "arguments":{"addr":{"type":"unix", + "data":{"path":"SOCK_DIR/nbd1"}}}} {"error": {"class": "GenericError", "desc": "NBD server already running"}} exports available: 0 -{"execute":"nbd-server-add", "arguments":{"device":"n", "bitmap":"b"}} +{"execute":"nbd-server-add", + "arguments":{"device":"n", "bitmap":"b"}} {"return": {}} -{"execute":"nbd-server-add", "arguments":{"device":"nosuch"}} +{"execute":"nbd-server-add", + "arguments":{"device":"nosuch"}} {"error": {"class": "GenericError", "desc": "Cannot find device=nosuch nor node_name=nosuch"}} -{"execute":"nbd-server-add", "arguments":{"device":"n"}} +{"execute":"nbd-server-add", + "arguments":{"device":"n"}} {"error": {"class": "GenericError", "desc": "Block export id 'n' is already in use"}} -{"execute":"nbd-server-add", "arguments":{"device":"n", "name":"n2", "bitmap":"b2"}} +{"execute":"nbd-server-add", + "arguments":{"device":"n", "name":"n2", + "bitmap":"b2"}} {"error": {"class": "GenericError", "desc": "Enabled bitmap 'b2' incompatible with readonly export"}} -{"execute":"nbd-server-add", "arguments":{"device":"n", "name":"n2", "bitmap":"b3"}} +{"execute":"nbd-server-add", + "arguments":{"device":"n", "name":"n2", + "bitmap":"b3"}} {"error": {"class": "GenericError", "desc": "Bitmap 'b3' is not found"}} -{"execute":"nbd-server-add", "arguments":{"device":"n", "name":"n2", "writable":true, "description":"some text", "bitmap":"b2"}} +{"execute":"nbd-server-add", + "arguments":{"device":"n", "name":"n2", "writable":true, + "description":"some text", "bitmap":"b2"}} {"return": {}} exports available: 2 export: 'n' @@ -XXX,XX +XXX,XX @@ read 2097152/2097152 bytes at offset 2097152 === End qemu NBD server === -{"execute":"nbd-server-remove", "arguments":{"name":"n"}} +{"execute":"nbd-server-remove", + "arguments":{"name":"n"}} {"return": {}} -{"execute":"nbd-server-remove", "arguments":{"name":"n2"}} +{"execute":"nbd-server-remove", + "arguments":{"name":"n2"}} {"timestamp": {"seconds": TIMESTAMP, "microseconds": TIMESTAMP}, "event": "BLOCK_EXPORT_DELETED", "data": {"id": "n"}} {"return": {}} -{"execute":"nbd-server-remove", "arguments":{"name":"n2"}} +{"execute":"nbd-server-remove", + "arguments":{"name":"n2"}} {"timestamp": {"seconds": TIMESTAMP, "microseconds": TIMESTAMP}, "event": "BLOCK_EXPORT_DELETED", "data": {"id": "n2"}} {"error": {"class": "GenericError", "desc": "Export 'n2' is not found"}} {"execute":"nbd-server-stop"} diff --git a/tests/qemu-iotests/229.out b/tests/qemu-iotests/229.out index XXXXXXX..XXXXXXX 100644 --- a/tests/qemu-iotests/229.out +++ b/tests/qemu-iotests/229.out @@ -XXX,XX +XXX,XX @@ wrote 2097152/2097152 bytes at offset 0 === Starting drive-mirror, causing error & stop === -{'execute': 'drive-mirror', 'arguments': {'device': 'testdisk', 'format': 'IMGFMT', 'target': 'blkdebug:TEST_DIR/blkdebug.conf:TEST_DIR/t.IMGFMT.dest', 'sync': 'full', 'mode': 'existing', 'on-source-error': 'stop', 'on-target-error': 'stop' }} +{'execute': 'drive-mirror', + 'arguments': {'device': 'testdisk', + 'format': 'IMGFMT', + 'target': 'blkdebug:TEST_DIR/blkdebug.conf:TEST_DIR/t.IMGFMT.dest', + 'sync': 'full', + 'mode': 'existing', + 'on-source-error': 'stop', + 'on-target-error': 'stop' }} {"timestamp": {"seconds": TIMESTAMP, "microseconds": TIMESTAMP}, "event": "JOB_STATUS_CHANGE", "data": {"status": "created", "id": "testdisk"}} {"timestamp": {"seconds": TIMESTAMP, "microseconds": TIMESTAMP}, "event": "JOB_STATUS_CHANGE", "data": {"status": "running", "id": "testdisk"}} {"return": {}} @@ -XXX,XX +XXX,XX @@ wrote 2097152/2097152 bytes at offset 0 === Force cancel job paused in error state === -{'execute': 'block-job-cancel', 'arguments': { 'device': 'testdisk', 'force': true}} +{'execute': 'block-job-cancel', + 'arguments': { 'device': 'testdisk', + 'force': true}} {"timestamp": {"seconds": TIMESTAMP, "microseconds": TIMESTAMP}, "event": "JOB_STATUS_CHANGE", "data": {"status": "running", "id": "testdisk"}} {"return": {}} {"timestamp": {"seconds": TIMESTAMP, "microseconds": TIMESTAMP}, "event": "JOB_STATUS_CHANGE", "data": {"status": "aborting", "id": "testdisk"}} diff --git a/tests/qemu-iotests/249.out b/tests/qemu-iotests/249.out index XXXXXXX..XXXXXXX 100644 --- a/tests/qemu-iotests/249.out +++ b/tests/qemu-iotests/249.out @@ -XXX,XX +XXX,XX @@ Formatting 'TEST_DIR/t.IMGFMT', fmt=IMGFMT size=1048576 backing_file=TEST_DIR/t. === Send a write command to a drive opened in read-only mode (1) -{ 'execute': 'human-monitor-command', 'arguments': {'command-line': 'qemu-io none0 "aio_write 0 2k"'}} +{ 'execute': 'human-monitor-command', + 'arguments': {'command-line': 'qemu-io none0 "aio_write 0 2k"'}} {"return": "Block node is read-onlyrn"} === Run block-commit on base using an invalid filter node name -{ 'execute': 'block-commit', 'arguments': {'job-id': 'job0', 'device': 'none1', 'top-node': 'int', 'filter-node-name': '1234'}} +{ 'execute': 'block-commit', + 'arguments': {'job-id': 'job0', 'device': 'none1', 'top-node': 'int', + 'filter-node-name': '1234'}} {"timestamp": {"seconds": TIMESTAMP, "microseconds": TIMESTAMP}, "event": "JOB_STATUS_CHANGE", "data": {"status": "created", "id": "job0"}} {"timestamp": {"seconds": TIMESTAMP, "microseconds": TIMESTAMP}, "event": "JOB_STATUS_CHANGE", "data": {"status": "null", "id": "job0"}} {"error": {"class": "GenericError", "desc": "Invalid node name"}} === Send a write command to a drive opened in read-only mode (2) -{ 'execute': 'human-monitor-command', 'arguments': {'command-line': 'qemu-io none0 "aio_write 0 2k"'}} +{ 'execute': 'human-monitor-command', + 'arguments': {'command-line': 'qemu-io none0 "aio_write 0 2k"'}} {"return": "Block node is read-onlyrn"} === Run block-commit on base using the default filter node name -{ 'execute': 'block-commit', 'arguments': {'job-id': 'job0', 'device': 'none1', 'top-node': 'int'}} +{ 'execute': 'block-commit', + 'arguments': {'job-id': 'job0', 'device': 'none1', 'top-node': 'int'}} {"timestamp": {"seconds": TIMESTAMP, "microseconds": TIMESTAMP}, "event": "JOB_STATUS_CHANGE", "data": {"status": "created", "id": "job0"}} {"timestamp": {"seconds": TIMESTAMP, "microseconds": TIMESTAMP}, "event": "JOB_STATUS_CHANGE", "data": {"status": "running", "id": "job0"}} {"return": {}} @@ -XXX,XX +XXX,XX @@ Formatting 'TEST_DIR/t.IMGFMT', fmt=IMGFMT size=1048576 backing_file=TEST_DIR/t. === Send a write command to a drive opened in read-only mode (3) -{ 'execute': 'human-monitor-command', 'arguments': {'command-line': 'qemu-io none0 "aio_write 0 2k"'}} +{ 'execute': 'human-monitor-command', + 'arguments': {'command-line': 'qemu-io none0 "aio_write 0 2k"'}} {"return": "Block node is read-onlyrn"} *** done diff --git a/tests/qemu-iotests/308.out b/tests/qemu-iotests/308.out index XXXXXXX..XXXXXXX 100644 --- a/tests/qemu-iotests/308.out +++ b/tests/qemu-iotests/308.out @@ -XXX,XX +XXX,XX @@ wrote 67108864/67108864 bytes at offset 0 64 MiB, X ops; XX:XX:XX.X (XXX YYY/sec and XXX ops/sec) {'execute': 'qmp_capabilities'} {"return": {}} -{'execute': 'blockdev-add', 'arguments': { 'driver': 'file', 'node-name': 'node-protocol', 'filename': 'TEST_DIR/t.IMGFMT' } } +{'execute': 'blockdev-add', + 'arguments': { + 'driver': 'file', + 'node-name': 'node-protocol', + 'filename': 'TEST_DIR/t.IMGFMT' + } } {"return": {}} -{'execute': 'blockdev-add', 'arguments': { 'driver': 'IMGFMT', 'node-name': 'node-format', 'file': 'node-protocol' } } +{'execute': 'blockdev-add', + 'arguments': { + 'driver': 'IMGFMT', + 'node-name': 'node-format', + 'file': 'node-protocol' + } } {"return": {}} === Mountpoint not present === -{'execute': 'block-export-add', 'arguments': { 'type': 'fuse', 'id': 'export-err', 'node-name': 'node-format', 'mountpoint': 'TEST_DIR/t.IMGFMT.fuse' } } +{'execute': 'block-export-add', + 'arguments': { + 'type': 'fuse', + 'id': 'export-err', + 'node-name': 'node-format', + 'mountpoint': 'TEST_DIR/t.IMGFMT.fuse' + } } {"error": {"class": "GenericError", "desc": "Failed to stat 'TEST_DIR/t.IMGFMT.fuse': No such file or directory"}} === Mountpoint is a directory === -{'execute': 'block-export-add', 'arguments': { 'type': 'fuse', 'id': 'export-err', 'node-name': 'node-format', 'mountpoint': 'TEST_DIR/t.IMGFMT.fuse' } } +{'execute': 'block-export-add', + 'arguments': { + 'type': 'fuse', + 'id': 'export-err', + 'node-name': 'node-format', + 'mountpoint': 'TEST_DIR/t.IMGFMT.fuse' + } } {"error": {"class": "GenericError", "desc": "'TEST_DIR/t.IMGFMT.fuse' is not a regular file"}} === Mountpoint is a regular file === -{'execute': 'block-export-add', 'arguments': { 'type': 'fuse', 'id': 'export-mp', 'node-name': 'node-format', 'mountpoint': 'TEST_DIR/t.IMGFMT.fuse' } } +{'execute': 'block-export-add', + 'arguments': { + 'type': 'fuse', + 'id': 'export-mp', + 'node-name': 'node-format', + 'mountpoint': 'TEST_DIR/t.IMGFMT.fuse' + } } {"return": {}} Images are identical. === Mount over existing file === -{'execute': 'block-export-add', 'arguments': { 'type': 'fuse', 'id': 'export-img', 'node-name': 'node-format', 'mountpoint': 'TEST_DIR/t.IMGFMT' } } +{'execute': 'block-export-add', + 'arguments': { + 'type': 'fuse', + 'id': 'export-img', + 'node-name': 'node-format', + 'mountpoint': 'TEST_DIR/t.IMGFMT' + } } {"return": {}} Images are identical. === Double export === -{'execute': 'block-export-add', 'arguments': { 'type': 'fuse', 'id': 'export-err', 'node-name': 'node-format', 'mountpoint': 'TEST_DIR/t.IMGFMT.fuse' } } +{'execute': 'block-export-add', + 'arguments': { + 'type': 'fuse', + 'id': 'export-err', + 'node-name': 'node-format', + 'mountpoint': 'TEST_DIR/t.IMGFMT.fuse' + } } {"error": {"class": "GenericError", "desc": "There already is a FUSE export on 'TEST_DIR/t.IMGFMT.fuse'"}} === Remove export === virtual size: 64 MiB (67108864 bytes) -{'execute': 'block-export-del', 'arguments': { 'id': 'export-mp' } } +{'execute': 'block-export-del', + 'arguments': { + 'id': 'export-mp' + } } {"return": {}} {"timestamp": {"seconds": TIMESTAMP, "microseconds": TIMESTAMP}, "event": "BLOCK_EXPORT_DELETED", "data": {"id": "export-mp"}} virtual size: 0 B (0 bytes) === Writable export === -{'execute': 'block-export-add', 'arguments': { 'type': 'fuse', 'id': 'export-mp', 'node-name': 'node-format', 'mountpoint': 'TEST_DIR/t.IMGFMT.fuse', 'writable': true } } +{'execute': 'block-export-add', + 'arguments': { + 'type': 'fuse', + 'id': 'export-mp', + 'node-name': 'node-format', + 'mountpoint': 'TEST_DIR/t.IMGFMT.fuse', 'writable': true + } } {"return": {}} write failed: Permission denied wrote 65536/65536 bytes at offset 1048576 @@ -XXX,XX +XXX,XX @@ wrote 65536/65536 bytes at offset 1048576 64 KiB, X ops; XX:XX:XX.X (XXX YYY/sec and XXX ops/sec) === Resizing exports === -{'execute': 'block-export-del', 'arguments': { 'id': 'export-mp' } } +{'execute': 'block-export-del', + 'arguments': { + 'id': 'export-mp' + } } {"return": {}} {"timestamp": {"seconds": TIMESTAMP, "microseconds": TIMESTAMP}, "event": "BLOCK_EXPORT_DELETED", "data": {"id": "export-mp"}} -{'execute': 'block-export-del', 'arguments': { 'id': 'export-img' } } +{'execute': 'block-export-del', + 'arguments': { + 'id': 'export-img' + } } {"return": {}} {"timestamp": {"seconds": TIMESTAMP, "microseconds": TIMESTAMP}, "event": "BLOCK_EXPORT_DELETED", "data": {"id": "export-img"}} -{'execute': 'blockdev-del', 'arguments': { 'node-name': 'node-format' } } +{'execute': 'blockdev-del', + 'arguments': { + 'node-name': 'node-format' + } } {"return": {}} -{'execute': 'block-export-add', 'arguments': { 'type': 'fuse', 'id': 'export-mp', 'node-name': 'node-protocol', 'mountpoint': 'TEST_DIR/t.IMGFMT.fuse', 'writable': true } } +{'execute': 'block-export-add', + 'arguments': { + 'type': 'fuse', + 'id': 'export-mp', + 'node-name': 'node-protocol', + 'mountpoint': 'TEST_DIR/t.IMGFMT.fuse', 'writable': true + } } {"return": {}} --- Try growing non-growable export --- @@ -XXX,XX +XXX,XX @@ OK: Post-truncate image size is as expected OK: Disk usage grew with fallocate --- Try growing growable export --- -{'execute': 'block-export-del', 'arguments': { 'id': 'export-mp' } } +{'execute': 'block-export-del', + 'arguments': { + 'id': 'export-mp' + } } {"return": {}} {"timestamp": {"seconds": TIMESTAMP, "microseconds": TIMESTAMP}, "event": "BLOCK_EXPORT_DELETED", "data": {"id": "export-mp"}} -{'execute': 'block-export-add', 'arguments': { 'type': 'fuse', 'id': 'export-mp', 'node-name': 'node-protocol', 'mountpoint': 'TEST_DIR/t.IMGFMT.fuse', 'writable': true, 'growable': true } } +{'execute': 'block-export-add', + 'arguments': { + 'type': 'fuse', + 'id': 'export-mp', + 'node-name': 'node-protocol', + 'mountpoint': 'TEST_DIR/t.IMGFMT.fuse', 'writable': true, 'growable': true + } } {"return": {}} 65536+0 records in 65536+0 records out diff --git a/tests/qemu-iotests/312.out b/tests/qemu-iotests/312.out index XXXXXXX..XXXXXXX 100644 --- a/tests/qemu-iotests/312.out +++ b/tests/qemu-iotests/312.out @@ -XXX,XX +XXX,XX @@ read 65536/65536 bytes at offset 2424832 { 'execute': 'qmp_capabilities' } {"return": {}} -{'execute': 'drive-mirror', 'arguments': {'device': 'virtio0', 'format': 'IMGFMT', 'target': 'TEST_DIR/t.IMGFMT.3', 'sync': 'full', 'mode': 'existing' }} +{'execute': 'drive-mirror', + 'arguments': {'device': 'virtio0', + 'format': 'IMGFMT', + 'target': 'TEST_DIR/t.IMGFMT.3', + 'sync': 'full', + 'mode': 'existing' }} {"timestamp": {"seconds": TIMESTAMP, "microseconds": TIMESTAMP}, "event": "JOB_STATUS_CHANGE", "data": {"status": "created", "id": "virtio0"}} {"timestamp": {"seconds": TIMESTAMP, "microseconds": TIMESTAMP}, "event": "JOB_STATUS_CHANGE", "data": {"status": "running", "id": "virtio0"}} {"return": {}} {"timestamp": {"seconds": TIMESTAMP, "microseconds": TIMESTAMP}, "event": "JOB_STATUS_CHANGE", "data": {"status": "ready", "id": "virtio0"}} {"timestamp": {"seconds": TIMESTAMP, "microseconds": TIMESTAMP}, "event": "BLOCK_JOB_READY", "data": {"device": "virtio0", "len": 10485760, "offset": 10485760, "speed": 0, "type": "mirror"}} -{ 'execute': 'block-job-complete', 'arguments': { 'device': 'virtio0' } } +{ 'execute': 'block-job-complete', + 'arguments': { 'device': 'virtio0' } } {"return": {}} {"timestamp": {"seconds": TIMESTAMP, "microseconds": TIMESTAMP}, "event": "JOB_STATUS_CHANGE", "data": {"status": "waiting", "id": "virtio0"}} {"timestamp": {"seconds": TIMESTAMP, "microseconds": TIMESTAMP}, "event": "JOB_STATUS_CHANGE", "data": {"status": "pending", "id": "virtio0"}} diff --git a/tests/qemu-iotests/common.qemu b/tests/qemu-iotests/common.qemu index XXXXXXX..XXXXXXX 100644 --- a/tests/qemu-iotests/common.qemu +++ b/tests/qemu-iotests/common.qemu @@ -XXX,XX +XXX,XX @@ _send_qemu_cmd() count=${qemu_cmd_repeat} use_error="no" fi - # This array element extraction is done to accommodate pathnames with spaces - if [ -z "${success_or_failure}" ]; then - cmd=${@: 1:${#@}-1} - shift $(($# - 1)) - else - cmd=${@: 1:${#@}-2} - shift $(($# - 2)) - fi + + cmd=$1 + shift # Display QMP being sent, but not HMP (since HMP already echoes its # input back to output); decide based on leading '{' -- 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