From: Stefan Hajnoczi <stefanha@redhat.com>

Commit 8565c3ab537e78f3e69977ec2c609dc9417a806e ("qemu-iotests: fix

185") identified a race condition in a sub-test.

Similar issues also affect the other sub-tests. If disk I/O completes

quickly, it races with the QMP 'quit' command. This causes spurious

test failures because QMP events are emitted in an unpredictable order.

This test relies on QEMU internals and there is no QMP API for getting

deterministic behavior needed to make this test 100% reliable. At the

same time, the test is useful and it would be a shame to remove it.

Add sleep 0.5 to reduce the chance of races. This is not a real fix but

appears to reduce spurious failures in practice.

Cc: Vladimir Sementsov-Ogievskiy <vsementsov@virtuozzo.com>

Signed-off-by: Stefan Hajnoczi <stefanha@redhat.com>

Reviewed-by: Eric Blake <eblake@redhat.com>

Message-id: 20180508135436.30140-2-stefanha@redhat.com

Reviewed-by: Jeff Cody <jcody@redhat.com>

Signed-off-by: Jeff Cody <jcody@redhat.com>

---

tests/qemu-iotests/185 | 12 ++++++++++++

1 file changed, 12 insertions(+)

diff --git a/tests/qemu-iotests/185 b/tests/qemu-iotests/185

index XXXXXXX..XXXXXXX 100755

--- a/tests/qemu-iotests/185

+++ b/tests/qemu-iotests/185

@@ -XXX,XX +XXX,XX @@ _send_qemu_cmd $h \

'speed': 65536 } }" \

"return"

+# If we don't sleep here 'quit' command races with disk I/O

+sleep 0.5

+

_send_qemu_cmd $h "{ 'execute': 'quit' }" "return"

wait=1 _cleanup_qemu

@@ -XXX,XX +XXX,XX @@ _send_qemu_cmd $h \

'speed': 65536 } }" \

"return"

+# If we don't sleep here 'quit' command races with disk I/O

+sleep 0.5

+

_send_qemu_cmd $h "{ 'execute': 'quit' }" "return"

wait=1 _cleanup_qemu

@@ -XXX,XX +XXX,XX @@ _send_qemu_cmd $h \

'speed': 65536 } }" \

"return"

+# If we don't sleep here 'quit' command races with disk I/O

+sleep 0.5

+

_send_qemu_cmd $h "{ 'execute': 'quit' }" "return"

wait=1 _cleanup_qemu

@@ -XXX,XX +XXX,XX @@ _send_qemu_cmd $h \

'speed': 65536 } }" \

"return"

+# If we don't sleep here 'quit' command races with disk I/O

+sleep 0.5

+

_send_qemu_cmd $h "{ 'execute': 'quit' }" "return"

wait=1 _cleanup_qemu

--

2.13.6

From: Stefan Hajnoczi <stefanha@redhat.com>

Currently the timer is cancelled and the block job is entered by

block_job_resume(). This behavior causes drain to run extra blockjob

iterations when the job was sleeping due to the ratelimit.

This patch leaves the job asleep when block_job_resume() is called.

Jobs can still be forcibly woken up using block_job_enter(), which is

used to cancel jobs.

After this patch drain no longer runs extra blockjob iterations. This

is the expected behavior that qemu-iotests 185 used to rely on. We

temporarily changed the 185 test output to make it pass for the QEMU

2.12 release but now it's time to address this issue.

Cc: QingFeng Hao <haoqf@linux.vnet.ibm.com>

Signed-off-by: Stefan Hajnoczi <stefanha@redhat.com>

Reviewed-by: Eric Blake <eblake@redhat.com>

Reviewed-by: QingFeng Hao <haoqf@linux.vnet.ibm.com>

Message-id: 20180508135436.30140-3-stefanha@redhat.com

Reviewed-by: Jeff Cody <jcody@redhat.com>

Signed-off-by: Jeff Cody <jcody@redhat.com>

---

blockjob.c | 22 +++++++++++++++-------

tests/qemu-iotests/185 | 5 +----

tests/qemu-iotests/185.out | 12 +++++-------

3 files changed, 21 insertions(+), 18 deletions(-)

diff --git a/blockjob.c b/blockjob.c

index XXXXXXX..XXXXXXX 100644

--- a/blockjob.c

+++ b/blockjob.c

@@ -XXX,XX +XXX,XX @@ static void block_job_txn_del_job(BlockJob *job)

}

}

+/* Assumes the block_job_mutex is held */

+static bool block_job_timer_pending(BlockJob *job)

+{

+ return timer_pending(&job->sleep_timer);

+}

+

+/* Assumes the block_job_mutex is held */

+static bool block_job_timer_not_pending(BlockJob *job)

+{

+ return !block_job_timer_pending(job);

+}

+

static void block_job_pause(BlockJob *job)

{

job->pause_count++;

@@ -XXX,XX +XXX,XX @@ static void block_job_resume(BlockJob *job)

if (job->pause_count) {

return;

}

- block_job_enter(job);

+

+ /* kick only if no timer is pending */

+ block_job_enter_cond(job, block_job_timer_not_pending);

}

void block_job_ref(BlockJob *job)

@@ -XXX,XX +XXX,XX @@ static void block_job_completed_txn_success(BlockJob *job)

}

}

-/* Assumes the block_job_mutex is held */

-static bool block_job_timer_pending(BlockJob *job)

-{

- return timer_pending(&job->sleep_timer);

-}

-

void block_job_set_speed(BlockJob *job, int64_t speed, Error **errp)

{

int64_t old_speed = job->speed;

diff --git a/tests/qemu-iotests/185 b/tests/qemu-iotests/185

index XXXXXXX..XXXXXXX 100755

--- a/tests/qemu-iotests/185

+++ b/tests/qemu-iotests/185

@@ -XXX,XX +XXX,XX @@ echo

# command to be received (after receiving the command, the rest runs

# synchronously, so jobs can arbitrarily continue or complete).

#

-# Jobs present while QEMU is terminating iterate once more due to

-# bdrv_drain_all().

-#

# The buffer size for commit and streaming is 512k (waiting for 8 seconds after

# the first request), for active commit and mirror it's large enough to cover

# the full 4M, and for backup it's the qcow2 cluster size, which we know is

# 64k. As all of these are at least as large as the speed, we are sure that the

-# offset advances exactly twice before qemu exits.

+# offset advances exactly once before qemu exits.

_send_qemu_cmd $h \

"{ 'execute': 'block-commit',

diff --git a/tests/qemu-iotests/185.out b/tests/qemu-iotests/185.out

index XXXXXXX..XXXXXXX 100644

--- a/tests/qemu-iotests/185.out

+++ b/tests/qemu-iotests/185.out

@@ -XXX,XX +XXX,XX @@ Formatting 'TEST_DIR/t.qcow2', fmt=qcow2 size=67108864 backing_file=TEST_DIR/t.q

{"return": {}}

{"return": {}}

{"timestamp": {"seconds": TIMESTAMP, "microseconds": TIMESTAMP}, "event": "SHUTDOWN", "data": {"guest": false}}

-{"timestamp": {"seconds": TIMESTAMP, "microseconds": TIMESTAMP}, "event": "BLOCK_JOB_CANCELLED", "data": {"device": "disk", "len": 67108864, "offset": 1048576, "speed": 65536, "type": "commit"}}

+{"timestamp": {"seconds": TIMESTAMP, "microseconds": TIMESTAMP}, "event": "BLOCK_JOB_CANCELLED", "data": {"device": "disk", "len": 67108864, "offset": 524288, "speed": 65536, "type": "commit"}}

=== Start active commit job and exit qemu ===

@@ -XXX,XX +XXX,XX @@ Formatting 'TEST_DIR/t.qcow2', fmt=qcow2 size=67108864 backing_file=TEST_DIR/t.q

{"return": {}}

{"return": {}}

{"timestamp": {"seconds": TIMESTAMP, "microseconds": TIMESTAMP}, "event": "SHUTDOWN", "data": {"guest": false}}

-{"timestamp": {"seconds": TIMESTAMP, "microseconds": TIMESTAMP}, "event": "BLOCK_JOB_READY", "data": {"device": "disk", "len": 4194304, "offset": 4194304, "speed": 65536, "type": "commit"}}

-{"timestamp": {"seconds": TIMESTAMP, "microseconds": TIMESTAMP}, "event": "BLOCK_JOB_COMPLETED", "data": {"device": "disk", "len": 4194304, "offset": 4194304, "speed": 65536, "type": "commit"}}

+{"timestamp": {"seconds": TIMESTAMP, "microseconds": TIMESTAMP}, "event": "BLOCK_JOB_CANCELLED", "data": {"device": "disk", "len": 4194304, "offset": 4194304, "speed": 65536, "type": "commit"}}

=== Start mirror job and exit qemu ===

@@ -XXX,XX +XXX,XX @@ Formatting 'TEST_DIR/t.qcow2.copy', fmt=qcow2 size=67108864 cluster_size=65536 l

{"return": {}}

{"return": {}}

{"timestamp": {"seconds": TIMESTAMP, "microseconds": TIMESTAMP}, "event": "SHUTDOWN", "data": {"guest": false}}

-{"timestamp": {"seconds": TIMESTAMP, "microseconds": TIMESTAMP}, "event": "BLOCK_JOB_READY", "data": {"device": "disk", "len": 4194304, "offset": 4194304, "speed": 65536, "type": "mirror"}}

-{"timestamp": {"seconds": TIMESTAMP, "microseconds": TIMESTAMP}, "event": "BLOCK_JOB_COMPLETED", "data": {"device": "disk", "len": 4194304, "offset": 4194304, "speed": 65536, "type": "mirror"}}

+{"timestamp": {"seconds": TIMESTAMP, "microseconds": TIMESTAMP}, "event": "BLOCK_JOB_CANCELLED", "data": {"device": "disk", "len": 4194304, "offset": 4194304, "speed": 65536, "type": "mirror"}}

=== Start backup job and exit qemu ===

@@ -XXX,XX +XXX,XX @@ Formatting 'TEST_DIR/t.qcow2.copy', fmt=qcow2 size=67108864 cluster_size=65536 l

{"return": {}}

{"return": {}}

{"timestamp": {"seconds": TIMESTAMP, "microseconds": TIMESTAMP}, "event": "SHUTDOWN", "data": {"guest": false}}

-{"timestamp": {"seconds": TIMESTAMP, "microseconds": TIMESTAMP}, "event": "BLOCK_JOB_CANCELLED", "data": {"device": "disk", "len": 67108864, "offset": 131072, "speed": 65536, "type": "backup"}}

+{"timestamp": {"seconds": TIMESTAMP, "microseconds": TIMESTAMP}, "event": "BLOCK_JOB_CANCELLED", "data": {"device": "disk", "len": 67108864, "offset": 65536, "speed": 65536, "type": "backup"}}

=== Start streaming job and exit qemu ===

@@ -XXX,XX +XXX,XX @@ Formatting 'TEST_DIR/t.qcow2.copy', fmt=qcow2 size=67108864 cluster_size=65536 l

{"return": {}}

{"return": {}}

{"timestamp": {"seconds": TIMESTAMP, "microseconds": TIMESTAMP}, "event": "SHUTDOWN", "data": {"guest": false}}

-{"timestamp": {"seconds": TIMESTAMP, "microseconds": TIMESTAMP}, "event": "BLOCK_JOB_CANCELLED", "data": {"device": "disk", "len": 67108864, "offset": 1048576, "speed": 65536, "type": "stream"}}

+{"timestamp": {"seconds": TIMESTAMP, "microseconds": TIMESTAMP}, "event": "BLOCK_JOB_CANCELLED", "data": {"device": "disk", "len": 67108864, "offset": 524288, "speed": 65536, "type": "stream"}}

No errors were found on the image.

*** done

--

2.13.6

From: Kevin Wolf <kwolf@redhat.com>

Don't throw away local_err, but propagate it to errp.

Signed-off-by: Kevin Wolf <kwolf@redhat.com>

Message-id: 20180516161034.27440-1-kwolf@redhat.com

Reviewed-by: Eric Blake <eblake@redhat.com>

Reviewed-by: Jeff Cody <jcody@redhat.com>

Signed-off-by: Jeff Cody <jcody@redhat.com>

---

block/nfs.c | 1 +

1 file changed, 1 insertion(+)

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 BlockdevOptionsNfs *nfs_options_qdict_to_qapi(QDict *options,

qobject_unref(crumpled);

if (local_err) {

+ error_propagate(errp, local_err);

return NULL;

}

--

2.13.6