diff options
author | Lukas Straub <lukasstraub2@web.de> | 2020-05-11 13:10:44 +0200 |
---|---|---|
committer | Dr. David Alan Gilbert <dgilbert@redhat.com> | 2020-06-01 18:44:27 +0100 |
commit | bb70b66ed7a5600a63437fb6d64dedb44f670e58 (patch) | |
tree | dcac9bc50eb0326987316259efe0b8de4e210cd1 /migration/colo.c | |
parent | e0d138aa9b3a4c72fe8bca735686132fdea646b7 (diff) |
migration/colo.c: Use event instead of semaphore
If multiple packets miscompare in a short timeframe, the semaphore
value will be increased multiple times. This causes multiple
checkpoints even if one would be sufficient.
Fix this by using a event instead of a semaphore for triggering
checkpoints. Now, checkpoint requests will be ignored until the
checkpoint event is sent to colo-compare (which releases the
miscompared packets).
Benchmark results (iperf3):
Client-to-server tcp:
without patch: ~66 Mbit/s
with patch: ~61 Mbit/s
Server-to-client tcp:
without patch: ~702 Kbit/s
with patch: ~16 Mbit/s
Signed-off-by: Lukas Straub <lukasstraub2@web.de>
Message-Id: <fd601ba1beb524aada54ba66e87ebfc12cf4574b.1589193382.git.lukasstraub2@web.de>
Reviewed-by: zhanghailiang <zhang.zhanghailiang@huawei.com>
Signed-off-by: Dr. David Alan Gilbert <dgilbert@redhat.com>
Diffstat (limited to 'migration/colo.c')
-rw-r--r-- | migration/colo.c | 9 |
1 files changed, 5 insertions, 4 deletions
diff --git a/migration/colo.c b/migration/colo.c index d015d4f84e..fe0d6e93e5 100644 --- a/migration/colo.c +++ b/migration/colo.c @@ -436,6 +436,7 @@ static int colo_do_checkpoint_transaction(MigrationState *s, goto out; } + qemu_event_reset(&s->colo_checkpoint_event); colo_notify_compares_event(NULL, COLO_EVENT_CHECKPOINT, &local_err); if (local_err) { goto out; @@ -589,7 +590,7 @@ static void colo_process_checkpoint(MigrationState *s) goto out; } - qemu_sem_wait(&s->colo_checkpoint_sem); + qemu_event_wait(&s->colo_checkpoint_event); if (s->state != MIGRATION_STATUS_COLO) { goto out; @@ -637,7 +638,7 @@ out: colo_compare_unregister_notifier(&packets_compare_notifier); timer_del(s->colo_delay_timer); timer_free(s->colo_delay_timer); - qemu_sem_destroy(&s->colo_checkpoint_sem); + qemu_event_destroy(&s->colo_checkpoint_event); /* * Must be called after failover BH is completed, @@ -654,7 +655,7 @@ void colo_checkpoint_notify(void *opaque) MigrationState *s = opaque; int64_t next_notify_time; - qemu_sem_post(&s->colo_checkpoint_sem); + qemu_event_set(&s->colo_checkpoint_event); s->colo_checkpoint_time = qemu_clock_get_ms(QEMU_CLOCK_HOST); next_notify_time = s->colo_checkpoint_time + s->parameters.x_checkpoint_delay; @@ -664,7 +665,7 @@ void colo_checkpoint_notify(void *opaque) void migrate_start_colo_process(MigrationState *s) { qemu_mutex_unlock_iothread(); - qemu_sem_init(&s->colo_checkpoint_sem, 0); + qemu_event_init(&s->colo_checkpoint_event, false); s->colo_delay_timer = timer_new_ms(QEMU_CLOCK_HOST, colo_checkpoint_notify, s); |