From: Ivan Ren <renyime@gmail.com>
When we 'migrate_cancel' a multifd migration, live_migration thread may
hung forever at some points, because of multifd_send_thread has already
exit for socket error:
1. multifd_send_pages may hung at qemu_sem_wait(&multifd_send_state->
channels_ready)
2. multifd_send_sync_main my hung at qemu_sem_wait(&multifd_send_state->
sem_sync)
Signed-off-by: Ivan Ren <ivanren@tencent.com>
Message-Id: <1561468699-9819-3-git-send-email-ivanren@tencent.com>
Reviewed-by: Dr. David Alan Gilbert <dgilbert@redhat.com>
Reviewed-by: Juan Quintela <quintela@redhat.com>
Signed-off-by: Juan Quintela <quintela@redhat.com>
---
Remove spurious not needed bits
---
migration/ram.c | 16 ++++++++++++++--
1 file changed, 14 insertions(+), 2 deletions(-)
diff --git a/migration/ram.c b/migration/ram.c
index 52a2d498e4..87bb7da8e2 100644
--- a/migration/ram.c
+++ b/migration/ram.c
@@ -1097,7 +1097,8 @@ static void *multifd_send_thread(void *opaque)
{
MultiFDSendParams *p = opaque;
Error *local_err = NULL;
- int ret;
+ int ret = 0;
+ uint32_t flags = 0;
trace_multifd_send_thread_start(p->id);
rcu_register_thread();
@@ -1115,7 +1116,7 @@ static void *multifd_send_thread(void *opaque)
if (p->pending_job) {
uint32_t used = p->pages->used;
uint64_t packet_num = p->packet_num;
- uint32_t flags = p->flags;
+ flags = p->flags;
p->next_packet_size = used * qemu_target_page_size();
multifd_send_fill_packet(p);
@@ -1164,6 +1165,17 @@ out:
multifd_send_terminate_threads(local_err);
}
+ /*
+ * Error happen, I will exit, but I can't just leave, tell
+ * who pay attention to me.
+ */
+ if (ret != 0) {
+ if (flags & MULTIFD_FLAG_SYNC) {
+ qemu_sem_post(&multifd_send_state->sem_sync);
+ }
+ qemu_sem_post(&multifd_send_state->channels_ready);
+ }
+
qemu_mutex_lock(&p->mutex);
p->running = false;
qemu_mutex_unlock(&p->mutex);
--
2.21.0