throttle-groups: forget timer and schedule next TGM on detach

tg->any_timer_armed[] must be cleared when detaching pending timers from
the AioContext.  Failure to do so leads to hung I/O because it looks
like there are still timers pending when in fact they have been removed.

Other ThrottleGroupMembers might have requests pending too so it's
necessary to schedule the next TGM so it can set a timer.

This patch fixes hung I/O when QEMU is launched with drives that are in
the same throttling group:

  (guest)$ dd if=/dev/zero of=/dev/vdb oflag=direct bs=512 &
  (guest)$ dd if=/dev/zero of=/dev/vdc oflag=direct bs=512 &
  (qemu) stop
  (qemu) cont
  ...I/O is stuck...

Signed-off-by: Stefan Hajnoczi <stefanha@redhat.com>
Message-id: 20171116112150.27607-1-stefanha@redhat.com
Signed-off-by: Stefan Hajnoczi <stefanha@redhat.com>

diff --git a/block/throttle-groups.c b/block/throttle-groups.c
index 2587f19ca33f76c96dd2d38535f4b2f3165b2a9a..f26bcb5eee466adafd3d65fdaef3abc5fa715ef5 100644 (file)
--- a/block/throttle-groups.c
+++ b/block/throttle-groups.c
@@ -593,13 +593,25 @@ void throttle_group_attach_aio_context(ThrottleGroupMember *tgm,
 
 void throttle_group_detach_aio_context(ThrottleGroupMember *tgm)
 {
+    ThrottleGroup *tg = container_of(tgm->throttle_state, ThrottleGroup, ts);
     ThrottleTimers *tt = &tgm->throttle_timers;
+    int i;
 
     /* Requests must have been drained */
     assert(tgm->pending_reqs[0] == 0 && tgm->pending_reqs[1] == 0);
     assert(qemu_co_queue_empty(&tgm->throttled_reqs[0]));
     assert(qemu_co_queue_empty(&tgm->throttled_reqs[1]));
 
+    /* Kick off next ThrottleGroupMember, if necessary */
+    qemu_mutex_lock(&tg->lock);
+    for (i = 0; i < 2; i++) {
+        if (timer_pending(tt->timers[i])) {
+            tg->any_timer_armed[i] = false;
+            schedule_next_request(tgm, i);
+        }
+    }
+    qemu_mutex_unlock(&tg->lock);
+
     throttle_timers_detach_aio_context(tt);
     tgm->aio_context = NULL;
 }