thread-pool: add missing qemu_bh_cancel in completion function

commit 3c80ca1 fixed a deadlock scenarion with nested aio_poll invocations. However, the rescheduling of the completion BH introcuded unnecessary spinning in the main-loop. On very fast file backends this can even lead to the "WARNING: I/O thread spun for 1000 iterations" message popping up. Callgrind reports about 3-4% less instructions with this patch running qemu-img bench on a ramdisk based VMDK file. Fixes: 3c80ca1 Cc: [email protected] Signed-off-by: Peter Lieven <[email protected]> Signed-off-by: Kevin Wolf <[email protected]>
NarutoGit · Mar 17, 2017 · b7a745d · b7a745d
1 parent 8cd1a3e
commit b7a745d
Showing 1 changed file with 7 additions and 0 deletions.
diff --git a/util/thread-pool.c b/util/thread-pool.c
@@ -188,6 +188,13 @@ static void thread_pool_completion_bh(void *opaque)
             aio_context_release(pool->ctx);
             elem->common.cb(elem->common.opaque, elem->ret);
             aio_context_acquire(pool->ctx);
+
+            /* We can safely cancel the completion_bh here regardless of someone
+             * else having scheduled it meanwhile because we reenter the
+             * completion function anyway (goto restart).
+             */
+            qemu_bh_cancel(pool->completion_bh);
+
             qemu_aio_unref(elem);
             goto restart;
         } else {