This patch drops a special case where aio_poll(ctx, true) returns false instead of blocking if no file descriptors are waiting on I/O. Now it is possible to block in aio_poll() to wait for aio_notify().
This change eliminates busy waiting. bdrv_drain_all() used to rely on busy waiting to completed throttled I/O requests but this is no longer required so we can simplify aio_poll(). Note that aio_poll() still returns false when aio_notify() was used. In other words, stopping a blocking aio_poll() wait is not considered making progress. Adjust test-aio /aio/bh/callback-delete/one which assumed aio_poll(ctx, true) would immediately return false instead of blocking. Signed-off-by: Stefan Hajnoczi <stefa...@redhat.com> --- aio-posix.c | 5 ----- aio-win32.c | 5 ----- tests/test-aio.c | 1 - 3 files changed, 11 deletions(-) diff --git a/aio-posix.c b/aio-posix.c index bd06f33..f921d4f 100644 --- a/aio-posix.c +++ b/aio-posix.c @@ -217,11 +217,6 @@ bool aio_poll(AioContext *ctx, bool blocking) ctx->walking_handlers--; - /* early return if we only have the aio_notify() fd */ - if (ctx->pollfds->len == 1) { - return progress; - } - /* wait until next event */ ret = qemu_poll_ns((GPollFD *)ctx->pollfds->data, ctx->pollfds->len, diff --git a/aio-win32.c b/aio-win32.c index f9cfbb7..23f4e5b 100644 --- a/aio-win32.c +++ b/aio-win32.c @@ -161,11 +161,6 @@ bool aio_poll(AioContext *ctx, bool blocking) ctx->walking_handlers--; - /* early return if we only have the aio_notify() fd */ - if (count == 1) { - return progress; - } - /* wait until next event */ while (count > 0) { int ret; diff --git a/tests/test-aio.c b/tests/test-aio.c index c4fe0fc..592721e 100644 --- a/tests/test-aio.c +++ b/tests/test-aio.c @@ -195,7 +195,6 @@ static void test_bh_delete_from_cb(void) g_assert(data1.bh == NULL); g_assert(!aio_poll(ctx, false)); - g_assert(!aio_poll(ctx, true)); } static void test_bh_delete_from_cb_many(void) -- 1.8.3.1