From e4346192f1c2e1683a807b46efac47ef0cf9b545 Mon Sep 17 00:00:00 2001 From: Stefan Hajnoczi Date: Thu, 5 Mar 2020 17:08:00 +0000 Subject: [PATCH] aio-posix: completely stop polling when disabled One iteration of polling is always performed even when polling is disabled. This is done because: 1. Userspace polling is cheaper than making a syscall. We might get lucky. 2. We must poll once more after polling has stopped in case an event occurred while stopping polling. However, there are downsides: 1. Polling becomes a bottleneck when the number of event sources is very high. It's more efficient to monitor fds in that case. 2. A high-frequency polling event source can starve non-polling event sources because ppoll(2)/epoll(7) is never invoked. This patch removes the forced polling iteration so that poll_ns=0 really means no polling. IOPS increases from 10k to 60k when the guest has 100 virtio-blk-pci,num-queues=32 devices and 1 virtio-blk-pci,num-queues=1 device because the large number of event sources being polled slows down the event loop. Signed-off-by: Stefan Hajnoczi Link: https://lore.kernel.org/r/20200305170806.1313245-2-stefanha@redhat.com Message-Id: <20200305170806.1313245-2-stefanha@redhat.com> --- util/aio-posix.c | 22 +++++++++++++++------- 1 file changed, 15 insertions(+), 7 deletions(-) diff --git a/util/aio-posix.c b/util/aio-posix.c index b339aab12c..65964a2597 100644 --- a/util/aio-posix.c +++ b/util/aio-posix.c @@ -361,12 +361,13 @@ void aio_set_event_notifier_poll(AioContext *ctx, (IOHandler *)io_poll_end); } -static void poll_set_started(AioContext *ctx, bool started) +static bool poll_set_started(AioContext *ctx, bool started) { AioHandler *node; + bool progress = false; if (started == ctx->poll_started) { - return; + return false; } ctx->poll_started = started; @@ -388,8 +389,15 @@ static void poll_set_started(AioContext *ctx, bool started) if (fn) { fn(node->opaque); } + + /* Poll one last time in case ->io_poll_end() raced with the event */ + if (!started) { + progress = node->io_poll(node->opaque) || progress; + } } qemu_lockcnt_dec(&ctx->list_lock); + + return progress; } @@ -670,12 +678,12 @@ static bool try_poll_mode(AioContext *ctx, int64_t *timeout) } } - poll_set_started(ctx, false); + if (poll_set_started(ctx, false)) { + *timeout = 0; + return true; + } - /* Even if we don't run busy polling, try polling once in case it can make - * progress and the caller will be able to avoid ppoll(2)/epoll_wait(2). - */ - return run_poll_handlers_once(ctx, timeout); + return false; } bool aio_poll(AioContext *ctx, bool blocking)