aio-posix: split poll check from ready handler

Adaptive polling measures the execution time of the polling check plus
handlers called when a polled event becomes ready. Handlers can take a
significant amount of time, making it look like polling was running for
a long time when in fact the event handler was running for a long time.

For example, on Linux the io_submit(2) syscall invoked when a virtio-blk
device's virtqueue becomes ready can take 10s of microseconds. This
can exceed the default polling interval (32 microseconds) and cause
adaptive polling to stop polling.

By excluding the handler's execution time from the polling check we make
the adaptive polling calculation more accurate. As a result, the event
loop now stays in polling mode where previously it would have fallen
back to file descriptor monitoring.

The following data was collected with virtio-blk num-queues=2
event_idx=off using an IOThread. Before:

168k IOPS, IOThread syscalls:

  9837.115 ( 0.020 ms): IO iothread1/620155 io_submit(ctx_id: 140512552468480, nr: 16, iocbpp: 0x7fcb9f937db0)    = 16
  9837.158 ( 0.002 ms): IO iothread1/620155 write(fd: 103, buf: 0x556a2ef71b88, count: 8)                         = 8
  9837.161 ( 0.001 ms): IO iothread1/620155 write(fd: 104, buf: 0x556a2ef71b88, count: 8)                         = 8
  9837.163 ( 0.001 ms): IO iothread1/620155 ppoll(ufds: 0x7fcb90002800, nfds: 4, tsp: 0x7fcb9f1342d0, sigsetsize: 8) = 3
  9837.164 ( 0.001 ms): IO iothread1/620155 read(fd: 107, buf: 0x7fcb9f939cc0, count: 512)                        = 8
  9837.174 ( 0.001 ms): IO iothread1/620155 read(fd: 105, buf: 0x7fcb9f939cc0, count: 512)                        = 8
  9837.176 ( 0.001 ms): IO iothread1/620155 read(fd: 106, buf: 0x7fcb9f939cc0, count: 512)                        = 8
  9837.209 ( 0.035 ms): IO iothread1/620155 io_submit(ctx_id: 140512552468480, nr: 32, iocbpp: 0x7fca7d0cebe0)    = 32

174k IOPS (+3.6%), IOThread syscalls:

  9809.566 ( 0.036 ms): IO iothread1/623061 io_submit(ctx_id: 140539805028352, nr: 32, iocbpp: 0x7fd0cdd62be0)    = 32
  9809.625 ( 0.001 ms): IO iothread1/623061 write(fd: 103, buf: 0x5647cfba5f58, count: 8)                         = 8
  9809.627 ( 0.002 ms): IO iothread1/623061 write(fd: 104, buf: 0x5647cfba5f58, count: 8)                         = 8
  9809.663 ( 0.036 ms): IO iothread1/623061 io_submit(ctx_id: 140539805028352, nr: 32, iocbpp: 0x7fd0d0388b50)    = 32

Notice that ppoll(2) and eventfd read(2) syscalls are eliminated because
the IOThread stays in polling mode instead of falling back to file
descriptor monitoring.

As usual, polling is not implemented on Windows so this patch ignores
the new io_poll_read() callback in aio-win32.c.

Signed-off-by: Stefan Hajnoczi <stefanha@redhat.com>
Reviewed-by: Stefano Garzarella <sgarzare@redhat.com>
Message-id: 20211207132336.36627-2-stefanha@redhat.com

[Fixed up aio_set_event_notifier() calls in
tests/unit/test-fdmon-epoll.c added after this series was queued.
--Stefan]

Signed-off-by: Stefan Hajnoczi <stefanha@redhat.com>

1 files changed, 11 insertions, 8 deletions

diff --git a/block/io_uring.c b/block/io_uring.c
index dfa475cc87..782afdb433 100644
--- a/block/io_uring.c
+++ b/block/io_uring.c
@@ -292,12 +292,14 @@ static bool qemu_luring_poll_cb(void *opaque)
 {
     LuringState *s = opaque;
 
-    if (io_uring_cq_ready(&s->ring)) {
-        luring_process_completions_and_submit(s);
-        return true;
-    }
+    return io_uring_cq_ready(&s->ring);
+}
+
+static void qemu_luring_poll_ready(void *opaque)
+{
+    LuringState *s = opaque;
 
-    return false;
+    luring_process_completions_and_submit(s);
 }
 
 static void ioq_init(LuringQueue *io_q)
@@ -402,8 +404,8 @@ int coroutine_fn luring_co_submit(BlockDriverState *bs, LuringState *s, int fd,
 
 void luring_detach_aio_context(LuringState *s, AioContext *old_context)
 {
-    aio_set_fd_handler(old_context, s->ring.ring_fd, false, NULL, NULL, NULL,
-                       s);
+    aio_set_fd_handler(old_context, s->ring.ring_fd, false,
+                       NULL, NULL, NULL, NULL, s);
     qemu_bh_delete(s->completion_bh);
     s->aio_context = NULL;
 }
@@ -413,7 +415,8 @@ void luring_attach_aio_context(LuringState *s, AioContext *new_context)
     s->aio_context = new_context;
     s->completion_bh = aio_bh_new(new_context, qemu_luring_completion_bh, s);
     aio_set_fd_handler(s->aio_context, s->ring.ring_fd, false,
-                       qemu_luring_completion_cb, NULL, qemu_luring_poll_cb, s);
+                       qemu_luring_completion_cb, NULL,
+                       qemu_luring_poll_cb, qemu_luring_poll_ready, s);
 }
 
 LuringState *luring_init(Error **errp)