util/aio-posix.c | 12 ++++++++---- 1 file changed, 8 insertions(+), 4 deletions(-)
With aio=thread, adaptive polling makes latency worse rather than
better, because it delays the execution of the ThreadPool's
completion bottom half.
event_notifier_poll() does run while polling, detecting that
a bottom half was scheduled by a worker thread, but because
ctx->notifier is explicitly ignored in run_poll_handlers_once(),
scheduling the BH does not count as making progress and
run_poll_handlers() keeps running. Fix this by recomputing
the deadline after *timeout could have changed.
With this change, ThreadPool still cannot participate in polling
but at least it does not suffer from extra latency.
Reported-by: Sergio Lopez <slp@redhat.com>
Cc: Stefan Hajnoczi <stefanha@gmail.com>
Cc: Kevin Wolf <kwolf@redhat.com>
Cc: qemu-block@nongnu.org
Signed-off-by: Paolo Bonzini <pbonzini@redhat.com>
Message-Id: <1553692145-86728-1-git-send-email-pbonzini@redhat.com>
Signed-off-by: Paolo Bonzini <pbonzini@redhat.com>
---
v1->v2: use qemu_soonest_timeout to handle timeout == -1
util/aio-posix.c | 12 ++++++++----
1 file changed, 8 insertions(+), 4 deletions(-)
diff --git a/util/aio-posix.c b/util/aio-posix.c
index 6fbfa7924f..db11021287 100644
--- a/util/aio-posix.c
+++ b/util/aio-posix.c
@@ -519,6 +519,10 @@ static bool run_poll_handlers_once(AioContext *ctx, int64_t *timeout)
if (!node->deleted && node->io_poll &&
aio_node_check(ctx, node->is_external) &&
node->io_poll(node->opaque)) {
+ /*
+ * Polling was successful, exit try_poll_mode immediately
+ * to adjust the next polling time.
+ */
*timeout = 0;
if (node->opaque != &ctx->notifier) {
progress = true;
@@ -558,8 +562,9 @@ static bool run_poll_handlers(AioContext *ctx, int64_t max_ns, int64_t *timeout)
do {
progress = run_poll_handlers_once(ctx, timeout);
elapsed_time = qemu_clock_get_ns(QEMU_CLOCK_REALTIME) - start_time;
- } while (!progress && elapsed_time < max_ns
- && !atomic_read(&ctx->poll_disable_cnt));
+ max_ns = qemu_soonest_timeout(*timeout, max_ns);
+ assert(!(max_ns && progress));
+ } while (elapsed_time < max_ns && !atomic_read(&ctx->poll_disable_cnt));
/* If time has passed with no successful polling, adjust *timeout to
* keep the same ending time.
@@ -585,8 +590,7 @@ static bool run_poll_handlers(AioContext *ctx, int64_t max_ns, int64_t *timeout)
*/
static bool try_poll_mode(AioContext *ctx, int64_t *timeout)
{
- /* See qemu_soonest_timeout() uint64_t hack */
- int64_t max_ns = MIN((uint64_t)*timeout, (uint64_t)ctx->poll_ns);
+ int64_t max_ns = qemu_soonest_timeout(*timeout, ctx->poll_ns);
if (max_ns && !atomic_read(&ctx->poll_disable_cnt)) {
poll_set_started(ctx, true);
--
2.21.0
Paolo Bonzini <pbonzini@redhat.com> writes: > With aio=thread, adaptive polling makes latency worse rather than > better, because it delays the execution of the ThreadPool's > completion bottom half. > > event_notifier_poll() does run while polling, detecting that > a bottom half was scheduled by a worker thread, but because > ctx->notifier is explicitly ignored in run_poll_handlers_once(), > scheduling the BH does not count as making progress and > run_poll_handlers() keeps running. Fix this by recomputing > the deadline after *timeout could have changed. > > With this change, ThreadPool still cannot participate in polling > but at least it does not suffer from extra latency. > > Reported-by: Sergio Lopez <slp@redhat.com> > Cc: Stefan Hajnoczi <stefanha@gmail.com> > Cc: Kevin Wolf <kwolf@redhat.com> > Cc: qemu-block@nongnu.org > Signed-off-by: Paolo Bonzini <pbonzini@redhat.com> > Message-Id: <1553692145-86728-1-git-send-email-pbonzini@redhat.com> > Signed-off-by: Paolo Bonzini <pbonzini@redhat.com> > --- > v1->v2: use qemu_soonest_timeout to handle timeout == -1 > util/aio-posix.c | 12 ++++++++---- > 1 file changed, 8 insertions(+), 4 deletions(-) > > diff --git a/util/aio-posix.c b/util/aio-posix.c > index 6fbfa7924f..db11021287 100644 > --- a/util/aio-posix.c > +++ b/util/aio-posix.c > @@ -519,6 +519,10 @@ static bool run_poll_handlers_once(AioContext *ctx, int64_t *timeout) > if (!node->deleted && node->io_poll && > aio_node_check(ctx, node->is_external) && > node->io_poll(node->opaque)) { > + /* > + * Polling was successful, exit try_poll_mode immediately > + * to adjust the next polling time. > + */ > *timeout = 0; > if (node->opaque != &ctx->notifier) { > progress = true; > @@ -558,8 +562,9 @@ static bool run_poll_handlers(AioContext *ctx, int64_t max_ns, int64_t *timeout) > do { > progress = run_poll_handlers_once(ctx, timeout); > elapsed_time = qemu_clock_get_ns(QEMU_CLOCK_REALTIME) - start_time; > - } while (!progress && elapsed_time < max_ns > - && !atomic_read(&ctx->poll_disable_cnt)); > + max_ns = qemu_soonest_timeout(*timeout, max_ns); > + assert(!(max_ns && progress)); > + } while (elapsed_time < max_ns && !atomic_read(&ctx->poll_disable_cnt)); > > /* If time has passed with no successful polling, adjust *timeout to > * keep the same ending time. > @@ -585,8 +590,7 @@ static bool run_poll_handlers(AioContext *ctx, int64_t max_ns, int64_t *timeout) > */ > static bool try_poll_mode(AioContext *ctx, int64_t *timeout) > { > - /* See qemu_soonest_timeout() uint64_t hack */ > - int64_t max_ns = MIN((uint64_t)*timeout, (uint64_t)ctx->poll_ns); > + int64_t max_ns = qemu_soonest_timeout(*timeout, ctx->poll_ns); > > if (max_ns && !atomic_read(&ctx->poll_disable_cnt)) { > poll_set_started(ctx, true); Thanks, this one does the trick. Reviewed-by: Sergio Lopez <slp@redhat.com>
On Tue, Apr 09, 2019 at 02:28:23PM +0200, Paolo Bonzini wrote: Why is this 4.0 material? It's not a 4.0 regression and tweaking the event loop is risky. I suggest waiting for 4.1. > With aio=thread, adaptive polling makes latency worse rather than > better, because it delays the execution of the ThreadPool's > completion bottom half. > > event_notifier_poll() does run while polling, detecting that > a bottom half was scheduled by a worker thread, but because > ctx->notifier is explicitly ignored in run_poll_handlers_once(), > scheduling the BH does not count as making progress and > run_poll_handlers() keeps running. Fix this by recomputing > the deadline after *timeout could have changed. > > With this change, ThreadPool still cannot participate in polling > but at least it does not suffer from extra latency. > > Reported-by: Sergio Lopez <slp@redhat.com> > Cc: Stefan Hajnoczi <stefanha@gmail.com> > Cc: Kevin Wolf <kwolf@redhat.com> > Cc: qemu-block@nongnu.org > Signed-off-by: Paolo Bonzini <pbonzini@redhat.com> > Message-Id: <1553692145-86728-1-git-send-email-pbonzini@redhat.com> > Signed-off-by: Paolo Bonzini <pbonzini@redhat.com> > --- > v1->v2: use qemu_soonest_timeout to handle timeout == -1 > util/aio-posix.c | 12 ++++++++---- > 1 file changed, 8 insertions(+), 4 deletions(-) Reviewed-by: Stefan Hajnoczi <stefanha@redhat.com>
On Tue, Apr 09, 2019 at 02:28:23PM +0200, Paolo Bonzini wrote: > With aio=thread, adaptive polling makes latency worse rather than > better, because it delays the execution of the ThreadPool's > completion bottom half. > > event_notifier_poll() does run while polling, detecting that > a bottom half was scheduled by a worker thread, but because > ctx->notifier is explicitly ignored in run_poll_handlers_once(), > scheduling the BH does not count as making progress and > run_poll_handlers() keeps running. Fix this by recomputing > the deadline after *timeout could have changed. > > With this change, ThreadPool still cannot participate in polling > but at least it does not suffer from extra latency. > > Reported-by: Sergio Lopez <slp@redhat.com> > Cc: Stefan Hajnoczi <stefanha@gmail.com> > Cc: Kevin Wolf <kwolf@redhat.com> > Cc: qemu-block@nongnu.org > Signed-off-by: Paolo Bonzini <pbonzini@redhat.com> > Message-Id: <1553692145-86728-1-git-send-email-pbonzini@redhat.com> > Signed-off-by: Paolo Bonzini <pbonzini@redhat.com> > --- > v1->v2: use qemu_soonest_timeout to handle timeout == -1 > util/aio-posix.c | 12 ++++++++---- > 1 file changed, 8 insertions(+), 4 deletions(-) Thanks, applied to my block-next tree: https://github.com/stefanha/qemu/commits/block-next Stefan
© 2016 - 2024 Red Hat, Inc.