Hi!
It's been almost 2 weeks since I've installed the patch and there were no
segfaults since then. It seems that the problem is fixed now. Thank you!
2018-03-19 23:16 GMT+03:00 William Dauchy <w.dau...@criteo.com>:
> On Mon, Mar 19, 2018 at 08:41:16PM +0100, Willy Tarreau wrote:
> > For me, "experimental" simply means "we did our best to ensure it works
> > but we're realist and know that bug-free doesn't exist, so a risk remains
> > that a bug will be hard enough to fix so as to force you to disable the
> > feature for the time it takes to fix it". This issue between threads and
> > queue is one such example. Some of the bugs faced on H2 requiring some
> > heavy changes were other examples. But overall we know these features
> > are highly demanded and are committed to make them work fine :-)
>
> you are right, we probably magnified in our head the different issues we
> had related to this.
>
> > I'm still interested in knowing if you find crazy last percentile values.
> > We've had that a very long time ago (version 1.3 or so) when some pending
> > conns were accidently skipped, so I know how queues can amplify small
> > issues. The only real risk here in my opinion is that the sync point was
> > only used for health checks till now so it was running at low loads and
> > if it had any issue, it would likely have remained unnoticed. But the
> code
> > is small enough to be audited, and after re-reading it this afternoon I
> > found it fine.
>
> will do, migrating some low latency applications is more mid/longterm but
> will see how the first results during the preparation tests.
>
> > If you want to run a quick test with epoll, just apply this dirty hack :
> >
> > diff --git a/src/ev_epoll.c b/src/ev_epoll.c
> > index b98ca8c..7bafd16 100644
> > --- a/src/ev_epoll.c
> > +++ b/src/ev_epoll.c
> > @@ -116,7 +116,9 @@ REGPRM2 static void _do_poll(struct poller *p, int
> exp)
> > fd_nbupdt = 0;
> >
> > /* compute the epoll_wait() timeout */
> > - if (!exp)
> > + if (1)
> > + wait_time = 0;
> > + else if (!exp)
> > wait_time = MAX_DELAY_MS;
> > else if (tick_is_expired(exp, now_ms)) {
> > activity[tid].poll_exp++;
> >
> > Please note that as this, it's suboptimal because it will increase the
> > contention on other places, causing the perfomance to be a bit lower in
> > certain situations. I do have some experimental code to loop on epoll
> > instead but it's not completely stable yet. We an exchange on this later
> > if you want. But feel free to apply this to your latency tests.
>
> thanks a lot, will give a try!
>
> --
> William
>
