Re: [PERFORM] 9.4 -> 9.5 regression with queries through pgbouncer on RHEL 6

On 2016-06-13 21:58:30 +0300, Vladimir Borodin wrote:
>
> > 13 июня 2016 г., в 0:51, Andres Freund <andres(at)anarazel(dot)de> написал(а):
> >
> > Hi Vladimir,
> >
> > Thanks for these reports.
> >
> > On 2016-06-13 00:42:19 +0300, Vladimir Borodin wrote:
> >> perf report -g -i pg9?_all.data >/tmp/pg9?_perf_report.txt
> >
> > Any chance you could redo the reports with --no-children --call-graph=fractal
> > added? The mode that includes child overheads unfortunately makes the
> > output hard to interpet/compare.
>
> Of course. Not sure if that is important but I upgraded perf for that (because --no-children option was introduced in ~3.16), so perf record and perf report were done with different perf versions.
>
>
>
> Also I’ve done the same test on same host (RHEL 6) but with 4.6 kernel/perf and writing perf data to /dev/shm for not loosing events. Perf report output is also attached but important thing is that the regression is not so significant:
>
> root(at)pgload05g ~ # uname -r
> 4.6.0-1.el6.elrepo.x86_64
> root(at)pgload05g ~ # cat /proc/sys/kernel/sched_autogroup_enabled
> 1
> root(at)pgload05g ~ # /tmp/run.sh
> RHEL 6 9.4 71634 0.893
> RHEL 6 9.5 54005 1.185
> RHEL 6 9.6 65550 0.976
> root(at)pgload05g ~ # echo 0 >/proc/sys/kernel/sched_autogroup_enabled
> root(at)pgload05g ~ # /tmp/run.sh
> RHEL 6 9.4 73041 0.876
> RHEL 6 9.5 60105 1.065
> RHEL 6 9.6 67984 0.941
> root(at)pgload05g ~ #

Hm. Have you measured how large the slowdown is if you connect via tcp
to pgbouncer, but have pgbouncer connect to postgres via unix sockets?

Andres