Re: swarm of processes in BIND state?

Hi

2016-05-28 7:19 GMT+02:00 hubert depesz lubaczewski <depesz(at)depesz(dot)com>:

> hi,
> we have following situation:
> pg 9.3.11 on ubuntu.
> we have master and slave.
> the db is large-ish, but we're removing *most* of its data from all
> across the tables, and lots of tables too.
>
> while we're doing it, sometimes, we get LOTS of processes, but only on
> slave, never on master, that spend long time in BIND state. same queries
> ran on master run without any problem, and are fast.
>
> any clues on where to start diagnosing it?
>
> So far we've:
> 1. ruled out IO problems (enough io both in terms of bandwidth and iops)
> 2. ruled out memory (plenty)
> 3. vacuumed all tables, including system ones, with analyze
> 4. did pg_repack on most of the tables to remove bloat.
>
> we are in process of doing the same operation to series of servers, so
> i'm not sure if the criteria on all of them are the same, but perhaps
> you can think of something we didn't?
>

It is looking like spinlock issue.

try to look there by "perf top"

Pavel

>
> depesz
>
> --
> The best thing about modern society is how easy it is to avoid contact
> with it.
>
> http://depesz.com/
>
>
> --
> Sent via pgsql-general mailing list (pgsql-general(at)postgresql(dot)org)
> To make changes to your subscription:
> http://www.postgresql.org/mailpref/pgsql-general
>