Re: BUG #12071: Stat collector went crasy (50MB/s constant writes)

From: Maxim Boguk <maxim(dot)boguk(at)gmail(dot)com>
To: Alvaro Herrera <alvherre(at)2ndquadrant(dot)com>
Cc: pgsql-bugs <pgsql-bugs(at)postgresql(dot)org>
Subject: Re: BUG #12071: Stat collector went crasy (50MB/s constant writes)
Date: 2014-11-26 14:02:05
Message-ID: CAK-MWwSnRjk-q_SNu+oOYwjU9fik5uXOez9v-v4Ua40aFjUNRA@mail.gmail.com
Views: Raw Message | Whole Thread | Download mbox | Resend email
Thread:
Lists: pgsql-bugs pgsql-hackers

On Wed, Nov 26, 2014 at 4:35 PM, Alvaro Herrera <alvherre(at)2ndquadrant(dot)com>
wrote:

> Maxim Boguk wrote:
>
> > After careful examination of strace output I found one strange thing:
> > constant flow of:
> > 16:22:33.202523 read(3, 0x7fff4148a5b0, 16) = -1 EAGAIN (Resource
> > temporarily unavailable)
>
> Uh. What is on fd 3? (check /proc). If it's the stat socket, maybe
> you're having network issues with localhost UDP connections or
> something.
>

It's pipe to itself:
root(at)db13:~# ls -la /proc/26933/fd/ | grep 1343367616
lr-x------ 1 postgres postgres 64 Nov 26 16:54 3 -> pipe:[1343367616]
l-wx------ 1 postgres postgres 64 Nov 26 16:54 6 -> pipe:[1343367616]

--
Maxim Boguk
Senior Postgresql DBA
http://www.postgresql-consulting.ru/ <http://www.postgresql-consulting.com/>

In response to

Browse pgsql-bugs by date

  From Date Subject
Next Message henrik-postgres 2014-11-26 14:19:24 BUG #12072: init script creates pid file with wrong owner
Previous Message Alvaro Herrera 2014-11-26 13:35:36 Re: BUG #12071: Stat collector went crasy (50MB/s constant writes)

Browse pgsql-hackers by date

  From Date Subject
Next Message Andres Freund 2014-11-26 14:03:36 Re: superuser() shortcuts
Previous Message Stephen Frost 2014-11-26 13:37:46 Re: Follow up to irc on CREATE INDEX vs. maintenance_work_mem on 9.3