From: Jakub Ouhrabka <kuba@comgate.cz>
To: Tom Lane <tgl@sss.pgh.pa.us>
Cc: pgsql-performance@postgresql.org
Subject: Re: Linux/PostgreSQL scalability issue - problem with 8 cores
Date: Fri, 11 Jan 2008 12:11:36 +0100
Message-ID: <47874EE8.2050406@comgate.cz> (raw)
In-Reply-To: <10713.1199813111@sss.pgh.pa.us>
References: <flii57$748$1@news.hub.org>
<7083.1199379570@sss.pgh.pa.us>
<477D1D59.7050002@comgate.cz>
<4782063C.7070105@comgate.cz>
<26502.1199745090@sss.pgh.pa.us>
<4782AB4D.8010009@comgate.cz>
<27655.1199750492@sss.pgh.pa.us>
<47836A4C.5080707@comgate.cz>
<10713.1199813111@sss.pgh.pa.us>
Hi Tom,
> I doubt we'd risk destabilizing 8.3 at this point, for a problem that
> affects so few people; let alone back-patching into 8.2.
understand.
> OK, that confirms the theory that it's sinval-queue contention.
We'we tried hard to identify what's the cause of filling sinval-queue.
We went through query logs as well as function bodies stored in the
database. We were not able to find any DDL, temp table creations etc.
We did following experiment: stop one of our clients, so there started
to be queue of events (aka rows in db) for it to process. Then we
started the client again, it started processing the queue - that means
calling simple selects, updates and complex plpgsql function(s). And at
this moment, the spike started even it shouldn't start to meet usual
periodicity. It's consistent. We are pretty sure that this client is not
doing any DDL...
What should we look for to find the cause?
Thanks for any hints,
Kuba
Reply instructions:
You may reply publicly to this message via plain-text email
using any one of the following methods:
* Reply to all the recipients using the --to and --cc options:
reply via email
To: pgsql-performance@postgresql.org
Cc: kuba@comgate.cz, tgl@sss.pgh.pa.us
Subject: Re: Linux/PostgreSQL scalability issue - problem with 8 cores
In-Reply-To: <47874EE8.2050406@comgate.cz>
* Save the following mbox file, import it into your mail client,
and reply-to-all from there: mbox
This inbox is served by DDX for PostgreSQL; see mirroring instructions
for how to clone and mirror all data and code used for this inbox