pg.ddx.io  pgsql-performance@postgresql.org mailing list archive  
help / color / mirror / Atom feed
From: Gnanakumar <gnanam@zoniac.com>
To: 'Tomas Vondra' <tv@fuzzy.cz>
To: 'Vitalii Tymchyshyn' <tivv00@gmail.com>
Cc: pgsql-performance@postgresql.org
Subject: Re: Write workload is causing severe slowdown in Production
Date: Thu, 22 Mar 2012 16:02:00 +0530
Message-ID: <008e01cd0817$06418680$12c49380$@com> (raw)
In-Reply-To: <dc1f59dfd626334d6f37d5a6ffb97bb9.squirrel@sq.gransy.com>
References: <006301cd07fd$358ebe40$a0ac3ac0$@com>
	<4F6AF3FE.30407@gmail.com>
	<dc1f59dfd626334d6f37d5a6ffb97bb9.squirrel@sq.gransy.com>

> There's a checkpoint_warning option. Set it to 3600 and you should get
> messages in the log. Correlate those to the issues (do they happen at the
> same time?).
After setting "checkpoint_warning" to 3600, can you explain on how do I correlate with the messages?

> If you can, install iotop and watch the processes that cause the I/O.
I tried installing "iotop", but it failed to run because it requires Linux >= 2.6.20.  Our CentOS5.2 is 2.6.18-8.

> What we need is more details about your setup, especially
>   - checkpoint_segments
>   - checkpoint_timeout
>   - shared_buffers
# - Memory -
shared_buffers=1536MB

# - Planner Cost Constants -
effective_cache_size = 4GB

# - Checkpoints -
checkpoint_segments=32
checkpoint_timeout=5min
checkpoint_warning=270s

# - Background writer -
bgwriter_delay = 200ms
bgwriter_lru_percent = 1.0
bgwriter_lru_maxpages = 5
bgwriter_all_percent = 0.333
bgwriter_all_maxpages = 5

> also it'd be nice to have samples from the vmstat/iostat and messages from
> the log.
Unfortunately, I don't have "exact" logs when the problem actually happened





view thread (16+ messages)  latest in thread

Message-ID: <008e01cd0817$06418680$12c49380$@com>
Permalink:  ../008e01cd0817$06418680$12c49380$@com/
Also on:    postgresql.org/message-id/008e01cd0817$06418680$12c49380$@com

 · 

reply

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: gnanam@zoniac.com, tv@fuzzy.cz, tivv00@gmail.com
  Subject: Re: Write workload is causing severe slowdown in Production
  In-Reply-To: <008e01cd0817$06418680$12c49380$@com>

* 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