Skip site navigation (1) Skip section navigation (2)

Re: Write workload is causing severe slowdown in Production

From: Mark Kirkwood <mark(dot)kirkwood(at)catalyst(dot)net(dot)nz>
To: pgsql-performance(at)postgresql(dot)org
Subject: Re: Write workload is causing severe slowdown in Production
Date: 2012-03-23 00:08:53
Message-ID: (view raw, whole thread or download thread mbox)
Lists: pgsql-performance
On 22/03/12 20:27, Gnanakumar wrote:
> The issue that we're facing currently in our Production server is, whenever
> this "newly" developed Java program is started/run, then immediately the
> entire web application becomes very slow in response.  At this time, I could
> also see from the output of " iostat -tx" that "%util" is even crossing more
> than 80%.  So, what I could infer here based on my knowledge is, this is
> creating heavy IO traffic because of write operation.  Since it was entirely
> slowing down web application, we've temporarily stopped running this
> standalone application.

I'd recommend taking a hard took at what the Java app is doing. You 
might be able to get useful data by adding:

log_min_duration_statement = 10000 # queries taking longer than 10 sec

into your postgresql.conf. I'd *guess* that locking is not the issue - 
as that is unlikely to cause high IO load (altho checking for lots of 
locks with granted= f in pg_locks might be worthwhile just to rule it out).

You could also try running the Java app in one of your development 
environments to see if you can provoke high load behaviour in a more 
easily studied environment.



In response to

pgsql-performance by date

Next:From: Stephen FrostDate: 2012-03-23 00:47:49
Subject: Re: Sudden Query slowdown on our Postgresql Server
Previous:From: Sebastian MelchiorDate: 2012-03-22 22:52:49
Subject: Sudden Query slowdown on our Postgresql Server

Privacy Policy | About PostgreSQL
Copyright © 1996-2017 The PostgreSQL Global Development Group