From: | Scott Marlowe <scott(dot)marlowe(at)gmail(dot)com> |
---|---|
To: | Thomas Pöhler <tp(at)turtle-entertainment(dot)de> |
Cc: | pgsql-performance(at)postgresql(dot)org, Felix Feinhals <ff(at)turtle-entertainment(dot)de>, Verteiler_A-Team <a-team(at)turtle-entertainment(dot)de>, Björn Metzdorf <bm(at)turtle-entertainment(dot)de> |
Subject: | Re: high user cpu, massive SELECTs, no io waiting problem |
Date: | 2011-02-15 18:01:53 |
Message-ID: | AANLkTikLYb1+4-ZUYvDV3uzQ3TB1qFkGVv1FH=eSiRxZ@mail.gmail.com |
Views: | Raw Message | Whole Thread | Download mbox | Resend email |
Thread: | |
Lists: | pgsql-performance |
On Tue, Feb 15, 2011 at 10:19 AM, Thomas Pöhler
<tp(at)turtle-entertainment(dot)de> wrote:
> Since a few weeks we have really strange peaks on this system. User CPU is
> increasing up to 100% and we have lots of SELECTs running.
Are you using pooling of some kind, or do you have LOTS of connections?
> There is no iowait at this time, only high user cpu and we don’t know where
> this is coming from. It seems like this is only happening under certain
> circumstances.
run htop and look for red. if youi've got lots of red bar on each CPU
but no io wait then it's waiting for memory access. Most of these
multi-core machines will be memory read / write speed bound. Pooling
will help relieve some of that memory bandwidth load, but might not be
enough to eliminate it.
From | Date | Subject | |
---|---|---|---|
Next Message | Kevin Grittner | 2011-02-15 18:06:56 | Re: high user cpu, massive SELECTs, no io waiting problem |
Previous Message | Kevin Grittner | 2011-02-15 17:51:24 | Re: Checkpointing question |