| From: | Tom Lane <tgl(at)sss(dot)pgh(dot)pa(dot)us> |
|---|---|
| To: | Josh Berkus <josh(at)agliodbs(dot)com> |
| Cc: | Simon Sadedin <pg_sicko(at)yahoo(dot)com>, pgsql-performance(at)postgresql(dot)org |
| Subject: | Re: poor cpu utilization on dual cpu box |
| Date: | 2003-10-22 17:02:56 |
| Message-ID: | 17145.1066842176@sss.pgh.pa.us |
| Views: | Raw Message | Whole Thread | Download mbox | Resend email |
| Thread: | |
| Lists: | pgsql-performance |
Josh Berkus <josh(at)agliodbs(dot)com> writes:
>> We are running with shared buffers large enough to hold the
>> entire database
> Which is bad. This is not what shared buffers are for. See:
> http://www.varlena.com/varlena/GeneralBits/Tidbits/perf.html
In fact, that may be the cause of the performance issue. The high
context-swap rate suggests heavy contention for shared-memory data
structures. The first explanation that occurs to me is that too much
time is being spent managing the buffer hashtable, causing that to
become a serialization bottleneck. Try setting shared_buffers to 10000
or so and see if it gets better.
regards, tom lane
| From | Date | Subject | |
|---|---|---|---|
| Next Message | Simon Sadedin | 2003-10-22 17:58:08 | Re: poor cpu utilization on dual cpu box |
| Previous Message | Josh Berkus | 2003-10-22 16:58:28 | Re: Low Insert/Update Performance |