From: | Tom Lane <tgl(at)sss(dot)pgh(dot)pa(dot)us> |
---|---|
To: | Javier Reyes <c(dot)javier(dot)reyes(dot)e(at)gmail(dot)com> |
Cc: | pgsql-admin(at)postgresql(dot)org |
Subject: | Re: Option shared_buffers in PostgreSQL |
Date: | 2011-05-01 16:17:10 |
Message-ID: | 18735.1304266630@sss.pgh.pa.us |
Views: | Raw Message | Whole Thread | Download mbox | Resend email |
Thread: | |
Lists: | pgsql-admin |
Javier Reyes <c(dot)javier(dot)reyes(dot)e(at)gmail(dot)com> writes:
> I have a server with 4GB of RAM and PostgreSQL 9.0.3 on Centos 5. I'm using
> pgbench and pgbench-tools to measure performance, using two pgbench-tools
> queries: select and tpc-b.
> With default settings of postgresql.conf and select query, I get the
> following results:
> Scale: 1, 10, 100, 1000.
> Transactions per second: 10000, 8800, 7500, 100.
These numbers look like complete junk from here. I suspect you were
using a number-of-transactions parameter that's too small to give stable
answers. If you don't have the value set high enough so that each
pgbench run lasts at least a couple of minutes, I wouldn't put any
credence in the results. See also the other "good practices" mentioned
at the bottom of the pgbench documentation page.
regards, tom lane
From | Date | Subject | |
---|---|---|---|
Next Message | Greg Smith | 2011-05-02 04:01:59 | Re: Re: best practice for moving millions of rows to child table when setting up partitioning? |
Previous Message | Lou Picciano | 2011-05-01 14:11:06 | Re: Option shared_buffers in PostgreSQL |