| From: | Tom Lane <tgl(at)sss(dot)pgh(dot)pa(dot)us> |
|---|---|
| To: | Scott Marlowe <scott(dot)marlowe(at)gmail(dot)com> |
| Cc: | "Dusek, Bob" <rd185032(at)ncr(dot)com>, Bob Dusek <redusek(at)gmail(dot)com>, Kevin Grittner <Kevin(dot)Grittner(at)wicourts(dot)gov>, "pgsql-performance(at)postgresql(dot)org" <pgsql-performance(at)postgresql(dot)org> |
| Subject: | Re: performance config help |
| Date: | 2010-01-11 20:25:57 |
| Message-ID: | 18927.1263241557@sss.pgh.pa.us |
| Views: | Raw Message | Whole Thread | Download mbox | Resend email |
| Thread: | |
| Lists: | pgsql-performance |
Scott Marlowe <scott(dot)marlowe(at)gmail(dot)com> writes:
> On Mon, Jan 11, 2010 at 1:13 PM, Dusek, Bob <rd185032(at)ncr(dot)com> wrote:
>> I haven't been involved in any benchmarking of PG8 with fsync=off, but we certainly did it with PG 7.4. fsync=0ff, for our purposes, was MUCH faster.
> And many changes have been made since then to make fsyncing much
> faster. You may be grinding the valves on a 2009 Ferrari because
> pappy used to have to do it on his 1958 pickup truck here.
Perhaps more to the point, synchronous_commit can get most of the same
speedup with much less risk to your database. You really owe it to
yourself to redo that benchmarking with a recent PG release.
regards, tom lane
| From | Date | Subject | |
|---|---|---|---|
| Next Message | Kevin Grittner | 2010-01-11 20:55:50 | Re: performance config help |
| Previous Message | Tom Lane | 2010-01-11 20:18:40 | Re: [PERFORMANCE] work_mem vs temp files issue |