| From: | Mark Kirkwood <markir(at)paradise(dot)net(dot)nz> |
|---|---|
| To: | Luke Lonergan <llonergan(at)greenplum(dot)com> |
| Cc: | stange(at)rentec(dot)com, Greg Stark <gsstark(at)mit(dot)edu>, Dave Cramer <pg(at)fastcrypt(dot)com>, Joshua Marsh <icub3d(at)gmail(dot)com>, pgsql-performance(at)postgresql(dot)org |
| Subject: | Re: Hardware/OS recommendations for large databases ( |
| Date: | 2005-11-24 09:26:44 |
| Message-ID: | 43858754.4020300@paradise.net.nz |
| Views: | Whole Thread | Raw Message | Download mbox | Resend email |
| Thread: | |
| Lists: | pgsql-performance |
Luke Lonergan wrote:
> Mark,
>
>
>>>Time: 197870.105 ms
>>
>>So 198 seconds is the uncached read time with count (Just for clarity,
>>did you clear the Pg and filesystem caches or unmount / remount the
>>filesystem?)
>
>
> Nope - the longer time is due to the "second write" known issue with
> Postgres - it writes the data to the table, but all of the pages are marked
> dirty? So, always on the first scan after loading they are written again.
> This is clear as you watch vmstat - the pattern on the first seq scan is
> half read / half write.
>
Ah - indeed - first access after a COPY no? I should have thought of
that, sorry!
| From | Date | Subject | |
|---|---|---|---|
| Next Message | Sven Geisler | 2005-11-24 10:38:47 | Re: High context switches occurring |
| Previous Message | Mark Kirkwood | 2005-11-24 09:24:35 | Re: Hardware/OS recommendations for large databases ( |