| From: | Greg Stark <gsstark(at)mit(dot)edu> |
|---|---|
| To: | "Magnus Hagander" <mha(at)sollentuna(dot)net> |
| Cc: | "Greg Stark" <gsstark(at)mit(dot)edu>, "David Brown" <time(at)bigpond(dot)net(dot)au>, "Gregory Stark" <pgsql-performance(at)postgresql(dot)org> |
| Subject: | Re: cpu_tuple_cost |
| Date: | 2005-03-16 15:42:52 |
| Message-ID: | 874qfblhqb.fsf@stark.xeocode.com |
| Views: | Raw Message | Whole Thread | Download mbox | Resend email |
| Thread: | |
| Lists: | pgsql-performance |
"Magnus Hagander" <mha(at)sollentuna(dot)net> writes:
> What about the cache memory on the disk? Even IDE disks have some 8Mb
> cache today, which makes a lot of difference for fairly short scans.
> Even if it's just read cache. That'll bring the speed of random access
> down to a 1=1 relationship with sequential access, assuming all fits in
> the cache.
8MB cache is really insignificant compared to the hundreds or thousands of
megabytes the OS would be using to cache. You could just add the 8MB to your
effective_cache_size (except it's not really 100% effective since it would
contain some of the same blocks as the OS cache).
--
greg
| From | Date | Subject | |
|---|---|---|---|
| Next Message | Daniel Crisan | 2005-03-16 16:08:59 | multi-column index |
| Previous Message | David Gagnon | 2005-03-16 15:13:42 | Re: Performance problem on delete from for 10k rows. May |