| From: | "scott(dot)marlowe" <scott(dot)marlowe(at)ihs(dot)com> |
|---|---|
| To: | <matt(at)ymogen(dot)net> |
| Cc: | Leon Out <leon-lists(at)comvision(dot)com>, <pgsql-performance(at)postgresql(dot)org> |
| Subject: | Re: Disappointing performance in db migrated from MS SQL |
| Date: | 2004-02-17 15:17:44 |
| Message-ID: | Pine.LNX.4.33.0402170816001.30371-100000@css120.ihs.com |
| Views: | Whole Thread | Raw Message | Download mbox | Resend email |
| Thread: | |
| Lists: | pgsql-performance |
On Fri, 13 Feb 2004 matt(at)ymogen(dot)net wrote:
> > Josh, the disks in the new system should be substantially faster than
> > the old. Both are Ultra160 SCSI RAID 5 arrays, but the new system has
> > 15k RPM disks, as opposed to the 10k RPM disks in the old system.
>
> Spindle speed does not correlate with 'throughput' in any easy way. What
> controllers are you using for these disks?
This is doubly so with a good RAID card with battery backed cache.
I'd bet that 10k rpm drives on a cached array card will beat an otherwise
equal setup with 15k rpm disks and no cache. I know that losing the cache
slows my system down to a crawl (i.e. set it to write thru instead of
write back.) comparitively speaking.
| From | Date | Subject | |
|---|---|---|---|
| Next Message | Todd Fulton | 2004-02-17 17:06:48 | long running query running too long |
| Previous Message | Tom Lane | 2004-02-17 15:02:37 | Re: Slow response of PostgreSQL |