| From: | Pierre-Frédéric Caillaud <lists(at)boutiquenumerique(dot)com> |
|---|---|
| To: | pgsql-performance(at)postgresql(dot)org |
| Subject: | Re: scalability issues on win32 |
| Date: | 2004-11-22 23:15:26 |
| Message-ID: | opshv2v01gcq72hf@musicbox |
| Views: | Whole Thread | Raw Message | Download mbox | Resend email |
| Thread: | |
| Lists: | pgsql-hackers-win32 pgsql-performance |
> Test platform:
> Pentium 4 3.06 GHz/HT
> 10k SATA Raptor
> 1Gb memory
> Windows XP Pro SP2/Redhat Fedora 3 (64 bit results coming soon)
Could you please add information about...
- filesystems ?
- windows configured as "network server" or as "desktop box" ?
- virtual memory
In my experience you MUST deactivate virtual memory on a Windows box to
avoid catastrophic competition between virtual memory and disk cache
- respective pgsql configurations (buffers...) identical ?
- explain analyze for the two, identical ?
- client on same machine or via network (100Mb ? 1G ?)
- size of the data set involved in query
- first query time after boot (with nothing in the cache), and times for
the next disk-cached runs ?
- are the N users doing the same query or exercising different parts of
the dataset ?
You don't do any writes in your test do you ? Just big SELECTs ?
| From | Date | Subject | |
|---|---|---|---|
| Next Message | Bruce Momjian | 2004-11-23 02:26:05 | Re: scalability issues on win32 |
| Previous Message | Claudio Natoli | 2004-11-22 23:01:11 | Re: Beta5 libpq Build broken with MS .NET 2 |
| From | Date | Subject | |
|---|---|---|---|
| Next Message | Alexandre Leclerc | 2004-11-22 23:26:00 | Re: Data type to use for primary key |
| Previous Message | Pierre-Frédéric Caillaud | 2004-11-22 23:06:13 | Re: Data type to use for primary key |