| From: | Bruce Momjian <bruce(at)momjian(dot)us> |
|---|---|
| To: | "Jonah H(dot) Harris" <jonah(dot)harris(at)gmail(dot)com> |
| Cc: | Hannu Krosing <hannu(at)2ndquadrant(dot)com>, Tom Lane <tgl(at)sss(dot)pgh(dot)pa(dot)us>, Greg Stark <greg(dot)stark(at)enterprisedb(dot)com>, Greg Smith <gsmith(at)gregsmith(dot)com>, Julius Stroffek <Julius(dot)Stroffek(at)sun(dot)com>, pgsql-hackers(at)postgresql(dot)org, Dano Vojtek <danielkov(at)gmail(dot)com> |
| Subject: | Re: Multi CPU Queries - Feedback and/or suggestions wanted! |
| Date: | 2008-10-24 14:18:57 |
| Message-ID: | 200810241418.m9OEIvs02737@momjian.us |
| Views: | Raw Message | Whole Thread | Download mbox | Resend email |
| Thread: | |
| Lists: | pgsql-hackers |
Jonah H. Harris wrote:
> On Fri, Oct 24, 2008 at 7:59 AM, Hannu Krosing <hannu(at)2ndquadrant(dot)com> wrote:
> > On Fri, 2008-10-24 at 00:52 -0400, Jonah H. Harris wrote:
> >> While we could build an
> >> abstract prefetch interface and simply use fadvise for it now (rather
> >> than OS-specific code), I don't see an easy win in any case.
> >
> > When building an abstract interface, always use at least two
> > implementations (I guess that would be fadvise on linux and AIO on
> > solaris in this case). You are much more likely to get the interface
> > right this way.
>
> I agree, I just wasn't sure as to whether Greg's patch supported both methods.
It does not, and probably will not for the near future; we can only
hope Solaris suports posix_fadvise() at some point.
--
Bruce Momjian <bruce(at)momjian(dot)us> http://momjian.us
EnterpriseDB http://enterprisedb.com
+ If your life is a hard drive, Christ can be your backup. +
| From | Date | Subject | |
|---|---|---|---|
| Next Message | Stefan Kaltenbrunner | 2008-10-24 14:43:31 | Re: tribble.postgresql.org maintenance/hardware replacement |
| Previous Message | Jonah H. Harris | 2008-10-24 13:35:19 | Re: Multi CPU Queries - Feedback and/or suggestions wanted! |