| From: | "Zeugswetter Andreas ADI SD" <ZeugswetterA(at)spardat(dot)at> |
|---|---|
| To: | "Tom Lane" <tgl(at)sss(dot)pgh(dot)pa(dot)us>, "Jim C(dot) Nasby" <jim(at)nasby(dot)net> |
| Cc: | "Heikki Linnakangas" <heikki(at)enterprisedb(dot)com>, "Bruce Momjian" <bruce(at)momjian(dot)us>, "ITAGAKI Takahiro" <itagaki(dot)takahiro(at)oss(dot)ntt(dot)co(dot)jp>, "PostgreSQL-development" <pgsql-hackers(at)postgresql(dot)org> |
| Subject: | Re: Load distributed checkpoint |
| Date: | 2007-01-03 11:18:42 |
| Message-ID: | E1539E0ED7043848906A8FF995BDA57901A355A0@m0143.s-mxs.net |
| Views: | Raw Message | Whole Thread | Download mbox | Resend email |
| Thread: | |
| Lists: | pgsql-hackers pgsql-patches |
> > I believe there's something similar for OS X as well. The question
is:
> > would it be better to do that, or to just delay calling fsync until
the
> > OS has had a chance to write things out.
>
> A delay is not going to help unless you can suppress additional writes
> to the file, which I don't think you can unless there's very little
> going on in the database --- dirty buffers have to get written to make
> room for other pages, checkpoint in progress or no.
But checkpoint first writes all dirty pages, so we have more than
average
pages that can be replaced without a write. Thus we have a window where
we can wait until dirty pages have to be replaced again. Since the
bgwriter
is sleeping until fsync, only pages that have to be replaced will be
written.
Question is, how do we time that window.
Andreas
| From | Date | Subject | |
|---|---|---|---|
| Next Message | Zeugswetter Andreas ADI SD | 2007-01-03 11:56:11 | Re: effective_cache_size vs units |
| Previous Message | Mark Cave-Ayland | 2007-01-03 09:15:41 | Re: WITH support |
| From | Date | Subject | |
|---|---|---|---|
| Next Message | Simon Riggs | 2007-01-03 15:35:44 | Re: [HACKERS] Patch to log usage of temporary files |
| Previous Message | Peter Eisentraut | 2007-01-03 08:52:29 | Re: xlog directory at initdb time |