| From: | "Zeugswetter Andreas ADI SD" <ZeugswetterA(at)spardat(dot)at> |
|---|---|
| To: | "Jeff Davis" <pgsql(at)j-davis(dot)com>, "Josh Berkus" <josh(at)agliodbs(dot)com> |
| Cc: | <pgsql-hackers(at)postgresql(dot)org>, "Tom Lane" <tgl(at)sss(dot)pgh(dot)pa(dot)us>, "Joshua D(dot) Drake" <jd(at)commandprompt(dot)com> |
| Subject: | Re: COMMIT NOWAIT Performance Option |
| Date: | 2007-02-28 10:40:29 |
| Message-ID: | E1539E0ED7043848906A8FF995BDA57901CAFD3F@m0143.s-mxs.net |
| Views: | Raw Message | Whole Thread | Download mbox | Resend email |
| Thread: | |
| Lists: | pgsql-hackers |
> > > > But we do don't we? fsync = off, full_page_writes = off?
> >
> > BTW, our testing seems to indicate that full_page_writes = off is
safe
> > on Solaris 10 on good hardware. At least, we haven't been able to
break it yet.
> >
>
> Is that an OS-dependent parameter? I always assumed it depended
entirely
> on hardware. I have no way to test it for myself though, so I just
leave
> full_page_writes=on to be safe.
It also depends on the FS implementation. The OS/FS must guarantee, that
it does not chunk single data page write calls. Usually that is the
case, when OS/FS pagesize and pg pagesize are identical. And the HW
needs to guarantee atomicity for single calls. e.g. on AIX you need to
reduce the pg page size to 4k to be able to give those guarantees.
Andreas
| From | Date | Subject | |
|---|---|---|---|
| Next Message | Simon Riggs | 2007-02-28 10:59:00 | VACUUM and spoiling the buffer manager cache |
| Previous Message | Zeugswetter Andreas ADI SD | 2007-02-28 10:34:14 | Re: Resumable vacuum proposal and design overview |