| From: | "Graeme B(dot) Bell" <graeme(dot)bell(at)nibio(dot)no> |
|---|---|
| To: | "hlinnaka(at)iki(dot)fi" <hlinnaka(at)iki(dot)fi> |
| Cc: | "Wes Vaske (wvaske)" <wvaske(at)micron(dot)com>, "Graeme B(dot) Bell" <graeme(dot)bell(at)nibio(dot)no>, "pgsql-performance(at)postgresql(dot)org" <pgsql-performance(at)postgresql(dot)org> |
| Subject: | Re: New server: SSD/RAID recommendations? |
| Date: | 2015-07-07 15:58:49 |
| Message-ID: | AB056B38-EC0F-46B6-90E6-0963604E0A9B@skogoglandskap.no |
| Views: | Whole Thread | Raw Message | Download mbox | Resend email |
| Thread: | |
| Lists: | pgsql-performance |
Yikes. I would not be able to sleep tonight if it were not for the BBU cache in front of these disks...
diskchecker.pl consistently reported several examples of corruption post-power-loss (usually 10 - 30 ) on unprotected M500s/M550s, so I think it's pretty much open to debate what types of madness and corruption you'll find if you look close enough.
G
On 07 Jul 2015, at 16:59, Heikki Linnakangas <hlinnaka(at)iki(dot)fi> wrote:
>
> So it lies about fsync()... The next question is, does it nevertheless enforce the correct ordering of persisting fsync'd data? If you write to file A and fsync it, then write to another file B and fsync it too, is it guaranteed that if B is persisted, A is as well? Because if it isn't, you can end up with filesystem (or database) corruption anyway.
>
> - Heikki
| From | Date | Subject | |
|---|---|---|---|
| Next Message | Tom Lane | 2015-07-07 16:02:49 | Re: wildcard text filter switched to boolean column, performance is way worse |
| Previous Message | Graeme B. Bell | 2015-07-07 15:53:43 | Re: New server: SSD/RAID recommendations? |