| From: | "Todd A(dot) Cook" <tcook(at)blackducksoftware(dot)com> |
|---|---|
| To: | Alex Hunsaker <badalex(at)gmail(dot)com> |
| Cc: | "pgsql-hackers(at)postgresql(dot)org" <pgsql-hackers(at)postgresql(dot)org> |
| Subject: | Re: slow commits with heavy temp table usage in 8.4.0 |
| Date: | 2009-08-07 16:10:47 |
| Message-ID: | 4A7C5207.4030801@blackducksoftware.com |
| Views: | Raw Message | Whole Thread | Download mbox | Resend email |
| Thread: | |
| Lists: | pgsql-hackers |
Alex Hunsaker wrote:
>
>> FYI, on my 8.2.13 system, the test created 30001 files which were all
>> deleted during the commit. Â On my 8.4.0 system, the test created 60001
>> files, of which 30000 were deleted at commit and 30001 disappeared
>> later (presumably during a checkpoint?).
>
> Smells like fsm?
Yes, that was it. 30000 of the filenames ended with "_fsm".
> With double the number of files maybe something
> simple like turning on dir_index if you are ext3 will help?
Thanks for the tip. Doing "tune2fs -O +dir_index" didn't seem to make
a difference, which is kinda expected for an existing directory. When
I get a chance, I'll try to recreate the filesystem.
-- todd
| From | Date | Subject | |
|---|---|---|---|
| Next Message | Sam Mason | 2009-08-07 16:12:56 | Re: Review: Revise parallel pg_restore's scheduling heuristic |
| Previous Message | Neil Best | 2009-08-07 16:08:07 | Re: \copy: unexpected response (4) |