| From: | Robert Haas <robertmhaas(at)gmail(dot)com> |
|---|---|
| To: | Merlin Moncure <mmoncure(at)gmail(dot)com> |
| Cc: | Sergey Koposov <koposov(at)ast(dot)cam(dot)ac(dot)uk>, Jeff Janes <jeff(dot)janes(at)gmail(dot)com>, pgsql-hackers(at)postgresql(dot)org |
| Subject: | Re: 9.2beta1, parallel queries, ReleasePredicateLocks, CheckForSerializableConflictIn in the oprofile |
| Date: | 2012-05-26 13:44:12 |
| Message-ID: | CA+TgmobF7yfPFgke71Efadqgoz6dxwfv+GOLy+1MPEmkSyUVpQ@mail.gmail.com |
| Views: | Raw Message | Whole Thread | Download mbox | Resend email |
| Thread: | |
| Lists: | pgsql-hackers |
On Fri, May 25, 2012 at 10:30 AM, Merlin Moncure <mmoncure(at)gmail(dot)com> wrote:
> I think what's happening here is that the buffer partitions don't help
> (in fact, they hurt) in the presence of multiple concurrent scans that
> are operating on approximately the same data. Sooner or later the
> scans line up on each other and start binding when reassigning lock
> tags (which take out up to two ordered exclusive lwlocks). This is on
> the read side, so the buffer access strategy is zero help (I confirmed
> this off list).
This theory is seeming fairly plausible - how can we test it?
How about trying it with synchronize_seqscans = off? If the
synchronized-seqscan logic is causing contention on the buf mapping
locks and individual buffer locks, that should fix it.
--
Robert Haas
EnterpriseDB: http://www.enterprisedb.com
The Enterprise PostgreSQL Company
| From | Date | Subject | |
|---|---|---|---|
| Next Message | Sergey Koposov | 2012-05-26 14:09:29 | Re: 9.2beta1, parallel queries, ReleasePredicateLocks, CheckForSerializableConflictIn in the oprofile |
| Previous Message | Florian Pflug | 2012-05-26 11:24:26 | Re: Interrupting long external library calls |