| From: | Peter Geoghegan <pg(at)heroku(dot)com> |
|---|---|
| To: | Andres Freund <andres(at)2ndquadrant(dot)com> |
| Cc: | Merlin Moncure <mmoncure(at)gmail(dot)com>, PostgreSQL-development <pgsql-hackers(at)postgresql(dot)org> |
| Subject: | Re: hung backends stuck in spinlock heavy endless loop |
| Date: | 2015-01-13 23:49:33 |
| Message-ID: | CAM3SWZQmAWR0Z6MgQMYzAGgzRGC498CCnJih18bj7Ydat4c93A@mail.gmail.com |
| Views: | Raw Message | Whole Thread | Download mbox | Resend email |
| Thread: | |
| Lists: | pgsql-hackers |
On Tue, Jan 13, 2015 at 3:21 PM, Andres Freund <andres(at)2ndquadrant(dot)com> wrote:
> My guess is rather that it's contention on the freelist lock via
> StrategyGetBuffer's. I've seen profiles like this due to exactly that
> before - and it fits to parallel loading quite well.
I'm not saying you're wrong, but the breakdown of _bt_moveright()
relative to _bt_relandgetbuf() calls seems a bit fishy to me.
I don't remember seeing _bt_moveright() or _bt_compare() figuring so
prominently, where _bt_binsrch() is nowhere to be seen. I can't see a
reference to _bt_binsrch() in either profile.
--
Peter Geoghegan
| From | Date | Subject | |
|---|---|---|---|
| Next Message | Merlin Moncure | 2015-01-13 23:50:34 | Re: hung backends stuck in spinlock heavy endless loop |
| Previous Message | Andres Freund | 2015-01-13 23:42:09 | Re: hung backends stuck in spinlock heavy endless loop |