| From: | Simon Riggs <simon(at)2ndquadrant(dot)com> |
|---|---|
| To: | Tom Lane <tgl(at)sss(dot)pgh(dot)pa(dot)us> |
| Cc: | Luke Lonergan <llonergan(at)greenplum(dot)com>, Gavin Hamill <gdh(at)laterooms(dot)com>, pgsql-performance(at)postgresql(dot)org |
| Subject: | Re: pg 8.1.3, AIX, huge box, painfully slow. |
| Date: | 2006-04-10 09:26:49 |
| Message-ID: | 1144661209.21409.131.camel@localhost.localdomain |
| Views: | Raw Message | Whole Thread | Download mbox | Resend email |
| Thread: | |
| Lists: | pgsql-performance |
On Fri, 2006-04-07 at 19:05 -0400, Tom Lane wrote:
> It's plausible though that we are seeing contention across members of
> the LWLock array, with the semop storm just being a higher-level symptom
> of the real hardware-level problem. You might try increasing
> LWLOCK_PADDED_SIZE to 64 or even 128, see
> src/backend/storage/lmgr/lwlock.c (this is something that does exist in
> 8.1, so it'd be easy to try).
pSeries cache lines are 128 bytes wide, so I'd go straight to 128.
If you're renting all 8 CPUs, I'd drop to 4 and try that instead. With 8
CPUs the contention will vary according to what each CPU is doing at any
one time - when they all hit the contention spot, things will get worse.
The pSeries has good CPUs and great caching, so I'd expect contention to
be somewhat more apparent as a bottleneck.
Best Regards, Simon Riggs
| From | Date | Subject | |
|---|---|---|---|
| Next Message | Gavin Hamill | 2006-04-10 09:41:42 | Re: pg 8.1.3, AIX, huge box, painfully slow. |
| Previous Message | Richard Huxton | 2006-04-10 09:23:48 | Re: OT: Data structure design question: How do they count |