| From: | Dave Cramer <pg(at)fastcrypt(dot)com> |
|---|---|
| To: | Josh Berkus <josh(at)agliodbs(dot)com> |
| Cc: | Tom Lane <tgl(at)sss(dot)pgh(dot)pa(dot)us>, Paul Tuckfield <paul(at)tuckfield(dot)com>, Anjan Dave <adave(at)vantage(dot)com>, Neil Conway <neilc(at)samurai(dot)com>, Dirk Lutzebäck <lutzeb(at)aeccom(dot)com>, pgsql-performance(at)postgresql(dot)org |
| Subject: | Re: Wierd context-switching issue on Xeon patch for 7.4.1 |
| Date: | 2004-04-22 03:18:47 |
| Message-ID: | 1082603927.1558.279.camel@localhost.localdomain |
| Views: | Whole Thread | Raw Message | Download mbox | Resend email |
| Thread: | |
| Lists: | pgsql-performance |
More data....
On a dual xeon with HTT enabled:
I tried increasing the NUM_SPINS to 1000 and it works better.
NUM_SPINLOCKS CS ID pgbench
100 250K 59% 230 TPS
1000 125K 55% 228 TPS
This is certainly heading in the right direction ? Although it looks
like it is highly dependent on the system you are running on.
--dc--
On Wed, 2004-04-21 at 22:53, Josh Berkus wrote:
> Tom,
>
> > As far as I can tell, this does reduce the rate of semop's
> > significantly, but it does so by bringing the overall processing rate
> > to a crawl :-(. I see 97% CPU idle time when using this patch.
> > I believe what is happening is that the select() delay in s_lock.c is
> > being hit frequently because the spin loop isn't allowed to run long
> > enough to let the other processor get out of the spinlock.
>
> Also, I tested it on production data, and it reduces the CSes by about 40%.
> An improvement, but not a magic bullet.
--
Dave Cramer
519 939 0336
ICQ # 14675561
| From | Date | Subject | |
|---|---|---|---|
| Next Message | Tom Lane | 2004-04-22 04:15:13 | Re: 225 times slower |
| Previous Message | Tom Lane | 2004-04-22 03:10:43 | Re: Wierd context-switching issue on Xeon |