pg.ddx.io  pgsql-performance@postgresql.org mailing list archive  
help / color / mirror / Atom feed
Context Switching issue: Spinlock doesn't fix.
3+ messages / 2 participants
[nested] [flat]

* Context Switching issue: Spinlock doesn't fix.
@ 2004-06-02 19:25 Josh Berkus <josh@agliodbs.com>
  2004-08-31 21:20 ` Re: Context Switching issue: Spinlock doesn't fix. jelle <jellej@pacbell.net>
  0 siblings, 1 reply; 3+ messages in thread

From: Josh Berkus @ 2004-06-02 19:25 UTC (permalink / raw)
  To: pgsql-performance; +Cc: pg@fastcrypt.com

Folks,

I've been testing varying SPINS_PER_DELAY in a client's installation of 
PostgreSQL against a copy of a production database, to test varying this 
statistic as a way of fixing the issue.   

It does not seem to work.

I've tested all of the following graduated levels:

100 (the original)
250
500
1000
2000
5000
10000
20000
30000
50000

None of these quantities seem to make any difference at all in the number of 
context switches -- neither down nor up.   Seems to me like this is a dead 
end.   Does anyone have test results that show otherwise?

-- 
-Josh Berkus
 Aglio Database Solutions
 San Francisco




^ permalink  raw  reply  [nested|flat] 3+ messages in thread

* Re: Context Switching issue: Spinlock doesn't fix.
  2004-06-02 19:25 Context Switching issue: Spinlock doesn't fix. Josh Berkus <josh@agliodbs.com>
@ 2004-08-31 21:20 ` jelle <jellej@pacbell.net>
  2004-08-31 22:03   ` Re: Context Switching issue: Spinlock doesn't fix. Josh Berkus <josh@agliodbs.com>
  0 siblings, 1 reply; 3+ messages in thread

From: jelle @ 2004-08-31 21:20 UTC (permalink / raw)
  To: pgsql-performance


Hello,

Is context switching problem resolved in 8.0?

Can I drop in another Xeon?

Thanks,
Jelle


On Wed, 2 Jun 2004, Josh Berkus wrote:

> Folks,
> 
> I've been testing varying SPINS_PER_DELAY in a client's installation of 
> PostgreSQL against a copy of a production database, to test varying this 
> statistic as a way of fixing the issue.   
> 
> It does not seem to work.
> 
> I've tested all of the following graduated levels:
> 
> 100 (the original)
> 250
> 500
> 1000
> 2000
> 5000
> 10000
> 20000
> 30000
> 50000
> 
> None of these quantities seem to make any difference at all in the number of 
> context switches -- neither down nor up.   Seems to me like this is a dead 
> end.   Does anyone have test results that show otherwise?
> 
> 

-- 

http://www.jibjab.com




^ permalink  raw  reply  [nested|flat] 3+ messages in thread

* Re: Context Switching issue: Spinlock doesn't fix.
  2004-06-02 19:25 Context Switching issue: Spinlock doesn't fix. Josh Berkus <josh@agliodbs.com>
  2004-08-31 21:20 ` Re: Context Switching issue: Spinlock doesn't fix. jelle <jellej@pacbell.net>
@ 2004-08-31 22:03   ` Josh Berkus <josh@agliodbs.com>
  0 siblings, 0 replies; 3+ messages in thread

From: Josh Berkus @ 2004-08-31 22:03 UTC (permalink / raw)
  To: jellej@pacbell.net; +Cc: pgsql-performance

Jellej,

> Is context switching problem resolved in 8.0?
>
> Can I drop in another Xeon?

Nope, not solved yet.   However, it only affects certain data access patterns.  
So don't use it as a reason not to go multi-processor.

-- 
--Josh

Josh Berkus
Aglio Database Solutions
San Francisco



^ permalink  raw  reply  [nested|flat] 3+ messages in thread


end of thread, other threads:[~2004-08-31 22:03 UTC | newest]

Thread overview: 3+ messages (download: mbox mbox.gz follow: Atom feed)
-- links below jump to the message on this page --
2004-06-02 19:25 Context Switching issue: Spinlock doesn't fix. Josh Berkus <josh@agliodbs.com>
2004-08-31 21:20 ` jelle <jellej@pacbell.net>
2004-08-31 22:03   ` Josh Berkus <josh@agliodbs.com>

This inbox is served by DDX for PostgreSQL; see mirroring instructions
for how to clone and mirror all data and code used for this inbox