Re: [Testperf-general] Re: 8.0beta5 results w/ dbt2 - Mailing list pgsql-hackers

From Mark Wong
Subject Re: [Testperf-general] Re: 8.0beta5 results w/ dbt2
Date
Msg-id 20041209132145.A26811@osdl.org
Whole thread Raw
In response to Re: [Testperf-general] Re: 8.0beta5 results w/ dbt2  (Simon Riggs <simon@2ndquadrant.com>)
Responses Checkpoint bugs?
List pgsql-hackers
On Mon, Dec 06, 2004 at 07:52:37PM +0000, Simon Riggs wrote:
> Varying bgwriter_maxpages upwards should take performance higher.
> 

I have 2 runs now.  I for both tests, I have bgwriter_percent=100,
checkpoint_segments=8192, checkpoint_timout=600,
debug_shared_buffers=10, log_min_messages=debug1 and varied
bgwriter_maxpages.

http://www.osdl.org/projects/dbt2dev/results/dev4-010/206/bgwriter_maxpages=100 (default)throughput 3816.51

http://www.osdl.org/projects/dbt2dev/results/dev4-010/207/bgwriter_maxpages=1000throughput 3865.50


Another 1% change in overall throughput.  I did catch in the oprofile
output that StrategyDirtyBufferList moved down the list a bit when I
increased bgwriter_maxpages.

Mark


pgsql-hackers by date:

Previous
From: Nicolai Tufar
Date:
Subject: Re: apparent problem on linux/s390
Next
From: "Zeugswetter Andreas DAZ SD"
Date:
Subject: Re: V8 Beta 5 on AIX