Tom Lane wrote:
> I don't feel this is quite ready to commit, but here it is if anyone
> would like to try some performance testing. Using "pgbench -s 10"
> on a single-CPU machine, I find this code a little slower than CVS tip
> at shared_buffers = 1000, but noticeably faster (~10% speedup) at
> 10000 buffers. So it's not a dead loss for single-CPU anyway. What
> we need now is some performance measurements on multi-CPU boxes.
> The bgwriter algorithm probably needs more work, maybe some more GUC
Here are some results for a 2xPIII 700Mhz with 2G ram running Freebsd 5.3:
Pgbench: s=10 c=4 t=1000
Pg: wal_buffers=128 checkpoint_segments=10
3 runs of each combination were averaged. the figure is the tps
including connection time (with range in the brackets).
shared_buffers=1000 tps=129 (129-131)
shared_buffers=10000 tps=146 (145-148)
8.1 CVS + buf patch
shared_buffers=1000 tps=135 (131-138)
shared_buffers=10000 tps=154 (154-155)
In response to
pgsql-patches by date
|Next:||From: Tom Lane||Date: 2005-02-17 01:05:50|
|Subject: Re: WIP: bufmgr rewrite per recent discussions |
|Previous:||From: Tom Lane||Date: 2005-02-17 00:50:28|
|Subject: WIP: buffer manager rewrite (take 2)|