Transaction tests on SMP Linux

From: Kenny H Klatt <kklatt(at)csd(dot)uwm(dot)edu>
To: Fredrik Estreen <estreen(at)algonet(dot)se>
Cc: pgsql-hackers(at)postgresql(dot)org
Subject: Transaction tests on SMP Linux
Date: 2002-01-04 02:35:11
Message-ID: 20020103203511.A22701@alpha3.csd.uwm.edu
Views: Raw Message | Whole Thread | Download mbox | Resend email
Thread:
Lists: pgsql-hackers pgsql-odbc

On Thu, Jan 03, 2002 at 11:17:04PM +0100, Fredrik Estreen wrote:
Fredrik:
Not sure who or where this should go to, but here is what I did,
hope it makes some sense.. The box normally runs oracle, its not
busy at the moment.. I sent a copy to pgsql-hackers(at)postgresql(dot)org,
I think that is the correct address.

For the SMP test (I think it was using pgbench)
downloaded the 7.2b4 source
build postgres from source into /usr/local tree
manually started the db with defaults
build pgbench

hardware is a 2-processor Dell box, 1.2 GZ Zeon processors
4G memory with RAID SCSI disks
Linux seti 2.4.7-10smp #1 SMP Thu Sep 6 17:09:31 EDT 2001 i686 unknown

setup pgbench with : pgbench -i testdb -c 50 -t 40 -s 10
changed postgresql.conf parameters
wal_files = 4 # range 0-64
shared_buffers = 200 # 2*max_connections, min 16

test run as pgbench testdb -- output follows:

[kklatt(at)seti pgbench]$ pgbench testdb -c 50 -t 40 -s 10
starting vacuum...end.
transaction type: TPC-B (sort of)
scaling factor: 10
number of clients: 50
number of transactions per client: 40
number of transactions actually processed: 2000/2000
tps = 101.847384(including connections establishing)
tps = 104.345472(excluding connections establishing)

Hope this makes some sense..

Kenny Klatt
Data Architect / Oracle DBA
University of Wisconsin Milwaukee

In response to

Browse pgsql-hackers by date

  From Date Subject
Next Message Haroldo Stenger 2002-01-04 03:05:46 Re: shmctl portability problem
Previous Message Gavin Sherry 2002-01-04 01:56:34 Re: [HACKERS] Updated TODO item

Browse pgsql-odbc by date

  From Date Subject
Next Message Bruce Momjian 2002-01-04 04:44:32 Re: LWLock contention: I think I understand the problem
Previous Message Tom Lane 2002-01-04 01:02:54 Re: LWLock contention: I think I understand the problem