Subjective question: What is a good TPS for pgbench?

From: mlw <markw(at)mohawksoft(dot)com>
To: PostgreSQL-development <pgsql-hackers(at)postgresql(dot)org>
Subject: Subjective question: What is a good TPS for pgbench?
Date: 2002-03-06 14:50:10
Message-ID: 3C862CA2.A226DC44@mohawksoft.com
Views: Raw Message | Whole Thread | Download mbox | Resend email
Thread:
Lists: pgsql-hackers

I am recreating my development environent, and tuning my PostgreSQL system.

Here is the question:

OK, I am running pgbench against my new server. How do I know it is doing well
or not? I understand it is all subjective, but what sort of numbers are you
guys getting?

I have a dual PIII, 1G RAM, two disks one dedicated to /pg_xlog and system, one
to /base.

Using a benchmark with a scale of 100, I hover around a tps of 110 (106~114)
for 25,50, and 100 concurrent users. Now, is that good? What do you guys get?

Browse pgsql-hackers by date

  From Date Subject
Next Message Oleg Bartunov 2002-03-06 15:36:21 Re: single task postgresql
Previous Message Bruce Momjian 2002-03-06 14:35:17 Re: Postgresql backend to perform vacuum automatically