What constitutes "reproducible" numbers from pgbench? - Mailing list pgsql-general

From
Subject What constitutes "reproducible" numbers from pgbench?
Date
Msg-id C5DBACC6DCC7604C9E4875FD9C7968B112D90C5000@ITXS01EVS.service.it.nrw.de
Whole thread Raw
Responses Re: What constitutes "reproducible" numbers from pgbench?
Re: What constitutes "reproducible" numbers from pgbench?
List pgsql-general
Hello list,
 
Exactly what constitutes „reproducible“ values from pgbench?  I keep getting a range between 340 tps and 440 tps or something like that using the same command line on the same machine.  Is that reproducible enough?
 
The docs state that one should verify that the numbers are reproducible, so I repeat any test run ten times before believing the results.  I’ve tried increasing the test duration (-T) from one minute to five minutes, then turning off autovacuum (in postgresql.conf) as recommended by the docs, but the range of results is not getting any narrower.  So what does “reproducible” mean as applied to pgbench?
 
Obviously I could be doing something wrong, such as missing some vital configuration option…
 
Thanks in advance for any insights.
 
Cheers,
Holger Friedrich
 

pgsql-general by date:

Previous
From: Craig Ringer
Date:
Subject: Re: monitoring bdr nodes
Next
From: Qingqing Zhou
Date:
Subject: Re: What constitutes "reproducible" numbers from pgbench?