Re: [ADMIN] pgbench Windows outperforms Debian in Write tests whileDebian is faster in SELECT only tests - Mailing list pgsql-admin

From Andres Freund
Subject Re: [ADMIN] pgbench Windows outperforms Debian in Write tests whileDebian is faster in SELECT only tests
Date
Msg-id 20170529181429.4hicimoro6jqog3s@alap3.anarazel.de
Whole thread Raw
In response to [ADMIN] pgbench Windows outperforms Debian in Write tests while Debian is faster in SELECT only tests  ("Klaus P. Pieper" <kpi6288@gmail.com>)
Responses Re: [ADMIN] pgbench Windows outperforms Debian in Write tests while Debian is faster in SELECT only tests  ("Klaus P. Pieper" <kpi6288@gmail.com>)
List pgsql-admin
On 2017-05-29 09:42:53 +0200, Klaus P. Pieper wrote:
> Mounting the file system with barriers=0 gives much better results on the
> Debian system (better than the Windows system). But since this machine does
> not have a battery buffered disk adapter, that wouldn't be an option for a
> production system.

> I'm in particular concerned about the disadvantage in the single client
> WRITE scenario running Debian. How can Windows outperform Debian by a factor
> of 2?

Windows IIRC defaults to something close to barriers=0.

- Andres


pgsql-admin by date:

Previous
From: stevenchang1213
Date:
Subject: [ADMIN] citus extension
Next
From: "Klaus P. Pieper"
Date:
Subject: Re: [ADMIN] pgbench Windows outperforms Debian in Write tests while Debian is faster in SELECT only tests