Re: in-transaction insert performance in 7.5devel

From: "Merlin Moncure" <merlin(dot)moncure(at)rcsonline(dot)com>
To: "Rod Taylor" <pg(at)rbt(dot)ca>
Cc: "Postgresql Performance" <pgsql-performance(at)postgresql(dot)org>
Subject: Re: in-transaction insert performance in 7.5devel
Date: 2004-06-11 19:04:03
Message-ID: 6EE64EF3AB31D5448D0007DD34EEB34101AE5A@Herge.rcsinc.local
Views: Raw Message | Whole Thread | Download mbox | Resend email
Thread:
Lists: pgsql-performance

Rod Taylor wrote:
> On Fri, 2004-06-11 at 14:40, Merlin Moncure wrote:
> > I am batch inserting insert statements into a database with fsync =
on.
> > My single disk system is on a 10k drive...even though I am inside a
> > transaction there is at least 1 file sync per row insert.
>
> Which filesystem?
>
> PostgreSQL isn't issuing the sync except at commit of a transaction,
but
> some filesystems do wacky things if you ask them too.

Um, NTFS. :) I'm playing with the new 'syncer' to get a feel for the
new performance considerations.

As I understand it, sync() is never called anymore. mdsync() hits the
all the files 1 by 1 with an fsync. My understanding of the commit
process is that 30 tps is quite reasonable for my hardware.

What surprised was that I am getting at least 1 seek/insert inside a
transaction.

Merlin

Responses

Browse pgsql-performance by date

  From Date Subject
Next Message Rod Taylor 2004-06-11 19:27:01 Re: in-transaction insert performance in 7.5devel
Previous Message Rod Taylor 2004-06-11 18:55:01 Re: in-transaction insert performance in 7.5devel