From: Bruce Momjian <bruce@momjian.us>
Message-Id: <201006232016.o5NKGAM26947@momjian.us>
Subject: Re: PostgreSQL as a local in-memory cache
In-Reply-To: <AANLkTimvzMwIrj912lg6u_LhU7FSN5fFe88K-k-Uggyz@mail.gmail.com>
To: Pavel Stehule <pavel.stehule@gmail.com>
Date: Wed, 23 Jun 2010 16:16:10 -0400 (EDT)
CC: Tom Lane <tgl@sss.pgh.pa.us>, Dimitri Fontaine <dfontaine@hi-media.com>,
	Josh Berkus <josh@agliodbs.com>,
	postgres performance list <pgsql-performance@postgresql.org>
MIME-Version: 1.0
Content-Transfer-Encoding: 7bit
Content-Type: text/plain; charset="US-ASCII"

Pavel Stehule wrote:
> 2010/6/23 Bruce Momjian <bruce@momjian.us>:
> > Tom Lane wrote:
> >> Dimitri Fontaine <dfontaine@hi-media.com> writes:
> >> > Josh Berkus <josh@agliodbs.com> writes:
> >> >> a) Eliminate WAL logging entirely
> >
> > If we elimiate WAL logging, that means a reinstall is required for even
> > a postmaster crash, which is a new non-durable behavior.
> >
> > Also, we just added wal_level = minimal, which might end up being a poor
> > name choice of we want wal_level = off in PG 9.1. ?Perhaps we should
> > have used wal_level = crash_safe in 9.0.
> >
> > I have added the following TODO:
> >
> > ? ? ? ?Consider a non-crash-safe wal_level that eliminates WAL activity
> >
> > ? ? ? ? ? ?* http://archives.postgresql.org/pgsql-performance/2010-06/msg00300.php
> >
> > --
> 
> isn't fsync to off enought?

Well,  testing reported in the thread showed other settings also help,
though the checkpoint lengthening was not tested.

-- 
  Bruce Momjian  <bruce@momjian.us>        http://momjian.us
  EnterpriseDB                             http://enterprisedb.com

  + None of us is going to be here forever. +