Message-ID: <4C1927BF.9030708@emolecules.com>
Date: Wed, 16 Jun 2010 12:36:31 -0700
From: Craig James <craig_james@emolecules.com>
User-Agent: Mozilla/5.0 (Macintosh; U; Intel Mac OS X 10.6; en-US;
	rv:1.9.1.9) Gecko/20100317 Thunderbird/3.0.4
MIME-Version: 1.0
To: Josh Berkus <josh@agliodbs.com>
CC: pgsql-performance@postgresql.org
Subject: Re: PostgreSQL as a local in-memory cache
References: <cb0fb58c-9134-4314-a1d0-08fc39f911a6@40g2000pry.googlegroups.com>
	<87bpbcpabg.fsf@cbbrowne-laptop.afilias-int.info>
	<4C17A417.2040600@noao.edu>
	<87ocfcnqmk.fsf@cbbrowne-laptop.afilias-int.info>
	<4C180A3B.7090905@agliodbs.com>
	<4634b12c-749f-4605-9d95-121b8e2bd9e4@k17g2000pro.googlegroups.com>
	<4C191F46.4060408@agliodbs.com>
In-Reply-To: <4C191F46.4060408@agliodbs.com>
Content-Type: text/plain; charset=ISO-8859-1; format=flowed
Content-Transfer-Encoding: 7bit

On 6/16/10 12:00 PM, Josh Berkus wrote:
>
>> * fsync=off =>  5,100
>> * fsync=off and synchronous_commit=off =>  5,500
>
> Now, this *is* interesting ... why should synch_commit make a difference
> if fsync is off?
>
> Anyone have any ideas?

I found that pgbench has "noise" of about 20% (I posted about this a couple days ago using data from 1000 identical pgbench runs).  Unless you make a bunch of runs and average them, a difference of 5,100 to 5,500 appears to be meaningless.

Craig

>
>> tmpfs, WAL on same tmpfs:
>> * Default config: 5,200
>> * full_page_writes=off =>  5,200
>> * fsync=off =>  5,250
>> * synchronous_commit=off =>  5,200
>> * fsync=off and synchronous_commit=off =>  5,450
>> * fsync=off and full_page_writes=off =>  5,250
>> * fsync=off, synchronous_commit=off and full_page_writes=off =>  5,500
>
> So, in this test, it seems like having WAL on tmpfs doesn't make a
> significant difference for everything == off.
>
> I'll try running some tests on Amazon when I have a chance.  It would be
> worthwhile to get figures without Python's "ceiling".
>