Skip site navigation (1) Skip section navigation (2)

Re: Testing Sandforce SSD

From: Scott Marlowe <scott(dot)marlowe(at)gmail(dot)com>
To: Greg Smith <greg(at)2ndquadrant(dot)com>
Cc: Greg Spiegelberg <gspiegelberg(at)gmail(dot)com>, Yeb Havinga <yebhavinga(at)gmail(dot)com>, Matthew Wakeling <matthew(at)flymine(dot)org>, pgsql-performance(at)postgresql(dot)org
Subject: Re: Testing Sandforce SSD
Date: 2010-07-26 19:47:14
Message-ID: AANLkTine0bsX_dvQgncDn600Vmt4KoUb3vSL3LW9qocB@mail.gmail.com (view raw or flat)
Thread:
Lists: pgsql-performance
On Mon, Jul 26, 2010 at 12:40 PM, Greg Smith <greg(at)2ndquadrant(dot)com> wrote:
> Greg Spiegelberg wrote:
>>
>> Speaking of the layers in-between, has this test been done with the ext3
>> journal on a different device?  Maybe the purpose is wrong for the SSD.  Use
>> the SSD for the ext3 journal and the spindled drives for filesystem?
>
> The main disk bottleneck on PostgreSQL databases are the random seeks for
> reading and writing to the main data blocks.  The journal information is
> practically noise in comparison--it barely matters because it's so much less
> difficult to keep up with.  This is why I don't really find ext2 interesting
> either.

Note that SSDs aren't usually real fast at large sequential writes
though, so it might be worth putting pg_xlog on a spinning pair in a
mirror and seeing how much, if any, the SSD drive speeds up when not
having to do pg_xlog.

In response to

Responses

pgsql-performance by date

Next:From: Hannu KrosingDate: 2010-07-26 20:40:49
Subject: Re: Testing Sandforce SSD
Previous:From: Greg SmithDate: 2010-07-26 19:45:13
Subject: Re: Testing Sandforce SSD

Privacy Policy | About PostgreSQL
Copyright © 1996-2014 The PostgreSQL Global Development Group