X-Original-To: pgsql-performance-postgresql.org@localhost.postgresql.org Received: from localhost (av.hub.org [200.46.204.144]) by svr1.postgresql.org (Postfix) with ESMTP id 4863BD8C5E for ; Tue, 20 Sep 2005 12:13:24 -0300 (ADT) Received: from svr1.postgresql.org ([200.46.204.71]) by localhost (av.hub.org [200.46.204.144]) (amavisd-new, port 10024) with ESMTP id 73246-08 for ; Tue, 20 Sep 2005 15:13:20 +0000 (GMT) Received: from zproxy.gmail.com (zproxy.gmail.com [64.233.162.205]) by svr1.postgresql.org (Postfix) with ESMTP id 26C7ED88B7 for ; Tue, 20 Sep 2005 12:13:16 -0300 (ADT) Received: by zproxy.gmail.com with SMTP id 40so276377nzk for ; Tue, 20 Sep 2005 08:13:16 -0700 (PDT) DomainKey-Signature: a=rsa-sha1; q=dns; c=nofws; s=beta; d=gmail.com; h=received:message-id:date:from:reply-to:to:subject:cc:in-reply-to:mime-version:content-type:references; b=DUhlpqOHzgdfPpTQysTYjzPuXtwizpn+zLatUoPGfh1lY4bH/1e9L54sbmByg6ZobCDYQCspY1dui6xTNFalF8/Wk/oO94mWkx1O6GE/UtmOvNTyQbtRq15qitMYXgCWv/ygSoOqlHBwOABA/mbb/9LxSRe84VoaLlUV3oprp5k= Received: by 10.54.36.79 with SMTP id j79mr1820780wrj; Tue, 20 Sep 2005 08:13:15 -0700 (PDT) Received: by 10.54.83.10 with HTTP; Tue, 20 Sep 2005 08:13:15 -0700 (PDT) Message-ID: <33c6269f050920081371bf3909@mail.gmail.com> Date: Tue, 20 Sep 2005 11:13:15 -0400 From: Alex Turner Reply-To: armtuk@gmail.com To: bmmbn Subject: Re: RAID Stripe size Cc: pgsql-performance@postgresql.org In-Reply-To: <1126871503.157442.314670@g49g2000cwa.googlegroups.com> Mime-Version: 1.0 Content-Type: multipart/alternative; boundary="----=_Part_3277_149750.1127229195559" References: <1126871503.157442.314670@g49g2000cwa.googlegroups.com> X-Virus-Scanned: by amavisd-new at hub.org X-Spam-Status: No, hits=0.249 required=5 tests=[AWL=-0.071, HTML_10_20=0.295, HTML_MESSAGE=0.001, RCVD_BY_IP=0.024] X-Spam-Level: X-Archive-Number: 200509/217 X-Sequence-Number: 14525 ------=_Part_3277_149750.1127229195559 Content-Type: text/plain; charset=ISO-8859-1 Content-Transfer-Encoding: quoted-printable Content-Disposition: inline I have benched different sripe sizes with different file systems, and the= =20 perfmance differences can be quite dramatic. Theoreticaly a smaller stripe is better for OLTP as you can write more smal= l=20 transactions independantly to more different disks more often than not, but= =20 a large stripe size is good for Data warehousing as you are often doing ver= y=20 large sequential reads, and a larger stripe size is going to exploit the=20 on-drive cache as you request larger single chunks from the disk at a time. It also seems that different controllers are partial to different defaults= =20 that can affect their performance, so I would suggest that testing this on= =20 two different controller cards man be less than optimal. I would also recommend looking at file system. For us JFS worked=20 signifcantly faster than resier for large read loads and large write loads,= =20 so we chose JFS over ext3 and reiser. I found that lower stripe sizes impacted performance badly as did overly=20 large stripe sizes. Alex Turner NetEconomist On 16 Sep 2005 04:51:43 -0700, bmmbn wrote: >=20 > Hi Everyone >=20 > The machine is IBM x345 with ServeRAID 6i 128mb cache and 6 SCSI 15k > disks. >=20 > 2 disks are in RAID1 and hold the OS, SWAP & pg_xlog > 4 disks are in RAID10 and hold the Cluster itself. >=20 > the DB will have two major tables 1 with 10 million rows and one with > 100 million rows. > All the activities against this tables will be SELECT. >=20 > Currently the strip size is 8k. I read in many place this is a poor > setting. >=20 > Am i right ? >=20 >=20 > ---------------------------(end of broadcast)--------------------------- > TIP 2: Don't 'kill -9' the postmaster > ------=_Part_3277_149750.1127229195559 Content-Type: text/html; charset=ISO-8859-1 Content-Transfer-Encoding: quoted-printable Content-Disposition: inline I have benched different sripe sizes with different file systems, and the p= erfmance differences can be quite dramatic.

Theoreticaly a smaller stripe is better for OLTP as you can write more small transactions independantly to more different disks more often than not, but a large stripe size is good for Data warehousing as you are often doing very large sequential reads, and a larger stripe size is going to exploit the on-drive cache as you request larger single chunks from the disk at a time.

It also seems that different controllers are partial to different defaults that can affect their performance, so I would suggest that testing this on two different controller cards man be less than optimal.
I would also recommend looking at file system.  For us JFS worked signifcantly faster than resier for large read loads and large write loads, so we chose JFS over ext3 and reiser.

I found that lower stripe sizes impacted performance badly as did overly la= rge stripe sizes.

Alex Turner
NetEconomist

On 16 Sep 2005 04:51:4= 3 -0700, bmmbn <miki@canaan.co.il> wrote:
Hi Everyone

The machine is IBM x345 with ServeRAID 6i 128mb cache an= d 6 SCSI 15k
disks.

2 disks are in RAID1 and hold the OS, SWAP &a= mp; pg_xlog
4 disks are in RAID10 and hold the Cluster itself.

the DB will have two major tables 1 with 10 million rows and one with
10= 0 million rows.
All the activities against this tables will be SELECT.
Currently the strip size is 8k. I read in many place this is a poor
setting.

Am i right ?


---------------------------(end= of broadcast)---------------------------
TIP 2: Don't 'kill -9' the pos= tmaster

------=_Part_3277_149750.1127229195559--