X-Original-To: pgsql-performance-postgresql.org@postgresql.org Received: from localhost (wm.hub.org [200.46.204.128]) by postgresql.org (Postfix) with ESMTP id 787439FA502 for ; Mon, 17 Jul 2006 03:13:14 -0300 (ADT) Received: from postgresql.org ([200.46.204.71]) by localhost (mx1.hub.org [200.46.204.128]) (amavisd-new, port 10024) with ESMTP id 54026-02 for ; Mon, 17 Jul 2006 06:13:06 +0000 (UTC) X-Greylist: domain auto-whitelisted by SQLgrey- Received: from nf-out-0910.google.com (nf-out-0910.google.com [64.233.182.187]) by postgresql.org (Postfix) with ESMTP id D47469F9F27 for ; Mon, 17 Jul 2006 03:13:05 -0300 (ADT) Received: by nf-out-0910.google.com with SMTP id p77so391142nfc for ; Sun, 16 Jul 2006 23:13:04 -0700 (PDT) DomainKey-Signature: a=rsa-sha1; q=dns; c=nofws; s=beta; d=gmail.com; h=received:message-id:date:from:to:subject:cc:in-reply-to:mime-version:content-type:references; b=N+eJuqLUyQkxY8+ZcAjJ8+3KA+c2f4ijdoa93XMP8xRC4leodR7ThiTCRj+659feHez6CRMLey4No67joj9aiHeEotmko15Q9nQHXj+4lX1VAwmzM2+/j/WgGraB45449+N4wFFNbP5G9kWpXxSPDX9MSquzGuFbRr0IHfQ82wk= Received: by 10.78.156.6 with SMTP id d6mr700085hue; Sun, 16 Jul 2006 23:13:04 -0700 (PDT) Received: by 10.78.140.7 with HTTP; Sun, 16 Jul 2006 23:13:04 -0700 (PDT) Message-ID: <33c6269f0607162313k1770ac16ld5e90e106bf5e8dc@mail.gmail.com> Date: Mon, 17 Jul 2006 02:13:04 -0400 From: "Alex Turner" To: "Mikael Carneholm" Subject: Re: RAID stripe size question Cc: pgsql-performance@postgresql.org In-Reply-To: <7F10D26ECFA1FB458B89C5B4B0D72C2B4E4BB1@sesrv12.wirelesscar.com> MIME-Version: 1.0 Content-Type: multipart/alternative; boundary="----=_Part_72759_32639676.1153116784159" References: <7F10D26ECFA1FB458B89C5B4B0D72C2B4E4BB1@sesrv12.wirelesscar.com> X-Virus-Scanned: Maia Mailguard 1.0.1 X-Archive-Number: 200607/160 X-Sequence-Number: 20020 ------=_Part_72759_32639676.1153116784159 Content-Type: text/plain; charset=ISO-8859-1; format=flowed Content-Transfer-Encoding: 7bit Content-Disposition: inline With 18 disks dedicated to data, you could make 100/7*9 seeks/second (7ms av seeks time, 9 independant units) which is 128seeks/second writing on average 64kb of data, which is 4.1MB/sec throughput worst case, probably 10x best case so 40Mb/sec - you might want to take more disks for your data and less for your WAL. Someone check my math here... And as always - run benchmarks with your app to verify Alex. On 7/16/06, Mikael Carneholm wrote: > > I have finally gotten my hands on the MSA1500 that we ordered some time > ago. It has 28 x 10K 146Gb drives, currently grouped as 10 (for wal) + 18 > (for data). There's only one controller (an emulex), but I hope performance > won't suffer too much from that. Raid level is 0+1, filesystem is ext3. > > Now to the interesting part: would it make sense to use different stripe > sizes on the separate disk arrays? In theory, a smaller stripe size (8-32K) > should increase sequential write throughput at the cost of decreased > positioning performance, which sounds good for WAL (assuming WAL is never > "searched" during normal operation). And for disks holding the data, a > larger stripe size (>32K) should provide for more concurrent (small) > reads/writes at the cost of decreased raw throughput. This is with an OLTP > type application in mind, so I'd rather have high transaction throughput > than high sequential read speed. The interface is a 2Gb FC so I'm throttled > to (theoretically) 192Mb/s, anyway. > > So, does this make sense? Has anyone tried it and seen any performance > gains from it? > > Regards, > Mikael. > ------=_Part_72759_32639676.1153116784159 Content-Type: text/html; charset=ISO-8859-1 Content-Transfer-Encoding: 7bit Content-Disposition: inline With 18 disks dedicated to  data, you could make 100/7*9 seeks/second (7ms av seeks time, 9 independant units) which is 128seeks/second writing on average 64kb of data, which is 4.1MB/sec throughput worst case, probably 10x best case so 40Mb/sec - you might want to take more disks for your data and less for your WAL.

Someone check my math here...

And as always - run benchmarks with your app to verify

Alex.

On 7/16/06, Mikael Carneholm < Mikael.Carneholm@wirelesscar.com> wrote:

I have finally gotten my hands on the MSA1500 that we ordered some time ago. It has 28 x 10K 146Gb drives, currently grouped as 10 (for wal) + 18 (for data). There's only one controller (an emulex), but I hope performance won't suffer too much from that. Raid level is 0+1, filesystem is ext3.

Now to the interesting part: would it make sense to use different stripe sizes on the separate disk arrays? In theory, a smaller stripe size (8-32K) should increase sequential write throughput at the cost of decreased positioning performance, which sounds good for WAL (assuming WAL is never "searched" during normal operation). And for disks holding the data, a larger stripe size (>32K) should provide for more concurrent (small) reads/writes at the cost of decreased raw throughput. This is with an OLTP type application in mind, so I'd rather have high transaction throughput than high sequential read speed. The interface is a 2Gb FC so I'm throttled to (theoretically) 192Mb/s, anyway.

So, does this make sense? Has anyone tried it and seen any performance gains from it?

Regards,
Mikael.


------=_Part_72759_32639676.1153116784159--