X-Original-To: pgsql-performance-postgresql.org@localhost.postgresql.org Received: from localhost (unknown [200.46.204.144]) by svr1.postgresql.org (Postfix) with ESMTP id 01B293A18A7 for ; Fri, 14 Jan 2005 15:58:42 +0000 (GMT) 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 82181-03 for ; Fri, 14 Jan 2005 15:58:27 +0000 (GMT) Received: from wproxy.gmail.com (wproxy.gmail.com [64.233.184.192]) by svr1.postgresql.org (Postfix) with ESMTP id 7B69F3A1A0F for ; Fri, 14 Jan 2005 15:58:29 +0000 (GMT) Received: by wproxy.gmail.com with SMTP id 71so215758wra for ; Fri, 14 Jan 2005 07:58:31 -0800 (PST) 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:content-transfer-encoding:references; b=B2uywHNYLNAI9NyJtEJenpAhrA8BKhGrjfMjPydRsBWCi+cFSARG1W6zN8SUz5wdBqlk8HUmFgnSKJTZCBEHivKMmM+0knajcLz5Gvx+uYa1p6HD2kKYF95TjYFgNgH04kusTivG2h9JbH5KatQu8NIGRALP43VoGoTGubE3hNo= Received: by 10.54.41.78 with SMTP id o78mr44946wro; Fri, 14 Jan 2005 07:58:30 -0800 (PST) Received: by 10.54.18.72 with HTTP; Fri, 14 Jan 2005 07:58:30 -0800 (PST) Message-ID: <33c6269f050114075842f07f35@mail.gmail.com> Date: Fri, 14 Jan 2005 10:58:30 -0500 From: Alex Turner Reply-To: alex@neteconomist.com To: Benjamin Wragg Subject: Re: which dual-CPU hardware/OS is fastest for PostgreSQL? Cc: pgsql-performance@postgresql.org In-Reply-To: <20050114055523.862838C882@vscan01.westnet.com.au> Mime-Version: 1.0 Content-Type: text/plain; charset=ISO-8859-1 Content-Transfer-Encoding: quoted-printable References: <200501102235.18887.josh@agliodbs.com> <20050114055523.862838C882@vscan01.westnet.com.au> X-Virus-Scanned: by amavisd-new at hub.org X-Spam-Status: No, hits=0.024 tagged_above=0 required=5 tests=RCVD_BY_IP X-Spam-Level: X-Archive-Number: 200501/187 X-Sequence-Number: 9877 Without starting too much controvesy I hope, I would seriously recommend you evaluate the AMCC Escalade 9500S SATA controller. It has many of the features of a SCSI controler, but works with cheaper drives, and for half the price or many SCSI controlers (9500S-8MI goes for abour $500). See http://plexq.com/~aturner/3ware.pdf for their 4 way, 8 way and 12 way RAID benchmarks including RAID 0, RAID 5 and RAID 10. If others have similar data, I would be very interested to see how it stacks up against other RAID controllers. Alex Turner NetEconomist On Fri, 14 Jan 2005 16:52:42 +1100, Benjamin Wragg wrot= e: > Hi, >=20 > From what I've been reading on the list for the last few months, adaptec > isn't that good when it comes to RAID controllers, but LSI keeps popping = up. > Is there any particual models that are recommended as I'm in the market f= or > two new servers both with RAID controllers. The server specs I'm thinking > are as follows: >=20 > Box 1 > Fedora 64bit core 3 > 4 GB RAM (2GB per CPU) > 2 x Opteron CPU ??? > Tyan K8S > LSI=AE 53C1030 U320 SCSI controller Dual-channel >=20 > Box 2 > Fedora 64bit core 3 > 2 GB RAM (1GB per CPU) > 2 x Opteron CPU ??? > Tyan K8S > LSI=AE 53C1030 U320 SCSI controller Dual-channel >=20 > This motherboard has can "Connects to PCI-X Bridge A, LSI=AE ZCR (Zero Ch= annel > RAID) support (SCSI Interface Steering Logic)". I believe this means I ca= n > get a LSI MegaRAID 320-0 which a few have mentioned on the list > (http://www.lsilogic.com/products/megaraid/scsi_320_0.html). It supports > RAID 10 and supports battery backed cache. Anyone had any experience with > this? >=20 > Any other particular controller that people recommend? From what I've bee= n > reading RAID 10 and battery backed cache sound like things I need. :) >=20 > Thanks, >=20 > Benjamin Wragg >=20 > -----Original Message----- > From: pgsql-performance-owner@postgresql.org > [mailto:pgsql-performance-owner@postgresql.org] On Behalf Of Josh Berkus > Sent: Tuesday, 11 January 2005 5:35 PM > To: pgsql-performance@postgresql.org > Cc: Christopher Browne > Subject: Re: [PERFORM] which dual-CPU hardware/OS is fastest for PostgreS= QL? >=20 > Chris, >=20 > > I don't know so much about FreeBSD's handling of this, but on Linux, > > there's pretty strong indication that _SOFTWARE_ RAID is faster than > > hardware RAID. >=20 > Certainly better than an Adaptec. But not necessarily better than a > medium-end RAID card, like an LSI. It really depends on the quality of t= he > controller. >=20 > Also, expected concurrent activity should influence you. On a dedicate= d > database server, you'll seldom max out the CPU but will often max of the > disk, so the CPU required by software RAID is "free". However, if you h= ave >=20 > a Web/PG/E-mail box which frequently hits 100% CPU, then even a lower-end > RAID card can be beneficial simply by taking load off the CPU. >=20 > -- > Josh Berkus > Aglio Database Solutions > San Francisco >=20 > ---------------------------(end of broadcast)--------------------------- > TIP 1: subscribe and unsubscribe commands go to majordomo@postgresql.org >=20 > -- > No virus found in this incoming message. > Checked by AVG Anti-Virus. > Version: 7.0.300 / Virus Database: 265.6.10 - Release Date: 10/01/2005 >=20 > -- > No virus found in this outgoing message. > Checked by AVG Anti-Virus. > Version: 7.0.300 / Virus Database: 265.6.11 - Release Date: 12/01/2005 >=20 >=20 > ---------------------------(end of broadcast)--------------------------- > TIP 7: don't forget to increase your free space map settings >