From barai@cs.ucr.edu Wed Jan 18 18:09:57 2006 X-Original-To: pgsql-performance-postgresql.org@localhost.postgresql.org Received: from localhost (av.hub.org [200.46.204.144]) by postgresql.org (Postfix) with ESMTP id B7F2D9DC833 for ; Wed, 18 Jan 2006 14:09:57 -0400 (AST) Received: from postgresql.org ([200.46.204.71]) by localhost (av.hub.org [200.46.204.144]) (amavisd-new, port 10024) with ESMTP id 93755-08 for ; Wed, 18 Jan 2006 14:09:56 -0400 (AST) X-Greylist: from auto-whitelisted by SQLgrey- Received: from server10.araisoft.com (server10.araisoft.com [72.9.228.195]) by postgresql.org (Postfix) with ESMTP id B7BC89DC9FB for ; Wed, 18 Jan 2006 14:09:54 -0400 (AST) Received: from localhost (unknown [127.0.0.1]) by server10.araisoft.com (Postfix) with ESMTP id 38FDB3D6200E for ; Wed, 18 Jan 2006 10:09:51 -0800 (PST) Received: from server10.araisoft.com ([127.0.0.1]) by localhost (server10.araisoft.com [127.0.0.1]) (amavisd-new, port 10024) with ESMTP id 11304-02 for ; Wed, 18 Jan 2006 10:09:46 -0800 (PST) Received: from uni (uni.cs.ucr.edu [138.23.204.215]) by server10.araisoft.com (Postfix) with ESMTP id 2DBE53D6200D for ; Wed, 18 Jan 2006 10:09:46 -0800 (PST) From: "Benjamin Arai" To: Subject: 3WARE Card performance boost? Date: Wed, 18 Jan 2006 10:09:46 -0800 Message-ID: <00ee01c61c5a$5db2c870$d7cc178a@uni> MIME-Version: 1.0 Content-Type: multipart/alternative; boundary="----=_NextPart_000_00EF_01C61C17.4F8F8870" X-Mailer: Microsoft Office Outlook 11 X-MimeOLE: Produced By Microsoft MimeOLE V6.00.2900.2670 Thread-Index: AcYcWl0K9MCKAwJ5TNuMbMCEFq0pEQ== X-Virus-Scanned: by amavisd-new at araisoft.com X-Virus-Scanned: by amavisd-new at hub.org X-Spam-Status: No, score=0.221 required=5 tests=[AWL=0.220, HTML_MESSAGE=0.001] X-Spam-Score: 0.221 X-Spam-Level: X-Archive-Number: 200601/302 X-Sequence-Number: 16780 This is a multi-part message in MIME format. ------=_NextPart_000_00EF_01C61C17.4F8F8870 Content-Type: text/plain; charset="US-ASCII" Content-Transfer-Encoding: 7bit Hi, I am currently doing large weekly updates with fsync=off. My updates involves SELECT, UPDATE, DELETE and etc. Setting fsync=off works for me since I take a complete backup before the weekly update and run a "sync" and "CHECKPOINT" after each weekly update has completed to ensure the data is all written to disk. Obviously, I have done this to improve write performance for the update each week. My question is if I install a 3ware or similar card to replace my current software RAID 1 configuration, am I going to see a very large improvement? If so, what would be a ball park figure? Benjamin Arai barai@cs.ucr.edu http://www.benjaminarai.com ------=_NextPart_000_00EF_01C61C17.4F8F8870 Content-Type: text/html; charset="US-ASCII" Content-Transfer-Encoding: quoted-printable
Hi,
 
I am = currently doing=20 large weekly updates with fsync=3Doff.  My updates involves SELECT, = UPDATE,=20 DELETE and etc.  Setting fsync=3Doff works for me since I take a = complete=20 backup before the weekly update and run a "sync" and "CHECKPOINT" after = each=20 weekly update has completed to ensure the data is all written to = disk. =20
 
Obviously, I have=20 done this to improve write performance for the update each = week.  My=20 question is if I install a 3ware or similar card to replace my = current=20 software RAID 1 configuration, am I going to see a very large = improvement? =20 If so, what would be a ball park figure?
 
Benjamin = Arai
barai@cs.ucr.edu
http://www.benjaminarai.com
 
------=_NextPart_000_00EF_01C61C17.4F8F8870-- From jd@commandprompt.com Wed Jan 18 18:21:30 2006 X-Original-To: pgsql-performance-postgresql.org@localhost.postgresql.org Received: from localhost (av.hub.org [200.46.204.144]) by postgresql.org (Postfix) with ESMTP id C0A079DC9E1 for ; Wed, 18 Jan 2006 14:21:30 -0400 (AST) Received: from postgresql.org ([200.46.204.71]) by localhost (av.hub.org [200.46.204.144]) (amavisd-new, port 10024) with ESMTP id 95886-08 for ; Wed, 18 Jan 2006 14:21:30 -0400 (AST) X-Greylist: from auto-whitelisted by SQLgrey- Received: from hosting.commandprompt.com (128.commandprompt.com [207.173.200.128]) by postgresql.org (Postfix) with ESMTP id 41BF99DC9BA for ; Wed, 18 Jan 2006 14:21:27 -0400 (AST) Received: from [192.168.1.55] (fc1smp [66.93.38.87]) (authenticated bits=0) by hosting.commandprompt.com (8.13.4/8.13.4) with ESMTP id k0IIC8Xw029995; Wed, 18 Jan 2006 10:12:08 -0800 Message-ID: <43CE87D1.6010904@commandprompt.com> Date: Wed, 18 Jan 2006 10:24:17 -0800 From: "Joshua D. Drake" Organization: Command Prompt, Inc. User-Agent: Thunderbird 1.5 (X11/20051025) MIME-Version: 1.0 To: Benjamin Arai CC: pgsql-performance@postgresql.org Subject: Re: 3WARE Card performance boost? References: <00ee01c61c5a$5db2c870$d7cc178a@uni> In-Reply-To: <00ee01c61c5a$5db2c870$d7cc178a@uni> Content-Type: text/plain; charset=ISO-8859-1; format=flowed Content-Transfer-Encoding: 7bit X-Greylist: Sender succeded SMTP AUTH authentication, not delayed by milter-greylist-1.6 (hosting.commandprompt.com [192.168.1.101]); Wed, 18 Jan 2006 10:12:08 -0800 (PST) X-Virus-Scanned: by amavisd-new at hub.org X-Spam-Status: No, score=0.146 required=5 tests=[AWL=0.146] X-Spam-Score: 0.146 X-Spam-Level: X-Archive-Number: 200601/303 X-Sequence-Number: 16781 > Obviously, I have done this to improve write performance for the update > each week. My question is if I install a 3ware or similar card to > replace my current software RAID 1 configuration, am I going to see a > very large improvement? If so, what would be a ball park figure? Well that entirely depends on what level... 1. I would suggest LSI 150-6 not 3ware Why? Because 3ware does not make a midrange card that has a battery backed cache :). That is the only reason. 3ware makes good stuff. So anyway... LSI150-6 with Battery Backed cache option. Put 6 drives on it with a RAID 10 array, turn on write cache and you should have a hauling drive. Joshua D. Drake > > *Benjamin Arai* > barai@cs.ucr.edu > http://www.benjaminarai.com > -- The PostgreSQL Company - Command Prompt, Inc. 1.503.667.4564 PostgreSQL Replication, Consulting, Custom Development, 24x7 support Managed Services, Shared and Dedicated Hosting Co-Authors: plPHP, plPerlNG - http://www.commandprompt.com/ From barai@cs.ucr.edu Wed Jan 18 18:26:44 2006 X-Original-To: pgsql-performance-postgresql.org@localhost.postgresql.org Received: from localhost (av.hub.org [200.46.204.144]) by postgresql.org (Postfix) with ESMTP id CD5CA9DC833 for ; Wed, 18 Jan 2006 14:26:44 -0400 (AST) Received: from postgresql.org ([200.46.204.71]) by localhost (av.hub.org [200.46.204.144]) (amavisd-new, port 10024) with ESMTP id 99365-01 for ; Wed, 18 Jan 2006 14:26:43 -0400 (AST) X-Greylist: from auto-whitelisted by SQLgrey- Received: from server10.araisoft.com (server10.araisoft.com [72.9.228.195]) by postgresql.org (Postfix) with ESMTP id 328ED9DC9F2 for ; Wed, 18 Jan 2006 14:26:42 -0400 (AST) Received: from localhost (unknown [127.0.0.1]) by server10.araisoft.com (Postfix) with ESMTP id DA7A13D6200F for ; Wed, 18 Jan 2006 10:26:41 -0800 (PST) Received: from server10.araisoft.com ([127.0.0.1]) by localhost (server10.araisoft.com [127.0.0.1]) (amavisd-new, port 10024) with ESMTP id 02858-01 for ; Wed, 18 Jan 2006 10:26:37 -0800 (PST) Received: from uni (uni.cs.ucr.edu [138.23.204.215]) by server10.araisoft.com (Postfix) with ESMTP id C32C03D6200D for ; Wed, 18 Jan 2006 10:26:36 -0800 (PST) From: "Benjamin Arai" To: Subject: Re: 3WARE Card performance boost? Date: Wed, 18 Jan 2006 10:26:37 -0800 Message-ID: <011201c61c5c$b81cc520$d7cc178a@uni> MIME-Version: 1.0 Content-Type: multipart/alternative; boundary="----=_NextPart_000_0113_01C61C19.A9F98520" X-Mailer: Microsoft Office Outlook 11 In-Reply-To: <00ee01c61c5a$5db2c870$d7cc178a@uni> X-MimeOLE: Produced By Microsoft MimeOLE V6.00.2900.2670 Thread-Index: AcYcWl0K9MCKAwJ5TNuMbMCEFq0pEQAAk7CA X-Virus-Scanned: by amavisd-new at araisoft.com X-Virus-Scanned: by amavisd-new at hub.org X-Spam-Status: No, score=0.199 required=5 tests=[AWL=0.198, HTML_MESSAGE=0.001] X-Spam-Score: 0.199 X-Spam-Level: X-Archive-Number: 200601/304 X-Sequence-Number: 16782 This is a multi-part message in MIME format. ------=_NextPart_000_0113_01C61C19.A9F98520 Content-Type: text/plain; charset="US-ASCII" Content-Transfer-Encoding: 7bit My original plan was to buy a 3WARE card and put a 1GB of memory on it to improve writes but I am not sure if that is actually going to help the issue if fsync=off. Benjamin Arai barai@cs.ucr.edu http://www.benjaminarai.com _____ From: pgsql-performance-owner@postgresql.org [mailto:pgsql-performance-owner@postgresql.org] On Behalf Of Benjamin Arai Sent: Wednesday, January 18, 2006 10:10 AM To: pgsql-performance@postgresql.org Subject: [PERFORM] 3WARE Card performance boost? Hi, I am currently doing large weekly updates with fsync=off. My updates involves SELECT, UPDATE, DELETE and etc. Setting fsync=off works for me since I take a complete backup before the weekly update and run a "sync" and "CHECKPOINT" after each weekly update has completed to ensure the data is all written to disk. Obviously, I have done this to improve write performance for the update each week. My question is if I install a 3ware or similar card to replace my current software RAID 1 configuration, am I going to see a very large improvement? If so, what would be a ball park figure? Benjamin Arai barai@cs.ucr.edu http://www.benjaminarai.com ------=_NextPart_000_0113_01C61C19.A9F98520 Content-Type: text/html; charset="US-ASCII" Content-Transfer-Encoding: quoted-printable
My original plan was to buy a 3WARE card and = put a 1GB of=20 memory on it to improve writes but I am not sure if that is actually = going to=20 help the issue if fsync=3Doff.
 
Benjamin = Arai
barai@cs.ucr.edu
http://www.benjaminarai.com
 


From: = pgsql-performance-owner@postgresql.org=20 [mailto:pgsql-performance-owner@postgresql.org] On Behalf Of = Benjamin=20 Arai
Sent: Wednesday, January 18, 2006 10:10 = AM
To:=20 pgsql-performance@postgresql.org
Subject: [PERFORM] 3WARE = Card=20 performance boost?

Hi,
 
I am = currently=20 doing large weekly updates with fsync=3Doff.  My updates involves = SELECT,=20 UPDATE, DELETE and etc.  Setting fsync=3Doff works for me since I = take a=20 complete backup before the weekly update and run a "sync" and = "CHECKPOINT"=20 after each weekly update has completed to ensure the data is all = written to=20 disk. 
 
Obviously, I have=20 done this to improve write performance for the update each = week.  My=20 question is if I install a 3ware or similar card to replace my = current=20 software RAID 1 configuration, am I going to see a very large=20 improvement?  If so, what would be a ball park=20 figure?
 
Benjamin = Arai
barai@cs.ucr.edu
http://www.benjaminarai.com
 
------=_NextPart_000_0113_01C61C19.A9F98520-- From armtuk@gmail.com Wed Jan 18 19:12:48 2006 X-Original-To: pgsql-performance-postgresql.org@localhost.postgresql.org Received: from localhost (av.hub.org [200.46.204.144]) by postgresql.org (Postfix) with ESMTP id 79AE69DC9E1 for ; Wed, 18 Jan 2006 15:12:48 -0400 (AST) Received: from postgresql.org ([200.46.204.71]) by localhost (av.hub.org [200.46.204.144]) (amavisd-new, port 10024) with ESMTP id 07911-04 for ; Wed, 18 Jan 2006 15:12:45 -0400 (AST) X-Greylist: domain auto-whitelisted by SQLgrey- Received: from uproxy.gmail.com (uproxy.gmail.com [66.249.92.194]) by postgresql.org (Postfix) with ESMTP id 973CC9DCA03 for ; Wed, 18 Jan 2006 15:12:43 -0400 (AST) Received: by uproxy.gmail.com with SMTP id s2so4161uge for ; Wed, 18 Jan 2006 11:12:43 -0800 (PST) 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:content-transfer-encoding:content-disposition:references; b=Jd5qg+cDMnQlLqIEs4oO0yVwjwhgEe6yPiDNWEbUiBXPIQABsgRqWzHcGiWG9fhqOB57eLSpt5WyB6uMWRWENKSjqbqJ1nomfixDOg02AUDyJiTEeN5hIEOwrI2tQ7/rhyzNLCHPLLClTWxpesqQBZdOB+XpUBPLCpJW6QhHXgo= Received: by 10.66.254.16 with SMTP id b16mr2684036ugi; Wed, 18 Jan 2006 11:12:43 -0800 (PST) Received: by 10.67.22.1 with HTTP; Wed, 18 Jan 2006 11:12:43 -0800 (PST) Message-ID: <33c6269f0601181112t4ab4c2b0wd48a4e47ab5e71ec@mail.gmail.com> Date: Wed, 18 Jan 2006 14:12:43 -0500 From: Alex Turner To: "Joshua D. Drake" Subject: Re: 3WARE Card performance boost? Cc: Benjamin Arai , pgsql-performance@postgresql.org In-Reply-To: <43CE87D1.6010904@commandprompt.com> MIME-Version: 1.0 Content-Type: text/plain; charset=ISO-8859-1 Content-Transfer-Encoding: quoted-printable Content-Disposition: inline References: <00ee01c61c5a$5db2c870$d7cc178a@uni> <43CE87D1.6010904@commandprompt.com> X-Virus-Scanned: by amavisd-new at hub.org X-Spam-Status: No, score=0.12 required=5 tests=[AWL=0.120] X-Spam-Score: 0.12 X-Spam-Level: X-Archive-Number: 200601/306 X-Sequence-Number: 16784 http://www.3ware.com/products/serial_ata2-9000.asp Check their data sheet - the cards are BBU ready - all you have to do is order a BBU which you can from here: http://www.newegg.com/Product/Product.asp?Item=3DN82E16815999601 Alex. On 1/18/06, Joshua D. Drake wrote: > > > Obviously, I have done this to improve write performance for the update > > each week. My question is if I install a 3ware or similar card to > > replace my current software RAID 1 configuration, am I going to see a > > very large improvement? If so, what would be a ball park figure? > > Well that entirely depends on what level... > > 1. I would suggest LSI 150-6 not 3ware > > Why? > > Because 3ware does not make a midrange card that has a battery backed > cache :). That is the only reason. 3ware makes good stuff. > > So anyway... LSI150-6 with Battery Backed cache option. Put 6 drives > on it with a RAID 10 array, turn on write cache and you should have > a hauling drive. > > Joshua D. Drake > > > > > > > *Benjamin Arai* > > barai@cs.ucr.edu > > http://www.benjaminarai.com > > > > > -- > The PostgreSQL Company - Command Prompt, Inc. 1.503.667.4564 > PostgreSQL Replication, Consulting, Custom Development, 24x7 support > Managed Services, Shared and Dedicated Hosting > Co-Authors: plPHP, plPerlNG - http://www.commandprompt.com/ > > ---------------------------(end of broadcast)--------------------------- > TIP 6: explain analyze is your friend > From armtuk@gmail.com Wed Jan 18 19:17:09 2006 X-Original-To: pgsql-performance-postgresql.org@localhost.postgresql.org Received: from localhost (av.hub.org [200.46.204.144]) by postgresql.org (Postfix) with ESMTP id B1C769DC87F for ; Wed, 18 Jan 2006 15:17:09 -0400 (AST) Received: from postgresql.org ([200.46.204.71]) by localhost (av.hub.org [200.46.204.144]) (amavisd-new, port 10024) with ESMTP id 05247-09 for ; Wed, 18 Jan 2006 15:17:09 -0400 (AST) X-Greylist: domain auto-whitelisted by SQLgrey- Received: from uproxy.gmail.com (uproxy.gmail.com [66.249.92.206]) by postgresql.org (Postfix) with ESMTP id DC6E19DC9A9 for ; Wed, 18 Jan 2006 15:17:05 -0400 (AST) Received: by uproxy.gmail.com with SMTP id s2so6018uge for ; Wed, 18 Jan 2006 11:17:06 -0800 (PST) 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:content-transfer-encoding:content-disposition:references; b=PiChSjjtBXvRG1sTrZSz9jSloKTMp3Fc8LsP2o5wOIl5ohTFpyZ8VdxCh/Qls/KJ3buuR4MpHzrmqUwibeToPn+GCdgpsgwwWVksQc2ejcMPkV6ydYcyxVEMDr1jPO+W+uO9+zSN8T2e4UBhp5XHf4hp0Sgn5hnGxKt+PNgf9KY= Received: by 10.66.249.17 with SMTP id w17mr2725249ugh; Wed, 18 Jan 2006 11:17:04 -0800 (PST) Received: by 10.67.22.1 with HTTP; Wed, 18 Jan 2006 11:17:04 -0800 (PST) Message-ID: <33c6269f0601181117j10bdeb27ke733c9b032e22cbc@mail.gmail.com> Date: Wed, 18 Jan 2006 14:17:04 -0500 From: Alex Turner To: Benjamin Arai Subject: Re: 3WARE Card performance boost? Cc: pgsql-performance@postgresql.org In-Reply-To: <00ee01c61c5a$5db2c870$d7cc178a@uni> MIME-Version: 1.0 Content-Type: text/plain; charset=ISO-8859-1 Content-Transfer-Encoding: quoted-printable Content-Disposition: inline References: <00ee01c61c5a$5db2c870$d7cc178a@uni> X-Virus-Scanned: by amavisd-new at hub.org X-Spam-Status: No, score=0.786 required=5 tests=[AWL=-0.546, RCVD_IN_BL_SPAMCOP_NET=1.332] X-Spam-Score: 0.786 X-Spam-Level: X-Archive-Number: 200601/308 X-Sequence-Number: 16786 A 3ware card will re-order your writes to put them more in disk order, which will probably improve performance a bit, but just going from a software RAID 1 to a hardware RAID 1, I would not imagine that you will see much of a performance boost. Really to get better performance you will need to add more drives, or faster drives. If you are currently running 7200 RPM consumer drives, going to a 10000RPM WD Raptor drive will probably increase performance by about 30%, again not all that much. Alex On 1/18/06, Benjamin Arai wrote: > > Hi, > > I am currently doing large weekly updates with fsync=3Doff. My updates > involves SELECT, UPDATE, DELETE and etc. Setting fsync=3Doff works for m= e > since I take a complete backup before the weekly update and run a "sync" = and > "CHECKPOINT" after each weekly update has completed to ensure the data is > all written to disk. > > Obviously, I have done this to improve write performance for the update e= ach > week. My question is if I install a 3ware or similar card to replace my > current software RAID 1 configuration, am I going to see a very large > improvement? If so, what would be a ball park figure? > > > Benjamin Arai > barai@cs.ucr.edu > http://www.benjaminarai.com > From J.Kraaijeveld@Askesis.nl Wed Jan 18 19:23:31 2006 X-Original-To: pgsql-performance-postgresql.org@localhost.postgresql.org Received: from localhost (av.hub.org [200.46.204.144]) by postgresql.org (Postfix) with ESMTP id 6856B9DC820 for ; Wed, 18 Jan 2006 15:23:31 -0400 (AST) Received: from postgresql.org ([200.46.204.71]) by localhost (av.hub.org [200.46.204.144]) (amavisd-new, port 10024) with ESMTP id 06459-06 for ; Wed, 18 Jan 2006 15:23:31 -0400 (AST) X-Greylist: from auto-whitelisted by SQLgrey- Received: from obelix.askesis.nl (laudanum.demon.nl [82.161.125.16]) by postgresql.org (Postfix) with ESMTP id BF98D9DC83F for ; Wed, 18 Jan 2006 15:23:25 -0400 (AST) Received: obelix.askesis.nl 172.31.0.1 from 172.31.1.8 172.31.1.8 via HTTP with MS-WebStorage 6.0.6249 Received: from Panoramix.Askesis.nl by obelix.askesis.nl; 18 Jan 2006 20:23:25 +0100 Subject: Re: 3WARE Card performance boost? From: Joost Kraaijeveld To: Benjamin Arai Cc: pgsql-performance@postgresql.org In-Reply-To: <011201c61c5c$b81cc520$d7cc178a@uni> References: <011201c61c5c$b81cc520$d7cc178a@uni> Content-Type: text/plain Content-Transfer-Encoding: 7bit Date: Wed, 18 Jan 2006 20:23:25 +0100 Message-Id: <1137612205.12172.3.camel@Panoramix.Askesis.nl> Mime-Version: 1.0 X-Mailer: Evolution 2.2.3 X-Virus-Scanned: by amavisd-new at hub.org X-Spam-Status: No, score=0.061 required=5 tests=[AWL=0.060, UNPARSEABLE_RELAY=0.001] X-Spam-Score: 0.061 X-Spam-Level: X-Archive-Number: 200601/309 X-Sequence-Number: 16787 On Wed, 2006-01-18 at 10:26 -0800, Benjamin Arai wrote: > My original plan was to buy a 3WARE card and put a 1GB of memory on it > to improve writes but I am not sure if that is actually going to help > the issue if fsync=off. My experience with a 3Ware 9500S-8 card are rather disappointing, especially the write performance of the card, which is extremely poor. Reading is OK. -- Groeten, Joost Kraaijeveld Askesis B.V. Molukkenstraat 14 6524NB Nijmegen tel: 024-3888063 / 06-51855277 fax: 024-3608416 e-mail: J.Kraaijeveld@Askesis.nl web: www.askesis.nl From wyu@talisys.com Wed Jan 18 21:58:17 2006 X-Original-To: pgsql-performance-postgresql.org@localhost.postgresql.org Received: from localhost (av.hub.org [200.46.204.144]) by postgresql.org (Postfix) with ESMTP id F228E9DCA0C for ; Wed, 18 Jan 2006 17:58:17 -0400 (AST) Received: from postgresql.org ([200.46.204.71]) by localhost (av.hub.org [200.46.204.144]) (amavisd-new, port 10024) with ESMTP id 84994-08 for ; Wed, 18 Jan 2006 17:58:19 -0400 (AST) X-Greylist: from auto-whitelisted by SQLgrey- Received: from floppy.pyrenet.fr (news.pyrenet.fr [194.116.145.2]) by postgresql.org (Postfix) with ESMTP id 0305E9DCA3D for ; Wed, 18 Jan 2006 17:58:13 -0400 (AST) Received: by floppy.pyrenet.fr (Postfix, from userid 106) id DC6CF30F0A; Wed, 18 Jan 2006 22:58:15 +0100 (MET) From: William Yu X-Newsgroups: pgsql.performance Subject: Re: 3WARE Card performance boost? Date: Wed, 18 Jan 2006 13:58:09 -0800 Organization: Hub.Org Networking Services Lines: 15 Message-ID: References: <00ee01c61c5a$5db2c870$d7cc178a@uni> Mime-Version: 1.0 Content-Type: text/plain; charset=ISO-8859-1; format=flowed Content-Transfer-Encoding: 7bit X-Complaints-To: usenet@news.hub.org User-Agent: Thunderbird 1.5 (Windows/20051201) In-Reply-To: <00ee01c61c5a$5db2c870$d7cc178a@uni> To: pgsql-performance@postgresql.org X-Virus-Scanned: by amavisd-new at hub.org X-Spam-Status: No, score=0.06 required=5 tests=[AWL=0.060] X-Spam-Score: 0.06 X-Spam-Level: X-Archive-Number: 200601/312 X-Sequence-Number: 16790 Benjamin Arai wrote: > Obviously, I have done this to improve write performance for the update > each week. My question is if I install a 3ware or similar card to > replace my current software RAID 1 configuration, am I going to see a > very large improvement? If so, what would be a ball park figure? The key is getting a card with the ability to upgrade the onboard ram. Our previous setup was a LSI MegaRAID 320-1 (128MB), 4xRAID10, fsync=off. Replaced it with a ARC-1170 (1GB) w/ 24x7200RPM SATA2 drives (split into 3 8-drive RAID6 arrays) and performance for us is through the ceiling. For OLTP type updates, we've gotten about +80% increase. For massive 1-statement updates, performance increase is in the +triple digits. From sgunderson@bigfoot.com Wed Jan 18 22:02:29 2006 X-Original-To: pgsql-performance-postgresql.org@localhost.postgresql.org Received: from localhost (av.hub.org [200.46.204.144]) by postgresql.org (Postfix) with ESMTP id B16E09DCA1E for ; Wed, 18 Jan 2006 18:02:29 -0400 (AST) Received: from postgresql.org ([200.46.204.71]) by localhost (av.hub.org [200.46.204.144]) (amavisd-new, port 10024) with ESMTP id 91070-10 for ; Wed, 18 Jan 2006 18:02:29 -0400 (AST) X-Greylist: from auto-whitelisted by SQLgrey- Received: from cassarossa.samfundet.no (cassarossa.samfundet.no [129.241.93.19]) by postgresql.org (Postfix) with ESMTP id 3AFB09DC9F1 for ; Wed, 18 Jan 2006 18:02:25 -0400 (AST) Received: from trofast.ipv6.sesse.net ([2001:700:300:dc03:20e:cff:fe36:a766] helo=trofast.sesse.net) by cassarossa.samfundet.no with esmtp (Exim 4.50) id 1EzLNq-0005wj-O8 for pgsql-performance@postgresql.org; Wed, 18 Jan 2006 23:02:26 +0100 Received: from sesse by trofast.sesse.net with local (Exim 3.36 #1 (Debian)) id 1EzLNw-0000NZ-00 for ; Wed, 18 Jan 2006 23:02:32 +0100 Date: Wed, 18 Jan 2006 23:02:32 +0100 From: "Steinar H. Gunderson" To: pgsql-performance@postgresql.org Subject: Re: 3WARE Card performance boost? Message-ID: <20060118220232.GB1393@uio.no> Mail-Followup-To: pgsql-performance@postgresql.org References: <00ee01c61c5a$5db2c870$d7cc178a@uni> MIME-Version: 1.0 Content-Type: text/plain; charset=utf-8 Content-Disposition: inline In-Reply-To: X-Operating-System: Linux 2.6.14.3 on a x86_64 X-Message-Flag: Outlook? --> http://www.mozilla.org/products/thunderbird/ User-Agent: Mutt/1.5.11 X-Virus-Scanned: by amavisd-new at hub.org X-Spam-Status: No, score=0.064 required=5 tests=[AWL=0.064] X-Spam-Score: 0.064 X-Spam-Level: X-Archive-Number: 200601/313 X-Sequence-Number: 16791 On Wed, Jan 18, 2006 at 01:58:09PM -0800, William Yu wrote: > The key is getting a card with the ability to upgrade the onboard ram. > > Our previous setup was a LSI MegaRAID 320-1 (128MB), 4xRAID10, > fsync=off. Replaced it with a ARC-1170 (1GB) w/ 24x7200RPM SATA2 drives > (split into 3 8-drive RAID6 arrays) and performance for us is through > the ceiling. Well, the fact that you went from four to 24 disks would perhaps be a bigger factor than the amount of RAM... /* Steinar */ -- Homepage: http://www.sesse.net/ From wyu@talisys.com Wed Jan 18 22:15:29 2006 X-Original-To: pgsql-performance-postgresql.org@localhost.postgresql.org Received: from localhost (av.hub.org [200.46.204.144]) by postgresql.org (Postfix) with ESMTP id C74479DCA0C for ; Wed, 18 Jan 2006 18:15:29 -0400 (AST) Received: from postgresql.org ([200.46.204.71]) by localhost (av.hub.org [200.46.204.144]) (amavisd-new, port 10024) with ESMTP id 04337-06 for ; Wed, 18 Jan 2006 18:15:31 -0400 (AST) X-Greylist: from auto-whitelisted by SQLgrey- Received: from floppy.pyrenet.fr (floppy.pyrenet.fr [194.116.145.2]) by postgresql.org (Postfix) with ESMTP id 146F99DC87F for ; Wed, 18 Jan 2006 18:15:27 -0400 (AST) Received: by floppy.pyrenet.fr (Postfix, from userid 106) id 08D2B30F0A; Wed, 18 Jan 2006 23:15:29 +0100 (MET) From: William Yu X-Newsgroups: pgsql.performance Subject: Re: 3WARE Card performance boost? Date: Wed, 18 Jan 2006 14:15:22 -0800 Organization: Hub.Org Networking Services Lines: 27 Message-ID: References: <00ee01c61c5a$5db2c870$d7cc178a@uni> <20060118220232.GB1393@uio.no> Mime-Version: 1.0 Content-Type: text/plain; charset=UTF-8; format=flowed Content-Transfer-Encoding: 7bit X-Complaints-To: usenet@news.hub.org User-Agent: Thunderbird 1.5 (Windows/20051201) In-Reply-To: <20060118220232.GB1393@uio.no> To: pgsql-performance@postgresql.org X-Virus-Scanned: by amavisd-new at hub.org X-Spam-Status: No, score=0.068 required=5 tests=[AWL=0.068] X-Spam-Score: 0.068 X-Spam-Level: X-Archive-Number: 200601/314 X-Sequence-Number: 16792 Steinar H. Gunderson wrote: > On Wed, Jan 18, 2006 at 01:58:09PM -0800, William Yu wrote: >> The key is getting a card with the ability to upgrade the onboard ram. >> >> Our previous setup was a LSI MegaRAID 320-1 (128MB), 4xRAID10, >> fsync=off. Replaced it with a ARC-1170 (1GB) w/ 24x7200RPM SATA2 drives >> (split into 3 8-drive RAID6 arrays) and performance for us is through >> the ceiling. > > Well, the fact that you went from four to 24 disks would perhaps be a bigger > factor than the amount of RAM... > > /* Steinar */ Actually no. Our 2xOpteron 244 server is NOT fast enough to drive an array this large. That's why we had to split it up into 3 different arrays. I tried all different RAID configs and once past about 8 drives, I got the same performance no matter what because the CPU was pegged at 100%. Right now, 2 of the arrays are just mirroring each other because we can't seem utilize the performance right now. (Also protects against cabling/power supply issues as we're using 3 seperate external enclosures.) The 1GB RAM is much bigger because it almost completely hides the write activity. Looking at iostat while all our jobs are running, there's almost no disk activity. If I manually type "sync", I see 1 big 250MB-500MB write storm for 2 seconds but otherwise, writes just slowly dribble out to disk. From jnasby@pervasive.com Wed Jan 18 23:05:31 2006 X-Original-To: pgsql-performance-postgresql.org@localhost.postgresql.org Received: from localhost (av.hub.org [200.46.204.144]) by postgresql.org (Postfix) with ESMTP id 7CC8C9DC899 for ; Wed, 18 Jan 2006 19:05:31 -0400 (AST) Received: from postgresql.org ([200.46.204.71]) by localhost (av.hub.org [200.46.204.144]) (amavisd-new, port 10024) with ESMTP id 45270-06 for ; Wed, 18 Jan 2006 19:05:33 -0400 (AST) X-Greylist: from auto-whitelisted by SQLgrey- Received: from noel.decibel.org (noel.decibel.org [67.100.216.10]) by postgresql.org (Postfix) with ESMTP id 4FB439DC87B for ; Wed, 18 Jan 2006 19:05:29 -0400 (AST) Received: by noel.decibel.org (Postfix, from userid 1001) id 46F5F3982E; Wed, 18 Jan 2006 17:05:32 -0600 (CST) Date: Wed, 18 Jan 2006 17:05:32 -0600 From: "Jim C. Nasby" To: "Joshua D. Drake" Cc: Benjamin Arai , pgsql-performance@postgresql.org Subject: Re: 3WARE Card performance boost? Message-ID: <20060118230532.GA17896@pervasive.com> References: <00ee01c61c5a$5db2c870$d7cc178a@uni> <43CE87D1.6010904@commandprompt.com> Mime-Version: 1.0 Content-Type: text/plain; charset=us-ascii Content-Disposition: inline In-Reply-To: <43CE87D1.6010904@commandprompt.com> X-Operating-System: FreeBSD 6.0-RELEASE amd64 X-Distributed: Join the Effort! http://www.distributed.net User-Agent: Mutt/1.5.11 X-Virus-Scanned: by amavisd-new at hub.org X-Spam-Status: No, score=0.095 required=5 tests=[AWL=0.095] X-Spam-Score: 0.095 X-Spam-Level: X-Archive-Number: 200601/319 X-Sequence-Number: 16797 On Wed, Jan 18, 2006 at 10:24:17AM -0800, Joshua D. Drake wrote: > Because 3ware does not make a midrange card that has a battery backed > cache :). That is the only reason. 3ware makes good stuff. Why worry about battery-backup if he's running with fsync off? -- Jim C. Nasby, Sr. Engineering Consultant jnasby@pervasive.com Pervasive Software http://pervasive.com work: 512-231-6117 vcard: http://jim.nasby.net/pervasive.vcf cell: 512-569-9461 From vivek@khera.org Thu Jan 19 21:38:35 2006 X-Original-To: pgsql-performance-postgresql.org@localhost.postgresql.org Received: from localhost (av.hub.org [200.46.204.144]) by postgresql.org (Postfix) with ESMTP id 7DCF29DCA11 for ; Thu, 19 Jan 2006 17:38:35 -0400 (AST) Received: from postgresql.org ([200.46.204.71]) by localhost (av.hub.org [200.46.204.144]) (amavisd-new, port 10024) with ESMTP id 14120-05 for ; Thu, 19 Jan 2006 17:38:36 -0400 (AST) X-Greylist: from auto-whitelisted by SQLgrey- Received: from yertle.kcilink.com (yertle.kcilink.com [65.205.34.180]) by postgresql.org (Postfix) with ESMTP id 5AE8A9DCA00 for ; Thu, 19 Jan 2006 17:38:32 -0400 (AST) Received: from [192.168.7.103] (host-103.int.kcilink.com [192.168.7.103]) by yertle.kcilink.com (Postfix) with ESMTP id 519E2B80F for ; Thu, 19 Jan 2006 16:38:34 -0500 (EST) Mime-Version: 1.0 (Apple Message framework v746.2) In-Reply-To: <00ee01c61c5a$5db2c870$d7cc178a@uni> References: <00ee01c61c5a$5db2c870$d7cc178a@uni> Content-Type: text/plain; charset=US-ASCII; delsp=yes; format=flowed Message-Id: <32A67C0F-9726-4E79-AA12-B1D2AD83748A@khera.org> Content-Transfer-Encoding: 7bit From: Vivek Khera Subject: Re: 3WARE Card performance boost? Date: Thu, 19 Jan 2006 16:38:33 -0500 To: Postgresql Performance X-Mailer: Apple Mail (2.746.2) X-Virus-Scanned: by amavisd-new at hub.org X-Spam-Status: No, score=0.042 required=5 tests=[AWL=0.042] X-Spam-Score: 0.042 X-Spam-Level: X-Archive-Number: 200601/329 X-Sequence-Number: 16807 On Jan 18, 2006, at 1:09 PM, Benjamin Arai wrote: > Obviously, I have done this to improve write performance for the > update each > week. My question is if I install a 3ware or similar card to > replace my I'll bet that if you increase your checkpoint_segments (and corresponding timeout value) to something in the 10's or higher it will help you a lot. From armtuk@gmail.com Thu Jan 19 22:54:33 2006 X-Original-To: pgsql-performance-postgresql.org@localhost.postgresql.org Received: from localhost (av.hub.org [200.46.204.144]) by postgresql.org (Postfix) with ESMTP id 8328C9DCB53 for ; Thu, 19 Jan 2006 18:54:33 -0400 (AST) Received: from postgresql.org ([200.46.204.71]) by localhost (av.hub.org [200.46.204.144]) (amavisd-new, port 10024) with ESMTP id 28793-07 for ; Thu, 19 Jan 2006 18:54:35 -0400 (AST) X-Greylist: domain auto-whitelisted by SQLgrey- Received: from uproxy.gmail.com (uproxy.gmail.com [66.249.92.202]) by postgresql.org (Postfix) with ESMTP id AF4ED9DCB4F for ; Thu, 19 Jan 2006 18:54:30 -0400 (AST) Received: by uproxy.gmail.com with SMTP id s2so104484uge for ; Thu, 19 Jan 2006 14:54:32 -0800 (PST) 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:content-transfer-encoding:content-disposition:references; b=RGqtYpNhmSlDgi+EEcwOrBUDnp9WsjYl/xHSzWjCiSFGrELokiDcVTDIUUTs8HCrTGiI8dAwtOoO5+JUsaDtM9l5pAVptk9aH8U5jiNwIZdpNo3prtumFK58KX1MFKjgmHU5EM1bFpyKKpUdQwYbdLIZdC2hajGQ9MxqrBAy4vw= Received: by 10.66.241.1 with SMTP id o1mr485432ugh; Thu, 19 Jan 2006 14:54:32 -0800 (PST) Received: by 10.67.22.1 with HTTP; Thu, 19 Jan 2006 14:54:32 -0800 (PST) Message-ID: <33c6269f0601191454u65191b61vcd105256db94a78d@mail.gmail.com> Date: Thu, 19 Jan 2006 17:54:32 -0500 From: Alex Turner To: William Yu Subject: Re: 3WARE Card performance boost? Cc: pgsql-performance@postgresql.org In-Reply-To: MIME-Version: 1.0 Content-Type: text/plain; charset=ISO-8859-1 Content-Transfer-Encoding: quoted-printable Content-Disposition: inline References: <00ee01c61c5a$5db2c870$d7cc178a@uni> X-Virus-Scanned: by amavisd-new at hub.org X-Spam-Status: No, score=0.209 required=5 tests=[AWL=0.209] X-Spam-Score: 0.209 X-Spam-Level: X-Archive-Number: 200601/333 X-Sequence-Number: 16811 He's talking about RAID 1 here, not a gargantuan RAID 6. Onboard RAM on the controller card is going to make very little difference. All it will do is allow the card to re-order writes to a point (not all cards even do this). Alex. On 1/18/06, William Yu wrote: > Benjamin Arai wrote: > > Obviously, I have done this to improve write performance for the update > > each week. My question is if I install a 3ware or similar card to > > replace my current software RAID 1 configuration, am I going to see a > > very large improvement? If so, what would be a ball park figure? > > The key is getting a card with the ability to upgrade the onboard ram. > > Our previous setup was a LSI MegaRAID 320-1 (128MB), 4xRAID10, > fsync=3Doff. Replaced it with a ARC-1170 (1GB) w/ 24x7200RPM SATA2 drives > (split into 3 8-drive RAID6 arrays) and performance for us is through > the ceiling. > > For OLTP type updates, we've gotten about +80% increase. For massive > 1-statement updates, performance increase is in the +triple digits. > > ---------------------------(end of broadcast)--------------------------- > TIP 2: Don't 'kill -9' the postmaster >