From balazs@neusolutions.com Thu Jul 17 02:57:17 2003 X-Original-To: pgsql-performance-postgresql.org@localhost.postgresql.org Received: from localhost (unknown [64.117.224.192]) by svr1.postgresql.org (Postfix) with ESMTP id 0D138CC415 for ; Thu, 17 Jul 2003 02:57:17 +0000 (GMT) Received: from svr1.postgresql.org ([64.117.224.193]) by localhost (svr4.postgresql.org [64.117.224.192]) (amavisd-new, port 10024) with ESMTP id 60016-07 for ; Thu, 17 Jul 2003 02:57:35 +0000 (GMT) Received: from v2.intertune.com (unknown [209.75.26.20]) by svr1.postgresql.org (Postfix) with ESMTP id EBC5CCADB5 for ; Wed, 16 Jul 2003 23:57:10 -0300 (ADT) Received: from home01 (66-75-1-38.san.rr.com [66.75.1.38]) (authenticated) by v2.intertune.com (8.11.6/8.11.6) with ESMTP id h6H3K3i17635 for ; Wed, 16 Jul 2003 20:20:03 -0700 Message-ID: <004b01c34c0f$256bfb80$0600a8c0@home01> From: "Balazs Wellisch" To: Subject: Hardware performance Date: Wed, 16 Jul 2003 19:57:22 -0700 MIME-Version: 1.0 Content-Type: multipart/alternative; boundary="----=_NextPart_000_0048_01C34BD4.789C1230" X-Priority: 3 X-MSMail-Priority: Normal X-Mailer: Microsoft Outlook Express 6.00.2800.1158 X-MimeOLE: Produced By Microsoft MimeOLE V6.00.2800.1165 X-Virus-Scanned: by amavisd-new at postgresql.org X-Spam-Status: No, hits=0.6 tagged_above=0.0 required=5.0 tests=BAYES_30, HTML_20_30 X-Spam-Level: X-Archive-Number: 200307/239 X-Sequence-Number: 2532 This is a multi-part message in MIME format. ------=_NextPart_000_0048_01C34BD4.789C1230 Content-Type: text/plain; charset="iso-8859-1" Content-Transfer-Encoding: quoted-printable Hi all, first of all I'd like to thank everyone who responded to my earlier post. I= have a much better understanding of postgres performance tuning now. In ca= se anyone's interested we've decided to go with RH9 and PostgreSQL 7.3 and = we'll do the OS and DB tuning ourselves. (should be a good learning experie= nce) We are now getting ready to purchase the hardware that will be used to run = the database server. We're spending quite a bit of money on it because this= will eventually, if things go well within two months, become a production = server. We're getting all RH certified hardware from Dell. (Dell 2650) We're now stuck on the question of what type of RAID configuration to use f= or this server. RAID 5 offers the best fault tolerance but doesn't perform = all that well. RAID 10 offers much better performance, but no hot swap. Or = should we not use RAID at all. I know that ideally the log (WAL) files shou= ld reside on a separate disk from the rest of the DB. Should we use 4 separ= ate drives instead? One for the OS, one for data, one for WAL, one for swap= ? Or RAID 10 for everything plus 1 drive for WAL? Or RAID 5 for everything? We have the budget for 5 drives. Does anyone have any real world experience= with what hard drive configuration works best for postgres? This is going = to be a dedicated DB server. There are going to be a large number of transa= ctions being written to the database. (Information is logged from a separat= e app through ODBC to postgres) And there will be some moderately complex q= ueries run concurrently to present this information in the form of various = reports on the web. (The app server is a separate machine and will connect = to the DB through JDBC to create the HTML reports) Any thoughts, ideas, comments would be appreciated. Thank you, Balazs Wellisch Neu Solutions balazs@neusolutions.com ------=_NextPart_000_0048_01C34BD4.789C1230 Content-Type: text/html; charset="iso-8859-1" Content-Transfer-Encoding: quoted-printable
Hi all,
 
first of all I'd like to thank everyone wh= o=20 responded to my earlier post. I have a much better understanding of postgre= s=20 performance tuning now. In case anyone's interested we've decided to go wit= h RH9=20 and PostgreSQL 7.3 and we'll do the OS and DB tuning ourselves. (should be = a=20 good learning experience)
 
We are now getting ready to purchase the h= ardware=20 that will be used to run the database server. We're spending quite a bit of= =20 money on it because this will eventually, if things go well within two= =20 months, become a production server. We're getting all RH certified hardware= from=20 Dell. (Dell 2650)
 
We're now stuck on the question of what ty= pe of=20 RAID configuration to use for this server. RAID 5 offers the best fault=20 tolerance but doesn't perform all that well. RAID 10 offers much better=20 performance, but no hot swap. Or should we not use RAID at all. I know that= =20 ideally the log (WAL) files should reside on a separate disk from the rest = of=20 the DB. Should we use 4 separate drives instead? One for the OS, one for da= ta,=20 one for WAL, one for swap? Or RAID 10 for everything plus 1 drive for WAL? = Or=20 RAID 5 for everything?
 
We have the budget for 5 drives. Does anyo= ne have=20 any real world experience with what hard drive configuration works best for= =20 postgres? This is going to be a dedicated DB server. There are going to be = a=20 large number of transactions being written to the database. (Information is= =20 logged from a separate app through ODBC to postgres) And there will be some= =20 moderately complex queries run concurrently to present this information&nbs= p;in=20 the form of various reports on the web. (The app server is a separate machi= ne=20 and will connect to the DB through JDBC to create the HTML reports)<= /DIV>
 
Any thoughts, ideas, comments would be=20 appreciated.
 
Thank you,
 
Balazs Wellisch
Neu Solutions
balazs@neusolutions.com<= /DIV>
 
------=_NextPart_000_0048_01C34BD4.789C1230-- From rfail@posportal.com Thu Jul 17 04:25:42 2003 X-Original-To: pgsql-performance-postgresql.org@localhost.postgresql.org Received: from localhost (unknown [64.117.225.181]) by svr1.postgresql.org (Postfix) with ESMTP id 21BCBCC88F for ; Thu, 17 Jul 2003 04:25:42 +0000 (GMT) Received: from svr1.postgresql.org ([64.117.224.193]) by localhost (svr5.postgresql.org [64.117.225.181]) (amavisd-new, port 10024) with ESMTP id 35392-10 for ; Thu, 17 Jul 2003 04:25:59 +0000 (GMT) Received: from pos_pdc.posportal.com (unknown [12.158.169.100]) by svr1.postgresql.org (Postfix) with ESMTP id 7A0ADCC886 for ; Thu, 17 Jul 2003 01:25:30 -0300 (ADT) X-MimeOLE: Produced By Microsoft Exchange V6.0.6249.0 content-class: urn:content-classes:message MIME-Version: 1.0 Content-Type: text/plain; charset="utf-8" Content-Transfer-Encoding: base64 Subject: Re: Hardware performance Date: Wed, 16 Jul 2003 21:25:43 -0700 Message-ID: <9B1C77393DED0D4B9DAA1AA1742942DA3BCCA3@pos_pdc.posportal.com> X-MS-Has-Attach: X-MS-TNEF-Correlator: Thread-Topic: [PERFORM] Hardware performance Thread-Index: AcNMDzqIhh5+uYI3QA6yk4RNVGBPvgACDyAP From: "Roman Fail" To: "Balazs Wellisch" , X-Virus-Scanned: by amavisd-new at postgresql.org X-Archive-Number: 200307/240 X-Sequence-Number: 2533 SSd2ZSBnb3QgYSBEZWxsIDI2NTAgc2V0IHVwIHdpdGggNSBkcml2ZXMgYW5k IGEgc2VwYXJhdGUgYXBwIHNlcnZlciBjb25uZWN0aW5nIHdpdGggSkRCQy4g IFNpbmNlIHlvdSd2ZSBvbmx5IGdvdCA1IGRyaXZlcywgbXkgY29uY2x1c2lv biByZWdhcmRpbmcgdGhlIGJlc3QgYmFsYW5jZSBvZiBwZXJmb3JtYW5jZSBh bmQgcmVkdW5kYW5jeSB3YXM6DQogDQoyIGRyaXZlcyBoYXZlIHRoZSBPUywg c3dhcCwgYW5kIFdBTCBpbiBSQUlELTENCjMgZHJpdmVzIGhhdmUgdGhlIGRh dGEgaW4gUkFJRC01DQogDQpJZiB5b3UgY2FuIGFmZm9yZCBpdCwgZ2V0IHRo ZSAyKzMgc3BsaXQgYmFja3BsYW5lIGFuZCBtYWtlIHRoZSAzIGRhdGEgZHJp dmVzIHRoZSBiaWdnZXN0LCBmYXN0ZXN0IHlvdSBjYW4gYWZmb3JkLiAgQ3Vy cmVudGx5IHRoYXQgbWVhbnMgdGhlIDE1ayA3M0dCIGRyaXZlcywgd2hpY2gg d291bGQgZ2l2ZSB5b3UgMTQ2R0IgZm9yIGRhdGEuICBNYWtlIHRoZSBPUyBk cml2ZXMgc21hbGxlciBhbmQgc2xvd2VyIGlmIHlvdSBuZWVkIHRvIHNhdmUg Y2FzaC4gIA0KIA0KSWYgb25seSBpdCBoYWQgc2l4IGRyaXZlIGJheXMuLi4u eW91IGNvdWxkIHVzZSA0IGRyaXZlcyBmb3IgdGhlIGRhdGEgYW5kIGRvIFJB SUQtMTAuICBJZiB5b3UndmUgZ290IHRoZSBhZGRpdGlvbmFsIHJhY2tzcGFj ZSBhdmFpbGFibGUsIHlvdSBjb3VsZCBnZXQgdGhlIDVVIERlbGwgMjYwMCBp bnN0ZWFkIGZvciB0aGUgc2FtZSBiYWxscGFyayBjb3N0LiAgSWYgeW91IG9y ZGVyIGl0IHdpdGggcmFjayByYWlscywgaXQgY29tZXMgYWxsIHNldCB1cCBm b3IgcmFjayBpbnN0YWxsYXRpb24uLi5hIHNwZWNpYWwgc2lkZXdheXMgZmFj ZXBsYXRlIGFuZCBldmVyeXRoaW5nLg0KIA0KQnkgdGhlIHdheSwgUkFJRC01 IGlzIG5vdCB0aGUgYmVzdCBmYXVsdCB0b2xlcmFuY2UsIFJBSUQtMSBvciBS QUlELTEwIGlzLiAgQW5kIHlvdSBjYW4gY2VydGFpbmx5IGhvdC1zd2FwIFJB SUQtMTAgYXJyYXlzLiAgSSd2ZSBhY3R1YWxseSBkb25lIGl0Li4uLnJlY2Vu dGx5ISAgSSBhbSBvZiB0aGUgbWluZCB0aGF0IHNpbmdsZSBkcml2ZXMgYXJl IG5vdCBhbiBvcHRpb24gZm9yIHByb2R1Y3Rpb24gc2VydmVycyAtIEkganVz dCBkb24ndCBuZWVkIHRoZSBwYWluIG9mIHRoZSBzZXJ2ZXIgZ29pbmcgZG93 biBhdCBhbGwuICBBbHRob3VnaCB0aGV5IERPIGdvIGRvd24gZGVzcGl0ZSBy ZWR1bmRhbmN5Li4uSSBqdXN0IGhhZCBhIFNDU0kgYmFja3BsYW5lIGdvIG91 dCBpbiBhIERlbGwgNjYwMCB0aGF0IGhhcyBldmVyeSBiaXQgb2YgcmVkdW5k YW5jeSB5b3UgY2FuIG9yZGVyLiAgV2hpbGUgdW5jb21tb24sIHRoZSBiYWNr cGxhbmUgaXMgb25lIG9uZSBvZiB0aGUgbWFueSBzaW5nbGUgcG9pbnRzIG9m IGZhaWx1cmUhICANCiANClJvbWFuIEZhaWwNClBPUyBQb3J0YWwsIEluYy4N CiANCiANCg0KCS0tLS0tT3JpZ2luYWwgTWVzc2FnZS0tLS0tIA0KCUZyb206 IEJhbGF6cyBXZWxsaXNjaCBbbWFpbHRvOmJhbGF6c0BuZXVzb2x1dGlvbnMu Y29tXSANCglTZW50OiBXZWQgNy8xNi8yMDAzIDc6NTcgUE0gDQoJVG86IHBn c3FsLXBlcmZvcm1hbmNlQHBvc3RncmVzcWwub3JnIA0KCUNjOiANCglTdWJq ZWN0OiBbUEVSRk9STV0gSGFyZHdhcmUgcGVyZm9ybWFuY2UNCgkNCgkNCglI aSBhbGwsDQoJIA0KCWZpcnN0IG9mIGFsbCBJJ2QgbGlrZSB0byB0aGFuayBl dmVyeW9uZSB3aG8gcmVzcG9uZGVkIHRvIG15IGVhcmxpZXIgcG9zdC4gSSBo YXZlIGEgbXVjaCBiZXR0ZXIgdW5kZXJzdGFuZGluZyBvZiBwb3N0Z3JlcyBw ZXJmb3JtYW5jZSB0dW5pbmcgbm93LiBJbiBjYXNlIGFueW9uZSdzIGludGVy ZXN0ZWQgd2UndmUgZGVjaWRlZCB0byBnbyB3aXRoIFJIOSBhbmQgUG9zdGdy ZVNRTCA3LjMgYW5kIHdlJ2xsIGRvIHRoZSBPUyBhbmQgREIgdHVuaW5nIG91 cnNlbHZlcy4gKHNob3VsZCBiZSBhIGdvb2QgbGVhcm5pbmcgZXhwZXJpZW5j ZSkNCgkgDQoJV2UgYXJlIG5vdyBnZXR0aW5nIHJlYWR5IHRvIHB1cmNoYXNl IHRoZSBoYXJkd2FyZSB0aGF0IHdpbGwgYmUgdXNlZCB0byBydW4gdGhlIGRh dGFiYXNlIHNlcnZlci4gV2UncmUgc3BlbmRpbmcgcXVpdGUgYSBiaXQgb2Yg bW9uZXkgb24gaXQgYmVjYXVzZSB0aGlzIHdpbGwgZXZlbnR1YWxseSwgaWYg dGhpbmdzIGdvIHdlbGwgd2l0aGluIHR3byBtb250aHMsIGJlY29tZSBhIHBy b2R1Y3Rpb24gc2VydmVyLiBXZSdyZSBnZXR0aW5nIGFsbCBSSCBjZXJ0aWZp ZWQgaGFyZHdhcmUgZnJvbSBEZWxsLiAoRGVsbCAyNjUwKQ0KCSANCglXZSdy ZSBub3cgc3R1Y2sgb24gdGhlIHF1ZXN0aW9uIG9mIHdoYXQgdHlwZSBvZiBS QUlEIGNvbmZpZ3VyYXRpb24gdG8gdXNlIGZvciB0aGlzIHNlcnZlci4gUkFJ RCA1IG9mZmVycyB0aGUgYmVzdCBmYXVsdCB0b2xlcmFuY2UgYnV0IGRvZXNu J3QgcGVyZm9ybSBhbGwgdGhhdCB3ZWxsLiBSQUlEIDEwIG9mZmVycyBtdWNo IGJldHRlciBwZXJmb3JtYW5jZSwgYnV0IG5vIGhvdCBzd2FwLiBPciBzaG91 bGQgd2Ugbm90IHVzZSBSQUlEIGF0IGFsbC4gSSBrbm93IHRoYXQgaWRlYWxs eSB0aGUgbG9nIChXQUwpIGZpbGVzIHNob3VsZCByZXNpZGUgb24gYSBzZXBh cmF0ZSBkaXNrIGZyb20gdGhlIHJlc3Qgb2YgdGhlIERCLiBTaG91bGQgd2Ug dXNlIDQgc2VwYXJhdGUgZHJpdmVzIGluc3RlYWQ/IE9uZSBmb3IgdGhlIE9T LCBvbmUgZm9yIGRhdGEsIG9uZSBmb3IgV0FMLCBvbmUgZm9yIHN3YXA/IE9y IFJBSUQgMTAgZm9yIGV2ZXJ5dGhpbmcgcGx1cyAxIGRyaXZlIGZvciBXQUw/ IE9yIFJBSUQgNSBmb3IgZXZlcnl0aGluZz8NCgkgDQoJV2UgaGF2ZSB0aGUg YnVkZ2V0IGZvciA1IGRyaXZlcy4gRG9lcyBhbnlvbmUgaGF2ZSBhbnkgcmVh bCB3b3JsZCBleHBlcmllbmNlIHdpdGggd2hhdCBoYXJkIGRyaXZlIGNvbmZp Z3VyYXRpb24gd29ya3MgYmVzdCBmb3IgcG9zdGdyZXM/IFRoaXMgaXMgZ29p bmcgdG8gYmUgYSBkZWRpY2F0ZWQgREIgc2VydmVyLiBUaGVyZSBhcmUgZ29p bmcgdG8gYmUgYSBsYXJnZSBudW1iZXIgb2YgdHJhbnNhY3Rpb25zIGJlaW5n IHdyaXR0ZW4gdG8gdGhlIGRhdGFiYXNlLiAoSW5mb3JtYXRpb24gaXMgbG9n Z2VkIGZyb20gYSBzZXBhcmF0ZSBhcHAgdGhyb3VnaCBPREJDIHRvIHBvc3Rn cmVzKSBBbmQgdGhlcmUgd2lsbCBiZSBzb21lIG1vZGVyYXRlbHkgY29tcGxl eCBxdWVyaWVzIHJ1biBjb25jdXJyZW50bHkgdG8gcHJlc2VudCB0aGlzIGlu Zm9ybWF0aW9uIGluIHRoZSBmb3JtIG9mIHZhcmlvdXMgcmVwb3J0cyBvbiB0 aGUgd2ViLiAoVGhlIGFwcCBzZXJ2ZXIgaXMgYSBzZXBhcmF0ZSBtYWNoaW5l IGFuZCB3aWxsIGNvbm5lY3QgdG8gdGhlIERCIHRocm91Z2ggSkRCQyB0byBj cmVhdGUgdGhlIEhUTUwgcmVwb3J0cykNCgkgDQoJQW55IHRob3VnaHRzLCBp ZGVhcywgY29tbWVudHMgd291bGQgYmUgYXBwcmVjaWF0ZWQuDQoJIA0KCVRo YW5rIHlvdSwNCgkgDQoJQmFsYXpzIFdlbGxpc2NoDQoJTmV1IFNvbHV0aW9u cw0KCWJhbGF6c0BuZXVzb2x1dGlvbnMuY29tDQoJIA0KDQo= From mail@joeconway.com Thu Jul 17 04:53:37 2003 X-Original-To: pgsql-performance-postgresql.org@localhost.postgresql.org Received: from localhost (unknown [64.117.225.181]) by svr1.postgresql.org (Postfix) with ESMTP id B6388CC86C for ; Thu, 17 Jul 2003 04:53:37 +0000 (GMT) Received: from svr1.postgresql.org ([64.117.224.193]) by localhost (svr5.postgresql.org [64.117.225.181]) (amavisd-new, port 10024) with ESMTP id 66337-06 for ; Thu, 17 Jul 2003 04:53:54 +0000 (GMT) Received: from joeconway.com (66-146-172-86.skyriver.net [66.146.172.86]) by svr1.postgresql.org (Postfix) with ESMTP id 682E4CADC4 for ; Thu, 17 Jul 2003 01:53:25 -0300 (ADT) Received: from [192.168.5.3] (account jconway HELO joeconway.com) by joeconway.com (CommuniGate Pro SMTP 4.0.6) with ESMTP-TLS id 1825975; Wed, 16 Jul 2003 21:20:02 -0700 Message-ID: <3F162B7D.1020106@joeconway.com> Date: Wed, 16 Jul 2003 21:52:13 -0700 From: Joe Conway User-Agent: Mozilla/5.0 (Windows; U; Windows NT 5.0; en-US; rv:1.3) Gecko/20030312 X-Accept-Language: en-us, en MIME-Version: 1.0 To: Balazs Wellisch Cc: pgsql-performance@postgresql.org Subject: Re: Hardware performance References: <004b01c34c0f$256bfb80$0600a8c0@home01> In-Reply-To: <004b01c34c0f$256bfb80$0600a8c0@home01> Content-Type: text/plain; charset=us-ascii; format=flowed Content-Transfer-Encoding: 7bit X-Virus-Scanned: by amavisd-new at postgresql.org X-Archive-Number: 200307/241 X-Sequence-Number: 2534 Balazs Wellisch wrote: > first of all I'd like to thank everyone who responded to my earlier > post. I have a much better understanding of postgres performance > tuning now. In case anyone's interested we've decided to go with RH9 > and PostgreSQL 7.3 and we'll do the OS and DB tuning ourselves. > (should be a good learning experience) Good choice! I think you'll find that this list will be a great resource as you learn. One point here is that you should use 7.3.3 (latest release version) instead of the version of Postgres in the distribution. Also, you might want to rebuild the RPMs from source using "--target i686". > We have the budget for 5 drives. Does anyone have any real world > experience with what hard drive configuration works best for > postgres? This is going to be a dedicated DB server. There are going > to be a large number of transactions being written to the database. To an extent it depends on how big the drives are and how large you expect the database to get. For maximal performance you want RAID 1+0 for data and WAL; and you want OS, data, and WAL each on their own drives. So with 5 drives one possible configuration is: 1 drive OS: OS on it's own drive makes it easy to upgrade, or restore the OS from CD if needed 2 drives, RAID 1+0: WAL 2 drives, RAID 1+0: data But I've seem reports that with fast I/O subsystems, there was no measurable difference with WAL separated from data. And to be honest, I've never personally found it necessary to separate WAL from data. You may want to test with WAL on the same volume as the data to see if there is enough difference to warrant separating it or not given your load and your actual hardware. If not, use 1 OS drive and 4 RAID 1+0 drives as one volume. You never want find any significant use of hard disk based swap space -- if you see that, you are probably misconfigured, and performance will be poor no matter how you've set up the drives. > And there will be some moderately complex queries run concurrently to > present this information in the form of various reports on the web. Once you have some data on your test server, and you have complex queries to tune, there will be a few details you'll get asked every time if you don't provide them when posting a question to the list: 1) Have you been running VACUUM and ANALYZE (or VACUUM ANALYZE) at appropriate intervals? 2) What are the table definitions and indexes for all tables involved? 3) What is the output of EXPLAIN ANALYZE? HTH, Joe From hannu@tm.ee Thu Jul 17 07:58:54 2003 X-Original-To: pgsql-performance-postgresql.org@localhost.postgresql.org Received: from localhost (unknown [64.117.225.181]) by svr1.postgresql.org (Postfix) with ESMTP id D13B4CC863 for ; Thu, 17 Jul 2003 07:58:54 +0000 (GMT) Received: from svr1.postgresql.org ([64.117.224.193]) by localhost (svr5.postgresql.org [64.117.225.181]) (amavisd-new, port 10024) with ESMTP id 07927-08 for ; Thu, 17 Jul 2003 07:59:11 +0000 (GMT) Received: from fuji.krosing.net (unknown [194.204.44.118]) by svr1.postgresql.org (Postfix) with ESMTP id 92222CC8F3 for ; Thu, 17 Jul 2003 04:58:42 -0300 (ADT) Received: from fuji.krosing.net (localhost.localdomain [127.0.0.1]) by fuji.krosing.net (8.12.8/8.12.8) with ESMTP id h6H7uphY004623; Thu, 17 Jul 2003 10:56:51 +0300 Received: (from hannu@localhost) by fuji.krosing.net (8.12.8/8.12.8/Submit) id h6H7unD7004621; Thu, 17 Jul 2003 10:56:49 +0300 X-Authentication-Warning: fuji.krosing.net: hannu set sender to hannu@tm.ee using -f Subject: Re: Hardware performance From: Hannu Krosing To: Joe Conway Cc: pgsql-performance@postgresql.org In-Reply-To: <3F162B7D.1020106@joeconway.com> References: <004b01c34c0f$256bfb80$0600a8c0@home01> <3F162B7D.1020106@joeconway.com> Content-Type: text/plain Content-Transfer-Encoding: 7bit Message-Id: <1058428609.4289.5.camel@fuji.krosing.net> Mime-Version: 1.0 X-Mailer: Ximian Evolution 1.4.3 Date: 17 Jul 2003 10:56:49 +0300 X-Virus-Scanned: by amavisd-new at postgresql.org X-Archive-Number: 200307/242 X-Sequence-Number: 2535 Joe Conway kirjutas N, 17.07.2003 kell 07:52: > To an extent it depends on how big the drives are and how large you > expect the database to get. For maximal performance you want RAID 1+0 > for data and WAL; and you want OS, data, and WAL each on their own > drives. So with 5 drives one possible configuration is: > > 1 drive OS: OS on it's own drive makes it easy to upgrade, or restore > the OS from CD if needed > 2 drives, RAID 1+0: WAL > 2 drives, RAID 1+0: data How do you do RAID 1+0 with just two drives ? -------------- Hannu From pgsql.spam@vinz.nl Thu Jul 17 10:14:02 2003 X-Original-To: pgsql-performance-postgresql.org@localhost.postgresql.org Received: from localhost (unknown [64.117.225.181]) by svr1.postgresql.org (Postfix) with ESMTP id 8B0A4CC918 for ; Thu, 17 Jul 2003 10:14:02 +0000 (GMT) Received: from svr1.postgresql.org ([64.117.224.193]) by localhost (svr5.postgresql.org [64.117.225.181]) (amavisd-new, port 10024) with ESMTP id 81081-08 for ; Thu, 17 Jul 2003 10:14:17 +0000 (GMT) Received: from mail2.mediadesign.nl (md2.mediadesign.nl [212.19.205.67]) by svr1.postgresql.org (Postfix) with SMTP id A089ECAE14 for ; Thu, 17 Jul 2003 07:13:49 -0300 (ADT) Received: (qmail 8997 invoked by uid 666); 17 Jul 2003 10:14:16 -0000 Date: Thu, 17 Jul 2003 12:14:16 +0200 From: Vincent van Leeuwen To: pgsql-performance@postgresql.org Subject: Re: Hardware performance Message-ID: <20030717101415.GR21071@md2.mediadesign.nl> Mail-Followup-To: pgsql-performance@postgresql.org References: <004b01c34c0f$256bfb80$0600a8c0@home01> Mime-Version: 1.0 Content-Type: text/plain; charset=us-ascii Content-Disposition: inline In-Reply-To: <004b01c34c0f$256bfb80$0600a8c0@home01> User-Agent: Mutt/1.3.28i X-Virus-Scanned: by amavisd-new at postgresql.org X-Archive-Number: 200307/246 X-Sequence-Number: 2539 On 2003-07-16 19:57:22 -0700, Balazs Wellisch wrote: > We're now stuck on the question of what type of RAID configuration to use > for this server. RAID 5 offers the best fault tolerance but doesn't perform > all that well. RAID 10 offers much better performance, but no hot swap. Or > should we not use RAID at all. I know that ideally the log (WAL) files > should reside on a separate disk from the rest of the DB. Should we use 4 > separate drives instead? One for the OS, one for data, one for WAL, one for > swap? Or RAID 10 for everything plus 1 drive for WAL? Or RAID 5 for > everything? > We have recently run our own test (simulating our own database load) on a new server which contained 7 15K rpm disks. Since we always want to have a hot-spare drive (servers are located in a hard-to-reach datacenter) and we always want redundancy, we tested two different configurations: - 6 disk RAID 10 array, holding everything - 4 disk RAID 5 array holding postgresql data and 2 disk RAID 1 array holding OS, swap and WAL logs Our database is used for a very busy community website, so our load contains a lot of inserts/updates for a website, but much more selects than there are updates. Our findings were that the 6 disk RAID 10 set was significantly faster than the other setup. So I'd recommend a 4-disk RAID 10 array. I'd use the 5th drive for a hot-spare drive, but that's your own call. However, it would be best if you tested some different setups under your own database load to see what works best for you. Vincent van Leeuwen Media Design - http://www.mediadesign.nl/ From mail@joeconway.com Thu Jul 17 14:59:17 2003 X-Original-To: pgsql-performance-postgresql.org@localhost.postgresql.org Received: from localhost (unknown [64.117.225.181]) by svr1.postgresql.org (Postfix) with ESMTP id DA879CCA2C for ; Thu, 17 Jul 2003 14:59:17 +0000 (GMT) Received: from svr1.postgresql.org ([64.117.224.193]) by localhost (svr5.postgresql.org [64.117.225.181]) (amavisd-new, port 10024) with ESMTP id 24586-08 for ; Thu, 17 Jul 2003 14:59:37 +0000 (GMT) Received: from joeconway.com (66-146-172-86.skyriver.net [66.146.172.86]) by svr1.postgresql.org (Postfix) with ESMTP id CEE1BCAE14 for ; Thu, 17 Jul 2003 11:59:05 -0300 (ADT) Received: from [192.168.5.3] (account jconway HELO joeconway.com) by joeconway.com (CommuniGate Pro SMTP 4.0.6) with ESMTP-TLS id 1826298; Thu, 17 Jul 2003 07:25:37 -0700 Message-ID: <3F16B971.7050104@joeconway.com> Date: Thu, 17 Jul 2003 07:57:53 -0700 From: Joe Conway User-Agent: Mozilla/5.0 (Windows; U; Windows NT 5.0; en-US; rv:1.3) Gecko/20030312 X-Accept-Language: en-us, en MIME-Version: 1.0 To: Hannu Krosing Cc: pgsql-performance@postgresql.org Subject: Re: Hardware performance References: <004b01c34c0f$256bfb80$0600a8c0@home01> <3F162B7D.1020106@joeconway.com> <1058428609.4289.5.camel@fuji.krosing.net> In-Reply-To: <1058428609.4289.5.camel@fuji.krosing.net> Content-Type: text/plain; charset=us-ascii; format=flowed Content-Transfer-Encoding: 7bit X-Virus-Scanned: by amavisd-new at postgresql.org X-Archive-Number: 200307/256 X-Sequence-Number: 2549 Hannu Krosing wrote: > How do you do RAID 1+0 with just two drives ? > Hmm, good point -- I must have been tired last night ;-). With two drives you can do mirroring or striping, but not both. Usually I've seen a pair of mirrored drives for the OS, and a RAID 1+0 array for data. But that requires 6 drives, not 5. On non-database servers usually the data array is RAID 5, and you could get away with 5 drives (as someone else pointed out). As I said, I've never personally found it necessary to move WAL off to a different physical drive. What do you think is the best configuration given the constraint of 5 drives? 1 drive for OS, and 4 for RAID 1+0 for data-plus-WAL? I guess the ideal would be to find enough money for that 6th drive, use the mirrored pair for both OS and WAL. Joe From awitney@sghms.ac.uk Thu Jul 17 15:05:55 2003 X-Original-To: pgsql-performance-postgresql.org@localhost.postgresql.org Received: from localhost (unknown [64.117.224.192]) by svr1.postgresql.org (Postfix) with ESMTP id 0742BCCA08 for ; Thu, 17 Jul 2003 15:05:55 +0000 (GMT) Received: from svr1.postgresql.org ([64.117.224.193]) by localhost (svr4.postgresql.org [64.117.224.192]) (amavisd-new, port 10024) with ESMTP id 52629-08 for ; Thu, 17 Jul 2003 15:06:23 +0000 (GMT) Received: from mailhub1.sghms.ac.uk (firewall.sghms.ac.uk [194.82.50.2]) by svr1.postgresql.org (Postfix) with ESMTP id F1087CCA3D for ; Thu, 17 Jul 2003 12:05:52 -0300 (ADT) Received: from [194.82.51.24] (helo=imail) by mailhub1.sghms.ac.uk with esmtp (Exim 4.12) id 19dAKy-0005Bv-00; Thu, 17 Jul 2003 16:06:28 +0100 Received: from [172.16.20.3] (mrc1-003.sghms.ac.uk [172.16.20.3]) by imail.sghms.ac.uk (iPlanet Messaging Server 5.1 HotFix 0.7 (built May 7 2002)) with ESMTPA id <0HI600BJCCM9G6@imail.sghms.ac.uk>; Thu, 17 Jul 2003 16:06:09 +0100 (BST) Date: Thu, 17 Jul 2003 16:04:38 +0100 From: Adam Witney Subject: Re: Hardware performance In-reply-to: <3F16B971.7050104@joeconway.com> To: Joe Conway Cc: pgsql-performance Message-id: MIME-version: 1.0 Content-type: text/plain; charset=US-ASCII Content-transfer-encoding: 7BIT User-Agent: Microsoft-Entourage/10.1.1.2418 X-MailScanner-Information: Please contact sysadmin at sghms.ac.uk for more information X-MailScanner-MH1: Found to be clean X-MailScanner-SpamCheck: not spam, SpamAssassin (score=-100.8, required 5, IN_REP_TO, QUOTED_EMAIL_TEXT, USER_AGENT_ENTOURAGE, USER_IN_WHITELIST) X-Virus-Scanned: by amavisd-new at postgresql.org X-Archive-Number: 200307/257 X-Sequence-Number: 2550 > As I said, I've never personally found it necessary to move WAL off to a > different physical drive. What do you think is the best configuration > given the constraint of 5 drives? 1 drive for OS, and 4 for RAID 1+0 for > data-plus-WAL? I guess the ideal would be to find enough money for that > 6th drive, use the mirrored pair for both OS and WAL. I think the issue from the original posters point of view is that the Dell PE2650 can only hold a maximum of 5 internal drives -- This message has been scanned for viruses and dangerous content by MailScanner, and is believed to be clean. From mail@joeconway.com Thu Jul 17 15:10:57 2003 X-Original-To: pgsql-performance-postgresql.org@localhost.postgresql.org Received: from localhost (unknown [64.117.224.192]) by svr1.postgresql.org (Postfix) with ESMTP id DA615CCA33 for ; Thu, 17 Jul 2003 15:10:57 +0000 (GMT) Received: from svr1.postgresql.org ([64.117.224.193]) by localhost (svr4.postgresql.org [64.117.224.192]) (amavisd-new, port 10024) with ESMTP id 55824-10 for ; Thu, 17 Jul 2003 15:11:26 +0000 (GMT) Received: from joeconway.com (66-146-172-86.skyriver.net [66.146.172.86]) by svr1.postgresql.org (Postfix) with ESMTP id 5E293CAE14 for ; Thu, 17 Jul 2003 12:10:55 -0300 (ADT) Received: from [192.168.5.3] (account jconway HELO joeconway.com) by joeconway.com (CommuniGate Pro SMTP 4.0.6) with ESMTP-TLS id 1826308; Thu, 17 Jul 2003 07:37:27 -0700 Message-ID: <3F16BC38.6070504@joeconway.com> Date: Thu, 17 Jul 2003 08:09:44 -0700 From: Joe Conway User-Agent: Mozilla/5.0 (Windows; U; Windows NT 5.0; en-US; rv:1.3) Gecko/20030312 X-Accept-Language: en-us, en MIME-Version: 1.0 To: Adam Witney Cc: pgsql-performance Subject: Re: Hardware performance References: In-Reply-To: Content-Type: text/plain; charset=us-ascii; format=flowed Content-Transfer-Encoding: 7bit X-Virus-Scanned: by amavisd-new at postgresql.org X-Archive-Number: 200307/258 X-Sequence-Number: 2551 Adam Witney wrote: > I think the issue from the original posters point of view is that the Dell > PE2650 can only hold a maximum of 5 internal drives > True enough, but maybe that's a reason to be looking at other alternatives. I think he said the hardware hasn't been bought yet. Joe From awitney@sghms.ac.uk Thu Jul 17 15:22:20 2003 X-Original-To: pgsql-performance-postgresql.org@localhost.postgresql.org Received: from localhost (unknown [64.117.225.181]) by svr1.postgresql.org (Postfix) with ESMTP id 4A4EECCA48 for ; Thu, 17 Jul 2003 15:22:20 +0000 (GMT) Received: from svr1.postgresql.org ([64.117.224.193]) by localhost (svr5.postgresql.org [64.117.225.181]) (amavisd-new, port 10024) with ESMTP id 49762-03 for ; Thu, 17 Jul 2003 15:22:39 +0000 (GMT) Received: from mailhub1.sghms.ac.uk (firewall.sghms.ac.uk [194.82.50.2]) by svr1.postgresql.org (Postfix) with ESMTP id 0ECF5CCA43 for ; Thu, 17 Jul 2003 12:22:09 -0300 (ADT) Received: from [194.82.51.24] (helo=imail) by mailhub1.sghms.ac.uk with esmtp (Exim 4.12) id 19dAaW-00060T-00; Thu, 17 Jul 2003 16:22:32 +0100 Received: from [172.16.20.3] (mrc1-003.sghms.ac.uk [172.16.20.3]) by imail.sghms.ac.uk (iPlanet Messaging Server 5.1 HotFix 0.7 (built May 7 2002)) with ESMTPA id <0HI600B7WDD1HM@imail.sghms.ac.uk>; Thu, 17 Jul 2003 16:22:13 +0100 (BST) Date: Thu, 17 Jul 2003 16:20:42 +0100 From: Adam Witney Subject: Re: Hardware performance In-reply-to: <3F16BC38.6070504@joeconway.com> To: Joe Conway Cc: pgsql-performance Message-id: MIME-version: 1.0 Content-type: text/plain; charset=US-ASCII Content-transfer-encoding: 7BIT User-Agent: Microsoft-Entourage/10.1.1.2418 X-MailScanner-Information: Please contact sysadmin at sghms.ac.uk for more information X-MailScanner-MH1: Found to be clean X-MailScanner-SpamCheck: not spam, SpamAssassin (score=-101.3, required 5, EMAIL_ATTRIBUTION, IN_REP_TO, QUOTED_EMAIL_TEXT, REPLY_WITH_QUOTES, USER_AGENT_ENTOURAGE, USER_IN_WHITELIST) X-Virus-Scanned: by amavisd-new at postgresql.org X-Archive-Number: 200307/259 X-Sequence-Number: 2552 On 17/7/03 4:09 pm, "Joe Conway" wrote: > Adam Witney wrote: >> I think the issue from the original posters point of view is that the Dell >> PE2650 can only hold a maximum of 5 internal drives >> > > True enough, but maybe that's a reason to be looking at other > alternatives. I think he said the hardware hasn't been bought yet. Actually I am going through the same questions myself at the moment.... I would like to have a 2 disk RAID1 and a 4 disk RAID5, so need at least 6 disks.... Anybody have any suggestions or experience with other hardware manufacturers for this size of setup? (2U rack, up to 6 disks, 2 processors, ~2GB RAM, if possible) Thanks adam -- This message has been scanned for viruses and dangerous content by MailScanner, and is believed to be clean. From jllachan@nsd.ca Thu Jul 17 16:11:59 2003 X-Original-To: pgsql-performance-postgresql.org@localhost.postgresql.org Received: from localhost (unknown [64.117.225.181]) by svr1.postgresql.org (Postfix) with ESMTP id 0DBD1CADD0 for ; Thu, 17 Jul 2003 16:11:59 +0000 (GMT) Received: from svr1.postgresql.org ([64.117.224.193]) by localhost (svr5.postgresql.org [64.117.225.181]) (amavisd-new, port 10024) with ESMTP id 38345-09 for ; Thu, 17 Jul 2003 16:12:18 +0000 (GMT) Received: from beamish.nsd.ca (beamish.nsd.ca [205.150.156.194]) by svr1.postgresql.org (Postfix) with ESMTP id AE4E9CCA46 for ; Thu, 17 Jul 2003 13:11:47 -0300 (ADT) Received: (from smap@localhost) by beamish.nsd.ca (8.9.3/8.9.3) id MAA08475; Thu, 17 Jul 2003 12:12:12 -0400 X-Authentication-Warning: beamish.nsd.ca: smap set sender to using -f Received: from reddog.nsd.ca(192.168.101.30) by beamish.nsd.ca via smap (V2.1/2.1+anti-relay+anti-spam) id xma008471; Thu, 17 Jul 03 12:12:03 -0400 Received: from nsd.ca (jllachan-linux.nsd.ca [192.168.101.148]) by reddog.nsd.ca (8.8.7/8.8.7) with ESMTP id MAA31821; Thu, 17 Jul 2003 12:02:20 -0400 Message-ID: <3F16CB27.23A29390@nsd.ca> Date: Thu, 17 Jul 2003 12:13:27 -0400 From: Jean-Luc Lachance X-Mailer: Mozilla 4.8 [en] (X11; U; Linux 2.4.18-24.7.x i686) X-Accept-Language: en MIME-Version: 1.0 To: Joe Conway Cc: Balazs Wellisch , pgsql-performance@postgresql.org Subject: Re: Hardware performance References: <004b01c34c0f$256bfb80$0600a8c0@home01> <3F162B7D.1020106@joeconway.com> Content-Type: text/plain; charset=us-ascii Content-Transfer-Encoding: 7bit X-Virus-Scanned: by amavisd-new at postgresql.org X-Archive-Number: 200307/262 X-Sequence-Number: 2555 I am currious. How can you have RAID 1+0 with only 2 drives? If you are thinking about partitioning the drives, wont this defeate the purpose? JLL Joe Conway wrote: > > [...] > 2 drives, RAID 1+0: WAL > 2 drives, RAID 1+0: data > [...] From mail@joeconway.com Thu Jul 17 16:23:00 2003 X-Original-To: pgsql-performance-postgresql.org@localhost.postgresql.org Received: from localhost (unknown [64.117.225.181]) by svr1.postgresql.org (Postfix) with ESMTP id 01B62CCA60 for ; Thu, 17 Jul 2003 16:23:00 +0000 (GMT) Received: from svr1.postgresql.org ([64.117.224.193]) by localhost (svr5.postgresql.org [64.117.225.181]) (amavisd-new, port 10024) with ESMTP id 48336-07 for ; Thu, 17 Jul 2003 16:23:19 +0000 (GMT) Received: from joeconway.com (66-146-172-86.skyriver.net [66.146.172.86]) by svr1.postgresql.org (Postfix) with ESMTP id 9C2B4CCA46 for ; Thu, 17 Jul 2003 13:22:48 -0300 (ADT) Received: from [206.19.64.3] (account jconway HELO joeconway.com) by joeconway.com (CommuniGate Pro SMTP 4.0.6) with ESMTP-TLS id 1826380; Thu, 17 Jul 2003 08:49:19 -0700 Message-ID: <3F16CD0C.6090600@joeconway.com> Date: Thu, 17 Jul 2003 09:21:32 -0700 From: Joe Conway User-Agent: Mozilla/5.0 (Windows; U; Windows NT 5.0; en-US; rv:1.3) Gecko/20030312 X-Accept-Language: en-us, en MIME-Version: 1.0 To: Jean-Luc Lachance Cc: Balazs Wellisch , pgsql-performance@postgresql.org Subject: Re: Hardware performance References: <004b01c34c0f$256bfb80$0600a8c0@home01> <3F162B7D.1020106@joeconway.com> <3F16CB27.23A29390@nsd.ca> In-Reply-To: <3F16CB27.23A29390@nsd.ca> Content-Type: text/plain; charset=us-ascii; format=flowed Content-Transfer-Encoding: 7bit X-Virus-Scanned: by amavisd-new at postgresql.org X-Archive-Number: 200307/266 X-Sequence-Number: 2559 Jean-Luc Lachance wrote: > I am currious. How can you have RAID 1+0 with only 2 drives? > If you are thinking about partitioning the drives, wont this defeate the > purpose? Yeah -- Hannu already pointed out that my mind was fuzzy when I made that statement :-(. See subsequent posts. Joe From mail@joeconway.com Thu Jul 17 16:30:38 2003 X-Original-To: pgsql-performance-postgresql.org@localhost.postgresql.org Received: from localhost (unknown [64.117.224.192]) by svr1.postgresql.org (Postfix) with ESMTP id 63266CCA62 for ; Thu, 17 Jul 2003 16:30:38 +0000 (GMT) Received: from svr1.postgresql.org ([64.117.224.193]) by localhost (svr4.postgresql.org [64.117.224.192]) (amavisd-new, port 10024) with ESMTP id 89318-08 for ; Thu, 17 Jul 2003 16:31:07 +0000 (GMT) Received: from joeconway.com (66-146-172-86.skyriver.net [66.146.172.86]) by svr1.postgresql.org (Postfix) with ESMTP id 64C70CCA60 for ; Thu, 17 Jul 2003 13:30:36 -0300 (ADT) Received: from [206.19.64.3] (account jconway HELO joeconway.com) by joeconway.com (CommuniGate Pro SMTP 4.0.6) with ESMTP-TLS id 1826389; Thu, 17 Jul 2003 08:57:07 -0700 Message-ID: <3F16CEDE.2070807@joeconway.com> Date: Thu, 17 Jul 2003 09:29:18 -0700 From: Joe Conway User-Agent: Mozilla/5.0 (Windows; U; Windows NT 5.0; en-US; rv:1.3) Gecko/20030312 X-Accept-Language: en-us, en MIME-Version: 1.0 To: Adam Witney Cc: pgsql-performance Subject: Re: Hardware performance References: In-Reply-To: Content-Type: text/plain; charset=windows-1252; format=flowed Content-Transfer-Encoding: 8bit X-Virus-Scanned: by amavisd-new at postgresql.org X-Archive-Number: 200307/267 X-Sequence-Number: 2560 Adam Witney wrote: > Actually I am going through the same questions myself at the moment.... I > would like to have a 2 disk RAID1 and a 4 disk RAID5, so need at least 6 > disks.... > > Anybody have any suggestions or experience with other hardware manufacturers > for this size of setup? (2U rack, up to 6 disks, 2 processors, ~2GB RAM, if > possible) I tend to use either 1U or 4U servers, depending on the application. But I've had good experiences with IBM recently, and a quick look on their site shows the x345 with these specs: • 2U, 2-way server delivers extreme performance and availability for demanding applications • Up to 2 Intel Xeon processors up to 3.06GHz with 533MHz front-side bus speed for outstanding performance • Features up to 8GB of DDR memory, 5 PCI (4 PCI-X) slots and up to 6 hard disk drives for robust expansion • Hot-swap redundant cooling, power and hard disk drives for high availability • Integrated dual Ultra320 SCSI with RAID-1 for data protection This may not wrap well, but here is the url: http://www-132.ibm.com/webapp/wcs/stores/servlet/CategoryDisplay?catalogId=-840&storeId=1&categoryId=2559454&langId=-1&dualCurrId=73 Handles 6 drives; maybe that fits the bill? Joe From jllachan@nsd.ca Thu Jul 17 16:42:17 2003 X-Original-To: pgsql-performance-postgresql.org@localhost.postgresql.org Received: from localhost (unknown [64.117.224.192]) by svr1.postgresql.org (Postfix) with ESMTP id 85618CCA5B for ; Thu, 17 Jul 2003 16:42:17 +0000 (GMT) Received: from svr1.postgresql.org ([64.117.224.193]) by localhost (svr4.postgresql.org [64.117.224.192]) (amavisd-new, port 10024) with ESMTP id 09203-01 for ; Thu, 17 Jul 2003 16:42:46 +0000 (GMT) Received: from beamish.nsd.ca (beamish.nsd.ca [205.150.156.194]) by svr1.postgresql.org (Postfix) with ESMTP id C542ACCA46 for ; Thu, 17 Jul 2003 13:42:15 -0300 (ADT) Received: (from smap@localhost) by beamish.nsd.ca (8.9.3/8.9.3) id MAA09348; Thu, 17 Jul 2003 12:42:42 -0400 X-Authentication-Warning: beamish.nsd.ca: smap set sender to using -f Received: from reddog.nsd.ca(192.168.101.30) by beamish.nsd.ca via smap (V2.1/2.1+anti-relay+anti-spam) id xma009344; Thu, 17 Jul 03 12:42:36 -0400 Received: from nsd.ca (jllachan-linux.nsd.ca [192.168.101.148]) by reddog.nsd.ca (8.8.7/8.8.7) with ESMTP id MAA32024; Thu, 17 Jul 2003 12:32:53 -0400 Message-ID: <3F16D251.73F84CD8@nsd.ca> Date: Thu, 17 Jul 2003 12:44:01 -0400 From: Jean-Luc Lachance X-Mailer: Mozilla 4.8 [en] (X11; U; Linux 2.4.18-24.7.x i686) X-Accept-Language: en MIME-Version: 1.0 To: Joe Conway Cc: Balazs Wellisch , pgsql-performance@postgresql.org Subject: Re: Hardware performance References: <004b01c34c0f$256bfb80$0600a8c0@home01> <3F162B7D.1020106@joeconway.com> <3F16CB27.23A29390@nsd.ca> <3F16CD0C.6090600@joeconway.com> Content-Type: text/plain; charset=us-ascii Content-Transfer-Encoding: 7bit X-Virus-Scanned: by amavisd-new at postgresql.org X-Archive-Number: 200307/269 X-Sequence-Number: 2562 Sorry for the redundant duplication of the repetition. I should have read the follow-up messages. Joe Conway wrote: > > Jean-Luc Lachance wrote: > > I am currious. How can you have RAID 1+0 with only 2 drives? > > If you are thinking about partitioning the drives, wont this defeate the > > purpose? > > Yeah -- Hannu already pointed out that my mind was fuzzy when I made > that statement :-(. See subsequent posts. > > Joe From jord@indygecko.com Thu Jul 17 16:54:05 2003 X-Original-To: pgsql-performance-postgresql.org@localhost.postgresql.org Received: from localhost (unknown [64.117.224.192]) by svr1.postgresql.org (Postfix) with ESMTP id 74274CCA7F for ; Thu, 17 Jul 2003 16:54:05 +0000 (GMT) Received: from svr1.postgresql.org ([64.117.224.193]) by localhost (svr4.postgresql.org [64.117.224.192]) (amavisd-new, port 10024) with ESMTP id 09203-03 for ; Thu, 17 Jul 2003 16:54:33 +0000 (GMT) Received: from indygecko.com (h24-77-222-182.ok.shawcable.net [24.77.222.182]) by svr1.postgresql.org (Postfix) with ESMTP id 8DDC9CCA78 for ; Thu, 17 Jul 2003 13:53:59 -0300 (ADT) Received: from [192.168.10.10] ([::ffff:192.168.10.10]) by indygecko.com with esmtp; Thu, 17 Jul 2003 09:54:27 -0700 Subject: Re: Hardware performance From: Jord Tanner To: Adam Witney Cc: pgsql-performance In-Reply-To: References: Organization: Message-Id: <1058460866.2010.11.camel@gecko> Mime-Version: 1.0 Content-Type: text/plain; charset=iso-8859-1 Content-Transfer-Encoding: 7bit X-Mailer: Ximian Evolution 1.2.2 (1.2.2-5) Date: 17 Jul 2003 09:54:26 -0700 X-Virus-Scanned: by amavisd-new at postgresql.org X-Archive-Number: 200307/270 X-Sequence-Number: 2563 On Thu, 2003-07-17 at 08:20, Adam Witney wrote: > Anybody have any suggestions or experience with other hardware manufacturers > for this size of setup? (2U rack, up to 6 disks, 2 processors, ~2GB RAM, if > possible) > > Thanks > > adam Check out http://www.amaxit.com It is all white box stuff, but they have some really cool gear. -- Jord Tanner From andrew@libertyrms.info Thu Jul 17 18:41:10 2003 X-Original-To: pgsql-performance-postgresql.org@localhost.postgresql.org Received: from localhost (unknown [64.117.225.181]) by svr1.postgresql.org (Postfix) with ESMTP id 68035CC4E3 for ; Thu, 17 Jul 2003 18:41:10 +0000 (GMT) Received: from svr1.postgresql.org ([64.117.224.193]) by localhost (svr5.postgresql.org [64.117.225.181]) (amavisd-new, port 10024) with ESMTP id 91806-09 for ; Thu, 17 Jul 2003 18:41:29 +0000 (GMT) Received: from mail.libertyrms.com (unknown [209.167.124.227]) by svr1.postgresql.org (Postfix) with ESMTP id 3BA08CBB94 for ; Thu, 17 Jul 2003 15:40:59 -0300 (ADT) Received: from [10.1.2.130] (helo=dba2) by mail.libertyrms.com with esmtp (Exim 3.22 #3 (Debian)) id 19dDh3-0000JG-00 for ; Thu, 17 Jul 2003 14:41:29 -0400 Received: by dba2 (Postfix, from userid 1019) id 173A5CEC9; Thu, 17 Jul 2003 14:41:52 -0400 (EDT) Date: Thu, 17 Jul 2003 14:41:52 -0400 From: Andrew Sullivan To: pgsql-performance@postgresql.org Subject: Re: Hardware performance Message-ID: <20030717184152.GG479@libertyrms.info> Mail-Followup-To: Andrew Sullivan , pgsql-performance@postgresql.org References: <004b01c34c0f$256bfb80$0600a8c0@home01> <3F162B7D.1020106@joeconway.com> <1058428609.4289.5.camel@fuji.krosing.net> <3F16B971.7050104@joeconway.com> Mime-Version: 1.0 Content-Type: text/plain; charset=us-ascii Content-Disposition: inline In-Reply-To: <3F16B971.7050104@joeconway.com> User-Agent: Mutt/1.5.4i X-Virus-Scanned: by amavisd-new at postgresql.org X-Archive-Number: 200307/274 X-Sequence-Number: 2567 On Thu, Jul 17, 2003 at 07:57:53AM -0700, Joe Conway wrote: > > As I said, I've never personally found it necessary to move WAL off to a > different physical drive. What do you think is the best configuration On our Solaris test boxes (where, alas, we do not have the luxury of 1/2 TB external RAID boxes :-( ), putting WAL on a disk of its own yielded something like 30% improvement in throughput on high transaciton volumes. So it's definitely important in some cases. A ---- Andrew Sullivan 204-4141 Yonge Street Liberty RMS Toronto, Ontario Canada M2P 2A8 +1 416 646 3304 x110 From mha@sollentuna.net Thu Jul 17 18:55:33 2003 X-Original-To: pgsql-performance-postgresql.org@localhost.postgresql.org Received: from localhost (unknown [64.117.225.181]) by svr1.postgresql.org (Postfix) with ESMTP id A4226CC9B3 for ; Thu, 17 Jul 2003 18:55:33 +0000 (GMT) Received: from svr1.postgresql.org ([64.117.224.193]) by localhost (svr5.postgresql.org [64.117.225.181]) (amavisd-new, port 10024) with ESMTP id 11761-01 for ; Thu, 17 Jul 2003 18:55:30 +0000 (GMT) Received: from mx-2.sollentuna.net (mx-2.sollentuna.net [195.84.163.199]) by svr1.postgresql.org (Postfix) with ESMTP id 5133DCC4E3 for ; Thu, 17 Jul 2003 15:55:00 -0300 (ADT) Received: from ALGOL.sollentuna.se (janus-en.sollentuna.se [195.84.163.194]) by mx-2.sollentuna.net (Postfix) with ESMTP id A87E434056; Thu, 17 Jul 2003 21:55:26 +0200 (CEST) content-class: urn:content-classes:message MIME-Version: 1.0 Content-Type: text/plain; charset="us-ascii" Content-Transfer-Encoding: quoted-printable X-MimeOLE: Produced By Microsoft Exchange V6.0.6249.0 Subject: Re: Hardware performance Date: Thu, 17 Jul 2003 20:55:29 +0200 Message-ID: <6BCB9D8A16AC4241919521715F4D8BCE1714F4@algol.sollentuna.se> X-MS-Has-Attach: X-MS-TNEF-Correlator: Thread-Topic: [PERFORM] Hardware performance Thread-Index: AcNMgPBfzoSlHqt1SXSaTP0oLgRXaAAEaNsw From: "Magnus Hagander" To: "Joe Conway" , "Adam Witney" Cc: "pgsql-performance" X-Virus-Scanned: by amavisd-new at postgresql.org X-Archive-Number: 200307/276 X-Sequence-Number: 2569 >Adam Witney wrote: >> Actually I am going through the same questions myself at the=20 >moment.... I >> would like to have a 2 disk RAID1 and a 4 disk RAID5, so=20 >need at least 6 >> disks.... >>=20 >> Anybody have any suggestions or experience with other=20 >hardware manufacturers >> for this size of setup? (2U rack, up to 6 disks, 2=20 >processors, ~2GB RAM, if >> possible) > >I tend to use either 1U or 4U servers, depending on the=20 >application. But=20 >I've had good experiences with IBM recently, and a quick look on their=20 >site shows the x345 with these specs: > >* 2U, 2-way server delivers extreme performance and availability for=20 >demanding applications >* Up to 2 Intel Xeon processors up to 3.06GHz with 533MHz front-side=20 >bus speed for outstanding performance >* Features up to 8GB of DDR memory, 5 PCI (4 PCI-X) slots and up to 6=20 >hard disk drives for robust expansion >* Hot-swap redundant cooling, power and hard disk drives for high=20 >availability >* Integrated dual Ultra320 SCSI with RAID-1 for data protection > >This may not wrap well, but here is the url: >http://www-132.ibm.com/webapp/wcs/stores/servlet/CategoryDispla > y?catalogId=3D-840&storeId=3D1&categoryId=3D2559454&langId=3D-1&dualCurrI= d=3D73 > > Handles 6 drives; maybe that fits the bill? [naturally, there should be one for each of the major server vendors, eh?] I've used mainly HP (as in former Compaq) machines here, with nothing but good experience. HPs machine in the scame class is the DL380G3. Almost identical specs to the IBM (I'd expect all major vendors have fairly similar machines). Holds 12Gb RAM. Only 3 PCI-X slots (2 of them hotplug). RPS. 6 disk slots (Ultra-320) that can be put on one or two SCSI chains (builtin RAID controller only handles a single channel, though, so you'd need an extra SmartArray controller if you want to split them). RAID0/1/1+0/5. If you would go with that one, make sure to get the optional BBWC (Battery Backed Write Cache). Without it the controller won't enable the write-back cache (which it really shouldn't, since it wouldn't be safe without the batteries). WB cache can really speed things on in many db situations - it's sort of like "speed of fsync off, security of fsync on". I've seen huge speedups with both postgresql and other databases on that. If you want to be "ready for more storage", I'd suggest looking at a 1U server with a 3U external disk rack. That'll give you 16 disks in 4U (2 in the server + 14 in the rack on 2 channels), which is hard to beat. If you have no need to go there, then sure, the 2U machine will be better. But I've found the "small machine with external rack" a lot more flexible than the "big machine with disks inside it". (For example, you can put two 1U servers to it, and have 7 disks assigned to each server) In HP world that would mean DL360G3 and the StorageWorks 4354. The mandatory link: http://h18004.www1.hp.com/products/servers/platforms/index-dl-ml.html Though if you are already equipped with servers from one vendor, I'd suggest sticking to it as long as the specs are fairly close. Then you only need one set of management software etc. //Magnus From Robert_Creager@LogicalChaos.org Fri Jul 18 03:23:06 2003 X-Original-To: pgsql-performance-postgresql.org@localhost.postgresql.org Received: from localhost (unknown [64.117.224.192]) by svr1.postgresql.org (Postfix) with ESMTP id C7D0FCCBFF for ; Fri, 18 Jul 2003 03:23:06 +0000 (GMT) Received: from svr1.postgresql.org ([64.117.224.193]) by localhost (svr4.postgresql.org [64.117.224.192]) (amavisd-new, port 10024) with ESMTP id 44527-07 for ; Fri, 18 Jul 2003 03:23:36 +0000 (GMT) Received: from srvr3.iniquinet.com (srvr2.iniquinet.com [64.240.87.12]) by svr1.postgresql.org (Postfix) with SMTP id 31732CCBBB for ; Fri, 18 Jul 2003 00:23:04 -0300 (ADT) Received: (qmail 28750 invoked by uid 104); 18 Jul 2003 03:23:50 -0000 Received: from Robert_Creager@LogicalChaos.org by srvr3.iniquinet.com by uid 101 with qmail-scanner-1.15 (clamscan: 0.54. spamassassin: 2.55. Clear:SA:0(-7.8/6.0):. Processed in 6.367231 secs); 18 Jul 2003 03:23:50 -0000 Received: from vsat-148-64-8-86.c119.t7.mrt.starband.net (HELO chaos.mshome.net) (148.64.8.86) by srvr3.iniquinet.com with SMTP; 18 Jul 2003 03:23:43 -0000 Received: from localhost.localdomain (thunder.mshome.net [192.168.0.250]) by chaos.mshome.net (Postfix) with ESMTP id EF4FA1B151A; Thu, 17 Jul 2003 21:23:22 -0600 (MDT) Received: from logicalchaos.org (thunder.mshome.net [192.168.0.250]) by chaos.mshome.net (Postfix) with SMTP id A17361B151A; Thu, 17 Jul 2003 21:23:09 -0600 (MDT) Date: Thu, 17 Jul 2003 21:23:08 -0600 From: Robert Creager To: Adam Witney Cc: pgsql-performance Subject: Re: Hardware performance Message-Id: <20030717212308.18f30b8d.Robert_Creager@LogicalChaos.org> In-Reply-To: References: <3F16BC38.6070504@joeconway.com> Organization: Starlight Vision, LLC. X-Mailer: Sylpheed version 0.9.0claws (GTK+ 1.2.10; i586-mandrake-linux-gnu) Mime-Version: 1.0 Content-Type: multipart/signed; protocol="application/pgp-signature"; micalg="pgp-sha1"; boundary="=.el8CPnV.YTisJS" X-Virus-Scanned: by amavisd-new at postgresql.org X-Archive-Number: 200307/278 X-Sequence-Number: 2571 --=.el8CPnV.YTisJS Content-Type: text/plain; charset=US-ASCII Content-Transfer-Encoding: 7bit On Thu, 17 Jul 2003 16:20:42 +0100 Adam Witney said something like: > > Actually I am going through the same questions myself at the > moment.... I would like to have a 2 disk RAID1 and a 4 disk RAID5, so > need at least 6 disks.... > > Anybody have any suggestions or experience with other hardware > manufacturers for this size of setup? (2U rack, up to 6 disks, 2 > processors, ~2GB RAM, if possible) > We recently bought a couple of Compaq Proliant DL380 units. They are 2u, and support 6 disks, 2 CPU's, 12Gb max. We purchased 2 units of 1CPU, 4x72Gb RAID 0+1, 1Gb mem, redundant fans and power supplies for around $11,000 total. Unfortunately they are running Win2K with SQLAnywhere (ClearQuest/Web server) ;-) So far (5 months), they're real board... Cheers, Rob -- 21:16:04 up 1:19, 1 user, load average: 2.04, 1.99, 1.38 --=.el8CPnV.YTisJS Content-Type: application/pgp-signature -----BEGIN PGP SIGNATURE----- Version: GnuPG v1.2.2 (GNU/Linux) iEYEARECAAYFAj8XaBwACgkQgy51bQc2FFmIHgCgpSpot6xnhD2bvE3mSmszvgvS QdsAoNzB3UInQszDezr4y+dlGYTxQT6b =Kl/j -----END PGP SIGNATURE----- --=.el8CPnV.YTisJS-- From ron.l.johnson@cox.net Fri Jul 18 10:14:18 2003 X-Original-To: pgsql-performance-postgresql.org@localhost.postgresql.org Received: from localhost (unknown [64.117.224.192]) by svr1.postgresql.org (Postfix) with ESMTP id 8E546CCCB8 for ; Fri, 18 Jul 2003 10:14:18 +0000 (GMT) Received: from svr1.postgresql.org ([64.117.224.193]) by localhost (svr4.postgresql.org [64.117.224.192]) (amavisd-new, port 10024) with ESMTP id 66628-01 for ; Fri, 18 Jul 2003 10:14:47 +0000 (GMT) Received: from lakemtao02.cox.net (lakemtao02.cox.net [68.1.17.243]) by svr1.postgresql.org (Postfix) with ESMTP id E0A89CCCB4 for ; Fri, 18 Jul 2003 07:14:16 -0300 (ADT) Received: from [192.168.1.1] ([68.11.66.83]) by lakemtao02.cox.net (InterMail vM.5.01.04.05 201-253-122-122-105-20011231) with ESMTP id <20030718101449.WYBG24359.lakemtao02.cox.net@[192.168.1.1]> for ; Fri, 18 Jul 2003 06:14:49 -0400 Subject: Re: Hardware performance From: Ron Johnson To: PgSQL Performance ML In-Reply-To: <9B1C77393DED0D4B9DAA1AA1742942DA3BCCA3@pos_pdc.posportal.com> References: <9B1C77393DED0D4B9DAA1AA1742942DA3BCCA3@pos_pdc.posportal.com> Content-Type: text/plain Message-Id: <1058523288.2373.10.camel@haggis> Mime-Version: 1.0 X-Mailer: Ximian Evolution 1.4.3 Date: 18 Jul 2003 05:14:48 -0500 Content-Transfer-Encoding: 7bit X-Virus-Scanned: by amavisd-new at postgresql.org X-Archive-Number: 200307/286 X-Sequence-Number: 2579 On Wed, 2003-07-16 at 23:25, Roman Fail wrote: [snip] > has every bit of redundancy you can order. While uncommon, the > backplane is one one of the many single points of failure! Unless you go with a shared-disk cluster (Oracle 9iRAC or OpenVMS) or replication. Face it, if your pockets are deep enough, you can make everything redundant and burden-sharing (i.e., not just waiting for the master system to die). (And with some enterprise FC controllers, you can mirror the disks many kilometers away.) -- +-----------------------------------------------------------------+ | Ron Johnson, Jr. Home: ron.l.johnson@cox.net | | Jefferson, LA USA | | | | "I'm not a vegetarian because I love animals, I'm a vegetarian | | because I hate vegetables!" | | unknown | +-----------------------------------------------------------------+ From ron.l.johnson@cox.net Fri Jul 18 10:18:31 2003 X-Original-To: pgsql-performance-postgresql.org@localhost.postgresql.org Received: from localhost (unknown [64.117.224.192]) by svr1.postgresql.org (Postfix) with ESMTP id 7C06ACCB30 for ; Fri, 18 Jul 2003 10:18:31 +0000 (GMT) Received: from svr1.postgresql.org ([64.117.224.193]) by localhost (svr4.postgresql.org [64.117.224.192]) (amavisd-new, port 10024) with ESMTP id 05341-09 for ; Fri, 18 Jul 2003 10:18:55 +0000 (GMT) Received: from lakemtao03.cox.net (lakemtao03.cox.net [68.1.17.242]) by svr1.postgresql.org (Postfix) with ESMTP id 22A96CC917 for ; Fri, 18 Jul 2003 07:18:25 -0300 (ADT) Received: from [192.168.1.1] ([68.11.66.83]) by lakemtao03.cox.net (InterMail vM.5.01.04.05 201-253-122-122-105-20011231) with ESMTP id <20030718101857.YAUP23518.lakemtao03.cox.net@[192.168.1.1]> for ; Fri, 18 Jul 2003 06:18:57 -0400 Subject: Re: Hardware performance From: Ron Johnson To: PgSQL Performance ML In-Reply-To: <6BCB9D8A16AC4241919521715F4D8BCE1714F4@algol.sollentuna.se> References: <6BCB9D8A16AC4241919521715F4D8BCE1714F4@algol.sollentuna.se> Content-Type: text/plain Message-Id: <1058523536.2376.14.camel@haggis> Mime-Version: 1.0 X-Mailer: Ximian Evolution 1.4.3 Date: 18 Jul 2003 05:18:57 -0500 Content-Transfer-Encoding: 7bit X-Virus-Scanned: by amavisd-new at postgresql.org X-Archive-Number: 200307/287 X-Sequence-Number: 2580 On Thu, 2003-07-17 at 13:55, Magnus Hagander wrote: > >Adam Witney wrote: [snip] > If you would go with that one, make sure to get the optional BBWC > (Battery Backed Write Cache). Without it the controller won't enable the > write-back cache (which it really shouldn't, since it wouldn't be safe > without the batteries). WB cache can really speed things on in many db > situations - it's sort of like "speed of fsync off, security of fsync > on". I've seen huge speedups with both postgresql and other databases on > that. Don't forget to check the batteries!!! And if you have an HPaq service contract, don't rely on them to do it... -- +-----------------------------------------------------------------+ | Ron Johnson, Jr. Home: ron.l.johnson@cox.net | | Jefferson, LA USA | | | | "I'm not a vegetarian because I love animals, I'm a vegetarian | | because I hate vegetables!" | | unknown | +-----------------------------------------------------------------+ From mha@sollentuna.net Fri Jul 18 13:25:34 2003 X-Original-To: pgsql-performance-postgresql.org@localhost.postgresql.org Received: from localhost (unknown [64.117.225.181]) by svr1.postgresql.org (Postfix) with ESMTP id 5DC7DCB576 for ; Fri, 18 Jul 2003 13:25:34 +0000 (GMT) Received: from svr1.postgresql.org ([64.117.224.193]) by localhost (svr5.postgresql.org [64.117.225.181]) (amavisd-new, port 10024) with ESMTP id 93813-05 for ; Fri, 18 Jul 2003 13:25:51 +0000 (GMT) Received: from mx-2.sollentuna.net (mx-2.sollentuna.net [195.84.163.199]) by svr1.postgresql.org (Postfix) with ESMTP id 22E0FCCD21 for ; Fri, 18 Jul 2003 10:25:22 -0300 (ADT) Received: from ALGOL.sollentuna.se (janus-en.sollentuna.se [195.84.163.194]) by mx-2.sollentuna.net (Postfix) with ESMTP id 8908E34068 for ; Fri, 18 Jul 2003 16:25:51 +0200 (CEST) content-class: urn:content-classes:message MIME-Version: 1.0 Content-Type: text/plain; charset="us-ascii" Content-Transfer-Encoding: quoted-printable X-MimeOLE: Produced By Microsoft Exchange V6.0.6249.0 Subject: Re: Hardware performance Date: Fri, 18 Jul 2003 15:25:54 +0200 Message-ID: <6BCB9D8A16AC4241919521715F4D8BCE16F96B@algol.sollentuna.se> X-MS-Has-Attach: X-MS-TNEF-Correlator: Thread-Topic: [PERFORM] Hardware performance Thread-Index: AcNNFiOa76J0U/aNShucWYrzN3HedQAGczUw From: "Magnus Hagander" To: "PgSQL Performance ML" X-Virus-Scanned: by amavisd-new at postgresql.org X-Archive-Number: 200307/291 X-Sequence-Number: 2584 > > >Adam Witney wrote: > [snip] > > If you would go with that one, make sure to get the optional BBWC=20 > > (Battery Backed Write Cache). Without it the controller=20 > won't enable=20 > > the write-back cache (which it really shouldn't, since it=20 > wouldn't be=20 > > safe without the batteries). WB cache can really speed things on in=20 > > many db situations - it's sort of like "speed of fsync off,=20 > security=20 > > of fsync on". I've seen huge speedups with both postgresql=20 > and other=20 > > databases on that. >=20 > Don't forget to check the batteries!!! And if you have an=20 > HPaq service contract, don't rely on them to do it... That's what management software is for.. :-) (Yes, it does check the batteries. They are also reported on reboot, but you don't want to do that often, of course) Under the service contract, HP will *replace* the batteries for free, though - but you have to know when to replace them. //Magnus