X-Original-To: pgsql-performance-postgresql.org@localhost.postgresql.org Received: from localhost (unknown [200.46.204.2]) by svr1.postgresql.org (Postfix) with ESMTP id B01F6D1D4E7 for ; Tue, 17 Feb 2004 21:54:07 +0000 (GMT) Received: from svr1.postgresql.org ([200.46.204.71]) by localhost (neptune.hub.org [200.46.204.2]) (amavisd-new, port 10024) with ESMTP id 51891-08 for ; Tue, 17 Feb 2004 17:54:04 -0400 (AST) Received: from pomeray.duluoz.net (c-24-20-13-125.client.comcast.net [24.20.13.125]) by svr1.postgresql.org (Postfix) with ESMTP id 87790D1DD71 for ; Tue, 17 Feb 2004 17:53:46 -0400 (AST) Received: (qmail 1647 invoked by uid 1000); 17 Feb 2004 13:53:46 -0800 Date: Tue, 17 Feb 2004 13:53:42 -0800 From: Mike Glover To: pgsql-performance@postgresql.org Subject: RAID or manual split? Message-Id: <20040217135342.1924326f.mpg4@duluoz.net> X-Mailer: Sylpheed version 0.9.0claws (GTK+ 1.2.10; i686-pc-linux-gnu) Mime-Version: 1.0 Content-Type: multipart/signed; protocol="application/pgp-signature"; micalg="pgp-sha1"; boundary="=.,2v/h'VCiHrz?i" X-Virus-Scanned: by amavisd-new at postgresql.org X-Archive-Number: 200402/197 X-Sequence-Number: 5721 --=.,2v/h'VCiHrz?i Content-Type: text/plain; charset=US-ASCII Content-Transfer-Encoding: 7bit It seems, that if I know the type and frequency of the queries a database will be seeing, I could split the database by hand over multiple disks and get better performance that I would with a RAID array with similar hardware. Most of the data is volatile and easily replaceable (and the rest is backed up independently), so redundancy isn't importand, and I'm willing to do some ongoing maintenance if I can get a decent speed boost. Am I misguided, or might this work? details of my setup are below: Six large (3-7 Mrow) 'summary' tables, each being updated continuously by 5-20 processes with about 0.5 transactions/second/process. Periodically (currently every two weeks), join queries are performed between one of the 'summary' tables(same one each time) and each of the other five. Each join touches most rows of both tables, indexes aren't used. Results are written into a separate group of 'inventory' tables (about 500 Krow each), one for each join. There are frequent (100-1000/day) queries of both the inventory and summary tables using the primary key -- always using the index and returning < 10 rows. We're currently getting (barely) acceptable performance from a single 15k U160 SCSI disk, but db size and activity are growing quickly. I've got more disks and a battery-backed LSI card on order. -mike -- Mike Glover GPG Key ID BFD19F2C --=.,2v/h'VCiHrz?i Content-Type: application/pgp-signature -----BEGIN PGP SIGNATURE----- Version: GnuPG v1.2.3 (GNU/Linux) iD8DBQFAMo1qZrNpxr/RnywRAsMpAJ98xSVSsJ0KhrVHueQYHvmYsFxJKwCbBEsM XMVL8I+rk0Xz+JWdCZirbio= =LxYr -----END PGP SIGNATURE----- --=.,2v/h'VCiHrz?i--