X-Original-To: pgsql-performance-postgresql.org@localhost.postgresql.org Received: from localhost (neptune.hub.org [200.46.204.2]) by svr1.postgresql.org (Postfix) with ESMTP id B7ACED1DA3B for ; Mon, 24 Nov 2003 13:39:06 +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 81119-06 for ; Mon, 24 Nov 2003 09:38:38 -0400 (AST) Received: from mta11.adelphia.net (mta11.adelphia.net [68.168.78.205]) by svr1.postgresql.org (Postfix) with ESMTP id D8E29D1DA2E for ; Mon, 24 Nov 2003 09:38:28 -0400 (AST) Received: from potentialtech.com ([68.68.113.33]) by mta11.adelphia.net (InterMail vM.5.01.06.05 201-253-122-130-105-20030824) with ESMTP id <20031124133835.QRGN1464.mta11.adelphia.net@potentialtech.com>; Mon, 24 Nov 2003 08:38:35 -0500 Message-ID: <3FC209D7.5080303@potentialtech.com> Date: Mon, 24 Nov 2003 08:38:31 -0500 From: Bill Moran User-Agent: Mozilla/5.0 (X11; U; FreeBSD i386; en-US; rv:1.4) Gecko/20031005 X-Accept-Language: en-us, en MIME-Version: 1.0 To: William Yu Cc: pgsql-performance@postgresql.org Subject: Re: Maximum Possible Insert 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: 200311/207 X-Sequence-Number: 4767 William Yu wrote: > My situation is this. We have a semi-production server where we > pre-process data and then upload the finished data to our production > servers. We need the fastest possible write performance. Having the DB > go corrupt due to power loss/OS crash is acceptable because we can > always restore from last night and re-run everything that was done since > then. > > I already have fsync off. Short of buying more hardware -- which I will > probably do anyways once I figure out whether I need more CPU, memory or > disk -- what else can I do to max out the speed? Operation mix is about > 50% select, 40% insert, 10% update. In line with what Tom Lane said, you may want to look at the various memory databases available (I'm not familiar with any one to recommend, though) If you can fit the whole database in RAM, that would work great, if not, you may be able to split the DB up and put the most used tables just in the memory database. I have also seen a number tutorials on how to put a database on a RAM disk. This helps, but it's still not as fast as a database server that's designed to keep all its data in RAM. -- Bill Moran Potential Technologies http://www.potentialtech.com