X-Original-To: pgsql-performance-postgresql.org@localhost.postgresql.org Received: from localhost (av.hub.org [200.46.204.144]) by svr1.postgresql.org (Postfix) with ESMTP id 68647D95E4 for ; Sun, 25 Sep 2005 14:41:27 -0300 (ADT) Received: from svr1.postgresql.org ([200.46.204.71]) by localhost (av.hub.org [200.46.204.144]) (amavisd-new, port 10024) with ESMTP id 90396-02 for ; Sun, 25 Sep 2005 17:41:21 +0000 (GMT) Received: from stark.xeocode.com (stark.xeocode.com [216.58.44.227]) by svr1.postgresql.org (Postfix) with ESMTP id 6110DD95F4 for ; Sun, 25 Sep 2005 14:41:20 -0300 (ADT) Received: from localhost ([127.0.0.1] helo=stark.xeocode.com) by stark.xeocode.com with smtp (Exim 3.36 #1 (Debian)) id 1EJaUs-0003Em-00; Sun, 25 Sep 2005 13:41:06 -0400 To: PFC Cc: "Joshua D. Drake" , "Dave Cramer" , "Michael Ben-Nes" , pgsql-performance@postgresql.org Subject: Re: Advice on RAID card References: <43367937.40809@canaan.co.il> <4336C57B.6090800@commandprompt.com> <4336CEAA.7070208@commandprompt.com> In-Reply-To: From: Greg Stark Organization: The Emacs Conspiracy; member since 1992 Date: 25 Sep 2005 13:41:06 -0400 Message-ID: <873bntjb9p.fsf@stark.xeocode.com> Lines: 20 User-Agent: Gnus/5.09 (Gnus v5.9.0) Emacs/21.4 MIME-Version: 1.0 Content-Type: text/plain; charset=us-ascii X-Virus-Scanned: by amavisd-new at hub.org X-Spam-Status: No, hits=0.011 required=5 tests=[AWL=0.011] X-Spam-Level: X-Archive-Number: 200509/337 X-Sequence-Number: 14645 PFC writes: > Which makes me think that I will use Software Raid 5 and convert the > price of the card into RAM. > This should be nice for a budget server. > Gonna investigate now if Linux software RAID5 is rugged enough. Can > always buy the a card later if not. Raid 5 is perhaps the exception here. For Raid 5 a substantial amount of CPU power is needed. Also, Raid 5 is particularly inappropriate for write-heavy Database traffic. Raid 5 actually hurts write latency dramatically and Databases are very sensitive to latency. On the other hand if your database is primarily read-only then Raid 5 may not be a problem and may be faster than raid 1+0. -- greg