From owner-freebsd-current@FreeBSD.ORG Sun Dec 16 09:40:24 2007 Return-Path: Delivered-To: freebsd-current@freebsd.org Received: from mx1.freebsd.org (mx1.freebsd.org [IPv6:2001:4f8:fff6::34]) by hub.freebsd.org (Postfix) with ESMTP id C752B16A417 for ; Sun, 16 Dec 2007 09:40:24 +0000 (UTC) (envelope-from darrenr@freebsd.org) Received: from out3.smtp.messagingengine.com (out3.smtp.messagingengine.com [66.111.4.27]) by mx1.freebsd.org (Postfix) with ESMTP id 8435A13C457 for ; Sun, 16 Dec 2007 09:40:24 +0000 (UTC) (envelope-from darrenr@freebsd.org) Received: from compute1.internal (compute1.internal [10.202.2.41]) by out1.messagingengine.com (Postfix) with ESMTP id 423FE7D9B2; Sun, 16 Dec 2007 04:40:24 -0500 (EST) Received: from heartbeat2.messagingengine.com ([10.202.2.161]) by compute1.internal (MEProxy); Sun, 16 Dec 2007 04:40:24 -0500 X-Sasl-enc: 1WP7jzYoDoXTZH4SMf1tAv8n8TUp8ACJ6kROZmgJke2W 1197798023 Received: from [192.168.1.100] (dsl-202-45-110-141-static.VIC.netspace.net.au [202.45.110.141]) by mail.messagingengine.com (Postfix) with ESMTP id A6E3023A76; Sun, 16 Dec 2007 04:40:22 -0500 (EST) Message-ID: <4764F282.7030706@freebsd.org> Date: Sun, 16 Dec 2007 20:40:18 +1100 From: Darren Reed Organization: FreeBSD User-Agent: Thunderbird 2.0.0.9 (Windows/20071031) MIME-Version: 1.0 To: ticso@cicely.de References: <06CAC7FC-DB58-441D-A6E0-76D1D8133393@tamu.edu> <86ir31xwlu.fsf@ds4.des.no> <476343B4.8080208@FreeBSD.org> <86tzmk54tt.fsf@ds4.des.no> <476419CD.9070401@terranova.net> <20071216024259.GI48684@cicely12.cicely.de> In-Reply-To: <20071216024259.GI48684@cicely12.cicely.de> Content-Type: text/plain; charset=ISO-8859-1 Content-Transfer-Encoding: 7bit Cc: freebsd-current@freebsd.org, Ivan Voras Subject: Re: ZFS melting under postgres... X-BeenThere: freebsd-current@freebsd.org X-Mailman-Version: 2.1.5 Precedence: list Reply-To: darrenr@freebsd.org List-Id: Discussions about the use of FreeBSD-current List-Unsubscribe: , List-Archive: List-Post: List-Help: List-Subscribe: , X-List-Received-Date: Sun, 16 Dec 2007 09:40:24 -0000 Bernd Walter wrote: ... > One problem is with the data blocks beeing that big, when writing > 512 Byte you effectifly do a read-modify-write of a larger physical > block. > This can be handled quite well with larger FS block. > The much bigger problem is with power loss when writing such a > maintenence block. > You loose a very large area of logical blocks when this fails, > since a 4k maintenence block contains the allocation for several hundert > kB of logical data blocks. > In other words - you possibly loose data blocks that were not written > a long time and the database wouldn't expect a problem with that data. > Even for ZIL it is very questionable if you loose a large data area, > since the purpose is to have the data that was already sinced readable > after a power loss. ... ZFS doesn't suffer from this problem because the design is to always write a new section of data rather than over write "current" data. So if you lose power in the middle of a write to a data block, there is no damage to the old data. Darren