Received: from localhost (unknown [200.46.204.183]) by postgresql.org (Postfix) with ESMTP id BA0B3650EF8 for ; Thu, 26 Jun 2008 17:23:49 -0300 (ADT) Received: from postgresql.org ([200.46.204.86]) by localhost (mx1.hub.org [200.46.204.183]) (amavisd-maia, port 10024) with ESMTP id 32597-07 for ; Thu, 26 Jun 2008 17:23:42 -0300 (ADT) X-Greylist: delayed 00:07:19.721901 by SQLgrey-1.7.6 Received: from bifrost.lang.hm (mail.lang.hm [64.81.33.126]) by postgresql.org (Postfix) with ESMTP id BF068650EFE for ; Thu, 26 Jun 2008 17:23:39 -0300 (ADT) Received: from [10.0.0.100] (asgard.lang.hm [10.0.0.100]) by bifrost.lang.hm (8.13.4/8.13.4/Debian-3) with ESMTP id m5QKG64E025160; Thu, 26 Jun 2008 13:16:06 -0700 Date: Thu, 26 Jun 2008 13:17:28 -0700 (PDT) From: david@lang.hm X-X-Sender: dlang@asgard To: "Peter T. Breuer" cc: Merlin Moncure , Matthew Wakeling , pgsql-performance@postgresql.org Subject: Re: Hardware vs Software Raid In-Reply-To: <200806260503.m5Q53cA24979@inv.it.uc3m.es> Message-ID: References: <200806260503.m5Q53cA24979@inv.it.uc3m.es> User-Agent: Alpine 1.10 (DEB 962 2008-03-14) MIME-Version: 1.0 Content-Type: TEXT/PLAIN; charset=US-ASCII; format=flowed X-Virus-Scanned: Maia Mailguard 1.0.1 X-Archive-Number: 200806/182 X-Sequence-Number: 30532 On Thu, 26 Jun 2008, Peter T. Breuer wrote: > "Also sprach Merlin Moncure:" >> The linux software raid algorithms are highly optimized, and run on a > > I can confidently tell you that that's balderdash both as a Linux author > and as a software RAID linux author (check the attributions in the > kernel source, or look up something like "Raiding the Noosphere" on > google). > >> presumably (much faster) cpu than what the controller supports. >> However, there is still some extra oomph you can get out of letting >> the raid controller do what the software raid can't...namely delay >> sync for a time. > > There are several design problems left in software raid in the linux kernel. > One of them is the need for extra memory to dispatch requests with and > as (i.e. buffer heads and buffers, both). bhs should be OK since the > small cache per device won't be exceeded while the raid driver itself > serialises requests, which is essentially the case (it does not do any > buffering, queuing, whatever .. and tries hard to avoid doing so). The > need for extra buffers for the data is a problem. On different > platforms different aspects of that problem are important (would you > believe that on ARM mere copying takes so much cpu time that one wants > to avoid it at all costs, whereas on intel it's a forgettable trivium). > > I also wouldn't aboslutely swear that request ordering is maintained > under ordinary circumstances. which flavor of linux raid are you talking about (the two main families I am aware of are the md and dm ones) David Lang