From mboxrd@z Thu Jan 1 00:00:00 1970 From: Bill Davidsen Subject: Re: In this partition scheme, grub does not find md information? Date: Wed, 30 Jan 2008 17:36:49 -0500 Message-ID: <47A0FC01.1090908@tmr.com> References: <479EAF42.6010604@pobox.com> <18334.46306.611615.493031@notabene.brown> <479F07E1.7060408@pobox.com> <479F0AAB.3090702@rabbit.us> <479F331F.7080902@msgid.tls.msk.ru> <479F3C74.1050605@rabbit.us> <479F42A5.8040007@msgid.tls.msk.ru> <479F5177.6060206@pobox.com> <479F557D.20502@rabbit.us> <479F7FCD.7030106@pobox.com> <20080129202156.GA32434@rap.rap.dk> <479FA540.70707@pobox.com> <479FBA98.10202@tmr.com> <479FC12C.9050602@pobox.com> Mime-Version: 1.0 Content-Type: text/plain; charset=ISO-8859-1; format=flowed Content-Transfer-Encoding: 7bit Return-path: In-Reply-To: <479FC12C.9050602@pobox.com> Sender: linux-raid-owner@vger.kernel.org To: Moshe Yudkowsky Cc: =?ISO-8859-1?Q?Keld_J=F8rn_Simonsen?= , linux-raid@vger.kernel.org List-Id: linux-raid.ids Moshe Yudkowsky wrote: > Bill Davidsen wrote: > >>> According to man md(4), the o2 is likely to offer the best >>> combination of read and write performance. Why would you consider f2 >>> instead? >>> >> f2 is faster for read, most systems spend more time reading than >> writing. > > According to md(4), offset "should give similar read characteristics > to 'far' if a suitably large chunk size is used, but without as much > seeking for writes." > > Is the man page not correct, conditionally true, or simply not > understood by me (most likely case)? > > I wonder what "suitably large" is... > My personal experience is that as chunk gets larger random write gets slower, sequential gets faster. I don't have numbers any more, but 20-30% is sort of the limit of what I saw for any chunk size I consider reasonable. f2 is faster for sequential reading, tune your system to annoy you least. ;-) -- Bill Davidsen "Woe unto the statesman who makes war without a reason that will still be valid when the war is over..." Otto von Bismark