From: Eric Sandeen Subject: Re: [PATCH -v2] ext4: Use inode preallocation with -o noextents Date: Thu, 12 Jun 2008 08:41:59 -0500 Message-ID: <485127A7.1000303@redhat.com> References: <1211229262-11012-1-git-send-email-aneesh.kumar@linux.vnet.ibm.com> <20080604022356.GA7094@mit.edu> <20080604040101.GA22348@skywalker> <20080605032220.GC10488@mit.edu> <20080605084329.GB8942@skywalker> <1212677741.3645.44.camel@localhost.localdomain> <20080605182455.GV2961@webber.adilger.int> <484F45C9.3030804@cn.fujitsu.com> <20080612093431.GZ3726@webber.adilger.int> Mime-Version: 1.0 Content-Type: text/plain; charset=ISO-8859-1 Content-Transfer-Encoding: 7bit Cc: Shen Feng , Mingming Cao , "Aneesh Kumar K.V" , Theodore Tso , linux-ext4@vger.kernel.org To: Andreas Dilger Return-path: Received: from mx1.redhat.com ([66.187.233.31]:50378 "EHLO mx1.redhat.com" rhost-flags-OK-OK-OK-OK) by vger.kernel.org with ESMTP id S1760193AbYFLNn3 (ORCPT ); Thu, 12 Jun 2008 09:43:29 -0400 In-Reply-To: <20080612093431.GZ3726@webber.adilger.int> Sender: linux-ext4-owner@vger.kernel.org List-ID: Andreas Dilger wrote: > On Jun 11, 2008 11:26 +0800, Shen Feng wrote: >> Andreas Dilger Wrote: >>> On Jun 05, 2008 07:55 -0700, Mingming Cao wrote: >>>>> /** >>>>> - * ext4_new_blocks_old() -- core block(s) allocation function >>>>> + * ext4_orlov_new_blocks() -- core block(s) allocation function >>>> what is orlov means? this is core function for non extent based without >>>> mballoc block allocation, right? >>> Orlov is the name of the INODE allocator, not the block allocator. I'm >>> not sure there is a name for the block allocator except "old" or "bitmap". >>> In the future I suspect we won't want to keep this version at all, using >>> the mballoc allocator even for block-mapped files, but it is useful for >>> now for performance comparisons. >>> >> Is that true? >> >> I got the following from the kernel ext4 documentation. >> orlov (*) This enables the new Orlov block allocator. It is >> enabled by default. >> >> oldalloc This disables the Orlov block allocator and enables >> the old block allocator. Orlov should have better >> performance - we'd like to get some feedback if it's >> the contrary for you. > > The documentation is incorrect then. The Orlov allocator is for inodes: Interestingly, though, the internets are full of references to "the orlov block allocator for ext*" anyway. :) (it seems that the original patches all referred to it this way): http://lwn.net/Articles/14447/ Plus, some Orlov history for those interested ;) http://web.archive.org/web/20070609035919/http://www.ptci.ru/gluk/dirpref/old/dirpref.html -Eric