From: Jeff Garzik Subject: Re: How git affects kernel.org performance Date: Mon, 08 Jan 2007 08:43:01 -0500 Message-ID: <45A24A65.1070706@garzik.org> References: <1166297434.26330.34.camel@localhost.localdomain> <1166304080.13548.8.camel@nigel.suspend2.net> <459152B1.9040106@zytor.com> <1168140954.2153.1.camel@nigel.suspend2.net> <45A08269.4050504@zytor.com> <45A083F2.5000000@zytor.com> <20070107085526.GR24090@1wt.eu> <20070107011542.3496bc76.akpm@osdl.org> <20070108030555.GA7289@in.ibm.com> <20070108125819.GA32756@thunk.org> Mime-Version: 1.0 Content-Type: text/plain; charset=ISO-8859-1; format=flowed Content-Transfer-Encoding: 7bit Return-path: To: Theodore Tso , Suparna Bhattacharya , Andrew Morton , Willy Tarreau , Linus Torvalds , "H. Peter Anvin" , git@vger.kernel.org, nigel@nigel.suspend2.net, "J.H." , Randy Dunlap , Pavel Machek , kernel list , webmaster@kernel.org, "linux-ext4@vger.kernel.org" In-Reply-To: <20070108125819.GA32756@thunk.org> Sender: git-owner@vger.kernel.org List-Id: linux-ext4.vger.kernel.org Theodore Tso wrote: > The fastest and probably most important thing to add is some readahead > smarts to directories --- both to the htree and non-htree cases. If > you're using some kind of b-tree structure, such as XFS does for > directories, preallocation doesn't help you much. Delayed allocation > can save you if your delayed allocator knows how to structure disk > blocks so that a btree-traversal is efficient, but I'm guessing the > biggest reason why we are losing is because we don't have sufficient > readahead. This also has the advantage that it will help without > needing to doing a backup/restore to improve layout. Something I just thought of: ATA and SCSI hard disks do their own read-ahead. Seeking all over the place to pick up bits of directory will hurt even more with the disk reading and throwing away data (albeit in its internal elevator and cache). Jeff