Return-Path: Received: (majordomo@vger.kernel.org) by vger.kernel.org via listexpand id ; Fri, 28 Feb 2003 23:20:51 -0500 Received: (majordomo@vger.kernel.org) by vger.kernel.org id ; Fri, 28 Feb 2003 23:20:51 -0500 Received: from tomts19-srv.bellnexxia.net ([209.226.175.73]:3236 "EHLO tomts19-srv.bellnexxia.net") by vger.kernel.org with ESMTP id ; Fri, 28 Feb 2003 23:20:49 -0500 From: Ed Tomlinson Subject: Re: [PATCH] New dcache / inode hash tuning patch To: Andi Kleen , linux-kernel@vger.kernel.org Reply-To: tomlins@cam.org Date: Fri, 28 Feb 2003 23:31:31 -0500 References:

<20030228185910.GA5694@wotan.suse.de> <20030301004942.GA16973@delft.aura.cs.cmu.edu> <20030301011723.GA31126@wotan.suse.de> Organization: me User-Agent: KNode/0.7.5 MIME-Version: 1.0 Content-Type: text/plain; charset=us-ascii Content-Transfer-Encoding: 7Bit Message-Id: <20030301043131.7D5301058@oscar.casa.dyndns.org> Sender: linux-kernel-owner@vger.kernel.org X-Mailing-List: linux-kernel@vger.kernel.org Content-Length: 823 Lines: 16 Andi Kleen wrote: > The hash function isn't good and the hash chains are far from evenly > distributed. There are typically 30-40% empty buckets, while some > others are rather long. > > In addition I think only a small fraction of the dentries are actually > hot. (no numbers on that, sorry) I wonder what would happen if you reordered the chains moving a 'found' dentry to the front of the chain? If this could be done without excessive locking it might help keep hot entries quickly accessable. This operation should be cheaper given you are using hlists. Ed Tomlinson - To unsubscribe from this list: send the line "unsubscribe linux-kernel" in the body of a message to majordomo@vger.kernel.org More majordomo info at http://vger.kernel.org/majordomo-info.html Please read the FAQ at http://www.tux.org/lkml/