From mboxrd@z Thu Jan 1 00:00:00 1970 Return-Path: Received: from relay.sgi.com (relay3.corp.sgi.com [198.149.34.15]) by oss.sgi.com (8.14.3/8.14.3/SuSE Linux 0.8) with ESMTP id oAGJJdJv105714 for ; Tue, 16 Nov 2010 13:19:39 -0600 Subject: Re: [PATCH v3 7/9] xfsrestore: make node lookup more efficient From: Alex Elder In-Reply-To: <20101116150705.030079100@sgi.com> References: <20101116150502.179825893@sgi.com> <20101116150705.030079100@sgi.com> Date: Tue, 16 Nov 2010 13:20:07 -0600 Message-ID: <1289935207.1950.89.camel@doink> Mime-Version: 1.0 Reply-To: aelder@sgi.com List-Id: XFS Filesystem from SGI List-Unsubscribe: , List-Archive: List-Post: List-Help: List-Subscribe: , Content-Type: text/plain; charset="us-ascii" Content-Transfer-Encoding: 7bit Sender: xfs-bounces@oss.sgi.com Errors-To: xfs-bounces@oss.sgi.com To: wkendall@sgi.com Cc: xfs@oss.sgi.com On Tue, 2010-11-16 at 09:05 -0600, wkendall@sgi.com wrote: > plain text document attachment (window_lookup_performance) > When converting an nh_t to a segment index and relative node index, > use shift and bitwise-and instead of division and modulo. Results show > this is about 50% faster than the current method. So the mapping interface now takes a segment index rather than a node index, and you have node_map_*() functions that operate on node handles. I think that's good. That change seems to be bigger, but it basically enabled you to make the switch to masking only affect those new functions. Anyway, looks good to me. Reviewed-by: Alex Elder > > Signed-off-by: Bill Kendall _______________________________________________ xfs mailing list xfs@oss.sgi.com http://oss.sgi.com/mailman/listinfo/xfs