Return-Path: Received: (majordomo@vger.kernel.org) by vger.kernel.org via listexpand id S932383Ab1EFQyG (ORCPT ); Fri, 6 May 2011 12:54:06 -0400 Received: from one.firstfloor.org ([213.235.205.2]:60206 "EHLO one.firstfloor.org" rhost-flags-OK-OK-OK-OK) by vger.kernel.org with ESMTP id S1756651Ab1EFQyD (ORCPT ); Fri, 6 May 2011 12:54:03 -0400 Date: Fri, 6 May 2011 18:53:59 +0200 From: Andi Kleen To: Ingo Molnar Cc: Thomas Gleixner , Andi Kleen , Eric Dumazet , john stultz , lkml , Paul Mackerras , "Paul E. McKenney" , Anton Blanchard Subject: Re: [RFC] time: xtime_lock is held too long Message-ID: <20110506165359.GE11636@one.firstfloor.org> References: <1304564090.2943.36.camel@work-vm> <1304574244.32152.666.camel@edumazet-laptop> <1304576495.2943.40.camel@work-vm> <1304604284.3032.78.camel@edumazet-laptop> <1304608095.3032.95.camel@edumazet-laptop> <20110505210118.GI2925@one.firstfloor.org> <20110506102232.GA11036@elte.hu> Mime-Version: 1.0 Content-Type: text/plain; charset=us-ascii Content-Disposition: inline In-Reply-To: <20110506102232.GA11036@elte.hu> User-Agent: Mutt/1.4.2.2i Sender: linux-kernel-owner@vger.kernel.org List-ID: X-Mailing-List: linux-kernel@vger.kernel.org Content-Length: 1007 Lines: 24 > Then precise measurements have to be done on the source of cache misses, the > total cost of the timer interrupt, etc. What we did was profiling the remote node cache misses using raw offcore events, and the xtime code was high up. I cannot share exact numbers for various reasons, but it was an improvement on a hard to improve workload. > I.e. this should be analyzed and improved properly, not just sloppily slapping > a few prefetches here and there, which wont really *solve* anything ... Well it made things faster. That's definitely something. I agree the cache lines need to be consolidated in a proper way. But well placed prefetches by themselves can be a useful tool, and placing them based on stable profile results is not "sloppy". -Andi -- 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/