From mboxrd@z Thu Jan 1 00:00:00 1970 Return-Path: Received: (majordomo@vger.kernel.org) by vger.kernel.org via listexpand id S1755342Ab1BHRyl (ORCPT ); Tue, 8 Feb 2011 12:54:41 -0500 Received: from e4.ny.us.ibm.com ([32.97.182.144]:38811 "EHLO e4.ny.us.ibm.com" rhost-flags-OK-OK-OK-OK) by vger.kernel.org with ESMTP id S1755037Ab1BHRyk (ORCPT ); Tue, 8 Feb 2011 12:54:40 -0500 Subject: Re: [RFC][PATCH 0/6] more detailed per-process transparent hugepage statistics From: Dave Hansen To: Andrea Arcangeli Cc: linux-kernel@vger.kernel.org, linux-mm@kvack.org, Michael J Wolf , Andrew Morton In-Reply-To: <20110202000750.GC16981@random.random> References: <20110201003357.D6F0BE0D@kernel> <20110201153857.GA18740@random.random> <1296580547.27022.3370.camel@nimitz> <20110201203936.GB16981@random.random> <1296593801.27022.3920.camel@nimitz> <20110202000750.GC16981@random.random> Content-Type: text/plain; charset="ANSI_X3.4-1968" Date: Tue, 08 Feb 2011 09:54:34 -0800 Message-ID: <1297187674.6737.12145.camel@nimitz> Mime-Version: 1.0 X-Mailer: Evolution 2.30.3 Content-Transfer-Encoding: 7bit X-Content-Scanned: Fidelis XPS MAILER Sender: linux-kernel-owner@vger.kernel.org List-ID: X-Mailing-List: linux-kernel@vger.kernel.org On Wed, 2011-02-02 at 01:07 +0100, Andrea Arcangeli wrote: > > I guess we could also try and figure out whether the khugepaged CPU > > overhead really comes from the scanning or the collapsing operations > > themselves. Should be as easy as some oprofiling. > > Actually I already know, the scanning is super fast. So it's no real > big deal to increase the scanning. It's big deal only if there are > plenty more of collapse/split. Compared to the KSM scan, the > khugepaged scan costs nothing. Just FYI, I did some profiling on a workload that constantly split and joined pages. Very little of the overhead was in the scanning itself, so I think you're dead-on here. -- Dave