From mboxrd@z Thu Jan 1 00:00:00 1970 Return-Path: Received: (majordomo@vger.kernel.org) by vger.kernel.org via listexpand id S932664AbZHNPsw (ORCPT ); Fri, 14 Aug 2009 11:48:52 -0400 Received: (majordomo@vger.kernel.org) by vger.kernel.org id S932603AbZHNPsv (ORCPT ); Fri, 14 Aug 2009 11:48:51 -0400 Received: from mailhost13.gawab.com ([66.220.20.13]:60445 "HELO info15.gawab.com" rhost-flags-OK-OK-OK-OK) by vger.kernel.org with SMTP id S932601AbZHNPsv (ORCPT ); Fri, 14 Aug 2009 11:48:51 -0400 X-Trusted: Whitelisted From: Al Boldi To: ngupta@vflare.org Subject: Re: compcache as a pre-swap area Date: Fri, 14 Aug 2009 18:49:19 +0300 User-Agent: KMail/1.5 Cc: Hugh Dickins , Matthew Wilcox , Ingo Molnar , Peter Zijlstra , linux-kernel@vger.kernel.org, linux-mm@kvack.org References: <200908122007.43522.ngupta@vflare.org> <200908140702.23947.a1426z@gawab.com> <4A84EDE4.1080605@vflare.org> In-Reply-To: <4A84EDE4.1080605@vflare.org> MIME-Version: 1.0 Content-Disposition: inline Content-Type: text/plain; charset="iso-8859-1" Content-Transfer-Encoding: 7bit Message-Id: <200908141849.19797.a1426z@gawab.com> Sender: linux-kernel-owner@vger.kernel.org List-ID: X-Mailing-List: linux-kernel@vger.kernel.org Nitin Gupta wrote: > On 08/14/2009 09:32 AM, Al Boldi wrote: > > So once compcache fills up, it will start to age its contents into normal > > swap? > > This is desirable but not yet implemented. For now, if 'backing swap' is > used, compcache will forward incompressible pages to the backing swap > device. If compcache fills up, kernel will simply send further swap-outs to > swap device which comes next in priority. Ok, this sounds acceptable for now. The important thing now is to improve performance to a level comparable to a system with normal ssd-swap. Do you have such a comparisson? Another interresting benchmark would be to use compcache in a maximized configuration, ie. on a system w/ 1024KB Ram assign 960KB for compcache and leave 64KB for the system, and then see how it performs. This may easily pinpoint any bottlenecks compcache has, if any. Also, a link to the latest patch against .30 would be helpful. Thanks! -- Al