From mboxrd@z Thu Jan 1 00:00:00 1970 Return-Path: Message-ID: <4208DC74.4000107@nortel.com> Date: Tue, 08 Feb 2005 09:36:20 -0600 From: Chris Friesen MIME-Version: 1.0 To: Dan Malek References: <41FECA18.50609@nortelnetworks.com> <1107243398.4208.47.camel@laptopd505.fenrus.org> <41FFA21C.8060203@nortelnetworks.com> <1107273017.4208.132.camel@laptopd505.fenrus.org> <20050204203050.GA5889@dmt.cnet> <4203D793.1040604@nortel.com> <1107595148.30302.5.camel@gaston> <42077EE0.2060505@nortel.com> <1107812101.7734.42.camel@gaston> In-Reply-To: Content-Type: text/plain; charset=us-ascii; format=flowed Cc: linuxppc-dev list , Arjan van de Ven , Linux Kernel list , linuxppc64-dev Subject: Re: question on symbol exports List-Id: Linux on PowerPC Developers Mail List List-Unsubscribe: , List-Archive: List-Post: List-Help: List-Subscribe: , Dan Malek wrote: > > On Feb 7, 2005, at 4:35 PM, Benjamin Herrenschmidt wrote: > >> Interesting... more than no swap, you must also make sure you have no >> r/w mmap'ed file (which are technically equivalent to swap). > > > Yeah, I kinda had a similar thought. Just because you aren't > swapping doesn't mean the VM subsystem isn't looking at dirty bits, > too. It could potentially steal a page that it thinks can be replaced > from either a zero-fill or reading again from persistent storage. In our existing case, the app also mlock()s the pages in question. This should get around these two possible sources of inaccuracy. Chris From mboxrd@z Thu Jan 1 00:00:00 1970 Return-Path: Received: (majordomo@vger.kernel.org) by vger.kernel.org via listexpand id S261545AbVBHPhI (ORCPT ); Tue, 8 Feb 2005 10:37:08 -0500 Received: (majordomo@vger.kernel.org) by vger.kernel.org id S261544AbVBHPhI (ORCPT ); Tue, 8 Feb 2005 10:37:08 -0500 Received: from zcars04f.nortelnetworks.com ([47.129.242.57]:9899 "EHLO zcars04f.nortelnetworks.com") by vger.kernel.org with ESMTP id S261542AbVBHPgx (ORCPT ); Tue, 8 Feb 2005 10:36:53 -0500 Message-ID: <4208DC74.4000107@nortel.com> Date: Tue, 08 Feb 2005 09:36:20 -0600 X-Sybari-Space: 00000000 00000000 00000000 00000000 From: Chris Friesen User-Agent: Mozilla/5.0 (X11; U; Linux i686; en-US; rv:1.6) Gecko/20040115 X-Accept-Language: en-us, en MIME-Version: 1.0 To: Dan Malek CC: Benjamin Herrenschmidt , linuxppc64-dev , Arjan van de Ven , linuxppc-dev list , Linux Kernel list Subject: Re: question on symbol exports References: <41FECA18.50609@nortelnetworks.com> <1107243398.4208.47.camel@laptopd505.fenrus.org> <41FFA21C.8060203@nortelnetworks.com> <1107273017.4208.132.camel@laptopd505.fenrus.org> <20050204203050.GA5889@dmt.cnet> <4203D793.1040604@nortel.com> <1107595148.30302.5.camel@gaston> <42077EE0.2060505@nortel.com> <1107812101.7734.42.camel@gaston> In-Reply-To: Content-Type: text/plain; charset=us-ascii; format=flowed Content-Transfer-Encoding: 7bit Sender: linux-kernel-owner@vger.kernel.org X-Mailing-List: linux-kernel@vger.kernel.org Dan Malek wrote: > > On Feb 7, 2005, at 4:35 PM, Benjamin Herrenschmidt wrote: > >> Interesting... more than no swap, you must also make sure you have no >> r/w mmap'ed file (which are technically equivalent to swap). > > > Yeah, I kinda had a similar thought. Just because you aren't > swapping doesn't mean the VM subsystem isn't looking at dirty bits, > too. It could potentially steal a page that it thinks can be replaced > from either a zero-fill or reading again from persistent storage. In our existing case, the app also mlock()s the pages in question. This should get around these two possible sources of inaccuracy. Chris