From mboxrd@z Thu Jan 1 00:00:00 1970 From: Arun Sharma Date: Thu, 11 Mar 2004 00:30:29 +0000 Subject: [Fwd: Re: Virtual memory leaking through IA32 emulation layer for Message-Id: <404FB325.9040502@intel.com> MIME-Version: 1 Content-Type: multipart/mixed; boundary="------------070306070906050501050108" List-Id: To: linux-ia64@vger.kernel.org This is a multi-part message in MIME format. --------------070306070906050501050108 Content-Type: text/plain; charset=us-ascii; format=flowed Content-Transfer-Encoding: 7bit [ I mistyped the email address for linux-ia64 ] --------------070306070906050501050108 Content-Type: message/rfc822; name="Re: Virtual memory leaking through IA32 emulation layer for mmap and munmap" Content-Transfer-Encoding: 7bit Content-Disposition: inline; filename="Re: Virtual memory leaking through IA32 emulation layer for mmap and munmap" Received: from scsmsx402.amr.corp.intel.com ([10.3.90.16]) by scsmsx401.amr.corp.intel.com with Microsoft SMTPSVC(5.0.2195.6713); Wed, 10 Mar 2004 11:45:04 -0800 Received: from fmsmsx312.amr.corp.intel.com ([132.233.42.227]) by scsmsx402.amr.corp.intel.com with Microsoft SMTPSVC(5.0.2195.6713); Wed, 10 Mar 2004 11:45:03 -0800 Received: from fmsmsx332.amr.corp.intel.com ([132.233.42.148]) by fmsmsx312.amr.corp.intel.com with Microsoft SMTPSVC(5.0.2195.6713); Wed, 10 Mar 2004 11:45:01 -0800 Received: from azsmsxvs041.ch.intel.com ([143.182.252.55]) by fmsmsx332.amr.corp.intel.com with Microsoft SMTPSVC(5.0.2195.6713); Wed, 10 Mar 2004 11:45:01 -0800 Received: from fcicdmzmail01.cs.intel.com ([192.55.36.23]) by azsmsxvs041.ch.intel.com (SAVSMTP 3.1.2.35) with SMTP id M2004031012450029904 for ; Wed, 10 Mar 2004 12:45:00 -0700 Received: from janus1.fc.hp.com ([15.232.16.17]) by fcicdmzmail01.cs.intel.com (SAVSMTP 3.1.2.35) with SMTP id M2004031012451425446 for ; Wed, 10 Mar 2004 12:45:14 -0700 Received: from palrel10.hp.com (palrel10.hp.com [15.81.168.20]) by janus1.fc.hp.com (Postfix) with ESMTP id 3F79063087; Wed, 10 Mar 2004 12:18:42 -0700 (MST) Received: from hplms2.hpl.hp.com (hplms2.hpl.hp.com [15.0.152.33]) by palrel10.hp.com (Postfix) with ESMTP id 223FD1C006B7; Wed, 10 Mar 2004 11:44:58 -0800 (PST) Received: from napali.hpl.hp.com (napali.hpl.hp.com [15.4.89.123]) by hplms2.hpl.hp.com (8.12.10/8.12.10/HPL-PA Hub) with ESMTP id i2AJiq7u007518; Wed, 10 Mar 2004 11:44:53 -0800 (PST) Received: from napali.hpl.hp.com (napali [127.0.0.1]) by napali.hpl.hp.com (8.12.11/8.12.11/Debian-1) with ESMTP id i2AJiq7h002381; Wed, 10 Mar 2004 11:44:52 -0800 Received: (from davidm@localhost) by napali.hpl.hp.com (8.12.11/8.12.11/Debian-1) id i2AJiqks002377; Wed, 10 Mar 2004 11:44:52 -0800 From: David Mosberger MIME-Version: 1.0 Content-Type: text/plain; charset=us-ascii Content-Transfer-Encoding: 7bit Message-ID: <16463.28724.277502.132751@napali.hpl.hp.com> Date: Wed, 10 Mar 2004 11:44:52 -0800 To: Arun Sharma Cc: davidm@hpl.hp.com, linux-ia64@vger.intel.com Subject: Re: Virtual memory leaking through IA32 emulation layer for mmap and munmap In-Reply-To: <404F6D26.8010502@intel.com> References: <16461.2968.682582.139300@wombat.chubb.wattle.id.au> <16461.3733.809634.212327@napali.hpl.hp.com> <16461.5771.740526.489351@wombat.chubb.wattle.id.au> <16461.6191.949155.778550@napali.hpl.hp.com> <20040310035801.GC23596@tlaloc.n0ano.com> <404F6D26.8010502@intel.com> X-Mailer: VM 7.18 under Emacs 21.3.1 Reply-To: davidm@hpl.hp.com X-URL: http://www.hpl.hp.com/personal/David_Mosberger/ Return-Path: davidm@napali.hpl.hp.com X-OriginalArrivalTime: 10 Mar 2004 19:45:01.0709 (UTC) FILETIME=[2D5E8BD0:01C406D8] >>>>> On Wed, 10 Mar 2004 11:31:50 -0800, Arun Sharma said: Arun> Yes, I'd really like to see this problem fixed. I think, the Arun> patch needs to be as memory efficient as possible - we're Arun> using non-pageable kernel memory. So some numbers on the two Arun> level bitmap scheme vs keeping lists of head/tail pages for Arun> common ia32 workloads would be good. Agreed. The good news is that the track is only needed for parially allocated pages, so the overhead should, in the worst-case, be proportional to the number of vmareas, not to the amount of memory mapped. --david --------------070306070906050501050108--