Received: by oss.sgi.com id ; Tue, 18 Apr 2000 09:30:18 -0700 Received: from pneumatic-tube.sgi.com ([204.94.214.22]:6732 "EHLO pneumatic-tube.sgi.com") by oss.sgi.com with ESMTP id ; Tue, 18 Apr 2000 09:30:08 -0700 Received: from ledzep.cray.com (ledzep.cray.com [137.38.226.97]) by pneumatic-tube.sgi.com (980327.SGI.8.8.8-aspam/980310.SGI-aspam) via ESMTP id JAA08969 for ; Tue, 18 Apr 2000 09:34:08 -0700 (PDT) mail_from (cattelan@thebarn.com) From: cattelan@thebarn.com Received: from ironwood-e185.americas.sgi.com (ironwood.cray.com [128.162.185.212]) by ledzep.cray.com (SGI-SGI-8.9.3/craymail-smart-nospam1.0) with ESMTP id LAA04118 for ; Tue, 18 Apr 2000 11:28:52 -0500 (CDT) Received: from gibble.americas.sgi.com (root@gibble.americas.sgi.com [128.162.195.80]) by ironwood-e185.americas.sgi.com (8.8.4/SGI-ironwood-e1.4) with ESMTP id LAA12878; Tue, 18 Apr 2000 11:28:43 -0500 (CDT) Received: from gibble.americas.sgi.com by gibble.americas.sgi.com (8.9.3/SGI-client.1.6) via ESMTP id LAA02932; Tue, 18 Apr 2000 11:28:49 -0500 Date: Tue, 18 Apr 2000 11:28:46 -0500 Message-ID: <14588.36158.760804.99827N@gibble.americas.sgi.com> To: lord@sgi.com Cc: linux-xfs@oss.sgi.com Subject: Re: TAKE - backport kswapd changes from later kernels In-Reply-To: In your message of "Tue, 18 Apr 2000 11:10:03 -0500 (CDT)" <200004181610.LAA79745@clink.americas.sgi.com> References: <200004181610.LAA79745@clink.americas.sgi.com> User-Agent: Wanderlust/1.0.3 (Notorious) tm/7.108 XEmacs/21.1 (Bryce Canyon) Sender: owner-linux-xfs@oss.sgi.com Precedence: bulk Return-Path: X-Orcpt: rfc822;linux-xfs-outgoing What to do you think... time to move the tree to pre5? At Tue, 18 Apr 2000 11:10:03 -0500 (CDT), Steve Lord wrote: > > > Modid: 2.3.99pre2-xfs:slinx:58410a > Date: Tue Apr 18 09:09:35 PDT 2000 > Workarea: clink.americas.sgi.com:/data/clink/io/lord/xfs-linux > > The following file(s) were checked into: > bonnie.engr.sgi.com:/isms/slinx/2.3.99pre2-xfs > > linux/mm/vmscan.c - 1.24 http://oss.sgi.com/cgi-bin/cvsweb.cgi/linux-2.4-xfs/> linux/mm/vmscan.c.diff?r1=text&tr1=1.24&r2=text&tr2=1.23&f=h > - Backport changes to kswapd into the xfs tree - this appeared to be having > bad interactions with XFS (memory corruption). I was able to do much more > with XFS after this change. [ The basic problem in kswapd was that it > ran for its complete timeslice even when there was nothing to do. ]