From mboxrd@z Thu Jan 1 00:00:00 1970 Date: Sun, 10 Nov 2002 07:06:26 -0800 From: William Lee Irwin III Subject: Re: 2.5.46-mm2 Message-ID: <20021110150626.GI23425@holomorphy.com> References: <3DCDD9AC.C3FB30D9@digeo.com> <20021110143208.GJ31134@suse.de> <20021110145203.GH23425@holomorphy.com> <20021110145757.GK31134@suse.de> Mime-Version: 1.0 Content-Type: text/plain; charset=us-ascii Content-Disposition: inline In-Reply-To: <20021110145757.GK31134@suse.de> Sender: owner-linux-mm@kvack.org Return-Path: To: Jens Axboe Cc: Andrew Morton , lkml , linux-mm@kvack.org List-ID: On Sun, Nov 10, 2002 at 03:32:08PM +0100, Jens Axboe wrote: >>> I've attached a small document describing the deadline io scheduler >>> tunables. stream_unit is not in Andrew's version, yet, it uses a hard >>> defined 128KiB. Also, Andrew didn't apply the rbtree patch only the >>> tunable patch. So it uses the same insertion algorithm as the default >>> kernel, two linked lists. On Sun, Nov 10 2002, William Lee Irwin III wrote: >> Okay, then I'll want the rbtree code for benchmarking. On Sun, Nov 10, 2002 at 03:57:57PM +0100, Jens Axboe wrote: > Sure, I want to talk akpm into merging the rbtree code for real. Or I > can just drop you my current version, if you want. Go for it, I'm just trying to get tiobench to actually run (seems to have new/different "die from too many threads" behavior wrt. --threads). Dropping me a fresh kernel shouldn't slow anything down. Bill P.S.: elvtune gets hung for a long time, it says: ioctl get: Inappropriate ioctl for device did it schedule with something held and get out of deadlock free? P.P.S: kgdb broke wchan reporting... investigating -- To unsubscribe, send a message with 'unsubscribe linux-mm' in the body to majordomo@kvack.org. For more info on Linux MM, see: http://www.linux-mm.org/