From owner-freebsd-hackers Sun Jan 12 11:51:41 1997 Return-Path: Received: (from root@localhost) by freefall.freebsd.org (8.8.4/8.8.4) id LAA16833 for hackers-outgoing; Sun, 12 Jan 1997 11:51:41 -0800 (PST) Received: from crh.cl.msu.edu (crh.cl.msu.edu [35.8.1.24]) by freefall.freebsd.org (8.8.4/8.8.4) with ESMTP id LAA16828 for ; Sun, 12 Jan 1997 11:51:39 -0800 (PST) Received: (from henrich@localhost) by crh.cl.msu.edu (8.8.4/8.8.4) id OAA14323; Sun, 12 Jan 1997 14:50:52 -0500 (EST) From: Charles Henrich Message-Id: <199701121950.OAA14323@crh.cl.msu.edu> Subject: Re: mount -o async on a news servre To: terry@lambert.org (Terry Lambert) Date: Sun, 12 Jan 1997 14:50:52 -0500 (EST) Cc: terry@lambert.org, freebsd-hackers@FreeBSD.org In-Reply-To: <199701121934.MAA26007@phaeton.artisoft.com> from Terry Lambert at "Jan 12, 97 12:34:40 pm" X-Mailer: ELM [version 2.4ME+ PL22 (25)] MIME-Version: 1.0 Content-Type: text/plain; charset=US-ASCII Content-Transfer-Encoding: 7bit Sender: owner-hackers@FreeBSD.org X-Loop: FreeBSD.org Precedence: bulk > > The "noatime" means "noatime", not "async atime". > I know this! You are reading words into my sentences that arent there! > I think changing the sync frequency for update will have no effect, > unless theres a conflict with the free buffer high water mark. Even > so, if that happened, then you are trading update time for blocking > access to buffers for some users (assuming the reclaim high water > mark is set correctly, which I believe it is). Changing the sync frequencey does matter, you get lots and lots of updates to the same metadate on incoming news feeds. You can gain some extra performance by not writing out the data that is under so much change so often. To be exact, you about halve the time (okay not quite so exact :) spent flushing disks over the 5 minute period. -Crh Charles Henrich Michigan State University henrich@msu.edu http://pilot.msu.edu/~henrich