Date: Mon, 17 Apr 2000 22:16:37 +0530 From: Rahul Siddharthan <rsidd@physics.iisc.ernet.in> To: Alfred Perlstein <bright@wintelcom.net> Cc: Rasmus Skaarup <rasmus@gal.dk>, freebsd-questions@FreeBSD.ORG Subject: Re: disc io - sync and async Message-ID: <20000417221637.A407@theory1.physics.iisc.ernet.in> In-Reply-To: <20000417084552.E4381@fw.wintelcom.net>; from bright@wintelcom.net on Mon, Apr 17, 2000 at 08:45:52AM -0700 References: <20000416120315.W4381@fw.wintelcom.net> <Pine.BSF.4.21.0004171300150.10236-100000@skaarup.org> <20000417185653.A7455@theory6.physics.iisc.ernet.in> <20000417084552.E4381@fw.wintelcom.net>
next in thread | previous in thread | raw e-mail | index | archive | help
Alfred Perlstein said on Apr 17, 2000 at 08:45:52: > As far as making softupdates the default, again you haven't read > everything you're supposed to: > > http://www.freebsd.org/cgi/cvsweb.cgi/src/sys/ufs/ffs/README.softupdates?rev=1.7 I think the question was on making async mounts the default (linux-style). The FreeBSD mount manpage warns against doing this; the linux manpage doesn't. (Unsurprising, since it's the default in linux). Also, Rasmus's earlier benchmarks suggest that FreeBSD's performance is 1/4 that of linux on the same hardware. Is that typical, or some freak of that particular hardware setup? How much of that can be compensated by softupdates (the README suggests a performance gain of 20% less running time and 40% less I/O)? Is there something especially dangerous about a FreeBSD async mount, or is the manpage merely being more "honest" than the linux manpage? When filesystem performance is important (say a heavy-duty mail server, or NFS server), and power/hardware-related crashes are not a worry and backup precautions have been taken, what would you recommend doing? Rahul. To Unsubscribe: send mail to majordomo@FreeBSD.org with "unsubscribe freebsd-questions" in the body of the message
Want to link to this message? Use this URL: <https://mail-archive.FreeBSD.org/cgi/mid.cgi?20000417221637.A407>