Date: Mon, 25 Feb 2002 00:55:48 -0800 From: Luigi Rizzo <rizzo@icir.org> To: Richard A Steenbergen <ras@e-gerbil.net> Cc: freebsd-net@FreeBSD.ORG Subject: Re: HZ=1000 and NFS Message-ID: <20020225005547.A89674@iguana.icir.org> In-Reply-To: <20020224095015.GJ413@overlord.e-gerbil.net> References: <20020224095015.GJ413@overlord.e-gerbil.net>
next in thread | previous in thread | raw e-mail | index | archive | help
There used to be, long ago, some problems with HZ=1000 which were related to some diskless stuff -- now i forget the details but i believe it was some timeout field or the like overflowing. This was fixed years ago, though, and i believe the relevant code was in /sys/nfs/bootp_subr.c and related ones. I am running an NFS server with 4.5 and HZ=1000 (no device_polling though) and it seems to work fine. cheers luigi On Sun, Feb 24, 2002 at 04:50:15AM -0500, Richard A Steenbergen wrote: > Is anyone aware of problems with HZ=1000 and NFS? > > I was playing around with Luigi's device polling and had no problems (and > significant performance improvement under heavy network load), except for > one server doing NFS. After playing around with it for a bit I found that > it worked perfectly if I did not set HZ=1000. I had a problem with HZ=1000 > and NFS once before when playing with ALTQ, but never persued it. > > The problem I'm experiencing now is a complete system lockup, no panic or > crashing or informative errors of any kind. The cursor still blinks but > everything else is totally frozen. > > -- > Richard A Steenbergen <ras@e-gerbil.net> http://www.e-gerbil.net/ras > PGP Key ID: 0x138EA177 (67 29 D7 BC E8 18 3E DA B2 46 B3 D8 14 36 FE B6) > > To Unsubscribe: send mail to majordomo@FreeBSD.org > with "unsubscribe freebsd-net" in the body of the message To Unsubscribe: send mail to majordomo@FreeBSD.org with "unsubscribe freebsd-net" in the body of the message
Want to link to this message? Use this URL: <https://mail-archive.FreeBSD.org/cgi/mid.cgi?20020225005547.A89674>