Date: Mon, 2 Nov 1998 11:46:10 -0700 (MST) From: David G Andersen <danderse@cs.utah.edu> To: mike@smith.net.au (Mike Smith) Cc: danderse@cs.utah.edu, hackers@FreeBSD.ORG, sclawson@cs.utah.edu, mike@fast.cs.utah.edu Subject: Re: nfs/amd hangs / getattr request flood problem Message-ID: <199811021846.LAA05127@lal.cs.utah.edu> In-Reply-To: <199810310018.QAA02943@dingo.cdrom.com> from "Mike Smith" at Oct 30, 98 04:18:57 pm
next in thread | previous in thread | raw e-mail | index | archive | help
Lo and behold, Mike Smith once said: > > This may be related to a known defect in the BSD NFS code; we don't > cache getattr requests nor do we cache access requests. > > > There don't seem to be any references to this in gnats or on the lists. > > We're working on forward-porting the 2.2.x amd to 3.0 to see if the > > behavior still exists, but in the meantime, if anyone has suggestions / > > thoughts / knows what's wrong and wants to clue me in, it'd be greatly > > appreciated. :) > > 2.2 has the same problems, although it's amd may not suffer the > consequences. You can save yourself a lot of effort by resurrecting > the 3.0 AMD from the attic (check out the relevant directories a few > days before the new AM-utils stuff went in). Effort saved - thanks again. Interestingly enough, the AMD from pre-8/23/1998 does not exhibit any of the symptoms we see in the 3.0-rel amd; there's no excessive getattr traffic, and (so far) we haven't been able to replicate the system hang behavior. Life seems fairly happy with the backed out AMD, but I do strongly suspect that there's some bug tickling going on with the august amd. If people experience stability problems and filesystem hangs with 3.0 and AMD, I'd suggest trying the older version. -Dave To Unsubscribe: send mail to majordomo@FreeBSD.org with "unsubscribe freebsd-hackers" in the body of the message
Want to link to this message? Use this URL: <https://mail-archive.FreeBSD.org/cgi/mid.cgi?199811021846.LAA05127>