mbuf leakage with nfs/zfs?

Daniel Braniss danny at cs.huji.ac.il
Sat Feb 27 07:24:13 UTC 2010


> On Fri, 26 Feb 2010 23:12:39 +0100 Willem Jan Withagen <wjw at digiware.nl>
> wrote about Re: mbuf leakage with nfs/zfs?:
> 
> WJW> > DB>  I'll have to do some packet snooping to check if it's TCP or
> WJW> > DB> UDP nfs traffic, since some of the clients are Linux ...
> 
> WJW> > I have Linux clients, too. Some use tcp, some udp.
> 
> WJW> I have Linux and FreeBSD clients running. The build system runs on 
> WJW> Linux. All Linux's are UDP....
> 
> Another shot in the dark:
> After upgrading the server, all my Linux clients hang with "stale nfs
> dir/file handle/whatever". I was not able to umount them (not even
> forcefully). I had to use either lazy forceful umount (-fl) or reboot. Some
> of these clients are still hanging around, because they are physically
> hard to access (clean room installs etc.). Maybe these clients still try to
> establish connections that eat up the buffers and never come back?

I doubt it, but here is another shot:
are we all running samba? I'm asking because the lock manager keeps dying and 
...

cheers,
	danny
PS: I dropped Jack from the CC, I think em is innocent :-)



More information about the freebsd-stable mailing list