Skip site navigation (1)Skip section navigation (2)
Date:      Tue, 2 Aug 2016 22:48:52 +0000
From:      Rick Macklem <rmacklem@uoguelph.ca>
To:        Slawa Olhovchenkov <slw@zxy.spb.ru>, "freebsd-net@freebsd.org" <freebsd-net@freebsd.org>
Subject:   Re: Is NFSv4 mount interruptible?
Message-ID:  <YTXPR01MB049518E305D351F36900774FDD050@YTXPR01MB0495.CANPRD01.PROD.OUTLOOK.COM>
In-Reply-To: <20160802223728.GN8192@zxy.spb.ru>
References:  <20160802223728.GN8192@zxy.spb.ru>

next in thread | previous in thread | raw e-mail | index | archive | help
Slawa wrote:
>I have autofs NFSv4 mount with /etc/nfs.map:
>
>/NFS    -nfsv4,intr,soft,sec=3Dkrb5i,gssname=3Dhost storage01:/
>
>Currently I am see NFS hung and I am can't kill shell and can't
>unmount /NFS.
>
>Is NFSv4 mount interruptible?
>Or intr support only by NFSv3?
Well, in the BUGS section of "man mount_nfs" it notes that soft and intr ca=
nnot be
safely used with NFSv4. The problem is that, if an RPC that updates state (=
Open, Close,...)
terminates, then the state is no longer usable.

You can "umount -f" the file system, but only if no other "umount" is alrea=
dy in progress.
(I am working on a new umount option that will allow "umount -f" to succeed=
 when another
 umount is stuck. It requires "umount(8)" to avoid all the path checking, e=
tc.)

Personally, I would never use "soft" for any mount (except read-only maybe)=
, since it can
result in a write failure when the NFS server is slow. Using "intr" should =
be ok for NFSv3,
since it is stateless.

rick

>_______________________________________________
>freebsd-net@freebsd.org mailing list
>https://lists.freebsd.org/mailman/listinfo/freebsd-net<https://lists.freeb=
sd.org/mailman/listinfo/freebsd-net>
>To unsubscribe, send any mail to "freebsd-net-unsubscribe@freebsd.org"



Want to link to this message? Use this URL: <https://mail-archive.FreeBSD.org/cgi/mid.cgi?YTXPR01MB049518E305D351F36900774FDD050>