From mboxrd@z Thu Jan 1 00:00:00 1970 From: =?ISO-8859-1?Q?BERTRAND_Jo=EBl?= Date: Fri, 23 Nov 2007 09:08:04 +0000 Subject: NFS hangs in D state Message-Id: <47469874.7070606@systella.fr> List-Id: MIME-Version: 1.0 Content-Type: text/plain; charset="us-ascii" Content-Transfer-Encoding: 7bit To: sparclinux@vger.kernel.org Hello, I'm using some sparc solaris diskless servers (Solaris 10 up to date) over a gigabit ethernet network. These servers use a cluster of sparc64 linux servers (rarpd+bootparamd+nfs v3/tcp). This nfs server is a T1000 running debian/testing with a 2.6.23.8 official kernel (with a raid5.c patch). Sometimes, nfsd hangs in D state : Root gershwin:[~] > ps auwx | grep nfs root 3641 0.5 0.0 0 0 ? D Nov21 14:02 [nfsd] root 15520 0.0 0.0 2048 800 pts/0 S+ 09:59 0:00 grep nfs nobody 24922 0.0 0.0 3880 1424 ? SN 06:25 0:00 su nobody -s /bin/sh -c /usr/bin/find / -ignore_readdir_race \( -fstype NFS -o -fstype nfs -o -fstype nfs4 -o -fstype afs -o -fstype binfmt_misc -o -fstype proc -o -fstype smbfs -o -fstype autofs -o -fstype iso9660 -o -fstype ncpfs -o -fstype coda -o -fstype devpts -o -fstype ftpfs -o -fstype devfs -o -fstype mfs -o -fstype shfs -o -fstype sysfs -o -fstype cifs -o -fstype lustre_lite -o -fstype tmpfs -o -fstype usbfs -o -fstype udf -o -type d -regex '\(^/tmp$\)\|\(^/usr/tmp$\)\|\(^/var/tmp$\)\|\(^/afs$\)\|\(^/amd$\)\|\(^/alex$\)\|\(^/var/spool$\)\|\(^/sfs$\)\|\(^/media$\)' \) -prune -o -print0 nobody 24923 1.4 0.0 2144 1136 ? DN 06:25 3:07 /usr/bin/find / -ignore_readdir_race ( -fstype NFS -o -fstype nfs -o -fstype nfs4 -o -fstype afs -o -fstype binfmt_misc -o -fstype proc -o -fstype smbfs -o -fstype autofs -o -fstype iso9660 -o -fstype ncpfs -o -fstype coda -o -fstype devpts -o -fstype ftpfs -o -fstype devfs -o -fstype mfs -o -fstype shfs -o -fstype sysfs -o -fstype cifs -o -fstype lustre_lite -o -fstype tmpfs -o -fstype usbfs -o -fstype udf -o -type d -regex \(^/tmp$\)\|\(^/usr/tmp$\)\|\(^/var/tmp$\)\|\(^/afs$\)\|\(^/amd$\)\|\(^/alex$\)\|\(^/var/spool$\)\|\(^/sfs$\)\|\(^/media$\) ) -prune -o -print0 Root gershwin:[~] > I don't have any information in log files. I have made similar constatation with 2.6.23. I use at home the same kernel on several U60/SMP, U80/SMP and U420/SMP with nfs v3 without any trouble. I'm not sure that this trouble come from Solaris side... Maybe from sun4v support... Any idea ? Thanks in advance, JKB