[Linux-cluster] GFS frozen again

[Brett Cave]

GFS has frozen again - after reconfiguring and running GFS for almost
a month now, have not been able to get GFS running stably.

[root at blade2 ~]# cat /etc/issue
CentOS release 5 (Final)
Kernel \r on an \m

[root at blade2 ~]# uname -a
Linux blade2 2.6.18-53.el5 #1 SMP Mon Nov 12 02:14:55 EST 2007 x86_64
x86_64 x86_64 GNU/Linux

[root at blade2 ~]# rpm -qa | grep gfs
gfs2-utils-0.1.38-1.el5
kmod-gfs-0.1.19-7.el5
gfs-utils-0.1.12-1.el5

[root at blade2 ~]# modinfo gfs
filename:       /lib/modules/2.6.18-53.el5/extra/gfs/gfs.ko
license:        GPL
author:         Red Hat, Inc.
description:    Global File System 0.1.19-7.el5
srcversion:     18B81D3FD6ECDCCFA53D745
depends:        gfs2
vermagic:       2.6.18-53.el5 SMP mod_unload gcc-4.1


Is anyone actually running GFS on Centos5 stably? Was running gfs2,
but was also unstable, hence the move back to gfs.

Setup: 3node cluster with 1 vote each and 1 quorum disk.
Each node has 1 x dual port hba connected to a fibra san (no
multipath, only single port on each card connected to SAN). SAN is
MSA1500. 2 GFS partitions, 1 qdisk partition on SAN.

System runs fine for a few days, and then will notice that some
mountpoints become unavailable. The entire system locks up when this
happens, and the only option I have is to reset all nodes in the
cluster to start up the cluster again. no errors in logs, nothing out
of the ordinary that i can see.