Hide Forgot
Can you please provide the volume files that were in use?
We have just installed the new released glusterfs 3.0.3 and are facing segfault with the following backtrace: pending frames: frame : type(1) op(READDIRP) frame : type(1) op(READDIRP) frame : type(1) op(LOOKUP) frame : type(1) op(LOOKUP) frame : type(1) op(LOOKUP) frame : type(1) op(TRUNCATE) frame : type(1) op(TRUNCATE) frame : type(1) op(TRUNCATE) frame : type(1) op(TRUNCATE) frame : type(1) op(TRUNCATE) frame : type(1) op(TRUNCATE) patchset: v3.0.2-41-g029062c signal received: 11 time of crash: 2010-03-15 04:57:14 configuration details: argp 1 backtrace 1 dlfcn 1 fdatasync 1 libpthread 1 llistxattr 1 setfsid 1 spinlock 1 epoll.h 1 xattr.h 1 st_atim.tv_nsec 1 package-string: glusterfs 3.0.3 /lib/libc.so.6[0x7f5aad076f40] /usr/lib/glusterfs/3.0.3/xlator/cluster/replicate.so(afr_readdirp_cbk+0x4d)[0x7f5aabdd0e7d] /usr/lib/libglusterfs.so.0(default_readdirp_cbk+0x79)[0x7f5aad7d1fc9] /usr/lib/libglusterfs.so.0(default_readdirp_cbk+0x79)[0x7f5aad7d1fc9] /usr/lib/libglusterfs.so.0(default_readdirp_cbk+0x79)[0x7f5aad7d1fc9] /usr/lib/glusterfs/3.0.3/xlator/protocol/client.so(client_readdirp+0x1a3)[0x7f5aac635b33] /usr/lib/libglusterfs.so.0(default_readdirp+0xe2)[0x7f5aad7d1df2] /usr/lib/libglusterfs.so.0(default_readdirp+0xe2)[0x7f5aad7d1df2] /usr/lib/libglusterfs.so.0(default_readdirp+0xe2)[0x7f5aad7d1df2] /usr/lib/glusterfs/3.0.3/xlator/cluster/replicate.so(afr_do_readdir+0x334)[0x7f5aabdd2614] /usr/lib/glusterfs/3.0.3/xlator/cluster/replicate.so(afr_readdirp+0xf)[0x7f5aabdd295f] /usr/lib/glusterfs/3.0.3/xlator/cluster/distribute.so(dht_do_readdir+0x171)[0x7f5aabbb77b1] /usr/lib/glusterfs/3.0.3/xlator/cluster/distribute.so(dht_readdirp+0xf)[0x7f5aabbb7a9f] /usr/lib/glusterfs/3.0.3/xlator/mount/fuse.so[0x7f5aab98f176] /usr/lib/glusterfs/3.0.3/xlator/mount/fuse.so[0x7f5aab98da11] /lib/libpthread.so.0[0x7f5aad39ffc7] /lib/libc.so.6(clone+0x6d)[0x7f5aad11483d] ---------
Created attachment 155 [details] This is the program that the customer is running accross nfs to exhibit the problem. attached the clients glusterfs.vol
Created attachment 156 [details] printcap All the servers are identical configured....
(In reply to comment #2) > Created an attachment (id=155) [details] > the clients glusterfs.vol > > attached the clients glusterfs.vol Can you please try glusterfs-volgen to generate configuration for you? Loading performance translators between replicate and client-protocol is not recommended by us.
PATCH: http://patches.gluster.com/patch/2936 in release-3.0 (cluster/afr: Fix possible NULL dereference in readdirp_cbk)
PATCH: http://patches.gluster.com/patch/3139 in master (cluster/afr: Fix possible NULL dereference in readdirp_cbk)