search

CAMH-Scientific-Computing / SCC

CAMH Specialised Computing Centre
0 stars 0 forks source link

node10 nfs problem #53

Closed andycamh closed 8 years ago

andycamh commented 9 years ago

could not mount mgmt1-ib mount mgmg1 ok mount mgmt2-ib ok mount mgmt2 ok

check mgmt1 /etc/exports, found two fsid=0, /tftpboot (rw,no_root_squash,sync,no_subtree_check) /install (rw,no_root_squash,sync,no_subtree_check) /export 10.0.0.0/255.0.0.0(rw,fsid=0,crossmnt) /EPIGENETICS/SCRATCH 10.0.0.0/255.0.0.0(rw,fsid=0,crossmnt)

andycamh commented 9 years ago

some node10 log INFO: task mount.nfs4:2339 blocked for more than 120 seconds. "echo 0 > /proc/sys/kernel/hung_task_timeout_secs" disables this message. mount.nfs4 D ffff881b7fc25d00 0 2339 2338 0x00000080 ffff881b05f47688 0000000000000082 0000000000000000 0000000300000001 000000000000000d ffff881b032a86d8 0000000000000286 00000000fffda5fa ffff881b0679f0e8 ffff881b05f47fd8 0000000000010518 ffff881b0679f0e8 Call Trace: [] nfs_idmap_id+0x207/0x310 [nfs] [] ? default_wake_function+0x0/0x20 [] nfs_map_name_to_uid+0x28/0x30 [nfs] [] decode_getfattr+0x9d4/0xe40 [nfs] [] ? finish_task_switch+0x42/0xd0 [] ? thread_return+0x6bd/0x778 [] ? decode_op_hdr+0x1c/0xc0 [nfs] [] ? nfs4_xdr_dec_lookup_root+0x0/0xc0 [nfs] [] nfs4_xdr_dec_lookup_root+0xb3/0xc0 [nfs] [] rpcauth_unwrap_resp+0x7c/0xb0 [sunrpc] [] ? nfs4_xdr_dec_lookup_root+0x0/0xc0 [nfs] [] call_decode+0x1b5/0x800 [sunrpc] [] ? wake_bit_function+0x0/0x50 [] __rpc_execute+0xa2/0x270 [sunrpc] [] rpc_execute+0x23/0x30 [sunrpc] [] rpc_run_task+0x29/0x40 [sunrpc] [] rpc_call_sync+0x42/0x70 [sunrpc] [] ? mntput_no_expire+0x30/0x110 [] _nfs4_call_sync+0x22/0x30 [nfs] [] _nfs4_lookup_root+0xa7/0xc0 [nfs] [] nfs4_proc_get_root+0x4e/0xa0 [nfs] [] ? nfs_alloc_fattr+0x2f/0xc0 [nfs] [] nfs4_get_rootfh+0x57/0x140 [nfs] [] ? nfs_alloc_fattr+0x2f/0xc0 [nfs] [] nfs4_server_common_setup+0x82/0x1f0 [nfs] [] nfs4_create_server+0x167/0x330 [nfs] [] nfs4_remote_get_sb+0xa0/0x2c0 [nfs] [] vfs_kern_mount+0x7b/0x1b0 [] nfs_do_root_mount+0x7f/0xb0 [nfs] [] nfs4_try_mount+0x52/0xd0 [nfs] [] nfs4_get_sb+0xa2/0x340 [nfs] [] vfs_kern_mount+0x7b/0x1b0 [] do_kern_mount+0x52/0x130 [] do_mount+0x2e7/0x870 [] ? copy_mount_options+0xf2/0x1a0 [] sys_mount+0x90/0xe0 [] system_call_fastpath+0x16/0x1b

andycamh commented 8 years ago

synchronize system from other node, recover and put into work queue