Hi!

I have a problem with mounting orangefs. 
I load kernel modules on all  server and client nodes and successfully create 
storage spaces on  
servers(opt02-opt04) and run servers.
on client nodes(opt06, opt08) I run pvfs2-clients, but i can't mount 
orangefs:

[mix@opt08 ~]$ sudo mount -t pvfs2 tcp://opt04:3335/pvfs-fs /mnt/pvfs2
mount: Resource temporarily unavailable
[mix@opt08 ~]$ sudo mount -t pvfs2 tcp://opt04:3335/pvfs-fs /mnt/pvfs2
mount: Broken pipe

i got "Resource temporarily unavailable" when i try to mount first time 
and "Broken pipe" when rtying to mount more times. server outputs nothing 
when "Resource temporarily unavailable" and outputs that otherwise:

[S 05/27/2011 15:31:28] PVFS2 Server on node opt04 version 2.8.4-orangefs 
starting...
[S 05/27/2011 15:31:28] PVFS2 Server ready.
[E 05/27/2011 16:05:31] Warning: exchange_data: write: Connection reset by 
peer.
[E 05/27/2011 16:05:33] Warning: exchange_data: write: Connection reset by 
peer.
[E 05/27/2011 16:05:35] Warning: exchange_data: write: Connection reset by 
peer.
[E 05/27/2011 16:05:37] Warning: exchange_data: write: Connection reset by 
peer.
[E 05/27/2011 16:05:39] Warning: exchange_data: write: Connection reset by 
peer.

when i run pvfs2-ping with -m /mnt/pvfs2 it work without errors:

[mix@opt08 ~]$ orangefs-bin/bin/pvfs2-ping -m /mnt/pvfs2

(1) Parsing tab file...

(2) Initializing system interface...

(3) Initializing each file system found in tab file: /etc/pvfs2tab...

PVFS2 servers: ib://opt02:3335
Storage name: pvfs2-fs
Local mount point: /mnt/pvfs2
/mnt/pvfs2: Ok

(4) Searching for /mnt/pvfs2 in pvfstab...

PVFS2 servers: ib://opt02:3335
Storage name: pvfs2-fs
Local mount point: /mnt/pvfs2

meta servers:
ib://opt02:3335
ib://opt03:3335
ib://opt04:3335

data servers:
ib://opt02:3335
ib://opt03:3335
ib://opt04:3335

(5) Verifying that all servers are responding...

meta servers:
ib://opt02:3335 Ok
ib://opt03:3335 Ok
ib://opt04:3335 Ok

data servers:
ib://opt02:3335 Ok
ib://opt03:3335 Ok
ib://opt04:3335 Ok

(6) Verifying that fsid 1317030806 is acceptable to all servers...

Ok; all servers understand fs_id 1317030806

(7) Verifying that root handle is owned by one server...

Root handle: 1048576
Ok; root handle is owned by exactly one server.

=============================================================

The PVFS2 filesystem at /mnt/pvfs2 appears to be correctly configured.

but:
[mix@opt08 ~]$ orangefs-bin/bin/pvfs2-ping -m pvfs2-fs

(1) Parsing tab file...

(2) Initializing system interface...

(3) Initializing each file system found in tab file: /etc/pvfs2tab...

PVFS2 servers: ib://opt02:3335
Storage name: pvfs2-fs
Local mount point: /mnt/pvfs2
/mnt/pvfs2: Ok

(4) Searching for pvfs2-fs in pvfstab...
Failure: could not find filesystem for pvfs2-fs in pvfs2tab /etc/pvfs2tab
Entry 0: /mnt/pvfs2

and that is right because i cant mount fs.

and there is client log file:

[E 16:32:05.713905] PVFS Client Daemon Started. Version 2.8.4-orangefs
[D 16:32:05.759078] [INFO]: Mapping pointer 0x2aaaaaabc000 for I/O.
[D 16:32:05.762098] [INFO]: Mapping pointer 0x6ca000 for I/O.
[E 16:32:20.511299] Warning: msgpair failed to tcp://opt04:3335, will 
retry: Resource temporarily unavailable
[E 16:32:22.515312] Warning: msgpair failed to tcp://opt04:3335, will 
retry: Resource temporarily unavailable
[E 16:32:24.518362] Warning: msgpair failed to tcp://opt04:3335, will 
retry: Resource temporarily unavailable
[E 16:32:26.526413] Warning: msgpair failed to tcp://opt04:3335, will 
retry: Resource temporarily unavailable
[E 16:32:28.529464] Warning: msgpair failed to tcp://opt04:3335, will 
retry: Resource temporarily unavailable
[E 16:32:30.532515] Warning: msgpair failed to tcp://opt04:3335, will 
retry: Resource temporarily unavailable
[E 16:32:30.532549] *** msgpairarray_completion_fn: msgpair to server 
[UNKNOWN] failed: Resource temporarily unavailable
[E 16:32:30.532574] *** Out of retries.
[E 16:32:30.532629] Failed to mount via host tcp://opt04:3335
[E 16:32:30.532662] Mount failed: Resource temporarily unavailable
[E 16:32:33.247302] Error: incomplete BMI TCP header after 10 seconds, 
closing connection.
[E 16:32:33.248594] Warning: msgpair failed to tcp://opt04:3335, will 
retry: Broken pipe
[E 16:32:35.249386] Error: incomplete BMI TCP header after 10 seconds, 
closing connection.
[E 16:32:35.250634] Warning: msgpair failed to tcp://opt04:3335, will 
retry: Broken pipe
[E 16:32:37.251180] Error: incomplete BMI TCP header after 10 seconds, 
closing connection.
[E 16:32:37.252684] Warning: msgpair failed to tcp://opt04:3335, will 
retry: Broken pipe
[E 16:32:39.259260] Error: incomplete BMI TCP header after 10 seconds, 
closing connection.
[E 16:32:39.259738] Warning: msgpair failed to tcp://opt04:3335, will 
retry: Broken pipe
[E 16:32:41.270296] Error: incomplete BMI TCP header after 10 seconds, 
closing connection.
[E 16:32:41.271787] Warning: msgpair failed to tcp://opt04:3335, will 
retry: Broken pipe
[E 16:32:43.278358] Error: incomplete BMI TCP header after 10 seconds, 
closing connection.
[E 16:32:43.278840] Warning: msgpair failed to tcp://opt04:3335, will 
retry: Broken pipe
[E 16:32:43.278868] *** msgpairarray_completion_fn: msgpair to server 
[UNKNOWN] failed: Broken pipe
[E 16:32:43.278893] *** Out of retries.
[E 16:32:43.278934] Failed to mount via host tcp://opt04:3335
[E 16:32:43.278959] Mount failed: Broken pipe

and there is nothing in server log on any server node.

centos 5.5 with 2.6.18 kernel installed on cluster .

What can be a problem?

Thanks,
Mikhail Gilmendinov.

_______________________________________________
Pvfs2-users mailing list
[email protected]
http://www.beowulf-underground.org/mailman/listinfo/pvfs2-users

Reply via email to