[Lustre-discuss] A Failed client soft lockup one OSS

Oleg Drokin Oleg.Drokin at Sun.COM
Sat Mar 27 12:55:05 PDT 2010


Hello!

On Mar 26, 2010, at 3:27 PM, Michael Sternberg wrote:

> +1 on this one, in my case using lustre-1.8.2 on RHEL-5.4 over o2ib, with patchless clients.

In your case you have an instance of bug 21937. There is a workaround patch in that bug.
> Mar 13 18:48:33 oss01 kernel:  [<ffffffff8008c86b>] default_wake_function+0x0/0xe
> Mar 13 18:48:33 oss01 kernel:  [<ffffffff800b7076>] audit_syscall_exit+0x336/0x362
> Mar 13 18:48:33 oss01 kernel:  [<ffffffff801522a0>] list_del+0xb/0x71
> Mar 13 18:48:33 oss01 kernel:  [<ffffffff8887314b>] :lnet:LNetMDAttach+0x37b/0x4c0
> Mar 13 18:48:33 oss01 kernel:  [<ffffffff88879b90>] :lnet:LNetPut+0x700/0x800
> Mar 13 18:48:33 oss01 kernel:  [<ffffffff88879c06>] :lnet:LNetPut+0x776/0x800
> Mar 13 18:48:33 oss01 kernel:  [<ffffffff88944380>] :ptlrpc:ldlm_lock_create+0x540/0x9f0
> Mar 13 18:48:33 oss01 kernel:  [<ffffffff88947eb6>] :ptlrpc:ldlm_lock_enqueue+0x186/0xb20
> Mar 13 18:48:33 oss01 kernel:  [<ffffffff8895b5f0>] :ptlrpc:ldlm_process_extent_lock+0x0/0xad0
> Mar 13 18:48:33 oss01 kernel:  [<ffffffff88966a06>] :ptlrpc:ldlm_server_glimpse_ast+0x266/0x3b0
> Mar 13 18:48:33 oss01 kernel:  [<ffffffff889693f9>] :ptlrpc:ldlm_handle_enqueue+0xbf9/0x11f0
> Mar 13 18:48:33 oss01 kernel:  [<ffffffff889736f3>] :ptlrpc:interval_iterate_reverse+0x73/0x240
> Mar 13 18:48:33 oss01 kernel:  [<ffffffff889763eb>] :ptlrpc:ptlrpc_expire_one_request+0x12b/0x630
> Mar 13 18:48:33 oss01 kernel:  [<ffffffff88976975>] :ptlrpc:ptlrpc_at_set_req_timeout+0x85/0xd0
> Mar 13 18:48:33 oss01 kernel:  [<ffffffff88977199>] :ptlrpc:ptlrpc_prep_req_pool+0x619/0x6b0
> Mar 13 18:48:33 oss01 kernel:  [<ffffffff88977d26>] :ptlrpc:ptlrpc_check_reply+0x1c6/0x610
> Mar 13 18:48:33 oss01 kernel:  [<ffffffff8897efc8>] :ptlrpc:ptlrpc_queue_wait+0x988/0x16f0
> Mar 13 18:48:33 oss01 kernel:  [<ffffffff88982613>] :ptlrpc:ptl_send_buf+0x3f3/0x5b0
> Mar 13 18:48:33 oss01 kernel:  [<ffffffff88985265>] :ptlrpc:ptl_send_rpc+0xb45/0xde0
> Mar 13 18:48:33 oss01 kernel:  [<ffffffff889872e8>] :ptlrpc:lustre_msg_check_version_v2+0x8/0x20
> Mar 13 18:48:33 oss01 kernel:  [<ffffffff8898d565>] :ptlrpc:lustre_msg_set_opc+0x45/0x120

Bye,
    Oleg



More information about the lustre-discuss mailing list