[sheepdog-users] cache performance test

[Liu Yuan]

On Fri, Jul 19, 2013 at 08:10:22AM +0200, Valerio Pachera wrote:
> 2013/7/19 Liu Yuan <namei.unix at gmail.com>:
> > can you paste the lines above 'leaving sheepdog cluster' ?
> 
> Jul 18 10:05:52 [main] main(878) shutdown
> Jul 18 10:24:28 [main] md_add_disk(146) /mnt/sheep/dsk02, nr 1
> Jul 18 10:24:28 [main] send_join_request(817) IPv4 ip:192.168.2.44 port:7000
> Jul 18 10:24:28 [main] for_each_object_in_stale(388) /mnt/sheep/dsk02/.stale
> Jul 18 10:24:31 [main] main(871) sheepdog daemon (version
> 0.6.0_128_g655027b) started
> Jul 18 10:24:43 [main] recover_object_main(620) done:1 count:124708,
> oid:c8d12800006f80
> Jul 18 10:24:43 [main] recover_object_main(620) done:2 count:124708,
> oid:c8d12800032a4c
> Jul 18 10:24:43 [main] recover_object_main(620) done:3 count:124708,
> oid:c8d1280001413d
> Jul 18 10:24:44 [main] recover_object_main(620) done:4 count:124708,
> oid:c8d12800015f3e
> ...
> Jul 18 10:25:34 [main] recover_object_main(620) done:124702
> count:124708, oid:c8d12800036cc7
> Jul 18 10:25:34 [main] recover_object_main(620) done:124703
> count:124708, oid:c8d12800004ebc
> Jul 18 10:25:34 [main] recover_object_main(620) done:124704
> count:124708, oid:c8d12800003faa
> Jul 18 10:25:34 [main] recover_object_main(620) done:124705
> count:124708, oid:c8d1280000117b
> Jul 18 10:25:34 [main] recover_object_main(620) done:124706
> count:124708, oid:c8d128000382d8
> Jul 18 10:25:34 [main] recover_object_main(620) done:124707
> count:124708, oid:c8d128000055fe
> Jul 18 10:25:34 [main] recover_object_main(620) done:124708
> count:124708, oid:c8d12800012667
> Jul 18 10:51:29 [main] gateway_op_done(119) leaving sheepdog cluster
> Jul 18 10:51:29 [main] gateway_op_done(119) leaving sheepdog cluster
> Jul 18 10:54:59 [gway 3195] do_read(296) failed to read from socket:
> -1, Resource temporarily unavailable
> Jul 18 10:54:59 [gway 3195] exec_req(404) failed to read a response
> Jul 18 10:54:59 [main] modify_event(150) event info for fd 32 not found

I didn't find what kind of error forced sheep out of cluster and became a
gateway-only node from log.

Could you grep 'failed' and paste?

Thanks
Yuan