[sheepdog-users] cache performance test

Valerio Pachera sirio81 at gmail.com
Thu Jul 18 12:14:03 CEST 2013


2013/7/18 Liu Yuan <namei.unix at gmail.com>:
> This means that deletion process takes too long and collie timeout. I'm writing
> a patch to have collie wait tight for ever (it should).

Agree.

Another note:

# grep -v recover_object_main sheep.log
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
--- 10:25xx <many recover_object_main> ---
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

root at test004:/mnt/sheep/meta# collie node list
M   Id   Host:Port         V-Nodes       Zone
-    0   192.168.2.45:7000      90  755148992
-    1   192.168.2.47:7000      38  788703424

it seem that test004 (192.168.2.44) became gateway only.



More information about the sheepdog-users mailing list