Chuck Lever ffe5a83005 NFS: Slow down state manager after an unhandled error
If the state manager thread is not actually able to fully recover from
some situation, it wakes up waiters, who kick off a new state manager
thread.  Quite often the fresh invocation of the state manager is just
as successful.

This results in a livelock as the client dumps thousands of NFS
requests a second on the network in a vain attempt to recover.  Not
very friendly.

To mitigate this situation, add a delay in the state manager after
an unhandled error, so that the client sends just a few requests
every second in this case.

Signed-off-by: Chuck Lever <chuck.lever@oracle.com>
Signed-off-by: Trond Myklebust <Trond.Myklebust@netapp.com>
2012-10-01 15:31:51 -07:00
..
2012-07-14 16:34:32 +04:00
2012-07-30 17:25:16 -07:00
2012-07-14 16:38:34 +04:00
2012-08-17 06:56:39 -07:00
2012-07-14 16:34:32 +04:00
2012-07-14 16:34:47 +04:00
2012-09-06 12:42:35 -05:00
2012-07-14 16:34:47 +04:00
2012-07-26 11:25:33 -07:00
2012-07-14 16:38:34 +04:00
2012-07-16 14:24:43 -05:00
2012-07-14 16:34:32 +04:00
2012-09-04 18:45:54 +02:00
2012-08-04 12:15:38 +04:00
2012-07-14 16:34:47 +04:00
2012-07-14 16:34:47 +04:00
2012-07-30 17:25:19 -07:00
2012-07-14 16:34:47 +04:00
2012-07-14 16:34:47 +04:00
2012-07-30 17:25:16 -07:00
2012-07-14 16:34:32 +04:00
2012-07-14 16:34:47 +04:00
2012-08-22 17:41:09 +03:00
2012-07-22 23:58:16 +04:00
2012-07-14 16:34:47 +04:00
2012-08-20 10:11:47 -07:00
2012-07-30 17:25:21 -07:00
2012-07-14 16:32:47 +04:00
2012-07-14 16:38:34 +04:00
2012-07-14 16:32:48 +04:00
2012-08-22 10:30:10 -04:00
2012-08-04 01:24:44 +04:00