From ffe5a83005b0d23575ab109755b4cb5518a5d91f Mon Sep 17 00:00:00 2001 From: Chuck Lever Date: Fri, 14 Sep 2012 17:23:23 -0400 Subject: 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 Signed-off-by: Trond Myklebust --- fs/nfs/nfs4state.c | 1 + 1 file changed, 1 insertion(+) (limited to 'fs/nfs/nfs4state.c') diff --git a/fs/nfs/nfs4state.c b/fs/nfs/nfs4state.c index bd8ed01cb0ea..38eeefd95375 100644 --- a/fs/nfs/nfs4state.c +++ b/fs/nfs/nfs4state.c @@ -2015,6 +2015,7 @@ out_error: pr_warn_ratelimited("NFS: state manager%s%s failed on NFSv4 server %s" " with error %d\n", section_sep, section, clp->cl_hostname, -status); + ssleep(1); nfs4_end_drain_session(clp); nfs4_clear_state_manager_bit(clp); } -- cgit v1.2.3