nfsd4: recognize callback channel failure earlier

When the callback channel fails, we inform the client of that by
returning a cb_path_down error the next time it tries to renew its
lease.

If we wait most of a lease period before deciding that a callback has
failed and that the callback channel is down, then we decrease the
chances that the client will find out in time to do anything about it.

So, mark the channel down as soon as we recognize that an rpc has
failed.  However, continue trying to recall delegations anyway, in hopes
it will come back up.  This will prevent more delegations from being
given out, and ensure cb_path_down is returned to renew calls earlier,
while still making the best effort to deliver recalls of existing
delegations.

Also fix a couple comments and remove a dprink that doesn't seem likely
to be useful.

Signed-off-by: J. Bruce Fields <bfields@citi.umich.edu>

diff --git a/fs/nfsd/nfs4callback.c b/fs/nfsd/nfs4callback.c
index 6eb5cd2381ab6fbb3f71f086381203c01634b9b4..aae2b29ae2c9e6d4b645f91bf68b50046030accc 100644 (file)
--- a/fs/nfsd/nfs4callback.c
+++ b/fs/nfsd/nfs4callback.c
@@ -457,9 +457,6 @@ nfsd4_cb_recall(struct nfs4_delegation *dp)
        int retries = 1;
        int status = 0;
 
-       if ((!atomic_read(&clp->cl_callback.cb_set)) || !clnt)
-               return;
-
        cbr->cbr_trunc = 0; /* XXX need to implement truncate optimization */
        cbr->cbr_dp = dp;
 
@@ -468,6 +465,7 @@ nfsd4_cb_recall(struct nfs4_delegation *dp)
                switch (status) {
                        case -EIO:
                                /* Network partition? */
+                               atomic_set(&clp->cl_callback.cb_set, 0);
                        case -EBADHANDLE:
                        case -NFS4ERR_BAD_STATEID:
                                /* Race: client probably got cb_recall
@@ -480,11 +478,10 @@ nfsd4_cb_recall(struct nfs4_delegation *dp)
                status = rpc_call_sync(clnt, &msg, RPC_TASK_SOFT);
        }
 out_put_cred:
-       if (status == -EIO)
-               atomic_set(&clp->cl_callback.cb_set, 0);
-       /* Success or failure, now we're either waiting for lease expiration
-        * or deleg_return. */
-       dprintk("NFSD: nfs4_cb_recall: dp %p dl_flock %p dl_count %d\n",dp, dp->dl_flock, atomic_read(&dp->dl_count));
+       /*
+        * Success or failure, now we're either waiting for lease expiration
+        * or deleg_return.
+        */
        put_nfs4_client(clp);
        nfs4_put_delegation(dp);
        return;

diff --git a/fs/nfsd/nfs4state.c b/fs/nfsd/nfs4state.c
index b9d395856b3a8d22e995d2955babe34998a46ec8..11aa4b6b4fa26918da5f9aa945daee8a0300ca47 100644 (file)
--- a/fs/nfsd/nfs4state.c
+++ b/fs/nfsd/nfs4state.c
@@ -361,8 +361,11 @@ shutdown_callback_client(struct nfs4_client *clp)
 {
        struct rpc_clnt *clnt = clp->cl_callback.cb_client;
 
-       /* shutdown rpc client, ending any outstanding recall rpcs */
        if (clnt) {
+               /*
+                * Callback threads take a reference on the client, so there
+                * should be no outstanding callbacks at this point.
+                */
                clp->cl_callback.cb_client = NULL;
                rpc_shutdown_client(clnt);
        }