NFSv4.1: LAYOUTGET EDELAY loops timeout to the MDS

The client will currently try LAYOUTGETs forever if a server is returning
NFS4ERR_LAYOUTTRYLATER or NFS4ERR_RECALLCONFLICT - even if the client no
longer needs the layout (ie process killed, unmounted).

This patch uses the DS timeout value (module parameter 'dataserver_timeo'
via rpc layer) to set an upper limit of how long the client tries LATOUTGETs
in this situation.  Once the timeout is reached, IO is redirected to the MDS.

This also changes how the client checks if a layout is on the clp list
to avoid a double list_add.

Signed-off-by: Weston Andros Adamson <dros@netapp.com>
Signed-off-by: Trond Myklebust <Trond.Myklebust@netapp.com>

2 files changed, 11 insertions, 5 deletions

diff --git a/fs/nfs/nfs4proc.c b/fs/nfs/nfs4proc.c
index 37eb38566fbc..b2671cb0f901 100644
--- a/fs/nfs/nfs4proc.c
+++ b/fs/nfs/nfs4proc.c
@@ -93,6 +93,8 @@ static int nfs4_map_errors(int err)
                 return err;
         switch (err) {
         case -NFS4ERR_RESOURCE:
+        case -NFS4ERR_LAYOUTTRYLATER:
+        case -NFS4ERR_RECALLCONFLICT:
                 return -EREMOTEIO;
         case -NFS4ERR_WRONGSEC:
                 return -EPERM;
@@ -6046,6 +6048,7 @@ static void nfs4_layoutget_done(struct rpc_task *task, void *calldata)
         struct nfs_server *server = NFS_SERVER(inode);
         struct pnfs_layout_hdr *lo;
         struct nfs4_state *state = NULL;
+        unsigned long timeo, giveup;
 
         dprintk("--> %s\n", __func__);
 
@@ -6057,7 +6060,10 @@ static void nfs4_layoutget_done(struct rpc_task *task, void *calldata)
                 goto out;
         case -NFS4ERR_LAYOUTTRYLATER:
         case -NFS4ERR_RECALLCONFLICT:
-                task->tk_status = -NFS4ERR_DELAY;
+                timeo = rpc_get_timeout(task->tk_client);
+                giveup = lgp->args.timestamp + timeo;
+                if (time_after(giveup, jiffies))
+                        task->tk_status = -NFS4ERR_DELAY;
                 break;
         case -NFS4ERR_EXPIRED:
         case -NFS4ERR_BAD_STATEID:
@@ -6178,6 +6184,7 @@ nfs4_proc_layoutget(struct nfs4_layoutget *lgp, gfp_t gfp_flags)
                 return ERR_PTR(-ENOMEM);
         }
         lgp->args.layout.pglen = max_pages * PAGE_SIZE;
+        lgp->args.timestamp = jiffies;
 
         lgp->res.layoutp = &lgp->args.layout;
         lgp->res.seq_res.sr_slot = NULL;
diff --git a/fs/nfs/pnfs.c b/fs/nfs/pnfs.c
index 97767c8683f9..48ac5aad6258 100644
--- a/fs/nfs/pnfs.c
+++ b/fs/nfs/pnfs.c
@@ -1181,7 +1181,7 @@ pnfs_update_layout(struct inode *ino,
         struct nfs_client *clp = server->nfs_client;
         struct pnfs_layout_hdr *lo;
         struct pnfs_layout_segment *lseg = NULL;
-        bool first = false;
+        bool first;
 
         if (!pnfs_enabled_sb(NFS_SERVER(ino)))
                 goto out;
@@ -1215,10 +1215,9 @@ pnfs_update_layout(struct inode *ino,
                 goto out_unlock;
         atomic_inc(&lo->plh_outstanding);
 
-        if (list_empty(&lo->plh_segs))
-                first = true;
-
+        first = list_empty(&lo->plh_layouts) ? true : false;
         spin_unlock(&ino->i_lock);
+
         if (first) {
                 /* The lo must be on the clp list if there is any
                  * chance of a CB_LAYOUTRECALL(FILE) coming in.