pnfs: Proper delay for NFS4ERR_RECALLCONFLICT in layout_get_done

An NFS4ERR_RECALLCONFLICT is returned by server from a GET_LAYOUT
only when a Server Sent a RECALL do to that GET_LAYOUT, or
the RECALL and GET_LAYOUT crossed on the wire.
In any way this means we want to wait at most until in-flight IO
is finished and the RECALL can be satisfied.

So a proper wait here is more like 1/10 of a second, not 15 seconds
like we have now. In case of a server bug we delay exponentially
longer on each retry.

Current code totally craps out performance of very large files on
most pnfs-objects layouts, because of how the map changes when the
file has grown into the next raid group.

[Stable: This will patch back to 3.9. If there are earlier still
 maintained trees, please tell me I'll send a patch]

CC: Stable Tree <stable@vger.kernel.org>
Signed-off-by: Boaz Harrosh <bharrosh@panasas.com>
Signed-off-by: Trond Myklebust <trond.myklebust@primarydata.com>

1 files changed, 30 insertions, 4 deletions

diff --git a/fs/nfs/nfs4proc.c b/fs/nfs/nfs4proc.c
index a9eaaaa436cb..a1965329a12c 100644
--- a/fs/nfs/nfs4proc.c
+++ b/fs/nfs/nfs4proc.c
@@ -7409,9 +7409,9 @@ 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;
+	unsigned long timeo, now, giveup;
 
-	dprintk("--> %s\n", __func__);
+	dprintk("--> %s tk_status => %d\n", __func__, -task->tk_status);
 
 	if (!nfs41_sequence_done(task, &lgp->res.seq_res))
 		goto out;
@@ -7419,12 +7419,38 @@ static void nfs4_layoutget_done(struct rpc_task *task, void *calldata)
 	switch (task->tk_status) {
 	case 0:
 		goto out;
+	/*
+	 * NFS4ERR_LAYOUTTRYLATER is a conflict with another client
+	 * (or clients) writing to the same RAID stripe
+	 */
 	case -NFS4ERR_LAYOUTTRYLATER:
+	/*
+	 * NFS4ERR_RECALLCONFLICT is when conflict with self (must recall
+	 * existing layout before getting a new one).
+	 */
 	case -NFS4ERR_RECALLCONFLICT:
 		timeo = rpc_get_timeout(task->tk_client);
 		giveup = lgp->args.timestamp + timeo;
-		if (time_after(giveup, jiffies))
-			task->tk_status = -NFS4ERR_DELAY;
+		now = jiffies;
+		if (time_after(giveup, now)) {
+			unsigned long delay;
+
+			/* Delay for:
+			 * - Not less then NFS4_POLL_RETRY_MIN.
+			 * - One last time a jiffie before we give up
+			 * - exponential backoff (time_now minus start_attempt)
+			 */
+			delay = max_t(unsigned long, NFS4_POLL_RETRY_MIN,
+				    min((giveup - now - 1),
+					now - lgp->args.timestamp));
+
+			dprintk("%s: NFS4ERR_RECALLCONFLICT waiting %lu\n",
+				__func__, delay);
+			rpc_delay(task, delay);
+			task->tk_status = 0;
+			rpc_restart_call_prepare(task);
+			goto out; /* Do not call nfs4_async_handle_error() */
+		}
 		break;
 	case -NFS4ERR_EXPIRED:
 	case -NFS4ERR_BAD_STATEID: