[lustre-devel] [PATCH 6/8] lustre: fld: fld client lookup should retry

[James Simmons]

From: wang di <di.wang at intel.com>

If FLD client lookup fails because of the remote target
is shutdown (or deactive), it should retry another target,
otherwise it will cause the application failure.

And FLD client should stop retry if the import has
been deactive.

WC-bug-id: https://jira.whamcloud.com/browse/LU-6419
Lustre-commit: 3ededde903c92f8485cae0dc9f958f194ff0b140
Signed-off-by: wang di <di.wang at intel.com>
Reviewed-on: http://review.whamcloud.com/14313
Reviewed-by: Lai Siyao <lai.siyao at intel.com>
Reviewed-by: Fan Yong <fan.yong at intel.com>
Reviewed-by: Alex Zhuravlev <alexey.zhuravlev at intel.com>
Reviewed-by: Oleg Drokin <oleg.drokin at intel.com>
---
 fs/lustre/fld/fld_request.c | 23 +++++++++++++++++++++--
 1 file changed, 21 insertions(+), 2 deletions(-)

diff --git a/fs/lustre/fld/fld_request.c b/fs/lustre/fld/fld_request.c
index 60e7105..dfd4ae9 100644
--- a/fs/lustre/fld/fld_request.c
+++ b/fs/lustre/fld/fld_request.c
@@ -367,7 +367,7 @@ int fld_client_rpc(struct obd_export *exp,
 	rc = ptlrpc_queue_wait(req);
 	obd_put_request_slot(&exp->exp_obd->u.cli);
 	if (rc != 0) {
-		if (imp->imp_state != LUSTRE_IMP_CLOSED) {
+		if (imp->imp_state != LUSTRE_IMP_CLOSED && !imp->imp_deactive) {
 			/* Since LWP is not replayable, so it will keep
 			 * trying unless umount happens, otherwise it would
 			 * cause unecessary failure of the application.
@@ -404,6 +404,7 @@ int fld_client_lookup(struct lu_client_fld *fld, u64 seq, u32 *mds,
 {
 	struct lu_seq_range res = { 0 };
 	struct lu_fld_target *target;
+	struct lu_fld_target *origin;
 	int rc;
 
 	rc = fld_cache_lookup(fld->lcf_cache, seq, &res);
@@ -415,7 +416,8 @@ int fld_client_lookup(struct lu_client_fld *fld, u64 seq, u32 *mds,
 	/* Can not find it in the cache */
 	target = fld_client_get_target(fld, seq);
 	LASSERT(target);
-
+	origin = target;
+again:
 	CDEBUG(D_INFO,
 	       "%s: Lookup fld entry (seq: %#llx) on target %s (idx %llu)\n",
 	       fld->lcf_name, seq, fld_target_name(target), target->ft_idx);
@@ -424,6 +426,23 @@ int fld_client_lookup(struct lu_client_fld *fld, u64 seq, u32 *mds,
 	fld_range_set_type(&res, flags);
 	rc = fld_client_rpc(target->ft_exp, &res, FLD_QUERY, NULL);
 
+	if (rc == -ESHUTDOWN) {
+		/* If fld lookup failed because the target has been shutdown,
+		 * then try next target in the list, until trying all targets
+		 * or fld lookup succeeds
+		 */
+		spin_lock(&fld->lcf_lock);
+		if (target->ft_chain.next == fld->lcf_targets.prev)
+			target = list_entry(fld->lcf_targets.next,
+					    struct lu_fld_target, ft_chain);
+		else
+			target = list_entry(target->ft_chain.next,
+						 struct lu_fld_target,
+						 ft_chain);
+		spin_unlock(&fld->lcf_lock);
+		if (target != origin)
+			goto again;
+	}
 	if (rc == 0) {
 		*mds = res.lsr_index;
 
-- 
1.8.3.1