LU-4571 fld: resend seq lookup RPC if it is on LWP

Because Light Weight connection might be evicted after
restart, then cause inflight RPC fails, to avoid this,
we need resend seq lookup RPC.

remove "-f" from "stop mdt" in sanity 17m, so umount can
keep the the connection, and otherwise the OSP might be
evicted.

Signed-off-by: wang di <di.wang@intel.com>
Change-Id: I032dfb95e65da56b198129c6d6d6039bad08ab9c
Reviewed-on: http://review.whamcloud.com/9106
Tested-by: Jenkins
Tested-by: Maloo <hpdd-maloo@intel.com>
Reviewed-by: Andreas Dilger <andreas.dilger@intel.com>
Reviewed-by: Jinshan Xiong <jinshan.xiong@intel.com>
Reviewed-by: Niu Yawei <yawei.niu@intel.com>

diff --git a/lustre/fld/fld_request.c b/lustre/fld/fld_request.c
index 8d7539d..3c2d48f 100644 (file)
--- a/lustre/fld/fld_request.c
+++ b/lustre/fld/fld_request.c
@@ -430,6 +430,7 @@ int fld_client_rpc(struct obd_export *exp,
 
        LASSERT(exp != NULL);
 
+again:
        imp = class_exp2cliimp(exp);
        switch (fld_op) {
        case FLD_QUERY:
@@ -443,8 +444,14 @@ int fld_client_rpc(struct obd_export *exp,
                op = req_capsule_client_get(&req->rq_pill, &RMF_FLD_OPC);
                *op = FLD_LOOKUP;
 
-               if (imp->imp_connect_flags_orig & OBD_CONNECT_MDS_MDS)
+               /* For MDS_MDS seq lookup, it will always use LWP connection,
+                * but LWP will be evicted after restart, so cause the error.
+                * so we will set no_delay for seq lookup request, once the
+                * request fails because of the eviction. always retry here */
+               if (imp->imp_connect_flags_orig & OBD_CONNECT_MDS_MDS) {
                        req->rq_allow_replay = 1;
+                       req->rq_no_delay = 1;
+               }
                break;
        case FLD_READ:
                req = ptlrpc_request_alloc_pack(imp, &RQF_FLD_READ,
@@ -473,8 +480,18 @@ int fld_client_rpc(struct obd_export *exp,
        fld_enter_request(&exp->exp_obd->u.cli);
        rc = ptlrpc_queue_wait(req);
        fld_exit_request(&exp->exp_obd->u.cli);
-       if (rc)
+       if (rc != 0) {
+               if (rc == -EWOULDBLOCK) {
+                       /* For no_delay req(see above), EWOULDBLOCK means the
+                        * connection is being evicted, but this seq lookup
+                        * should not return error, since it would cause
+                        * unecessary failure of the application, instead
+                        * it should retry here */
+                       ptlrpc_req_finished(req);
+                       goto again;
+               }
                GOTO(out_req, rc);
+       }
 
        if (fld_op == FLD_QUERY) {
                prange = req_capsule_server_get(&req->rq_pill,

diff --git a/lustre/tests/sanity.sh b/lustre/tests/sanity.sh
index 5b959cf..e25c2f6 100644 (file)
--- a/lustre/tests/sanity.sh
+++ b/lustre/tests/sanity.sh
@@ -571,7 +571,7 @@ test_17m() {
 
        echo "stop and checking mds${mds_index}: $cmd"
        # e2fsck should not return error
-       stop mds${mds_index} -f
+       stop mds${mds_index}
        do_facet mds${mds_index} $cmd || rc=$?
 
        start mds${mds_index} $devname $MDS_MOUNT_OPTS