LU-7734 lnet: set primary NID in ptlrpc_connection_get()

Set the NID in ptlrpc_connection::c_peer to the primary NID of a peer.
This ensures that regardless of the NID used to start a connection, we
consistently use the same NID (the primary NID) to identify a peer. It
also means that PtlRPC will not create multiple connections to a peer.

The primary NID is obtained by calling LNetPrimaryNID(), an addition
to the exported symbols of the LNet module. The name was chosen to
match the existing naming pattern.

Test-Parameters: trivial
Signed-off-by: Olaf Weber <olaf@sgi.com>
Change-Id: Idc0605d17a58678b634db246221028cf81ad2407
Reviewed-on: http://review.whamcloud.com/21710
Tested-by: Jenkins
Tested-by: Maloo <hpdd-maloo@intel.com>
Reviewed-by: Amir Shehata <amir.shehata@intel.com>
Tested-by: Amir Shehata <amir.shehata@intel.com>

diff --git a/lnet/include/lnet/api.h b/lnet/include/lnet/api.h
index 6098439..337b986 100644 (file)
--- a/lnet/include/lnet/api.h
+++ b/lnet/include/lnet/api.h
@@ -78,6 +78,7 @@ int LNetNIFini(void);
 int LNetGetId(unsigned int index, lnet_process_id_t *id);
 int LNetDist(lnet_nid_t nid, lnet_nid_t *srcnid, __u32 *order);
 void LNetSnprintHandle(char *str, int str_len, lnet_handle_any_t handle);
+lnet_nid_t LNetPrimaryNID(lnet_nid_t nid);
 
 /** @} lnet_addr */
 

diff --git a/lnet/lnet/peer.c b/lnet/lnet/peer.c
index 6b19d2d..c73668c 100644 (file)
--- a/lnet/lnet/peer.c
+++ b/lnet/lnet/peer.c
@@ -604,6 +604,31 @@ lnet_peer_primary_nid(lnet_nid_t nid)
        return primary_nid;
 }
 
+lnet_nid_t
+LNetPrimaryNID(lnet_nid_t nid)
+{
+       struct lnet_peer_ni *lpni;
+       lnet_nid_t primary_nid = nid;
+       int rc = 0;
+       int cpt;
+
+       cpt = lnet_net_lock_current();
+       lpni = lnet_nid2peerni_locked(nid, cpt);
+       if (IS_ERR(lpni)) {
+               rc = PTR_ERR(lpni);
+               goto out_unlock;
+       }
+       primary_nid = lpni->lpni_peer_net->lpn_peer->lp_primary_nid;
+       lnet_peer_ni_decref_locked(lpni);
+out_unlock:
+       lnet_net_unlock(cpt);
+
+       CDEBUG(D_NET, "NID %s primary NID %s rc %d\n", libcfs_nid2str(nid),
+              libcfs_nid2str(primary_nid), rc);
+       return primary_nid;
+}
+EXPORT_SYMBOL(LNetPrimaryNID);
+
 struct lnet_peer_net *
 lnet_peer_get_net_locked(struct lnet_peer *peer, __u32 net_id)
 {

diff --git a/lustre/ptlrpc/connection.c b/lustre/ptlrpc/connection.c
index 8d8a365..8aaf5a4 100644 (file)
--- a/lustre/ptlrpc/connection.c
+++ b/lustre/ptlrpc/connection.c
@@ -42,30 +42,31 @@ static struct cfs_hash_ops conn_hash_ops;
 
 struct ptlrpc_connection *
 ptlrpc_connection_get(lnet_process_id_t peer, lnet_nid_t self,
-                      struct obd_uuid *uuid)
+                     struct obd_uuid *uuid)
 {
-        struct ptlrpc_connection *conn, *conn2;
-        ENTRY;
+       struct ptlrpc_connection *conn, *conn2;
+       ENTRY;
 
-        conn = cfs_hash_lookup(conn_hash, &peer);
-        if (conn)
-                GOTO(out, conn);
+       peer.nid = LNetPrimaryNID(peer.nid);
+       conn = cfs_hash_lookup(conn_hash, &peer);
+       if (conn)
+               GOTO(out, conn);
 
-        OBD_ALLOC_PTR(conn);
-        if (!conn)
-                RETURN(NULL);
+       OBD_ALLOC_PTR(conn);
+       if (!conn)
+               RETURN(NULL);
 
-        conn->c_peer = peer;
-        conn->c_self = self;
+       conn->c_peer = peer;
+       conn->c_self = self;
        INIT_HLIST_NODE(&conn->c_hash);
        atomic_set(&conn->c_refcount, 1);
-        if (uuid)
-                obd_str2uuid(&conn->c_remote_uuid, uuid->uuid);
+       if (uuid)
+               obd_str2uuid(&conn->c_remote_uuid, uuid->uuid);
 
        /*
         * Add the newly created conn to the hash, on key collision we
         * lost a racing addition and must destroy our newly allocated
-        * connection.  The object which exists in the has will be
+        * connection.  The object which exists in the hash will be
         * returned and may be compared against out object.
         */
        /* In the function below, .hs_keycmp resolves to