LU-13471 lnet: use the same src nid for discovery

When discovering a remote peer (not on the same network) a GET is
sent to the peer to retrieve the peer's interfaces.  This is followed
by a PUSH, if discovery is on, to push the node's interfaces However,
if both node and peer have multiple interfaces it is likely that the
GET and the PUSH will originate on different interfaces. When the
peer receives the PUSH it will not be able to connect the two NIDs
and will not be able to consolidate the node's NIDs.  This issue is
specific for remote peers because at the time the push handler is
invoked the remote lpni has not been created yet. lnet_parse()
creates the lpni of the gateway.

Similar to the strategy already in place of using the same source NID
for all the messages of an RPC, discovery should use the same source
NID for both the GET and PUSH.

This patch stores the source NID interfaces the GET was sent on and
uses it for the PUSH.

Signed-off-by: Amir Shehata <ashehata@whamcloud.com>
Change-Id: I5a13ab7799b2ddc47714202bcbed786b0d3940b7
Reviewed-on: https://review.whamcloud.com/38320
Tested-by: jenkins <devops@whamcloud.com>
Reviewed-by: Chris Horn <chris.horn@hpe.com>
Tested-by: Maloo <maloo@whamcloud.com>
Reviewed-by: Serguei Smirnov <ssmirnov@whamcloud.com>
Reviewed-by: Oleg Drokin <green@whamcloud.com>

diff --git a/lnet/include/lnet/lib-types.h b/lnet/include/lnet/lib-types.h
index f0f4181..76ac7e3 100644 (file)
--- a/lnet/include/lnet/lib-types.h
+++ b/lnet/include/lnet/lib-types.h
@@ -593,6 +593,9 @@ struct lnet_peer {
        /* primary NID of the peer */
        lnet_nid_t              lp_primary_nid;
 
        /* primary NID of the peer */
        lnet_nid_t              lp_primary_nid;
 

+       /* source NID to use during discovery */
+       lnet_nid_t              lp_disc_src_nid;
+

        /* net to perform discovery on */
        __u32                   lp_disc_net_id;
 
        /* net to perform discovery on */
        __u32                   lp_disc_net_id;
 

diff --git a/lnet/lnet/peer.c b/lnet/lnet/peer.c
index 210a96b..3719a74 100644 (file)
--- a/lnet/lnet/peer.c
+++ b/lnet/lnet/peer.c
@@ -258,6 +258,7 @@ lnet_peer_alloc(lnet_nid_t nid)
        init_waitqueue_head(&lp->lp_dc_waitq);
        spin_lock_init(&lp->lp_lock);
        lp->lp_primary_nid = nid;
        init_waitqueue_head(&lp->lp_dc_waitq);
        spin_lock_init(&lp->lp_lock);
        lp->lp_primary_nid = nid;

+       lp->lp_disc_src_nid = LNET_NID_ANY;

        if (lnet_peers_start_down())
                lp->lp_alive = false;
        else
        if (lnet_peers_start_down())
                lp->lp_alive = false;
        else


@@ -2291,6 +2292,8 @@ lnet_discovery_event_reply(struct lnet_peer *lp, struct lnet_event *ev)
 
        spin_lock(&lp->lp_lock);
 
 
        spin_lock(&lp->lp_lock);
 

+       lp->lp_disc_src_nid = ev->target.nid;
+

        /*
         * If some kind of error happened the contents of message
         * cannot be used. Set PING_FAILED to trigger a retry.
        /*
         * If some kind of error happened the contents of message
         * cannot be used. Set PING_FAILED to trigger a retry.


@@ -3109,10 +3112,18 @@ __must_hold(&lp->lp_lock)
                goto fail_unlink;
        }
 
                goto fail_unlink;
        }
 

-       rc = LNetPut(LNET_NID_ANY, lp->lp_push_mdh,
+       rc = LNetPut(lp->lp_disc_src_nid, lp->lp_push_mdh,

                     LNET_ACK_REQ, id, LNET_RESERVED_PORTAL,
                     LNET_PROTO_PING_MATCHBITS, 0, 0);
 
                     LNET_ACK_REQ, id, LNET_RESERVED_PORTAL,
                     LNET_PROTO_PING_MATCHBITS, 0, 0);
 

+       /*
+        * reset the discovery nid. There is no need to restrict sending
+        * from that source, if we call lnet_push_update_to_peers(). It'll
+        * get set to a specific NID, if we initiate discovery from the
+        * scratch
+        */
+       lp->lp_disc_src_nid = LNET_NID_ANY;
+

        if (rc)
                goto fail_unlink;
 
        if (rc)
                goto fail_unlink;