LU-14566 lnet: Skip discovery in LNetPrimaryNID if DD disabled

If discovery is disabled locally then the discovery thread will not
modify any peer objects as a result of the discovery process. Thus,
the primary NID of any peer we're asked to discover will not change
as a result of discovery. Therefore, we do not need to actually
perform discovery in LNetPrimaryNID() if discovery is disabled
locally. Since this routine can result in long client mount times
when a Lustre server is down we should avoid this unnecessary
discovery.

Lustre-change: https://review.whamcloud.com/43141
Lustre-commit: 16264da9e3c43a6368a25b6ded4113e8cfa57427

Test-Parameters: trivial
HPE-bug-id: LUS-9887
Signed-off-by: Chris Horn <chris.horn@hpe.com>
Change-Id: I6d188e16422ad47a146d52bb24cdd1b77a30aa71
Reviewed-on: https://review.whamcloud.com/43141
Reviewed-by: Serguei Smirnov <ssmirnov@whamcloud.com>
Reviewed-by: James Simmons <jsimmons@infradead.org>
Reviewed-on: https://review.whamcloud.com/44224
Tested-by: jenkins <devops@whamcloud.com>
Tested-by: Maloo <maloo@whamcloud.com>
Reviewed-by: Andreas Dilger <adilger@whamcloud.com>

diff --git a/lnet/lnet/peer.c b/lnet/lnet/peer.c
index a6943e7..b376fe1 100644 (file)
--- a/lnet/lnet/peer.c
+++ b/lnet/lnet/peer.c
@@ -1193,7 +1193,13 @@ LNetPrimaryNID(lnet_nid_t nid)
        }
        lp = lpni->lpni_peer_net->lpn_peer;
 
-       while (!lnet_peer_is_uptodate(lp)) {
+       /* If discovery is disabled locally then we needn't bother running
+        * discovery here because discovery will not modify whatever
+        * primary NID is currently set for this peer. If the specified peer is
+        * down then this discovery can introduce long delays into the mount
+        * process, so skip it if it isn't necessary.
+        */
+       while (!lnet_peer_discovery_disabled && !lnet_peer_is_uptodate(lp)) {
                spin_lock(&lp->lp_lock);
                /* force a full discovery cycle */
                lp->lp_state |= LNET_PEER_FORCE_PING | LNET_PEER_FORCE_PUSH;
@@ -1204,7 +1210,11 @@ LNetPrimaryNID(lnet_nid_t nid)
                        goto out_decref;
                lp = lpni->lpni_peer_net->lpn_peer;
 
-               /* Only try once if discovery is disabled */
+               /* If we find that the peer has discovery disabled then we will
+                * not modify whatever primary NID is currently set for this
+                * peer. Thus, we can break out of this loop even if the peer
+                * is not fully up to date.
+                */
                if (lnet_is_discovery_disabled(lp))
                        break;
        }