spin_lock_init(&lp->lp_lock);
lp->lp_primary_nid = nid;
lp->lp_disc_src_nid = LNET_NID_ANY;
+ lp->lp_disc_dst_nid = LNET_NID_ANY;
if (lnet_peers_start_down())
lp->lp_alive = false;
else
}
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;
}
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;
}
spin_lock(&lp->lp_lock);
lp->lp_disc_src_nid = ev->target.nid;
+ lp->lp_disc_dst_nid = ev->source.nid;
/*
* If some kind of error happened the contents of message
goto out;
}
-
/*
* The peer may have discovery disabled at its end. Set
* NO_DISCOVERY as appropriate.
*/
- if ((pbuf->pb_info.pi_features & LNET_PING_FEAT_DISCOVERY) &&
- !lnet_peer_discovery_disabled) {
- CDEBUG(D_NET, "Peer %s has discovery enabled\n",
- libcfs_nid2str(lp->lp_primary_nid));
- lp->lp_state &= ~LNET_PEER_NO_DISCOVERY;
- } else {
+ if (!(pbuf->pb_info.pi_features & LNET_PING_FEAT_DISCOVERY) ||
+ lnet_peer_discovery_disabled) {
CDEBUG(D_NET, "Peer %s has discovery disabled\n",
libcfs_nid2str(lp->lp_primary_nid));
+
+ /* Detect whether this peer has toggled discovery from on to
+ * off and whether we can delete and re-create the peer. Peers
+ * that were manually configured cannot be deleted by discovery.
+ * We need to delete this peer and re-create it if the peer was
+ * not configured manually, is currently considered DD capable,
+ * and either:
+ * 1. We've already discovered the peer (the peer has toggled
+ * the discovery feature from on to off), or
+ * 2. The peer is considered MR, but it was not user configured
+ * (this was a "temporary" peer created via the kernel APIs
+ * that we're discovering for the first time)
+ */
+ if (!(lp->lp_state & (LNET_PEER_CONFIGURED |
+ LNET_PEER_NO_DISCOVERY)) &&
+ (lp->lp_state & (LNET_PEER_DISCOVERED |
+ LNET_PEER_MULTI_RAIL))) {
+ CDEBUG(D_NET, "Marking %s:0x%x for deletion\n",
+ libcfs_nid2str(lp->lp_primary_nid),
+ lp->lp_state);
+ lp->lp_state |= LNET_PEER_MARK_DELETION;
+ }
lp->lp_state |= LNET_PEER_NO_DISCOVERY;
+ } else {
+ CDEBUG(D_NET, "Peer %s has discovery enabled\n",
+ libcfs_nid2str(lp->lp_primary_nid));
+ lp->lp_state &= ~LNET_PEER_NO_DISCOVERY;
}
/*
/* put peer back at end of request queue, if discovery not already
* done */
- if (rc == LNET_REDISCOVER_PEER && !lnet_peer_is_uptodate(lp)) {
+ if (rc == LNET_REDISCOVER_PEER && !lnet_peer_is_uptodate(lp) &&
+ lnet_peer_queue_for_discovery(lp)) {
list_move_tail(&lp->lp_dc_list, &the_lnet.ln_dc_request);
wake_up(&the_lnet.ln_dc_waitq);
}
* of deleting it.
*/
if (!list_empty(&lp->lp_dc_list))
- list_del(&lp->lp_dc_list);
+ list_del_init(&lp->lp_dc_list);
list_for_each_entry_safe(route, tmp,
&lp->lp_routes,
lr_gwlist)
* received by lp, we need to set the discovery source
* NID for new_lp to the NID stored in lp.
*/
- if (lp->lp_disc_src_nid != LNET_NID_ANY)
+ if (lp->lp_disc_src_nid != LNET_NID_ANY) {
new_lp->lp_disc_src_nid = lp->lp_disc_src_nid;
+ new_lp->lp_disc_dst_nid = lp->lp_disc_dst_nid;
+ }
spin_unlock(&new_lp->lp_lock);
spin_unlock(&lp->lp_lock);
return rc ? rc : LNET_REDISCOVER_PEER;
}
-/*
- * Select NID to send a Ping or Push to.
- */
-static lnet_nid_t lnet_peer_select_nid(struct lnet_peer *lp)
-{
- struct lnet_peer_ni *lpni;
-
- /* Look for a direct-connected NID for this peer. */
- lpni = NULL;
- while ((lpni = lnet_get_next_peer_ni_locked(lp, NULL, lpni)) != NULL) {
- if (!lnet_get_net_locked(lpni->lpni_peer_net->lpn_net_id))
- continue;
- break;
- }
- if (lpni)
- return lpni->lpni_nid;
-
- /* Look for a routed-connected NID for this peer. */
- lpni = NULL;
- while ((lpni = lnet_get_next_peer_ni_locked(lp, NULL, lpni)) != NULL) {
- if (!lnet_find_rnet_locked(lpni->lpni_peer_net->lpn_net_id))
- continue;
- break;
- }
- if (lpni)
- return lpni->lpni_nid;
-
- return LNET_NID_ANY;
-}
-
/* Active side of ping. */
static int lnet_peer_send_ping(struct lnet_peer *lp)
__must_hold(&lp->lp_lock)
{
- lnet_nid_t pnid;
int nnis;
int rc;
int cpt;
cpt = lnet_net_lock_current();
/* Refcount for MD. */
lnet_peer_addref_locked(lp);
- pnid = lnet_peer_select_nid(lp);
lnet_net_unlock(cpt);
nnis = max(lp->lp_data_nnis, LNET_INTERFACES_MIN);
- rc = lnet_send_ping(pnid, &lp->lp_ping_mdh, nnis, lp,
+ rc = lnet_send_ping(lp->lp_primary_nid, &lp->lp_ping_mdh, nnis, lp,
the_lnet.ln_dc_handler, false);
/*
CERROR("Can't bind push source MD: %d\n", rc);
goto fail_error;
}
+
cpt = lnet_net_lock_current();
/* Refcount for MD. */
lnet_peer_addref_locked(lp);
id.pid = LNET_PID_LUSTRE;
- id.nid = lnet_peer_select_nid(lp);
+ if (lp->lp_disc_dst_nid != LNET_NID_ANY)
+ id.nid = lp->lp_disc_dst_nid;
+ else
+ id.nid = lp->lp_primary_nid;
lnet_net_unlock(cpt);
- if (id.nid == LNET_NID_ANY) {
- rc = -EHOSTUNREACH;
- goto fail_unlink;
- }
-
rc = LNetPut(lp->lp_disc_src_nid, lp->lp_push_mdh,
LNET_ACK_REQ, id, LNET_RESERVED_PORTAL,
LNET_PROTO_PING_MATCHBITS, 0, 0);
* scratch
*/
lp->lp_disc_src_nid = LNET_NID_ANY;
+ lp->lp_disc_dst_nid = LNET_NID_ANY;
if (rc)
goto fail_unlink;
atomic_read(&lpni->lpni_hstats.hlt_remote_error);
lpni_hstats->hlpni_health_value =
atomic_read(&lpni->lpni_healthv);
+ lpni_hstats->hlpni_ping_count = lpni->lpni_ping_count;
+ lpni_hstats->hlpni_next_ping = lpni->lpni_next_ping;
if (copy_to_user(bulk, lpni_hstats, sizeof(*lpni_hstats)))
goto out_free_hstats;
bulk += sizeof(*lpni_hstats);
lnet_net_unlock(LNET_LOCK_EX);
return;
}
- atomic_set(&lpni->lpni_healthv, value);
+ lnet_set_lpni_healthv_locked(lpni, value);
lnet_peer_ni_add_to_recoveryq_locked(lpni,
&the_lnet.ln_mt_peerNIRecovq, now);
lnet_peer_ni_decref_locked(lpni);
list_for_each_entry(lpn, &lp->lp_peer_nets, lpn_peer_nets) {
list_for_each_entry(lpni, &lpn->lpn_peer_nis,
lpni_peer_nis) {
- atomic_set(&lpni->lpni_healthv, value);
+ lnet_set_lpni_healthv_locked(lpni,
+ value);
lnet_peer_ni_add_to_recoveryq_locked(lpni,
&the_lnet.ln_mt_peerNIRecovq, now);
}
git://git.whamcloud.com / fs / lustre-release.git / blobdiff