#define LNET_NRB_LARGE_PAGES ((LNET_MTU + PAGE_SIZE - 1) >> \
PAGE_SHIFT)
+extern unsigned int lnet_current_net_count;
+
static char *forwarding = "";
module_param(forwarding, charp, 0444);
MODULE_PARM_DESC(forwarding, "Explicitly enable/disable forwarding between networks");
module_param(avoid_asym_router_failure, int, 0644);
MODULE_PARM_DESC(avoid_asym_router_failure, "Avoid asymmetrical router failures (0 to disable)");
-static int dead_router_check_interval = 60;
-module_param(dead_router_check_interval, int, 0644);
-MODULE_PARM_DESC(dead_router_check_interval, "Seconds between dead router health checks (<= 0 to disable)");
+int dead_router_check_interval = INT_MIN;
+module_param(dead_router_check_interval, int, 0444);
+MODULE_PARM_DESC(dead_router_check_interval, "(DEPRECATED - Use alive_router_check_interval)");
+
+int live_router_check_interval = INT_MIN;
+module_param(live_router_check_interval, int, 0444);
+MODULE_PARM_DESC(live_router_check_interval, "(DEPRECATED - Use alive_router_check_interval)");
-static int live_router_check_interval = 60;
-module_param(live_router_check_interval, int, 0644);
-MODULE_PARM_DESC(live_router_check_interval, "Seconds between live router health checks (<= 0 to disable)");
+int alive_router_check_interval = 60;
+module_param(alive_router_check_interval, int, 0644);
+MODULE_PARM_DESC(alive_router_check_interval, "Seconds between live router health checks (<= 0 to disable)");
static int router_ping_timeout = 50;
module_param(router_ping_timeout, int, 0644);
return 0;
}
+void
+lnet_rtr_transfer_to_peer(struct lnet_peer *src, struct lnet_peer *target)
+{
+ struct lnet_route *route;
+
+ lnet_net_lock(LNET_LOCK_EX);
+ target->lp_rtr_refcount += src->lp_rtr_refcount;
+ /* move the list of queued messages to the new peer */
+ list_splice_init(&src->lp_rtrq, &target->lp_rtrq);
+ /* move all the routes that reference the peer */
+ list_splice_init(&src->lp_routes, &target->lp_routes);
+ /* update all the routes to point to the new peer */
+ list_for_each_entry(route, &target->lp_routes, lr_gwlist)
+ route->lr_gateway = target;
+ /* remove the old peer from the ln_routers list */
+ list_del_init(&src->lp_rtr_list);
+ /* add the new peer to the ln_routers list */
+ if (list_empty(&target->lp_rtr_list)) {
+ lnet_peer_addref_locked(target);
+ list_add_tail(&target->lp_rtr_list, &the_lnet.ln_routers);
+ }
+ /* reset the ref count on the old peer and decrement its ref count */
+ src->lp_rtr_refcount = 0;
+ lnet_peer_decref_locked(src);
+ /* update the router version */
+ the_lnet.ln_routers_version++;
+ lnet_net_unlock(LNET_LOCK_EX);
+}
+
int
lnet_peers_start_down(void)
{
}
void
-lnet_notify_locked(struct lnet_peer_ni *lp, int notifylnd, int alive,
- time64_t when)
+lnet_consolidate_routes_locked(struct lnet_peer *orig_lp,
+ struct lnet_peer *new_lp)
{
- if (lp->lpni_timestamp > when) { /* out of date information */
- CDEBUG(D_NET, "Out of date\n");
- return;
- }
+ struct lnet_peer_ni *lpni;
+ struct lnet_route *route;
/*
- * This function can be called with different cpt locks being
- * held. lpni_alive_count modification needs to be properly protected.
- * Significant reads to lpni_alive_count are also protected with
- * the same lock
+ * Although a route is correlated with a peer, but when it's added
+ * a specific NID is used. That NID refers to a peer_ni within
+ * a peer. There could be other peer_nis on the same net, which
+ * can be used to send to that gateway. However when we are
+ * consolidating gateways because of discovery, the nid used to
+ * add the route might've moved between gateway peers. In this
+ * case we want to move the route to the new gateway as well. The
+ * intent here is not to confuse the user who added the route.
*/
- spin_lock(&lp->lpni_lock);
-
- lp->lpni_timestamp = when; /* update timestamp */
-
- /* got old news */
- if (lp->lpni_alive_count != 0 &&
- /* new date for old news */
- (!lnet_is_peer_ni_alive(lp)) == (!alive)) {
- spin_unlock(&lp->lpni_lock);
- CDEBUG(D_NET, "Old news\n");
- return;
+ list_for_each_entry(route, &orig_lp->lp_routes, lr_gwlist) {
+ lpni = lnet_peer_get_ni_locked(orig_lp, route->lr_nid);
+ if (!lpni) {
+ lnet_net_lock(LNET_LOCK_EX);
+ list_move(&route->lr_gwlist, &new_lp->lp_routes);
+ lnet_net_unlock(LNET_LOCK_EX);
+ }
}
- /* Flag that notification is outstanding */
-
- lp->lpni_alive_count++;
- lp->lpni_notify = 1;
- lp->lpni_notifylnd = notifylnd;
- if (lnet_is_peer_ni_alive(lp))
- lp->lpni_ping_feats = LNET_PING_FEAT_INVAL; /* reset */
-
- spin_unlock(&lp->lpni_lock);
-
- CDEBUG(D_NET, "set %s %d\n", libcfs_nid2str(lp->lpni_nid), alive);
}
-/*
- * This function will always be called with lp->lpni_cpt lock held.
- */
-static void
-lnet_ni_notify_locked(struct lnet_ni *ni, struct lnet_peer_ni *lp)
+void
+lnet_router_discovery_complete(struct lnet_peer *lp)
{
- int alive;
- int notifylnd;
-
- /* Notify only in 1 thread at any time to ensure ordered notification.
- * NB individual events can be missed; the only guarantee is that you
- * always get the most recent news */
+ struct lnet_peer_ni *lpni = NULL;
- spin_lock(&lp->lpni_lock);
+ spin_lock(&lp->lp_lock);
+ lp->lp_state &= ~LNET_PEER_RTR_DISCOVERY;
+ spin_unlock(&lp->lp_lock);
- if (lp->lpni_notifying || ni == NULL) {
- spin_unlock(&lp->lpni_lock);
+ /*
+ * Router discovery successful? All peer information would've been
+ * updated already. No need to do any more processing
+ */
+ if (!lp->lp_dc_error)
return;
- }
-
- lp->lpni_notifying = 1;
-
/*
- * lp->lpni_notify needs to be protected because it can be set in
- * lnet_notify_locked().
+ * discovery failed? then we need to set the status of each lpni
+ * to DOWN. It will be updated the next time we discover the
+ * router. For router peer NIs not on local networks, we never send
+ * messages directly to them, so their health will always remain
+ * at maximum. We can only tell if they are up or down from the
+ * status returned in the PING response. If we fail to get that
+ * status in our scheduled router discovery, then we'll assume
+ * it's down until we're told otherwise.
*/
- while (lp->lpni_notify) {
- alive = lnet_is_peer_ni_alive(lp);
- notifylnd = lp->lpni_notifylnd;
-
- lp->lpni_notifylnd = 0;
- lp->lpni_notify = 0;
-
- if (notifylnd && ni->ni_net->net_lnd->lnd_notify != NULL) {
- spin_unlock(&lp->lpni_lock);
- lnet_net_unlock(lp->lpni_cpt);
-
- /* A new notification could happen now; I'll handle it
- * when control returns to me */
-
- (ni->ni_net->net_lnd->lnd_notify)(ni, lp->lpni_nid,
- alive);
-
- lnet_net_lock(lp->lpni_cpt);
- spin_lock(&lp->lpni_lock);
- }
- }
-
- lp->lpni_notifying = 0;
- spin_unlock(&lp->lpni_lock);
+ CDEBUG(D_NET, "%s: Router discovery failed %d\n",
+ libcfs_nid2str(lp->lp_primary_nid), lp->lp_dc_error);
+ while ((lpni = lnet_get_next_peer_ni_locked(lp, NULL, lpni)) != NULL)
+ lpni->lpni_ns_status = LNET_NI_STATUS_DOWN;
}
static void
static void
lnet_add_route_to_rnet(struct lnet_remotenet *rnet, struct lnet_route *route)
{
- unsigned int len = 0;
+ struct lnet_peer_net *lpn;
unsigned int offset = 0;
+ unsigned int len = 0;
struct list_head *e;
lnet_shuffle_seed();
* different nodes are using the same list of routers, they end up
* preferring different routers.
*/
- offset = cfs_rand() % (len + 1);
+ offset = prandom_u32_max(len + 1);
list_for_each(e, &rnet->lrn_routes) {
if (offset == 0)
break;
* force a router check on the gateway to make sure the route is
* alive
*/
- route->lr_gateway->lp_rtrcheck_timestamp = 0;
+ list_for_each_entry(lpn, &route->lr_gateway->lp_peer_nets,
+ lpn_peer_nets) {
+ lpn->lpn_rtrcheck_timestamp = 0;
+ }
the_lnet.ln_remote_nets_version++;
int
lnet_add_route(__u32 net, __u32 hops, lnet_nid_t gateway,
- unsigned int priority)
+ __u32 priority, __u32 sensitivity)
{
struct list_head *route_entry;
struct lnet_remotenet *rnet;
if (lnet_islocalnet(net))
return -EEXIST;
+ if (!lnet_islocalnet(LNET_NIDNET(gateway))) {
+ CERROR("Cannot add route with gateway %s. There is no local interface configured on LNet %s\n",
+ libcfs_nid2str(gateway),
+ libcfs_net2str(LNET_NIDNET(gateway)));
+ return -EINVAL;
+ }
+
/* Assume net, route, all new */
LIBCFS_ALLOC(route, sizeof(*route));
LIBCFS_ALLOC(rnet, sizeof(*rnet));
/* store the local and remote net that the route represents */
route->lr_lnet = LNET_NIDNET(gateway);
route->lr_net = net;
+ route->lr_nid = gateway;
route->lr_priority = priority;
route->lr_hops = hops;
* to move the routes from the peer that's being deleted to the
* consolidated peer lp_routes list
*/
- if (add_route)
+ if (add_route) {
+ gw->lp_health_sensitivity = sensitivity;
lnet_add_route_to_rnet(rnet2, route);
+ if (lnet_peer_discovery_disabled)
+ CWARN("Consider turning discovery on to enable full "
+ "Multi-Rail routing functionality\n");
+ }
/*
* get rid of the reference on the lpni.
}
delete_zombies:
+ /*
+ * check if there are any routes remaining on the gateway
+ * If there are no more routes make sure to set the peer's
+ * lp_disc_net_id to 0 (invalid), in case we add more routes in
+ * the future on that gateway, then we start our discovery process
+ * from scratch
+ */
+ if (lpni) {
+ if (list_empty(&lp->lp_routes))
+ lp->lp_disc_net_id = 0;
+ }
+
lnet_net_unlock(LNET_LOCK_EX);
while (!list_empty(&zombies)) {
int
lnet_get_route(int idx, __u32 *net, __u32 *hops,
- lnet_nid_t *gateway, __u32 *alive, __u32 *priority)
+ lnet_nid_t *gateway, __u32 *alive, __u32 *priority, __u32 *sensitivity)
{
- struct list_head *e1;
- struct list_head *e2;
struct lnet_remotenet *rnet;
- struct lnet_route *route;
- int cpt;
- int i;
struct list_head *rn_list;
+ struct lnet_route *route;
+ struct list_head *e1;
+ struct list_head *e2;
+ int cpt;
+ int i;
cpt = lnet_net_lock_current();
if (idx-- == 0) {
*net = rnet->lrn_net;
+ *gateway = route->lr_nid;
*hops = route->lr_hops;
*priority = route->lr_priority;
- *gateway = route->lr_gateway->lp_primary_nid;
+ *sensitivity = route->lr_gateway->
+ lp_health_sensitivity;
*alive = lnet_is_route_alive(route);
lnet_net_unlock(cpt);
return 0;
return -ENOENT;
}
-void
-lnet_swap_pinginfo(struct lnet_ping_buffer *pbuf)
-{
- struct lnet_ni_status *stat;
- int nnis;
- int i;
-
- __swab32s(&pbuf->pb_info.pi_magic);
- __swab32s(&pbuf->pb_info.pi_features);
- __swab32s(&pbuf->pb_info.pi_pid);
- __swab32s(&pbuf->pb_info.pi_nnis);
- nnis = pbuf->pb_info.pi_nnis;
- if (nnis > pbuf->pb_nnis)
- nnis = pbuf->pb_nnis;
- for (i = 0; i < nnis; i++) {
- stat = &pbuf->pb_info.pi_ni[i];
- __swab64s(&stat->ns_nid);
- __swab32s(&stat->ns_status);
- }
- return;
-}
-
-/**
- * TODO: re-implement
- */
-static void
-lnet_parse_rc_info(struct lnet_rc_data *rcd)
-{
- rcd = rcd;
-}
-
-static void
-lnet_router_checker_event(struct lnet_event *event)
-{
- struct lnet_rc_data *rcd = event->md.user_ptr;
- struct lnet_peer_ni *lp;
-
- LASSERT(rcd != NULL);
-
- if (event->unlinked) {
- LNetInvalidateMDHandle(&rcd->rcd_mdh);
- return;
- }
-
- LASSERT(event->type == LNET_EVENT_SEND ||
- event->type == LNET_EVENT_REPLY);
-
- lp = rcd->rcd_gateway;
- LASSERT(lp != NULL);
-
- /* NB: it's called with holding lnet_res_lock, we have a few
- * places need to hold both locks at the same time, please take
- * care of lock ordering */
- lnet_net_lock(lp->lpni_cpt);
- if (!lnet_isrouter(lp) || lp->lpni_rcd != rcd) {
- /* ignore if no longer a router or rcd is replaced */
- goto out;
- }
-
- if (event->type == LNET_EVENT_SEND) {
- if (event->status == 0)
- goto out;
- }
-
- /* LNET_EVENT_REPLY */
- /* A successful REPLY means the router is up. If _any_ comms
- * to the router fail I assume it's down (this will happen if
- * we ping alive routers to try to detect router death before
- * apps get burned). */
-
- lnet_notify_locked(lp, 1, !event->status, ktime_get_seconds());
- /* The router checker will wake up very shortly and do the
- * actual notification.
- * XXX If 'lp' stops being a router before then, it will still
- * have the notification pending!!! */
-
- if (avoid_asym_router_failure && event->status == 0)
- lnet_parse_rc_info(rcd);
-
- out:
- lnet_net_unlock(lp->lpni_cpt);
-}
-
static void
lnet_wait_known_routerstate(void)
{
}
}
-/* TODO: reimplement */
-void
-lnet_router_ni_update_locked(struct lnet_peer_ni *gw, __u32 net)
+static inline bool
+lnet_net_set_status_locked(struct lnet_net *net, __u32 status)
{
- struct lnet_route *rte;
- struct lnet_peer *lp;
-
- if ((gw->lpni_ping_feats & LNET_PING_FEAT_NI_STATUS) != 0)
- lp = gw->lpni_peer_net->lpn_peer;
- else
- return;
+ struct lnet_ni *ni;
+ bool update = false;
- list_for_each_entry(rte, &lp->lp_routes, lr_gwlist) {
- if (rte->lr_net == net) {
- rte->lr_downis = 0;
- break;
+ list_for_each_entry(ni, &net->net_ni_list, ni_netlist) {
+ lnet_ni_lock(ni);
+ if (ni->ni_status &&
+ ni->ni_status->ns_status != status) {
+ ni->ni_status->ns_status = status;
+ update = true;
}
+ lnet_ni_unlock(ni);
}
+
+ return update;
}
-static void
+static bool
lnet_update_ni_status_locked(void)
{
- struct lnet_ni *ni = NULL;
+ struct lnet_net *net;
+ bool push = false;
time64_t now;
time64_t timeout;
LASSERT(the_lnet.ln_routing);
- timeout = router_ping_timeout +
- MAX(live_router_check_interval, dead_router_check_interval);
+ timeout = router_ping_timeout + alive_router_check_interval;
now = ktime_get_real_seconds();
- while ((ni = lnet_get_next_ni_locked(NULL, ni))) {
- if (ni->ni_net->net_lnd->lnd_type == LOLND)
+ list_for_each_entry(net, &the_lnet.ln_nets, net_list) {
+ if (net->net_lnd->lnd_type == LOLND)
continue;
- if (now < ni->ni_last_alive + timeout)
+ if (now < net->net_last_alive + timeout)
continue;
- lnet_ni_lock(ni);
+ spin_lock(&net->net_lock);
/* re-check with lock */
- if (now < ni->ni_last_alive + timeout) {
- lnet_ni_unlock(ni);
+ if (now < net->net_last_alive + timeout) {
+ spin_unlock(&net->net_lock);
continue;
}
+ spin_unlock(&net->net_lock);
- LASSERT(ni->ni_status != NULL);
-
- if (ni->ni_status->ns_status != LNET_NI_STATUS_DOWN) {
- CDEBUG(D_NET, "NI(%s:%lld) status changed to down\n",
- libcfs_nid2str(ni->ni_nid), timeout);
- /* NB: so far, this is the only place to set
- * NI status to "down" */
- ni->ni_status->ns_status = LNET_NI_STATUS_DOWN;
- }
- lnet_ni_unlock(ni);
- }
-}
-
-int lnet_router_pre_mt_start(void)
-{
- int rc;
-
- if (check_routers_before_use &&
- dead_router_check_interval <= 0) {
- LCONSOLE_ERROR_MSG(0x10a, "'dead_router_check_interval' must be"
- " set if 'check_routers_before_use' is set"
- "\n");
- return -EINVAL;
- }
-
- rc = LNetEQAlloc(0, lnet_router_checker_event, &the_lnet.ln_rc_eqh);
- if (rc != 0) {
- CERROR("Can't allocate EQ(0): %d\n", rc);
- return -ENOMEM;
+ /*
+ * if the net didn't receive any traffic for past the
+ * timeout on any of its constituent NIs, then mark all
+ * the NIs down.
+ */
+ push = lnet_net_set_status_locked(net, LNET_NI_STATUS_DOWN);
}
- return 0;
+ return push;
}
-void lnet_router_post_mt_start(void)
+void lnet_wait_router_start(void)
{
if (check_routers_before_use) {
/* Note that a helpful side-effect of pinging all known routers
}
}
-void
-lnet_router_cleanup(void)
-{
- int rc;
-
- rc = LNetEQFree(the_lnet.ln_rc_eqh);
- LASSERT(rc == 0);
- return;
-}
-
-void
-lnet_prune_rc_data(int wait_unlink)
-{
- wait_unlink = wait_unlink;
-}
-
/*
* This function is called from the monitor thread to check if there are
* any active routers that need to be checked.
inline bool
lnet_router_checker_active(void)
{
- if (the_lnet.ln_mt_state != LNET_MT_STATE_RUNNING)
- return true;
-
/* Router Checker thread needs to run when routing is enabled in
* order to call lnet_update_ni_status_locked() */
if (the_lnet.ln_routing)
return true;
- /* if there are routers that need to be cleaned up then do so */
- if (!list_empty(&the_lnet.ln_rcd_deathrow) ||
- !list_empty(&the_lnet.ln_rcd_zombie))
- return true;
-
return !list_empty(&the_lnet.ln_routers) &&
- (live_router_check_interval > 0 ||
- dead_router_check_interval > 0);
+ alive_router_check_interval > 0;
}
void
lnet_check_routers(void)
{
- struct lnet_peer *rtr;
+ struct lnet_peer_net *first_lpn = NULL;
+ struct lnet_peer_net *lpn;
+ struct lnet_peer_ni *lpni;
struct list_head *entry;
- __u64 version;
- int cpt;
+ struct lnet_peer *rtr;
+ bool push = false;
+ bool found_lpn;
+ __u64 version;
+ __u32 net_id;
+ time64_t now;
+ int cpt;
+ int rc;
cpt = lnet_net_lock_current();
rescan:
rtr = list_entry(entry, struct lnet_peer,
lp_rtr_list);
- /* TODO use discovery to determine if router is alive */
+ now = ktime_get_real_seconds();
+
+ /*
+ * only discover the router if we've passed
+ * alive_router_check_interval seconds. Some of the router
+ * interfaces could be down and in that case they would be
+ * undergoing recovery separately from this discovery.
+ */
+ /* find next peer net which is also local */
+ net_id = rtr->lp_disc_net_id;
+ do {
+ lpn = lnet_get_next_peer_net_locked(rtr, net_id);
+ if (!lpn) {
+ CERROR("gateway %s has no networks\n",
+ libcfs_nid2str(rtr->lp_primary_nid));
+ break;
+ }
+ if (first_lpn == lpn)
+ break;
+ if (!first_lpn)
+ first_lpn = lpn;
+ found_lpn = lnet_islocalnet_locked(lpn->lpn_net_id);
+ net_id = lpn->lpn_net_id;
+ } while (!found_lpn);
+
+ if (!found_lpn || !lpn) {
+ CERROR("no local network found for gateway %s\n",
+ libcfs_nid2str(rtr->lp_primary_nid));
+ continue;
+ }
+
+ if (now - lpn->lpn_rtrcheck_timestamp <
+ alive_router_check_interval / lnet_current_net_count)
+ continue;
+
+ /*
+ * If we're currently discovering the peer then don't
+ * issue another discovery
+ */
+ spin_lock(&rtr->lp_lock);
+ if (rtr->lp_state & LNET_PEER_RTR_DISCOVERY) {
+ spin_unlock(&rtr->lp_lock);
+ continue;
+ }
+ /* make sure we actively discover the router */
+ rtr->lp_state &= ~LNET_PEER_NIDS_UPTODATE;
+ rtr->lp_state |= LNET_PEER_RTR_DISCOVERY;
+ spin_unlock(&rtr->lp_lock);
+
+ /* find the peer_ni associated with the primary NID */
+ lpni = lnet_peer_get_ni_locked(rtr, rtr->lp_primary_nid);
+ if (!lpni) {
+ CDEBUG(D_NET, "Expected to find an lpni for %s, but non found\n",
+ libcfs_nid2str(rtr->lp_primary_nid));
+ continue;
+ }
+ lnet_peer_ni_addref_locked(lpni);
+
+ /* specify the net to use */
+ rtr->lp_disc_net_id = lpn->lpn_net_id;
+
+ /* discover the router */
+ CDEBUG(D_NET, "discover %s, cpt = %d\n",
+ libcfs_nid2str(lpni->lpni_nid), cpt);
+ rc = lnet_discover_peer_locked(lpni, cpt, false);
+
+ /* decrement ref count acquired by find_peer_ni_locked() */
+ lnet_peer_ni_decref_locked(lpni);
+
+ if (!rc)
+ lpn->lpn_rtrcheck_timestamp = now;
+ else
+ CERROR("Failed to discover router %s\n",
+ libcfs_nid2str(rtr->lp_primary_nid));
/* NB dropped lock */
if (version != the_lnet.ln_routers_version) {
}
if (the_lnet.ln_routing)
- lnet_update_ni_status_locked();
+ push = lnet_update_ni_status_locked();
lnet_net_unlock(cpt);
- lnet_prune_rc_data(0); /* don't wait for UNLINK */
+ /* if the status of the ni changed update the peers */
+ if (push)
+ lnet_push_update_to_peers(1);
}
void
~LNET_PING_FEAT_RTE_DISABLED;
lnet_net_unlock(LNET_LOCK_EX);
+ if (lnet_peer_discovery_disabled)
+ CWARN("Consider turning discovery on to enable full "
+ "Multi-Rail routing functionality\n");
+
return rc;
}
lnet_rtrpools_free(1);
}
+static inline void
+lnet_notify_peer_down(struct lnet_ni *ni, lnet_nid_t nid)
+{
+ if (ni->ni_net->net_lnd->lnd_notify_peer_down != NULL)
+ (ni->ni_net->net_lnd->lnd_notify_peer_down)(nid);
+}
+
+/*
+ * ni: local NI used to communicate with the peer
+ * nid: peer NID
+ * alive: true if peer is alive, false otherwise
+ * reset: reset health value. This is requested by the LND.
+ * when: notificaiton time.
+ */
int
-lnet_notify(struct lnet_ni *ni, lnet_nid_t nid, int alive, time64_t when)
+lnet_notify(struct lnet_ni *ni, lnet_nid_t nid, bool alive, bool reset,
+ time64_t when)
{
- struct lnet_peer_ni *lp = NULL;
+ struct lnet_peer_ni *lpni = NULL;
time64_t now = ktime_get_seconds();
- int cpt = lnet_cpt_of_nid(nid, ni);
+ int cpt;
LASSERT (!in_interrupt ());
return 0;
}
- lnet_net_lock(cpt);
+ /* must lock 0 since this is used for synchronization */
+ lnet_net_lock(0);
if (the_lnet.ln_state != LNET_STATE_RUNNING) {
- lnet_net_unlock(cpt);
+ lnet_net_unlock(0);
return -ESHUTDOWN;
}
- lp = lnet_find_peer_ni_locked(nid);
- if (lp == NULL) {
+ lpni = lnet_find_peer_ni_locked(nid);
+ if (lpni == NULL) {
/* nid not found */
- lnet_net_unlock(cpt);
+ lnet_net_unlock(0);
CDEBUG(D_NET, "%s not found\n", libcfs_nid2str(nid));
return 0;
}
- /*
- * It is possible for this function to be called for the same peer
- * but with different NIs. We want to synchronize the notification
- * between the different calls. So we will use the lpni_cpt to
- * grab the net lock.
- */
- if (lp->lpni_cpt != cpt) {
- lnet_net_unlock(cpt);
- cpt = lp->lpni_cpt;
- lnet_net_lock(cpt);
+ if (alive) {
+ if (reset)
+ lnet_set_healthv(&lpni->lpni_healthv,
+ LNET_MAX_HEALTH_VALUE);
+ else
+ lnet_inc_healthv(&lpni->lpni_healthv);
+ } else {
+ lnet_handle_remote_failure_locked(lpni);
}
- /* We can't fully trust LND on reporting exact peer last_alive
- * if he notifies us about dead peer. For example ksocklnd can
- * call us with when == _time_when_the_node_was_booted_ if
- * no connections were successfully established */
- if (ni != NULL && !alive && when < lp->lpni_last_alive)
- when = lp->lpni_last_alive;
+ /* recalculate aliveness */
+ alive = lnet_is_peer_ni_alive(lpni);
+ lnet_net_unlock(0);
- lnet_notify_locked(lp, ni == NULL, alive, when);
-
- if (ni != NULL)
- lnet_ni_notify_locked(ni, lp);
-
- lnet_peer_ni_decref_locked(lp);
+ if (ni != NULL && !alive)
+ lnet_notify_peer_down(ni, lpni->lpni_nid);
+ cpt = lpni->lpni_cpt;
+ lnet_net_lock(cpt);
+ lnet_peer_ni_decref_locked(lpni);
lnet_net_unlock(cpt);
+
return 0;
}
EXPORT_SYMBOL(lnet_notify);
git://git.whamcloud.com / fs / lustre-release.git / blobdiff