#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_PARM_DESC(router_sensitivity_percentage,
"How healthy a gateway should be to be used in percent");
+static void lnet_add_route_to_rnet(struct lnet_remotenet *rnet,
+ struct lnet_route *route);
+static void lnet_del_route_from_rnet(lnet_nid_t gw_nid, struct list_head *route_list,
+ struct list_head *zombies);
+
static int
rtr_sensitivity_set(const char *val, cfs_kernel_param_arg_t *kp)
{
}
void
+lnet_move_route(struct lnet_route *route, struct lnet_peer *lp,
+ struct list_head *rt_list)
+{
+ struct lnet_remotenet *rnet;
+ struct list_head zombies;
+ struct list_head *l;
+
+ INIT_LIST_HEAD(&zombies);
+
+ if (rt_list)
+ l = rt_list;
+ else
+ l = &zombies;
+
+ rnet = lnet_find_rnet_locked(route->lr_net);
+ LASSERT(rnet);
+
+ CDEBUG(D_NET, "deleting route %s->%s\n",
+ libcfs_net2str(route->lr_net),
+ libcfs_nid2str(route->lr_nid));
+
+ /*
+ * use the gateway's lp_primary_nid to delete the route as the
+ * lr_nid can be a constituent NID of the peer
+ */
+ lnet_del_route_from_rnet(route->lr_gateway->lp_primary_nid,
+ &rnet->lrn_routes, l);
+
+ if (lp) {
+ route = list_first_entry(l, struct lnet_route,
+ lr_list);
+ route->lr_gateway = lp;
+ lnet_add_route_to_rnet(rnet, route);
+ } else {
+ while (!list_empty(l) && !rt_list) {
+ route = list_first_entry(l, struct lnet_route,
+ lr_list);
+ list_del(&route->lr_list);
+ LIBCFS_FREE(route, sizeof(*route));
+ }
+ }
+}
+
+void
lnet_rtr_transfer_to_peer(struct lnet_peer *src, struct lnet_peer *target)
{
struct lnet_route *route;
+ struct lnet_route *tmp, *tmp2;
lnet_net_lock(LNET_LOCK_EX);
- target->lp_rtr_refcount += src->lp_rtr_refcount;
- /* move the list of queued messages to the new peer */
+ CDEBUG(D_NET, "transfering routes from %s -> %s\n",
+ libcfs_nid2str(src->lp_primary_nid),
+ libcfs_nid2str(target->lp_primary_nid));
+ list_for_each_entry(route, &src->lp_routes, lr_gwlist) {
+ CDEBUG(D_NET, "%s: %s->%s\n", libcfs_nid2str(src->lp_primary_nid),
+ libcfs_net2str(route->lr_net),
+ libcfs_nid2str(route->lr_nid));
+ }
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 */
+ list_for_each_entry_safe(route, tmp, &src->lp_routes, lr_gwlist) {
+ struct lnet_route *r2;
+ bool present = false;
+ list_for_each_entry_safe(r2, tmp2, &target->lp_routes, lr_gwlist) {
+ if (route->lr_net == r2->lr_net) {
+ if (route->lr_priority >= r2->lr_priority)
+ present = true;
+ else if (route->lr_hops >= r2->lr_hops)
+ present = true;
+ else
+ lnet_move_route(r2, NULL, NULL);
+ }
+ }
+ if (present)
+ lnet_move_route(route, NULL, NULL);
+ else
+ lnet_move_route(route, target, NULL);
+ }
+
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);
}
}
/*
- * A net is alive if at least one gateway NI on the network is alive.
+ * The peer_net of a gateway is alive if at least one of the peer_ni's on
+ * that peer_net is alive.
*/
static bool
lnet_is_gateway_net_alive(struct lnet_peer_net *lpn)
{
struct lnet_peer_net *lpn;
+ if (!gw->lp_alive)
+ return false;
+
list_for_each_entry(lpn, &gw->lp_peer_nets, lpn_peer_nets) {
if (!lnet_is_gateway_net_alive(lpn))
return false;
struct lnet_peer *gw = route->lr_gateway;
struct lnet_peer_net *llpn;
struct lnet_peer_net *rlpn;
- bool route_alive;
+
+ /* If the gateway is down then all routes are considered down */
+ if (!gw->lp_alive)
+ return false;
/*
* if discovery is disabled then rely on the cached aliveness
* enabled.
*/
if (lnet_is_discovery_disabled(gw))
- return route->lr_alive;
+ return atomic_read(&route->lr_alive) == 1;
/*
- * check the gateway's interfaces on the route rnet to make sure
- * that the gateway is viable.
+ * check the gateway's interfaces on the local network
*/
llpn = lnet_peer_get_net_locked(gw, route->lr_lnet);
if (!llpn)
return false;
- route_alive = lnet_is_gateway_net_alive(llpn);
+ if (!lnet_is_gateway_net_alive(llpn))
+ return false;
- if (avoid_asym_router_failure) {
+ /*
+ * For single hop routes avoid_asym_router_failure dictates
+ * that the remote net must exist on the gateway. For multi-hop
+ * routes the next-hop will not have the remote net.
+ */
+ if (avoid_asym_router_failure &&
+ (route->lr_hops == 1 || route->lr_hops == LNET_UNDEFINED_HOPS)) {
rlpn = lnet_peer_get_net_locked(gw, route->lr_net);
if (!rlpn)
return false;
- route_alive = route_alive &&
- lnet_is_gateway_net_alive(rlpn);
+ if (!lnet_is_gateway_net_alive(rlpn))
+ return false;
}
- if (!route_alive)
- return route_alive;
-
spin_lock(&gw->lp_lock);
if (!(gw->lp_state & LNET_PEER_ROUTER_ENABLED)) {
+ spin_unlock(&gw->lp_lock);
if (gw->lp_rtr_refcount > 0)
CERROR("peer %s is being used as a gateway but routing feature is not turned on\n",
libcfs_nid2str(gw->lp_primary_nid));
- route_alive = false;
+ return false;
}
spin_unlock(&gw->lp_lock);
- return route_alive;
+ return true;
}
void
lnet_net_unlock(LNET_LOCK_EX);
}
}
-
}
static inline void
-lnet_set_route_aliveness(struct lnet_route *route, bool alive)
+lnet_check_route_inconsistency(struct lnet_route *route)
{
- /* Log when there's a state change */
- if (route->lr_alive != alive) {
- CERROR("route to %s through %s has gone from %s to %s\n",
- libcfs_net2str(route->lr_net),
- libcfs_nid2str(route->lr_gateway->lp_primary_nid),
- (route->lr_alive) ? "up" : "down",
- alive ? "up" : "down");
- route->lr_alive = alive;
+ if (!route->lr_single_hop &&
+ (route->lr_hops == 1 || route->lr_hops == LNET_UNDEFINED_HOPS)) {
+ CWARN("route %s->%s is detected to be multi-hop but hop count is set to %d\n",
+ libcfs_net2str(route->lr_net),
+ libcfs_nid2str(route->lr_gateway->lp_primary_nid),
+ (int) route->lr_hops);
+ }
+}
+
+static void
+lnet_set_route_hop_type(struct lnet_peer *gw, struct lnet_route *route)
+{
+ struct lnet_peer_net *lpn;
+ bool single_hop = false;
+
+ list_for_each_entry(lpn, &gw->lp_peer_nets, lpn_peer_nets) {
+ if (route->lr_net == lpn->lpn_net_id) {
+ single_hop = true;
+ break;
+ }
}
+ route->lr_single_hop = single_hop;
+ lnet_check_route_inconsistency(route);
}
+/* Must hold net_lock/EX */
void
lnet_router_discovery_ping_reply(struct lnet_peer *lp)
{
struct lnet_ping_buffer *pbuf = lp->lp_data;
- struct lnet_remotenet *rnet;
struct lnet_peer_net *llpn;
struct lnet_route *route;
+ bool single_hop = false;
bool net_up = false;
unsigned lp_state;
- __u32 net, net2;
- int i, j;
+ __u32 net;
+ int i;
spin_lock(&lp->lp_lock);
spin_unlock(&lp->lp_lock);
- if (lp_state & LNET_PEER_PING_FAILED) {
- CDEBUG(D_NET,
- "Ping failed with %d. Set routes down for gw %s\n",
- lp->lp_ping_error, libcfs_nid2str(lp->lp_primary_nid));
- /* If the ping failed then mark the routes served by this
- * peer down
+ if (lp_state & LNET_PEER_PING_FAILED ||
+ pbuf->pb_info.pi_features & LNET_PING_FEAT_RTE_DISABLED) {
+ CDEBUG(D_NET, "Set routes down for gw %s because %s %d\n",
+ libcfs_nid2str(lp->lp_primary_nid),
+ lp_state & LNET_PEER_PING_FAILED ? "ping failed" :
+ "route feature is disabled", lp->lp_ping_error);
+ /* If the ping failed or the peer has routing disabled then
+ * mark the routes served by this peer down
*/
list_for_each_entry(route, &lp->lp_routes, lr_gwlist)
lnet_set_route_aliveness(route, false);
return;
}
- CDEBUG(D_NET, "Discovery is disabled. Processing reply for gw: %s\n",
- libcfs_nid2str(lp->lp_primary_nid));
+ CDEBUG(D_NET, "Discovery is disabled. Processing reply for gw: %s:%d\n",
+ libcfs_nid2str(lp->lp_primary_nid), pbuf->pb_info.pi_nnis);
/*
- * examine the ping response:
- * For each NID in the ping response, extract the net
- * if the net exists on our remote net list then
- * iterate over the routes on the rnet and if:
- * The route's local net is healthy and
- * The remote net status is UP, then mark the route up
- * otherwise mark the route down
+ * examine the ping response to determine if the routes on that
+ * gateway should be declared alive.
+ * The route is alive if:
+ * 1. local network to reach the route is alive and
+ * 2. route is single hop, avoid_async_router_failure is set and
+ * there exists at least one NI on the route's remote net
*/
- for (i = 1; i < pbuf->pb_info.pi_nnis; i++) {
- net = LNET_NIDNET(pbuf->pb_info.pi_ni[i].ns_nid);
- rnet = lnet_find_rnet_locked(net);
- if (!rnet)
+ list_for_each_entry(route, &lp->lp_routes, lr_gwlist) {
+ llpn = lnet_peer_get_net_locked(lp, route->lr_lnet);
+ if (!llpn) {
+ lnet_set_route_aliveness(route, false);
continue;
- list_for_each_entry(route, &rnet->lrn_routes, lr_list) {
- /* check if this is the route's gateway */
- if (lp->lp_primary_nid !=
- route->lr_gateway->lp_primary_nid)
- continue;
-
- /* gateway has the routing feature disabled */
- if (pbuf->pb_info.pi_features &
- LNET_PING_FEAT_RTE_DISABLED) {
- lnet_set_route_aliveness(route, false);
- continue;
- }
+ }
- llpn = lnet_peer_get_net_locked(lp, route->lr_lnet);
- if (!llpn) {
- lnet_set_route_aliveness(route, false);
- continue;
- }
+ if (!lnet_is_gateway_net_alive(llpn)) {
+ lnet_set_route_aliveness(route, false);
+ continue;
+ }
- if (!lnet_is_gateway_net_alive(llpn)) {
- lnet_set_route_aliveness(route, false);
- continue;
- }
+ single_hop = net_up = false;
+ for (i = 1; i < pbuf->pb_info.pi_nnis; i++) {
+ net = LNET_NIDNET(pbuf->pb_info.pi_ni[i].ns_nid);
- if (avoid_asym_router_failure &&
- pbuf->pb_info.pi_ni[i].ns_status !=
- LNET_NI_STATUS_UP) {
- net_up = false;
-
- /*
- * revisit all previous NIDs and check if
- * any on the network we're examining is
- * up. If at least one is up then we consider
- * the route to be alive.
- */
- for (j = 1; j < i; j++) {
- net2 = LNET_NIDNET(pbuf->pb_info.
- pi_ni[j].ns_nid);
- if (net2 == net &&
- pbuf->pb_info.pi_ni[j].ns_status ==
- LNET_NI_STATUS_UP)
- net_up = true;
- }
- if (!net_up) {
- lnet_set_route_aliveness(route, false);
- continue;
+ if (route->lr_net == net) {
+ single_hop = true;
+ if (pbuf->pb_info.pi_ni[i].ns_status ==
+ LNET_NI_STATUS_UP) {
+ net_up = true;
+ break;
}
}
+ }
+ route->lr_single_hop = single_hop;
+ if (avoid_asym_router_failure &&
+ (route->lr_hops == 1 ||
+ route->lr_hops == LNET_UNDEFINED_HOPS))
+ lnet_set_route_aliveness(route, net_up);
+ else
lnet_set_route_aliveness(route, true);
- }
+
+ /*
+ * warn that the route is configured as single-hop but it
+ * really is multi-hop as far as we can tell.
+ */
+ lnet_check_route_inconsistency(route);
}
}
spin_lock(&lp->lp_lock);
lp->lp_state &= ~LNET_PEER_RTR_DISCOVERY;
+ lp->lp_state |= LNET_PEER_RTR_DISCOVERED;
+ lp->lp_alive = lp->lp_dc_error == 0;
spin_unlock(&lp->lp_lock);
- /*
- * Router discovery successful? All peer information would've been
- * updated already. No need to do any more processing
- */
- if (!lp->lp_dc_error)
+ if (!lp->lp_dc_error) {
+ /* ping replies are being handled when discovery is disabled */
+ if (lnet_is_discovery_disabled_locked(lp))
+ return;
+
+ /*
+ * mark single-hop routes. If the remote net is not configured on
+ * the gateway we assume this is intentional and we mark the
+ * gateway as multi-hop
+ */
+ list_for_each_entry(route, &lp->lp_routes, lr_gwlist) {
+ lnet_set_route_aliveness(route, true);
+ lnet_set_route_hop_type(lp, route);
+ }
+
return;
+ }
+
/*
- * 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.
+ * We do not send messages directly to the remote interfaces
+ * of an LNet router. As such, we rely on the PING response
+ * to determine the up/down status of these interfaces. If
+ * a PING response is not receieved, or some other problem with
+ * discovery occurs that prevents us from getting this status,
+ * we assume all interfaces are down until we're able to
+ * determine otherwise.
*/
CDEBUG(D_NET, "%s: Router discovery failed %d\n",
libcfs_nid2str(lp->lp_primary_nid), lp->lp_dc_error);
add_device_randomness(&ni->ni_nid, sizeof(ni->ni_nid));
seeded = 1;
- return;
}
/* NB expects LNET_LOCK held */
libcfs_net2str(net), hops, priority, libcfs_nid2str(gateway));
if (gateway == LNET_NID_ANY ||
- LNET_NETTYP(LNET_NIDNET(gateway)) == LOLND ||
- net == LNET_NIDNET(LNET_NID_ANY) ||
+ gateway == LNET_NID_LO_0 ||
+ net == LNET_NET_ANY ||
LNET_NETTYP(net) == LOLND ||
LNET_NIDNET(gateway) == net ||
(hops != LNET_UNDEFINED_HOPS && (hops < 1 || hops > 255)))
route->lr_nid = gateway;
route->lr_priority = priority;
route->lr_hops = hops;
+ if (lnet_peers_start_down())
+ atomic_set(&route->lr_alive, 0);
+ else
+ atomic_set(&route->lr_alive, 1);
lnet_net_lock(LNET_LOCK_EX);
return rc;
}
-static void
+void
lnet_del_route_from_rnet(lnet_nid_t gw_nid, struct list_head *route_list,
struct list_head *zombies)
{
int
lnet_del_route(__u32 net, lnet_nid_t gw_nid)
{
- struct list_head rnet_zombies;
+ LIST_HEAD(rnet_zombies);
struct lnet_remotenet *rnet;
struct lnet_remotenet *tmp;
struct list_head *rn_list;
struct lnet_peer_ni *lpni;
struct lnet_route *route;
- struct list_head zombies;
- struct lnet_peer *lp;
+ LIST_HEAD(zombies);
+ struct lnet_peer *lp = NULL;
int i = 0;
- INIT_LIST_HEAD(&rnet_zombies);
- INIT_LIST_HEAD(&zombies);
-
CDEBUG(D_NET, "Del route: net %s : gw %s\n",
libcfs_net2str(net), libcfs_nid2str(gw_nid));
lnet_peer_ni_decref_locked(lpni);
}
- if (net != LNET_NIDNET(LNET_NID_ANY)) {
+ if (net != LNET_NET_ANY) {
rnet = lnet_find_rnet_locked(net);
if (!rnet) {
lnet_net_unlock(LNET_LOCK_EX);
void
lnet_destroy_routes (void)
{
- lnet_del_route(LNET_NIDNET(LNET_NID_ANY), LNET_NID_ANY);
+ lnet_del_route(LNET_NET_ANY, LNET_NID_ANY);
}
int lnet_get_rtr_pool_cfg(int cpt, struct lnet_ioctl_pool_cfg *pool_cfg)
int
lnet_get_route(int idx, __u32 *net, __u32 *hops,
- lnet_nid_t *gateway, __u32 *alive, __u32 *priority, __u32 *sensitivity)
+ lnet_nid_t *gateway, __u32 *flags, __u32 *priority, __u32 *sensitivity)
{
struct lnet_remotenet *rnet;
struct list_head *rn_list;
*priority = route->lr_priority;
*sensitivity = route->lr_gateway->
lp_health_sensitivity;
- *alive = lnet_is_route_alive(route);
+ if (lnet_is_route_alive(route))
+ *flags |= LNET_RT_ALIVE;
+ else
+ *flags &= ~LNET_RT_ALIVE;
+ if (route->lr_single_hop)
+ *flags &= ~LNET_RT_MULTI_HOP;
+ else
+ *flags |= LNET_RT_MULTI_HOP;
lnet_net_unlock(cpt);
return 0;
}
spin_lock(&rtr->lp_lock);
- if ((rtr->lp_state & LNET_PEER_DISCOVERED) == 0) {
+ if ((rtr->lp_state & LNET_PEER_RTR_DISCOVERED) == 0) {
all_known = 0;
spin_unlock(&rtr->lp_lock);
break;
if (all_known)
return;
- set_current_state(TASK_UNINTERRUPTIBLE);
- schedule_timeout(cfs_time_seconds(1));
+ schedule_timeout_uninterruptible(cfs_time_seconds(1));
}
}
struct lnet_ni *ni;
bool update = false;
- 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);
- }
+ list_for_each_entry(ni, &net->net_ni_list, ni_netlist)
+ if (lnet_ni_set_status(ni, status))
+ update = true;
return update;
}
lnet_update_ni_status_locked(void)
{
struct lnet_net *net;
+ struct lnet_ni *ni;
bool push = false;
time64_t now;
time64_t timeout;
continue;
if (now < net->net_last_alive + timeout)
- continue;
+ goto check_ni_fatal;
spin_lock(&net->net_lock);
/* re-check with lock */
if (now < net->net_last_alive + timeout) {
spin_unlock(&net->net_lock);
- continue;
+ goto check_ni_fatal;
}
spin_unlock(&net->net_lock);
* timeout on any of its constituent NIs, then mark all
* the NIs down.
*/
- push = lnet_net_set_status_locked(net, LNET_NI_STATUS_DOWN);
+ if (lnet_net_set_status_locked(net, LNET_NI_STATUS_DOWN)) {
+ push = true;
+ continue;
+ }
+
+check_ni_fatal:
+ list_for_each_entry(ni, &net->net_ni_list, ni_netlist) {
+ /* lnet_ni_set_status() will perform the same check of
+ * ni_status while holding the ni lock. We can safely
+ * check ni_status without that lock because it is only
+ * written to under net_lock/EX and our caller is
+ * holding a net lock.
+ */
+ if (atomic_read(&ni->ni_fatal_error_on) &&
+ ni->ni_status &&
+ ni->ni_status->ns_status != LNET_NI_STATUS_DOWN &&
+ lnet_ni_set_status(ni, LNET_NI_STATUS_DOWN))
+ push = true;
+ }
}
return push;
* 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)
+bool lnet_router_checker_active(void)
{
/* Router Checker thread needs to run when routing is enabled in
* order to call lnet_update_ni_status_locked() */
spin_unlock(&rtr->lp_lock);
continue;
}
- /* make sure we actively discover the router */
+ /* make sure we fully discover the router */
rtr->lp_state &= ~LNET_PEER_NIDS_UPTODATE;
- rtr->lp_state |= LNET_PEER_RTR_DISCOVERY;
+ rtr->lp_state |= LNET_PEER_FORCE_PING | LNET_PEER_FORCE_PUSH |
+ LNET_PEER_RTR_DISCOVERY;
spin_unlock(&rtr->lp_lock);
/* find the peer_ni associated with the primary NID */
int sz = offsetof(struct lnet_rtrbuf, rb_kiov[npages]);
while (--npages >= 0)
- __free_page(rb->rb_kiov[npages].kiov_page);
+ __free_page(rb->rb_kiov[npages].bv_page);
LIBCFS_FREE(rb, sz);
}
GFP_KERNEL | __GFP_ZERO);
if (page == NULL) {
while (--i >= 0)
- __free_page(rb->rb_kiov[i].kiov_page);
+ __free_page(rb->rb_kiov[i].bv_page);
LIBCFS_FREE(rb, sz);
return NULL;
}
- rb->rb_kiov[i].kiov_len = PAGE_SIZE;
- rb->rb_kiov[i].kiov_offset = 0;
- rb->rb_kiov[i].kiov_page = page;
+ rb->rb_kiov[i].bv_len = PAGE_SIZE;
+ rb->rb_kiov[i].bv_offset = 0;
+ rb->rb_kiov[i].bv_page = page;
}
return rb;
{
int npages = rbp->rbp_npages;
struct lnet_rtrbuf *rb;
- struct list_head tmp;
+ LIST_HEAD(tmp);
if (rbp->rbp_nbuffers == 0) /* not initialized or already freed */
return;
- INIT_LIST_HEAD(&tmp);
-
lnet_net_lock(cpt);
list_splice_init(&rbp->rbp_msgs, &tmp);
lnet_drop_routed_msgs_locked(&tmp, cpt);
static int
lnet_rtrpool_adjust_bufs(struct lnet_rtrbufpool *rbp, int nbufs, int cpt)
{
- struct list_head rb_list;
+ LIST_HEAD(rb_list);
struct lnet_rtrbuf *rb;
int num_rb;
int num_buffers = 0;
rbp->rbp_req_nbuffers = nbufs;
lnet_net_unlock(cpt);
- INIT_LIST_HEAD(&rb_list);
-
/* allocate the buffers on a local list first. If all buffers are
* allocated successfully then join this list to the rbp buffer
* list. If not then free all allocated buffers. */
time64_t now = ktime_get_seconds();
int cpt;
- LASSERT (!in_interrupt ());
+ LASSERT(!in_interrupt());
- CDEBUG (D_NET, "%s notifying %s: %s\n",
- (ni == NULL) ? "userspace" : libcfs_nid2str(ni->ni_nid),
- libcfs_nid2str(nid),
- alive ? "up" : "down");
+ CDEBUG(D_NET, "%s notifying %s: %s\n",
+ (ni == NULL) ? "userspace" : libcfs_nid2str(ni->ni_nid),
+ libcfs_nid2str(nid), alive ? "up" : "down");
if (ni != NULL &&
LNET_NIDNET(ni->ni_nid) != LNET_NIDNET(nid)) {
}
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);
+ if (reset) {
+ lpni->lpni_ns_status = LNET_NI_STATUS_UP;
+ lnet_set_lpni_healthv_locked(lpni,
+ LNET_MAX_HEALTH_VALUE);
+ } else {
+ __u32 sensitivity = lpni->lpni_peer_net->
+ lpn_peer->lp_health_sensitivity;
+
+ lnet_inc_lpni_healthv_locked(lpni,
+ (sensitivity) ? sensitivity :
+ lnet_health_sensitivity);
+ }
+ } else if (reset) {
+ lpni->lpni_ns_status = LNET_NI_STATUS_DOWN;
}
/* recalculate aliveness */
alive = lnet_is_peer_ni_alive(lpni);
+
+ lp = lpni->lpni_peer_net->lpn_peer;
+ /* If this is an LNet router then update route aliveness */
+ if (lp->lp_rtr_refcount) {
+ if (reset)
+ /* reset flag indicates gateway peer went up or down */
+ lp->lp_alive = alive;
+
+ /* If discovery is disabled, locally or on the gateway, then
+ * any routes using lpni as next-hop need to be updated
+ *
+ * NB: We can get many notifications while a route is down, so
+ * we try and avoid the expensive net_lock/EX here for the
+ * common case of receiving duplicate lnet_notify() calls (i.e.
+ * only grab EX lock when we actually need to update the route
+ * aliveness).
+ */
+ if (lnet_is_discovery_disabled(lp)) {
+ list_for_each_entry(route, &lp->lp_routes, lr_gwlist) {
+ if (route->lr_nid == lpni->lpni_nid)
+ lnet_set_route_aliveness(route, alive);
+ }
+ }
+ }
+
lnet_net_unlock(0);
if (ni != NULL && !alive)
cpt = lpni->lpni_cpt;
lnet_net_lock(cpt);
lnet_peer_ni_decref_locked(lpni);
- if (lpni && lpni->lpni_peer_net && lpni->lpni_peer_net->lpn_peer) {
- lp = lpni->lpni_peer_net->lpn_peer;
- list_for_each_entry(route, &lp->lp_routes, lr_gwlist)
- lnet_set_route_aliveness(route, alive);
- }
lnet_net_unlock(cpt);
return 0;
git://git.whamcloud.com / fs / lustre-release.git / blobdiff