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,
+static void lnet_del_route_from_rnet(struct lnet_nid *gw_nid,
+ struct list_head *route_list,
struct list_head *zombies);
static int
CDEBUG(D_NET, "deleting route %s->%s\n",
libcfs_net2str(route->lr_net),
- libcfs_nid2str(route->lr_nid));
+ libcfs_nidstr(&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);
+ 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);
+ 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);
+ lr_list);
list_del(&route->lr_list);
LIBCFS_FREE(route, sizeof(*route));
}
lnet_net_lock(LNET_LOCK_EX);
CDEBUG(D_NET, "transfering routes from %s -> %s\n",
- libcfs_nid2str(src->lp_primary_nid),
- libcfs_nid2str(target->lp_primary_nid));
+ libcfs_nidstr(&src->lp_primary_nid),
+ libcfs_nidstr(&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),
+ CDEBUG(D_NET, "%s: %s->%s\n",
+ libcfs_nidstr(&src->lp_primary_nid),
libcfs_net2str(route->lr_net),
- libcfs_nid2str(route->lr_nid));
+ libcfs_nidstr(&route->lr_nid));
}
list_splice_init(&src->lp_rtrq, &target->lp_rtrq);
list_for_each_entry_safe(route, tmp, &src->lp_routes, lr_gwlist) {
* 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 local network
* 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_single_hop) {
+ if (avoid_asym_router_failure &&
+ (route->lr_hops == 1 || route->lr_single_hop)) {
rlpn = lnet_peer_get_net_locked(gw, route->lr_net);
if (!rlpn)
return false;
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));
+ libcfs_nidstr(&gw->lp_primary_nid));
return false;
}
spin_unlock(&gw->lp_lock);
* intent here is not to confuse the user who added the route.
*/
list_for_each_entry(route, &orig_lp->lp_routes, lr_gwlist) {
- lpni = lnet_peer_get_ni_locked(orig_lp, route->lr_nid);
+ lpni = lnet_peer_ni_get_locked(orig_lp, &route->lr_nid);
if (!lpni) {
lnet_net_lock(LNET_LOCK_EX);
list_move(&route->lr_gwlist, &new_lp->lp_routes);
static inline void
lnet_check_route_inconsistency(struct lnet_route *route)
{
- if (!route->lr_single_hop && (int)route->lr_hops <= 1) {
+ 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),
+ libcfs_nidstr(&route->lr_gateway->lp_primary_nid),
(int) route->lr_hops);
}
}
lnet_check_route_inconsistency(route);
}
-static inline void
-lnet_set_route_aliveness(struct lnet_route *route, bool alive)
-{
- /* 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;
- }
-}
-
+/* Must hold net_lock/EX */
void
lnet_router_discovery_ping_reply(struct lnet_peer *lp)
{
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),
+ libcfs_nidstr(&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
}
CDEBUG(D_NET, "Discovery is disabled. Processing reply for gw: %s:%d\n",
- libcfs_nid2str(lp->lp_primary_nid), pbuf->pb_info.pi_nnis);
+ libcfs_nidstr(&lp->lp_primary_nid), pbuf->pb_info.pi_nnis);
/*
* examine the ping response to determine if the routes on that
}
route->lr_single_hop = single_hop;
- if (avoid_asym_router_failure && single_hop)
+ if (avoid_asym_router_failure &&
+ (route->lr_hops == 1 || route->lr_single_hop))
lnet_set_route_aliveness(route, net_up);
else
lnet_set_route_aliveness(route, true);
lp->lp_alive = lp->lp_dc_error == 0;
spin_unlock(&lp->lp_lock);
- /* ping replies are being handled when discovery is disabled */
- if (lnet_is_discovery_disabled_locked(lp))
- return;
-
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)
+ list_for_each_entry(route, &lp->lp_routes, lr_gwlist) {
+ lnet_set_route_aliveness(route, true);
lnet_set_route_hop_type(lp, route);
+ }
return;
}
* determine otherwise.
*/
CDEBUG(D_NET, "%s: Router discovery failed %d\n",
- libcfs_nid2str(lp->lp_primary_nid), lp->lp_dc_error);
+ libcfs_nidstr(&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;
lnet_find_rnet_locked(__u32 net)
{
struct lnet_remotenet *rnet;
- struct list_head *tmp;
struct list_head *rn_list;
LASSERT(the_lnet.ln_state == LNET_STATE_RUNNING);
rn_list = lnet_net2rnethash(net);
- list_for_each(tmp, rn_list) {
- rnet = list_entry(tmp, struct lnet_remotenet, lrn_list);
-
+ list_for_each_entry(rnet, rn_list, lrn_list) {
if (rnet->lrn_net == net)
return rnet;
}
unsigned int offset = 0;
unsigned int len = 0;
struct list_head *e;
+ time64_t now;
lnet_shuffle_seed();
* force a router check on the gateway to make sure the route is
* alive
*/
+ now = ktime_get_real_seconds();
list_for_each_entry(lpn, &route->lr_gateway->lp_peer_nets,
lpn_peer_nets) {
- lpn->lpn_rtrcheck_timestamp = 0;
+ lpn->lpn_next_ping = now;
}
the_lnet.ln_remote_nets_version++;
}
int
-lnet_add_route(__u32 net, __u32 hops, lnet_nid_t gateway,
+lnet_add_route(__u32 net, __u32 hops, struct lnet_nid *gateway,
__u32 priority, __u32 sensitivity)
{
struct list_head *route_entry;
int rc;
CDEBUG(D_NET, "Add route: remote net %s hops %d priority %u gw %s\n",
- libcfs_net2str(net), hops, priority, libcfs_nid2str(gateway));
+ libcfs_net2str(net), hops, priority, libcfs_nidstr(gateway));
- if (gateway == LNET_NID_ANY ||
- gateway == LNET_NID_LO_0 ||
- net == LNET_NIDNET(LNET_NID_ANY) ||
+ if (LNET_NID_IS_ANY(gateway) ||
+ nid_is_lo0(gateway) ||
+ net == LNET_NET_ANY ||
LNET_NETTYP(net) == LOLND ||
- LNET_NIDNET(gateway) == net ||
+ LNET_NID_NET(gateway) == net ||
(hops != LNET_UNDEFINED_HOPS && (hops < 1 || hops > 255)))
return -EINVAL;
if (lnet_islocalnet(net))
return -EEXIST;
- if (!lnet_islocalnet(LNET_NIDNET(gateway))) {
+ if (!lnet_islocalnet(LNET_NID_NET(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)));
+ libcfs_nidstr(gateway),
+ libcfs_net2str(LNET_NID_NET(gateway)));
return -EHOSTUNREACH;
}
LIBCFS_ALLOC(rnet, sizeof(*rnet));
if (route == NULL || rnet == NULL) {
CERROR("Out of memory creating route %s %d %s\n",
- libcfs_net2str(net), hops, libcfs_nid2str(gateway));
+ libcfs_net2str(net), hops, libcfs_nidstr(gateway));
if (route != NULL)
LIBCFS_FREE(route, sizeof(*route));
if (rnet != NULL)
INIT_LIST_HEAD(&rnet->lrn_routes);
rnet->lrn_net = net;
/* store the local and remote net that the route represents */
- route->lr_lnet = LNET_NIDNET(gateway);
+ route->lr_lnet = LNET_NID_NET(gateway);
route->lr_net = net;
- route->lr_nid = gateway;
+ 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);
* lnet_nid2peerni_ex() grabs a ref on the lpni. We will need to
* lose that once we're done
*/
- lpni = lnet_nid2peerni_ex(gateway, LNET_LOCK_EX);
+ lpni = lnet_nid2peerni_ex(gateway);
if (IS_ERR(lpni)) {
lnet_net_unlock(LNET_LOCK_EX);
rc = PTR_ERR(lpni);
CERROR("Error %d creating route %s %d %s\n", rc,
libcfs_net2str(net), hops,
- libcfs_nid2str(gateway));
+ libcfs_nidstr(gateway));
return rc;
}
- LASSERT(lpni->lpni_peer_net && lpni->lpni_peer_net->lpn_peer);
+ LASSERT(lpni);
+ LASSERT(lpni->lpni_peer_net);
+ LASSERT(lpni->lpni_peer_net->lpn_peer);
gw = lpni->lpni_peer_net->lpn_peer;
route->lr_gateway = gw;
}
/* our lookups must be true */
- LASSERT(route2->lr_gateway->lp_primary_nid != gateway);
+ LASSERT(!nid_same(&route2->lr_gateway->lp_primary_nid,
+ gateway));
}
/*
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");
+ CWARN("Consider turning discovery on to enable full Multi-Rail routing functionality\n");
}
/*
lnet_peer_ni_decref_locked(lpni);
lnet_net_unlock(LNET_LOCK_EX);
+ /* If avoid_asym_router_failure is enabled and hop count is not
+ * set to 1 for a route that is actually single-hop, then the
+ * feature will fail to prevent the router from being selected
+ * if it is missing a NI on the remote network due to misconfiguration.
+ */
+ if (avoid_asym_router_failure && hops == LNET_UNDEFINED_HOPS)
+ CWARN("Use hops = 1 for a single-hop route when avoid_asym_router_failure feature is enabled\n");
+
rc = 0;
if (!add_route) {
}
void
-lnet_del_route_from_rnet(lnet_nid_t gw_nid, struct list_head *route_list,
+lnet_del_route_from_rnet(struct lnet_nid *gw_nid,
+ struct list_head *route_list,
struct list_head *zombies)
{
struct lnet_peer *gateway;
list_for_each_entry_safe(route, tmp, route_list, lr_list) {
gateway = route->lr_gateway;
- if (gw_nid != LNET_NID_ANY &&
- gw_nid != gateway->lp_primary_nid)
+ if (gw_nid && !nid_same(gw_nid, &gateway->lp_primary_nid))
continue;
/*
}
int
-lnet_del_route(__u32 net, lnet_nid_t gw_nid)
+lnet_del_route(__u32 net, struct lnet_nid *gw)
{
LIST_HEAD(rnet_zombies);
struct lnet_remotenet *rnet;
struct list_head *rn_list;
struct lnet_peer_ni *lpni;
struct lnet_route *route;
+ struct lnet_nid gw_nid;
LIST_HEAD(zombies);
struct lnet_peer *lp = NULL;
int i = 0;
CDEBUG(D_NET, "Del route: net %s : gw %s\n",
- libcfs_net2str(net), libcfs_nid2str(gw_nid));
+ libcfs_net2str(net), libcfs_nidstr(gw));
/* NB Caller may specify either all routes via the given gateway
* or a specific route entry actual NIDs) */
lnet_net_lock(LNET_LOCK_EX);
- lpni = lnet_find_peer_ni_locked(gw_nid);
+ if (gw)
+ lpni = lnet_peer_ni_find_locked(gw);
+ else
+ lpni = NULL;
if (lpni) {
lp = lpni->lpni_peer_net->lpn_peer;
LASSERT(lp);
gw_nid = lp->lp_primary_nid;
+ gw = &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);
return -ENOENT;
}
- lnet_del_route_from_rnet(gw_nid, &rnet->lrn_routes,
+ lnet_del_route_from_rnet(gw, &rnet->lrn_routes,
&zombies);
if (list_empty(&rnet->lrn_routes))
list_move(&rnet->lrn_list, &rnet_zombies);
rn_list = &the_lnet.ln_remote_nets_hash[i];
list_for_each_entry_safe(rnet, tmp, rn_list, lrn_list) {
- lnet_del_route_from_rnet(gw_nid, &rnet->lrn_routes,
+ lnet_del_route_from_rnet(gw, &rnet->lrn_routes,
&zombies);
if (list_empty(&rnet->lrn_routes))
list_move(&rnet->lrn_list, &rnet_zombies);
}
void
-lnet_destroy_routes (void)
+lnet_destroy_routes(void)
{
- lnet_del_route(LNET_NIDNET(LNET_NID_ANY), LNET_NID_ANY);
+ lnet_del_route(LNET_NET_ANY, NULL);
}
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 *flags, __u32 *priority, __u32 *sensitivity)
+lnet_get_route(int idx, __u32 *net, __u32 *hops, lnet_nid_t *gateway,
+ __u32 *flags, __u32 *priority, __u32 *sensitivity)
{
struct lnet_remotenet *rnet;
struct list_head *rn_list;
struct lnet_route *route;
- struct list_head *e1;
- struct list_head *e2;
int cpt;
int i;
for (i = 0; i < LNET_REMOTE_NETS_HASH_SIZE; i++) {
rn_list = &the_lnet.ln_remote_nets_hash[i];
- list_for_each(e1, rn_list) {
- rnet = list_entry(e1, struct lnet_remotenet, lrn_list);
-
- list_for_each(e2, &rnet->lrn_routes) {
- route = list_entry(e2, struct lnet_route,
- lr_list);
-
+ list_for_each_entry(rnet, rn_list, lrn_list) {
+ list_for_each_entry(route, &rnet->lrn_routes, lr_list) {
if (idx-- == 0) {
*net = rnet->lrn_net;
- *gateway = route->lr_nid;
+ *gateway = lnet_nid_to_nid4(&route->lr_nid);
*hops = route->lr_hops;
*priority = route->lr_priority;
*sensitivity = route->lr_gateway->
lnet_wait_known_routerstate(void)
{
struct lnet_peer *rtr;
- struct list_head *entry;
int all_known;
LASSERT(the_lnet.ln_mt_state == LNET_MT_STATE_RUNNING);
int cpt = lnet_net_lock_current();
all_known = 1;
- list_for_each(entry, &the_lnet.ln_routers) {
- rtr = list_entry(entry, struct lnet_peer,
- lp_rtr_list);
-
+ list_for_each_entry(rtr, &the_lnet.ln_routers, lp_rtr_list) {
spin_lock(&rtr->lp_lock);
if ((rtr->lp_state & LNET_PEER_RTR_DISCOVERED) == 0) {
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;
timeout = router_ping_timeout + alive_router_check_interval;
- now = ktime_get_real_seconds();
+ now = ktime_get_seconds();
list_for_each_entry(net, &the_lnet.ln_nets, net_list) {
if (net->net_lnd->lnd_type == LOLND)
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() */
void
lnet_check_routers(void)
{
- struct lnet_peer_net *first_lpn = NULL;
+ struct lnet_peer_net *first_lpn;
struct lnet_peer_net *lpn;
struct lnet_peer_ni *lpni;
- struct list_head *entry;
struct lnet_peer *rtr;
bool push = false;
+ bool needs_ping;
bool found_lpn;
__u64 version;
__u32 net_id;
rescan:
version = the_lnet.ln_routers_version;
- list_for_each(entry, &the_lnet.ln_routers) {
- rtr = list_entry(entry, struct lnet_peer,
- lp_rtr_list);
+ list_for_each_entry(rtr, &the_lnet.ln_routers, lp_rtr_list) {
+ /* If we're currently discovering the peer then don't
+ * issue another discovery
+ */
+ if (rtr->lp_state & LNET_PEER_RTR_DISCOVERY)
+ continue;
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 */
+ /* find the next local peer net which needs to be ping'd */
+ needs_ping = false;
+ first_lpn = NULL;
+ found_lpn = false;
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));
+ libcfs_nidstr(&rtr->lp_primary_nid));
break;
}
+
+ /* We looped back to the first peer net */
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 (!lnet_islocalnet_locked(net_id))
+ continue;
+
+ found_lpn = true;
+
+ CDEBUG(D_NET, "rtr %s(%p) %s(%p) next ping %lld\n",
+ libcfs_nidstr(&rtr->lp_primary_nid), rtr,
+ libcfs_net2str(net_id), lpn,
+ lpn->lpn_next_ping);
+
+ needs_ping = now >= lpn->lpn_next_ping;
+
+ } while (!needs_ping);
if (!found_lpn || !lpn) {
CERROR("no local network found for gateway %s\n",
- libcfs_nid2str(rtr->lp_primary_nid));
+ libcfs_nidstr(&rtr->lp_primary_nid));
continue;
}
- if (now - lpn->lpn_rtrcheck_timestamp <
- alive_router_check_interval / lnet_current_net_count)
- continue;
+ if (!needs_ping)
+ 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 fully discover the router */
rtr->lp_state &= ~LNET_PEER_NIDS_UPTODATE;
rtr->lp_state |= LNET_PEER_FORCE_PING | LNET_PEER_FORCE_PUSH |
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);
+ lpni = lnet_peer_ni_get_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));
+ libcfs_nidstr(&rtr->lp_primary_nid));
continue;
}
lnet_peer_ni_addref_locked(lpni);
/* discover the router */
CDEBUG(D_NET, "discover %s, cpt = %d\n",
- libcfs_nid2str(lpni->lpni_nid), cpt);
+ libcfs_nidstr(&lpni->lpni_nid), cpt);
rc = lnet_discover_peer_locked(lpni, cpt, false);
- /* decrement ref count acquired by find_peer_ni_locked() */
+ /* drop ref taken above */
lnet_peer_ni_decref_locked(lpni);
if (!rc)
- lpn->lpn_rtrcheck_timestamp = now;
+ lpn->lpn_next_ping = now + alive_router_check_interval;
else
CERROR("Failed to discover router %s\n",
- libcfs_nid2str(rtr->lp_primary_nid));
+ libcfs_nidstr(&rtr->lp_primary_nid));
- /* NB dropped lock */
+ /* NB cpt lock was dropped in lnet_discover_peer_locked() */
if (version != the_lnet.ln_routers_version) {
/* the routers list has changed */
goto rescan;
rb->rb_pool = rbp;
for (i = 0; i < npages; i++) {
- page = cfs_page_cpt_alloc(lnet_cpt_table(), cpt,
- GFP_KERNEL | __GFP_ZERO);
+ page = cfs_page_cpt_alloc(lnet_cpt_table(), cpt, GFP_KERNEL |
+ __GFP_ZERO | __GFP_NORETRY);
if (page == NULL) {
while (--i >= 0)
__free_page(rb->rb_kiov[i].bv_page);
/* Free buffers on the free list. */
while (!list_empty(&tmp)) {
- rb = list_entry(tmp.next, struct lnet_rtrbuf, rb_list);
+ rb = list_first_entry(&tmp, struct lnet_rtrbuf, rb_list);
list_del(&rb->rb_list);
lnet_destroy_rtrbuf(rb, npages);
}
while (num_rb-- > 0) {
rb = lnet_new_rtrbuf(rbp, cpt);
if (rb == NULL) {
- CERROR("Failed to allocate %d route bufs of %d pages\n",
- nbufs, npages);
+ CERROR("lnet: error allocating %ux%u page router buffers on CPT %u: rc = %d\n",
+ nbufs, npages, cpt, -ENOMEM);
lnet_net_lock(cpt);
rbp->rbp_req_nbuffers = old_req_nbufs;
return 0;
failed:
- while (!list_empty(&rb_list)) {
- rb = list_entry(rb_list.next, struct lnet_rtrbuf, rb_list);
+ while ((rb = list_first_entry_or_null(&rb_list,
+ struct lnet_rtrbuf,
+ rb_list)) != NULL) {
list_del(&rb->rb_list);
lnet_destroy_rtrbuf(rb, npages);
}
} else if (!strcmp(forwarding, "enabled")) {
/* explicitly enabled */
} else {
- LCONSOLE_ERROR_MSG(0x10b, "'forwarding' not set to either "
- "'enabled' or 'disabled'\n");
- return -EINVAL;
+ rc = -EINVAL;
+ LCONSOLE_ERROR_MSG(0x10b,
+ "lnet: forwarding='%s' not set to either 'enabled' or 'disabled': rc = %d\n",
+ forwarding, rc);
+ return rc;
}
nrb_tiny = lnet_nrb_tiny_calculate();
LNET_NRBPOOLS *
sizeof(struct lnet_rtrbufpool));
if (the_lnet.ln_rtrpools == NULL) {
+ rc = -ENOMEM;
LCONSOLE_ERROR_MSG(0x10c,
- "Failed to initialize router buffe pool\n");
- return -ENOMEM;
+ "lnet: error allocating router buffer pool: rc = %d\n",
+ rc);
+ return rc;
}
cfs_percpt_for_each(rtrp, i, the_lnet.ln_rtrpools) {
lnet_rtrpool_init(&rtrp[LNET_TINY_BUF_IDX], 0);
rc = lnet_rtrpool_adjust_bufs(&rtrp[LNET_TINY_BUF_IDX],
nrb_tiny, i);
- if (rc != 0)
+ if (rc)
goto failed;
lnet_rtrpool_init(&rtrp[LNET_SMALL_BUF_IDX],
LNET_NRB_SMALL_PAGES);
rc = lnet_rtrpool_adjust_bufs(&rtrp[LNET_SMALL_BUF_IDX],
nrb_small, i);
- if (rc != 0)
+ if (rc)
goto failed;
lnet_rtrpool_init(&rtrp[LNET_LARGE_BUF_IDX],
LNET_NRB_LARGE_PAGES);
rc = lnet_rtrpool_adjust_bufs(&rtrp[LNET_LARGE_BUF_IDX],
nrb_large, i);
- if (rc != 0)
+ if (rc)
goto failed;
}
}
static inline void
-lnet_notify_peer_down(struct lnet_ni *ni, lnet_nid_t nid)
+lnet_notify_peer_down(struct lnet_ni *ni, struct lnet_nid *nid)
{
if (ni->ni_net->net_lnd->lnd_notify_peer_down != NULL)
(ni->ni_net->net_lnd->lnd_notify_peer_down)(nid);
* when: notificaiton time.
*/
int
-lnet_notify(struct lnet_ni *ni, lnet_nid_t nid, bool alive, bool reset,
+lnet_notify(struct lnet_ni *ni, lnet_nid_t nid4, bool alive, bool reset,
time64_t when)
{
struct lnet_peer_ni *lpni = NULL;
struct lnet_route *route;
struct lnet_peer *lp;
time64_t now = ktime_get_seconds();
+ struct lnet_nid nid;
int cpt;
- LASSERT (!in_interrupt ());
+ lnet_nid4_to_nid(nid4, &nid);
+ 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_nidstr(&ni->ni_nid),
+ libcfs_nidstr(&nid), alive ? "up" : "down");
if (ni != NULL &&
- LNET_NIDNET(ni->ni_nid) != LNET_NIDNET(nid)) {
+ LNET_NID_NET(&ni->ni_nid) != LNET_NID_NET(&nid)) {
CWARN("Ignoring notification of %s %s by %s (different net)\n",
- libcfs_nid2str(nid), alive ? "birth" : "death",
- libcfs_nid2str(ni->ni_nid));
+ libcfs_nidstr(&nid), alive ? "birth" : "death",
+ libcfs_nidstr(&ni->ni_nid));
return -EINVAL;
}
/* can't do predictions... */
if (when > now) {
- CWARN("Ignoring prediction from %s of %s %s "
- "%lld seconds in the future\n",
- (ni == NULL) ? "userspace" : libcfs_nid2str(ni->ni_nid),
- libcfs_nid2str(nid), alive ? "up" : "down", when - now);
+ CWARN("Ignoring prediction from %s of %s %s %lld seconds in the future\n",
+ ni ? libcfs_nidstr(&ni->ni_nid) : "userspace",
+ libcfs_nidstr(&nid), alive ? "up" : "down", when - now);
return -EINVAL;
}
return -ESHUTDOWN;
}
- lpni = lnet_find_peer_ni_locked(nid);
+ lpni = lnet_peer_ni_find_locked(&nid);
if (lpni == NULL) {
/* nid not found */
lnet_net_unlock(0);
- CDEBUG(D_NET, "%s not found\n", libcfs_nid2str(nid));
+ CDEBUG(D_NET, "%s not found\n", libcfs_nidstr(&nid));
return 0;
}
if (alive) {
if (reset) {
+ lpni->lpni_ns_status = LNET_NI_STATUS_UP;
lnet_set_lpni_healthv_locked(lpni,
LNET_MAX_HEALTH_VALUE);
} else {
(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 (nid_same(&route->lr_nid, &lpni->lpni_nid))
+ lnet_set_route_aliveness(route, alive);
+ }
+ }
+ }
+
lnet_net_unlock(0);
if (ni != NULL && !alive)
- lnet_notify_peer_down(ni, lpni->lpni_nid);
+ lnet_notify_peer_down(ni, &lpni->lpni_nid);
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;
- lp->lp_alive = alive;
- 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