LASSERT(!do_send || msg->msg_tx_delayed);
LASSERT(!msg->msg_receiving);
LASSERT(msg->msg_tx_committed);
+
/* can't get here if we're sending to the loopback interface */
- LASSERT(lp->lpni_nid != the_lnet.ln_loni->ni_nid);
+ if (the_lnet.ln_loni)
+ LASSERT(lp->lpni_nid != the_lnet.ln_loni->ni_nid);
/* NB 'lp' is always the next hop */
if ((msg->msg_target.pid & LNET_PID_USERFLAG) == 0 &&
}
}
-static int
-lnet_compare_gw_lpnis(struct lnet_peer_ni *p1, struct lnet_peer_ni *p2)
-{
- if (p1->lpni_txqnob < p2->lpni_txqnob)
- return 1;
-
- if (p1->lpni_txqnob > p2->lpni_txqnob)
- return -1;
-
- if (p1->lpni_txcredits > p2->lpni_txcredits)
- return 1;
-
- if (p1->lpni_txcredits < p2->lpni_txcredits)
- return -1;
-
- return 0;
-}
-
static struct lnet_peer_ni *
lnet_select_peer_ni(struct lnet_ni *best_ni, lnet_nid_t dst_nid,
struct lnet_peer *peer,
INT_MIN;
int best_lpni_healthv = (best_lpni) ?
atomic_read(&best_lpni->lpni_healthv) : 0;
- bool preferred = false;
- bool ni_is_pref;
+ bool best_lpni_is_preferred = false;
+ bool lpni_is_preferred;
int lpni_healthv;
+ __u32 lpni_sel_prio;
+ __u32 best_sel_prio = LNET_MAX_SELECTION_PRIORITY;
while ((lpni = lnet_get_next_peer_ni_locked(peer, peer_net, lpni))) {
/*
* preferred, then let's use it
*/
if (best_ni) {
- ni_is_pref = lnet_peer_is_pref_nid_locked(lpni,
+ lpni_is_preferred = lnet_peer_is_pref_nid_locked(lpni,
best_ni->ni_nid);
- CDEBUG(D_NET, "%s ni_is_pref = %d\n",
- libcfs_nid2str(best_ni->ni_nid), ni_is_pref);
+ CDEBUG(D_NET, "%s lpni_is_preferred = %d\n",
+ libcfs_nid2str(best_ni->ni_nid),
+ lpni_is_preferred);
} else {
- ni_is_pref = false;
+ lpni_is_preferred = false;
}
lpni_healthv = atomic_read(&lpni->lpni_healthv);
+ lpni_sel_prio = lpni->lpni_sel_priority;
if (best_lpni)
- CDEBUG(D_NET, "%s c:[%d, %d], s:[%d, %d]\n",
+ CDEBUG(D_NET, "n:[%s, %s] h:[%d, %d] p:[%d, %d] c:[%d, %d] s:[%d, %d]\n",
libcfs_nid2str(lpni->lpni_nid),
+ libcfs_nid2str(best_lpni->lpni_nid),
+ lpni_healthv, best_lpni_healthv,
+ lpni_sel_prio, best_sel_prio,
lpni->lpni_txcredits, best_lpni_credits,
lpni->lpni_seq, best_lpni->lpni_seq);
+ else
+ goto select_lpni;
/* pick the healthiest peer ni */
- if (lpni_healthv < best_lpni_healthv) {
+ if (lpni_healthv < best_lpni_healthv)
continue;
- } else if (lpni_healthv > best_lpni_healthv) {
- best_lpni_healthv = lpni_healthv;
+ else if (lpni_healthv > best_lpni_healthv) {
+ if (best_lpni_is_preferred)
+ best_lpni_is_preferred = false;
+ goto select_lpni;
+ }
+
+ if (lpni_sel_prio > best_sel_prio)
+ continue;
+ else if (lpni_sel_prio < best_sel_prio) {
+ if (best_lpni_is_preferred)
+ best_lpni_is_preferred = false;
+ goto select_lpni;
+ }
+
/* if this is a preferred peer use it */
- } else if (!preferred && ni_is_pref) {
- preferred = true;
- } else if (preferred && !ni_is_pref) {
- /*
- * this is not the preferred peer so let's ignore
+ if (!best_lpni_is_preferred && lpni_is_preferred) {
+ best_lpni_is_preferred = true;
+ goto select_lpni;
+ } else if (best_lpni_is_preferred && !lpni_is_preferred) {
+ /* this is not the preferred peer so let's ignore
* it.
*/
continue;
- } else if (lpni->lpni_txcredits < best_lpni_credits) {
- /*
- * We already have a peer that has more credits
+ }
+
+ if (lpni->lpni_txcredits < best_lpni_credits)
+ /* We already have a peer that has more credits
* available than this one. No need to consider
* this peer further.
*/
continue;
- } else if (lpni->lpni_txcredits == best_lpni_credits) {
- /*
- * The best peer found so far and the current peer
- * have the same number of available credits let's
- * make sure to select between them using Round
- * Robin
- */
- if (best_lpni) {
- if (best_lpni->lpni_seq <= lpni->lpni_seq)
- continue;
- }
- }
+ else if (lpni->lpni_txcredits > best_lpni_credits)
+ goto select_lpni;
+ /* The best peer found so far and the current peer
+ * have the same number of available credits let's
+ * make sure to select between them using Round Robin
+ */
+ if (best_lpni && (best_lpni->lpni_seq <= lpni->lpni_seq))
+ continue;
+select_lpni:
+ best_lpni_is_preferred = lpni_is_preferred;
+ best_lpni_healthv = lpni_healthv;
+ best_sel_prio = lpni_sel_prio;
best_lpni = lpni;
best_lpni_credits = lpni->lpni_txcredits;
}
struct lnet_peer *peer, __u32 net_id)
{
struct lnet_peer_net *peer_net;
- __u32 any_net = LNET_NIDNET(LNET_NID_ANY);
/* find the best_lpni on any local network */
- if (net_id == any_net) {
+ if (net_id == LNET_NET_ANY) {
struct lnet_peer_ni *best_lpni = NULL;
struct lnet_peer_net *lpn;
list_for_each_entry(lpn, &peer->lp_peer_nets, lpn_peer_nets) {
return NULL;
}
+static int
+lnet_compare_gw_lpnis(struct lnet_peer_ni *lpni1, struct lnet_peer_ni *lpni2)
+{
+ if (lpni1->lpni_txqnob < lpni2->lpni_txqnob)
+ return 1;
+
+ if (lpni1->lpni_txqnob > lpni2->lpni_txqnob)
+ return -1;
+
+ if (lpni1->lpni_txcredits > lpni2->lpni_txcredits)
+ return 1;
+
+ if (lpni1->lpni_txcredits < lpni2->lpni_txcredits)
+ return -1;
+
+ return 0;
+}
+
/* Compare route priorities and hop counts */
static int
lnet_compare_routes(struct lnet_route *r1, struct lnet_route *r2)
static struct lnet_route *
lnet_find_route_locked(struct lnet_remotenet *rnet, __u32 src_net,
+ struct lnet_peer_ni *remote_lpni,
struct lnet_route **prev_route,
struct lnet_peer_ni **gwni)
{
struct lnet_route *last_route;
struct lnet_route *route;
int rc;
+ bool best_rte_is_preferred = false;
+ lnet_nid_t gw_pnid;
CDEBUG(D_NET, "Looking up a route to %s, from %s\n",
libcfs_net2str(rnet->lrn_net), libcfs_net2str(src_net));
list_for_each_entry(route, &rnet->lrn_routes, lr_list) {
if (!lnet_is_route_alive(route))
continue;
+ gw_pnid = route->lr_gateway->lp_primary_nid;
- /*
- * Restrict the selection of the router NI on the src_net
- * provided. If the src_net is LNET_NID_ANY, then select
- * the best interface available.
+ /* no protection on below fields, but it's harmless */
+ if (last_route && (last_route->lr_seq - route->lr_seq < 0))
+ last_route = route;
+
+ /* if the best route found is in the preferred list then
+ * tag it as preferred and use it later on. But if we
+ * didn't find any routes which are on the preferred list
+ * then just use the best route possible.
*/
- if (!best_route) {
+ rc = lnet_peer_is_pref_rtr_locked(remote_lpni, gw_pnid);
+
+ if (!best_route || (rc && !best_rte_is_preferred)) {
+ /* Restrict the selection of the router NI on the
+ * src_net provided. If the src_net is LNET_NID_ANY,
+ * then select the best interface available.
+ */
lpni = lnet_find_best_lpni(NULL, LNET_NID_ANY,
route->lr_gateway,
src_net);
- if (lpni) {
- best_route = last_route = route;
- best_gw_ni = lpni;
- } else {
- CDEBUG(D_NET, "Gateway %s does not have a peer NI on net %s\n",
- libcfs_nid2str(route->lr_gateway->lp_primary_nid),
+ if (!lpni) {
+ CDEBUG(D_NET,
+ "Gateway %s does not have a peer NI on net %s\n",
+ libcfs_nid2str(gw_pnid),
libcfs_net2str(src_net));
+ continue;
}
+ }
+ if (rc && !best_rte_is_preferred) {
+ /* This is the first preferred route we found,
+ * so it beats any route found previously
+ */
+ best_route = route;
+ if (!last_route)
+ last_route = route;
+ best_gw_ni = lpni;
+ best_rte_is_preferred = true;
+ CDEBUG(D_NET, "preferred gw = %s\n",
+ libcfs_nid2str(gw_pnid));
+ continue;
+ } else if ((!rc) && best_rte_is_preferred)
+ /* The best route we found so far is in the preferred
+ * list, so it beats any non-preferred route
+ */
continue;
- }
- /* no protection on below fields, but it's harmless */
- if (last_route->lr_seq - route->lr_seq < 0)
- last_route = route;
+ if (!best_route) {
+ best_route = last_route = route;
+ best_gw_ni = lpni;
+ continue;
+ }
rc = lnet_compare_routes(route, best_route);
if (rc == -1)
continue;
+ /* Restrict the selection of the router NI on the
+ * src_net provided. If the src_net is LNET_NID_ANY,
+ * then select the best interface available.
+ */
lpni = lnet_find_best_lpni(NULL, LNET_NID_ANY,
route->lr_gateway,
src_net);
- /* restrict the lpni on the src_net if specified */
if (!lpni) {
- CDEBUG(D_NET, "Gateway %s does not have a peer NI on net %s\n",
- libcfs_nid2str(route->lr_gateway->lp_primary_nid),
+ CDEBUG(D_NET,
+ "Gateway %s does not have a peer NI on net %s\n",
+ libcfs_nid2str(gw_pnid),
libcfs_net2str(src_net));
continue;
}
unsigned int shortest_distance;
int best_credits;
int best_healthv;
+ __u32 best_sel_prio;
/*
* If there is no peer_ni that we can send to on this network,
return best_ni;
if (best_ni == NULL) {
+ best_sel_prio = LNET_MAX_SELECTION_PRIORITY;
shortest_distance = UINT_MAX;
best_credits = INT_MIN;
best_healthv = 0;
best_ni->ni_dev_cpt);
best_credits = atomic_read(&best_ni->ni_tx_credits);
best_healthv = atomic_read(&best_ni->ni_healthv);
+ best_sel_prio = best_ni->ni_sel_priority;
}
while ((ni = lnet_get_next_ni_locked(local_net, ni))) {
int ni_credits;
int ni_healthv;
int ni_fatal;
+ __u32 ni_sel_prio;
ni_credits = atomic_read(&ni->ni_tx_credits);
ni_healthv = atomic_read(&ni->ni_healthv);
ni_fatal = atomic_read(&ni->ni_fatal_error_on);
+ ni_sel_prio = ni->ni_sel_priority;
/*
* calculate the distance from the CPT on which
md_cpt,
ni->ni_dev_cpt);
- CDEBUG(D_NET, "compare ni %s [c:%d, d:%d, s:%d] with best_ni %s [c:%d, d:%d, s:%d]\n",
- libcfs_nid2str(ni->ni_nid), ni_credits, distance,
- ni->ni_seq, (best_ni) ? libcfs_nid2str(best_ni->ni_nid)
- : "not seleced", best_credits, shortest_distance,
- (best_ni) ? best_ni->ni_seq : 0);
-
/*
* All distances smaller than the NUMA range
* are treated equally.
* Select on health, shorter distance, available
* credits, then round-robin.
*/
- if (ni_fatal) {
+ if (ni_fatal)
continue;
- } else if (ni_healthv < best_healthv) {
+
+ if (best_ni)
+ CDEBUG(D_NET, "compare ni %s [c:%d, d:%d, s:%d, p:%u] with best_ni %s [c:%d, d:%d, s:%d, p:%u]\n",
+ libcfs_nid2str(ni->ni_nid), ni_credits, distance,
+ ni->ni_seq, ni_sel_prio,
+ (best_ni) ? libcfs_nid2str(best_ni->ni_nid)
+ : "not selected", best_credits, shortest_distance,
+ (best_ni) ? best_ni->ni_seq : 0,
+ best_sel_prio);
+ else
+ goto select_ni;
+
+ if (ni_healthv < best_healthv)
continue;
- } else if (ni_healthv > best_healthv) {
- best_healthv = ni_healthv;
- /*
- * If we're going to prefer this ni because it's
- * the healthiest, then we should set the
- * shortest_distance in the algorithm in case
- * there are multiple NIs with the same health but
- * different distances.
- */
- if (distance < shortest_distance)
- shortest_distance = distance;
- } else if (distance > shortest_distance) {
+ else if (ni_healthv > best_healthv)
+ goto select_ni;
+
+ if (ni_sel_prio > best_sel_prio)
continue;
- } else if (distance < shortest_distance) {
- shortest_distance = distance;
- } else if (ni_credits < best_credits) {
+ else if (ni_sel_prio < best_sel_prio)
+ goto select_ni;
+
+ if (distance > shortest_distance)
continue;
- } else if (ni_credits == best_credits) {
- if (best_ni && best_ni->ni_seq <= ni->ni_seq)
- continue;
- }
+ else if (distance < shortest_distance)
+ goto select_ni;
+
+ if (ni_credits < best_credits)
+ continue;
+ else if (ni_credits > best_credits)
+ goto select_ni;
+
+ if (best_ni && best_ni->ni_seq <= ni->ni_seq)
+ continue;
+
+select_ni:
+ best_sel_prio = ni_sel_prio;
+ shortest_distance = distance;
+ best_healthv = ni_healthv;
best_ni = ni;
best_credits = ni_credits;
}
struct lnet_msg *msg = sd->sd_msg;
int cpt = sd->sd_cpt;
+ if (the_lnet.ln_state != LNET_STATE_RUNNING)
+ return -ESHUTDOWN;
+
/* No send credit hassles with LOLND */
lnet_ni_addref_locked(the_lnet.ln_loni, cpt);
msg->msg_hdr.dest_nid = cpu_to_le64(the_lnet.ln_loni->ni_nid);
__u32 routing = send_case & REMOTE_DST;
struct lnet_rsp_tracker *rspt;
- /*
- * Increment sequence number of the selected peer so that we
- * pick the next one in Round Robin.
+ /* Increment sequence number of the selected peer, peer net,
+ * local ni and local net so that we pick the next ones
+ * in Round Robin.
*/
best_lpni->lpni_seq++;
+ best_lpni->lpni_peer_net->lpn_seq++;
+ best_ni->ni_seq++;
+ best_ni->ni_net->net_seq++;
+
+ CDEBUG(D_NET, "%s NI seq info: [%d:%d:%d:%u] %s LPNI seq info [%d:%d:%d:%u]\n",
+ libcfs_nid2str(best_ni->ni_nid),
+ best_ni->ni_seq, best_ni->ni_net->net_seq,
+ atomic_read(&best_ni->ni_tx_credits),
+ best_ni->ni_sel_priority,
+ libcfs_nid2str(best_lpni->lpni_nid),
+ best_lpni->lpni_seq, best_lpni->lpni_peer_net->lpn_seq,
+ best_lpni->lpni_txcredits,
+ best_lpni->lpni_sel_priority);
/*
* grab a reference on the peer_ni so it sticks around even if
lnet_find_best_ni_on_spec_net(struct lnet_ni *cur_best_ni,
struct lnet_peer *peer,
struct lnet_peer_net *peer_net,
- int cpt,
- bool incr_seq)
+ int cpt)
{
struct lnet_net *local_net;
struct lnet_ni *best_ni;
best_ni = lnet_get_best_ni(local_net, cur_best_ni,
peer, peer_net, cpt);
- if (incr_seq && best_ni)
- best_ni->ni_seq++;
-
return best_ni;
}
int cpt)
{
struct lnet_peer *peer;
+ struct lnet_peer_ni *new_lpni;
int rc;
lnet_peer_ni_addref_locked(lpni);
lnet_peer_ni_decref_locked(lpni);
return rc;
}
- /* The peer may have changed. */
- peer = lpni->lpni_peer_net->lpn_peer;
+
+ new_lpni = lnet_find_peer_ni_locked(lpni->lpni_nid);
+ if (!new_lpni) {
+ lnet_peer_ni_decref_locked(lpni);
+ return -ENOENT;
+ }
+
+ peer = new_lpni->lpni_peer_net->lpn_peer;
spin_lock(&peer->lp_lock);
- if (lnet_peer_is_uptodate_locked(peer)) {
+ if (lpni == new_lpni && lnet_peer_is_uptodate_locked(peer)) {
+ /* The peer NI did not change and the peer is up to date.
+ * Nothing more to do.
+ */
spin_unlock(&peer->lp_lock);
lnet_peer_ni_decref_locked(lpni);
+ lnet_peer_ni_decref_locked(new_lpni);
return 0;
}
- /* queue message and return */
+ spin_unlock(&peer->lp_lock);
+
+ /* Either the peer NI changed during discovery, or the peer isn't up
+ * to date. In both cases we want to queue the message on the
+ * (possibly new) peer's pending queue and queue the peer for discovery
+ */
msg->msg_sending = 0;
msg->msg_txpeer = NULL;
- list_add_tail(&msg->msg_list, &peer->lp_dc_pendq);
- spin_unlock(&peer->lp_lock);
+ lnet_net_unlock(cpt);
+ lnet_peer_queue_message(peer, msg);
+ lnet_net_lock(cpt);
lnet_peer_ni_decref_locked(lpni);
+ lnet_peer_ni_decref_locked(new_lpni);
CDEBUG(D_NET, "msg %p delayed. %s pending discovery\n",
msg, libcfs_nid2str(peer->lp_primary_nid));
lnet_nid_t src_nid = (sd->sd_src_nid != LNET_NID_ANY) ? sd->sd_src_nid :
(sd->sd_best_ni != NULL) ? sd->sd_best_ni->ni_nid :
LNET_NID_ANY;
+ int best_lpn_healthv = 0;
+ __u32 best_lpn_sel_prio = LNET_MAX_SELECTION_PRIORITY;
CDEBUG(D_NET, "using src nid %s for route restriction\n",
libcfs_nid2str(src_nid));
}
if (!route_found) {
- /* we've already looked up the initial lpni using dst_nid */
- lpni = sd->sd_best_lpni;
- /* the peer tree must be in existence */
- LASSERT(lpni && lpni->lpni_peer_net &&
- lpni->lpni_peer_net->lpn_peer);
- lp = lpni->lpni_peer_net->lpn_peer;
-
- list_for_each_entry(lpn, &lp->lp_peer_nets, lpn_peer_nets) {
- /* is this remote network reachable? */
- rnet = lnet_find_rnet_locked(lpn->lpn_net_id);
- if (!rnet)
- continue;
+ if (sd->sd_msg->msg_routing) {
+ /* If I'm routing this message then I need to find the
+ * next hop based on the destination NID
+ */
+ best_rnet = lnet_find_rnet_locked(LNET_NIDNET(sd->sd_dst_nid));
+ if (!best_rnet) {
+ CERROR("Unable to route message to %s - Route table may be misconfigured\n",
+ libcfs_nid2str(sd->sd_dst_nid));
+ return -EHOSTUNREACH;
+ }
+ } else {
+ /* we've already looked up the initial lpni using
+ * dst_nid
+ */
+ lpni = sd->sd_best_lpni;
+ /* the peer tree must be in existence */
+ LASSERT(lpni && lpni->lpni_peer_net &&
+ lpni->lpni_peer_net->lpn_peer);
+ lp = lpni->lpni_peer_net->lpn_peer;
+
+ list_for_each_entry(lpn, &lp->lp_peer_nets, lpn_peer_nets) {
+ /* is this remote network reachable? */
+ rnet = lnet_find_rnet_locked(lpn->lpn_net_id);
+ if (!rnet)
+ continue;
- if (!best_lpn) {
+ if (!best_lpn) {
+ best_lpn = lpn;
+ best_rnet = rnet;
+ }
+
+ /* select the preferred peer net */
+ if (best_lpn_healthv > lpn->lpn_healthv)
+ continue;
+ else if (best_lpn_healthv < lpn->lpn_healthv)
+ goto use_lpn;
+
+ if (best_lpn_sel_prio < lpn->lpn_sel_priority)
+ continue;
+ else if (best_lpn_sel_prio > lpn->lpn_sel_priority)
+ goto use_lpn;
+
+ if (best_lpn->lpn_seq <= lpn->lpn_seq)
+ continue;
+use_lpn:
+ best_lpn_healthv = lpn->lpn_healthv;
+ best_lpn_sel_prio = lpn->lpn_sel_priority;
best_lpn = lpn;
best_rnet = rnet;
}
- if (best_lpn->lpn_seq <= lpn->lpn_seq)
- continue;
+ if (!best_lpn) {
+ CERROR("peer %s has no available nets\n",
+ libcfs_nid2str(sd->sd_dst_nid));
+ return -EHOSTUNREACH;
+ }
- best_lpn = lpn;
- best_rnet = rnet;
- }
+ sd->sd_best_lpni = lnet_find_best_lpni(sd->sd_best_ni,
+ sd->sd_dst_nid,
+ lp,
+ best_lpn->lpn_net_id);
+ if (!sd->sd_best_lpni) {
+ CERROR("peer %s is unreachable\n",
+ libcfs_nid2str(sd->sd_dst_nid));
+ return -EHOSTUNREACH;
+ }
- if (!best_lpn) {
- CERROR("peer %s has no available nets\n",
- libcfs_nid2str(sd->sd_dst_nid));
- return -EHOSTUNREACH;
- }
+ /* We're attempting to round robin over the remote peer
+ * NI's so update the final destination we selected
+ */
+ sd->sd_final_dst_lpni = sd->sd_best_lpni;
- sd->sd_best_lpni = lnet_find_best_lpni(sd->sd_best_ni,
- sd->sd_dst_nid,
- lp,
- best_lpn->lpn_net_id);
- if (!sd->sd_best_lpni) {
- CERROR("peer %s is unreachable\n",
- libcfs_nid2str(sd->sd_dst_nid));
- return -EHOSTUNREACH;
+ /* Increment the sequence number of the remote lpni so
+ * we can round robin over the different interfaces of
+ * the remote lpni
+ */
+ sd->sd_best_lpni->lpni_seq++;
}
/*
- * We're attempting to round robin over the remote peer
- * NI's so update the final destination we selected
- */
- sd->sd_final_dst_lpni = sd->sd_best_lpni;
-
- /*
* find the best route. Restrict the selection on the net of the
* local NI if we've already picked the local NI to send from.
* Otherwise, let's pick any route we can find and then find
- * a local NI we can reach the route's gateway on. Any route we select
- * will be reachable by virtue of the restriction we have when
- * adding a route.
+ * a local NI we can reach the route's gateway on. Any route we
+ * select will be reachable by virtue of the restriction we have
+ * when adding a route.
*/
best_route = lnet_find_route_locked(best_rnet,
LNET_NIDNET(src_nid),
+ sd->sd_best_lpni,
&last_route, &gwni);
if (!best_route) {
gw = best_route->lr_gateway;
LASSERT(gw == gwni->lpni_peer_net->lpn_peer);
local_lnet = best_route->lr_lnet;
-
- /*
- * Increment the sequence number of the remote lpni so we
- * can round robin over the different interfaces of the
- * remote lpni
- */
- sd->sd_best_lpni->lpni_seq++;
}
/*
sd->sd_best_ni = lnet_find_best_ni_on_spec_net(NULL, gw,
lnet_peer_get_net_locked(gw,
local_lnet),
- sd->sd_md_cpt,
- true);
+ sd->sd_md_cpt);
if (!sd->sd_best_ni) {
CERROR("Internal Error. Expected local ni on %s but non found :%s\n",
if (sd->sd_rtr_nid == LNET_NID_ANY) {
LASSERT(best_route && last_route);
best_route->lr_seq = last_route->lr_seq + 1;
- best_lpn->lpn_seq++;
+ if (best_lpn)
+ best_lpn->lpn_seq++;
}
return 0;
lnet_find_best_ni_on_local_net(struct lnet_peer *peer, int md_cpt,
bool discovery)
{
- struct lnet_peer_net *peer_net = NULL;
+ struct lnet_peer_net *lpn = NULL;
+ struct lnet_peer_net *best_lpn = NULL;
+ struct lnet_net *net = NULL;
+ struct lnet_net *best_net = NULL;
struct lnet_ni *best_ni = NULL;
- int lpn_healthv = 0;
+ int best_lpn_healthv = 0;
+ int best_net_healthv = 0;
+ int net_healthv;
+ __u32 best_lpn_sel_prio = LNET_MAX_SELECTION_PRIORITY;
+ __u32 lpn_sel_prio;
+ __u32 best_net_sel_prio = LNET_MAX_SELECTION_PRIORITY;
+ __u32 net_sel_prio;
+ bool exit = false;
/*
* The peer can have multiple interfaces, some of them can be on
*/
/* go through all the peer nets and find the best_ni */
- list_for_each_entry(peer_net, &peer->lp_peer_nets, lpn_peer_nets) {
+ list_for_each_entry(lpn, &peer->lp_peer_nets, lpn_peer_nets) {
/*
* The peer's list of nets can contain non-local nets. We
* want to only examine the local ones.
*/
- if (!lnet_get_net_locked(peer_net->lpn_net_id))
- continue;
-
- /* always select the lpn with the best health */
- if (lpn_healthv <= peer_net->lpn_healthv)
- lpn_healthv = peer_net->lpn_healthv;
- else
+ net = lnet_get_net_locked(lpn->lpn_net_id);
+ if (!net)
continue;
- best_ni = lnet_find_best_ni_on_spec_net(best_ni, peer, peer_net,
- md_cpt, false);
+ lpn_sel_prio = lpn->lpn_sel_priority;
+ net_healthv = lnet_get_net_healthv_locked(net);
+ net_sel_prio = net->net_sel_priority;
/*
* if this is a discovery message and lp_disc_net_id is
* specified then use that net to send the discovery on.
*/
- if (peer->lp_disc_net_id == peer_net->lpn_net_id &&
- discovery)
+ if (peer->lp_disc_net_id == lpn->lpn_net_id &&
+ discovery) {
+ exit = true;
+ goto select_lpn;
+ }
+
+ if (!best_lpn)
+ goto select_lpn;
+
+ /* always select the lpn with the best health */
+ if (best_lpn_healthv > lpn->lpn_healthv)
+ continue;
+ else if (best_lpn_healthv < lpn->lpn_healthv)
+ goto select_lpn;
+
+ /* select the preferred peer and local nets */
+ if (best_lpn_sel_prio < lpn_sel_prio)
+ continue;
+ else if (best_lpn_sel_prio > lpn_sel_prio)
+ goto select_lpn;
+
+ if (best_net_healthv > net_healthv)
+ continue;
+ else if (best_net_healthv < net_healthv)
+ goto select_lpn;
+
+ if (best_net_sel_prio < net_sel_prio)
+ continue;
+ else if (best_net_sel_prio > net_sel_prio)
+ goto select_lpn;
+
+ if (best_lpn->lpn_seq < lpn->lpn_seq)
+ continue;
+ else if (best_lpn->lpn_seq > lpn->lpn_seq)
+ goto select_lpn;
+
+ /* round robin over the local networks */
+ if (best_net->net_seq <= net->net_seq)
+ continue;
+
+select_lpn:
+ best_net_healthv = net_healthv;
+ best_net_sel_prio = net_sel_prio;
+ best_lpn_healthv = lpn->lpn_healthv;
+ best_lpn_sel_prio = lpn_sel_prio;
+ best_lpn = lpn;
+ best_net = net;
+
+ if (exit)
break;
}
- if (best_ni)
- /* increment sequence number so we can round robin */
- best_ni->ni_seq++;
+ if (best_lpn) {
+ /* Select the best NI on the same net as best_lpn chosen
+ * above
+ */
+ best_ni = lnet_find_best_ni_on_spec_net(NULL, peer,
+ best_lpn, md_cpt);
+ }
return best_ni;
}
best_ni =
lnet_find_best_ni_on_spec_net(NULL, sd->sd_peer,
sd->sd_best_lpni->lpni_peer_net,
- sd->sd_md_cpt, true);
+ sd->sd_md_cpt);
/* If there is no best_ni we don't have a route */
if (!best_ni) {
CERROR("no path to %s from net %s\n",
sd->sd_best_ni = lnet_find_best_ni_on_spec_net(NULL,
sd->sd_peer,
sd->sd_best_lpni->lpni_peer_net,
- sd->sd_md_cpt,
- true);
+ sd->sd_md_cpt);
if (!sd->sd_best_ni) {
CERROR("Unable to forward message to %s. No local NI available\n",
libcfs_nid2str(sd->sd_dst_nid));
sd->sd_best_ni =
lnet_find_best_ni_on_spec_net(NULL, sd->sd_peer,
sd->sd_best_lpni->lpni_peer_net,
- sd->sd_md_cpt, true);
+ sd->sd_md_cpt);
if (!sd->sd_best_ni) {
/*
* try to send it via non-multi-rail criteria
*/
if (!IS_ERR(src_lpni)) {
+ /* Drop ref taken by lnet_nid2peerni_locked() */
+ lnet_peer_ni_decref_locked(src_lpni);
src_lp = lpni->lpni_peer_net->lpn_peer;
if (lnet_peer_is_multi_rail(src_lp) &&
!lnet_is_peer_ni_alive(lpni))
lnet_nid_t nid;
int healthv;
int rc;
+ time64_t now;
/*
* Always use cpt 0 for locking across all interactions with
&local_queue);
lnet_net_unlock(0);
+ now = ktime_get_seconds();
+
list_for_each_entry_safe(lpni, tmp, &local_queue,
lpni_recovery) {
/*
}
lpni->lpni_recovery_ping_mdh = mdh;
- /*
- * While we're unlocked the lpni could've been
- * readded on the recovery queue. In this case we
- * don't need to add it to the local queue, since
- * it's already on there and the thread that added
- * it would've incremented the refcount on the
- * peer, which means we need to decref the refcount
- * that was implicitly grabbed by find_peer_ni_locked.
- * Otherwise, if the lpni is still not on
- * the recovery queue, then we'll add it to the
- * processed list.
- */
- if (list_empty(&lpni->lpni_recovery))
- list_add_tail(&lpni->lpni_recovery, &processed_list);
- else
- lnet_peer_ni_decref_locked(lpni);
- lnet_net_unlock(0);
- spin_lock(&lpni->lpni_lock);
- if (rc)
+ lnet_peer_ni_add_to_recoveryq_locked(lpni,
+ &processed_list,
+ now);
+ if (rc) {
+ spin_lock(&lpni->lpni_lock);
lpni->lpni_state &= ~LNET_PEER_NI_RECOVERY_PENDING;
- }
- spin_unlock(&lpni->lpni_lock);
+ spin_unlock(&lpni->lpni_lock);
+ }
+
+ /* Drop the ref taken by lnet_find_peer_ni_locked() */
+ lnet_peer_ni_decref_locked(lpni);
+ lnet_net_unlock(0);
+ } else
+ spin_unlock(&lpni->lpni_lock);
}
list_splice_init(&processed_list, &local_queue);
goto drop;
}
- if (lnet_drop_asym_route && for_me &&
- LNET_NIDNET(src_nid) != LNET_NIDNET(from_nid)) {
- struct lnet_net *net;
- struct lnet_remotenet *rnet;
- bool found = true;
-
- /* we are dealing with a routed message,
- * so see if route to reach src_nid goes through from_nid
- */
- lnet_net_lock(cpt);
- net = lnet_get_net_locked(LNET_NIDNET(ni->ni_nid));
- if (!net) {
- lnet_net_unlock(cpt);
- CERROR("net %s not found\n",
- libcfs_net2str(LNET_NIDNET(ni->ni_nid)));
- return -EPROTO;
- }
-
- rnet = lnet_find_rnet_locked(LNET_NIDNET(src_nid));
- if (rnet) {
- struct lnet_peer *gw = NULL;
- struct lnet_peer_ni *lpni = NULL;
- struct lnet_route *route;
-
- list_for_each_entry(route, &rnet->lrn_routes, lr_list) {
- found = false;
- gw = route->lr_gateway;
- if (route->lr_lnet != net->net_id)
- continue;
- /*
- * if the nid is one of the gateway's NIDs
- * then this is a valid gateway
- */
- while ((lpni = lnet_get_next_peer_ni_locked(gw,
- NULL, lpni)) != NULL) {
- if (lpni->lpni_nid == from_nid) {
- found = true;
- break;
- }
- }
- }
- }
- lnet_net_unlock(cpt);
- if (!found) {
- /* we would not use from_nid to route a message to
- * src_nid
- * => asymmetric routing detected but forbidden
- */
- CERROR("%s, src %s: Dropping asymmetrical route %s\n",
- libcfs_nid2str(from_nid),
- libcfs_nid2str(src_nid), lnet_msgtyp2str(type));
- goto drop;
- }
- }
-
msg = lnet_msg_alloc();
if (msg == NULL) {
CERROR("%s, src %s: Dropping %s (out of memory)\n",
goto drop;
}
- if (the_lnet.ln_routing)
- lpni->lpni_last_alive = ktime_get_seconds();
+ if (lnet_drop_asym_route && for_me &&
+ LNET_NIDNET(src_nid) != LNET_NIDNET(from_nid)) {
+ __u32 src_net_id = LNET_NIDNET(src_nid);
+ struct lnet_peer *gw = lpni->lpni_peer_net->lpn_peer;
+ struct lnet_route *route;
+ bool found = false;
+
+ list_for_each_entry(route, &gw->lp_routes, lr_gwlist) {
+ if (route->lr_net == src_net_id) {
+ found = true;
+ break;
+ }
+ }
+ if (!found) {
+ lnet_net_unlock(cpt);
+ /* we would not use from_nid to route a message to
+ * src_nid
+ * => asymmetric routing detected but forbidden
+ */
+ CERROR("%s, src %s: Dropping asymmetrical route %s\n",
+ libcfs_nid2str(from_nid),
+ libcfs_nid2str(src_nid), lnet_msgtyp2str(type));
+ lnet_msg_free(msg);
+ goto drop;
+ }
+ }
+
+ lpni->lpni_last_alive = ktime_get_seconds();
msg->msg_rxpeer = lpni;
msg->msg_rxni = ni;
git://git.whamcloud.com / fs / lustre-release.git / blobdiff