if (ev_type == LNET_EVENT_SEND) {
/* event for active message */
- ev->target.nid = le64_to_cpu(hdr->dest_nid);
- ev->target.pid = le32_to_cpu(hdr->dest_pid);
- ev->initiator.nid = LNET_NID_ANY;
+ ev->target.nid = hdr->dest_nid;
+ ev->target.pid = hdr->dest_pid;
+ ev->initiator.nid = LNET_ANY_NID;
ev->initiator.pid = the_lnet.ln_pid;
- ev->source.nid = LNET_NID_ANY;
+ ev->source.nid = LNET_ANY_NID;
ev->source.pid = the_lnet.ln_pid;
- ev->sender = LNET_NID_ANY;
+ ev->sender = LNET_ANY_NID;
} else {
/* event for passive message */
ev->target.pid = hdr->dest_pid;
/* Multi-Rail: track source NID. */
ev->source.pid = hdr->src_pid;
ev->source.nid = hdr->src_nid;
- ev->rlength = hdr->payload_length;
+ ev->rlength = hdr->payload_length;
ev->sender = msg->msg_from;
ev->mlength = msg->msg_wanted;
ev->offset = msg->msg_offset;
ack_wmd = msg->msg_hdr.msg.put.ack_wmd;
- lnet_prep_send(msg, LNET_MSG_ACK, msg->msg_ev.source, 0, 0);
+ lnet_prep_send(msg, LNET_MSG_ACK, &msg->msg_ev.source, 0, 0);
msg->msg_hdr.msg.ack.dst_wmd = ack_wmd;
msg->msg_hdr.msg.ack.match_bits = msg->msg_ev.match_bits;
msg->msg_hdr.msg.ack.mlength = cpu_to_le32(msg->msg_ev.mlength);
- rc = lnet_send(msg->msg_ev.target.nid, msg, msg->msg_from);
+ rc = lnet_send(&msg->msg_ev.target.nid, msg,
+ &msg->msg_from);
lnet_net_lock(cpt);
/*
LASSERT(!msg->msg_receiving); /* called back recv already */
lnet_net_unlock(cpt);
- rc = lnet_send(LNET_NID_ANY, msg, LNET_NID_ANY);
+ rc = lnet_send(NULL, msg, NULL);
lnet_net_lock(cpt);
/*
msg->msg_target_is_router = 0;
CDEBUG(D_NET, "%s->%s:%s:%s - queuing msg (%p) for resend\n",
- libcfs_nid2str(msg->msg_hdr.src_nid),
- libcfs_nid2str(msg->msg_hdr.dest_nid),
+ libcfs_nidstr(&msg->msg_hdr.src_nid),
+ libcfs_nidstr(&msg->msg_hdr.dest_nid),
lnet_msgtyp2str(msg->msg_type),
lnet_health_error2str(msg->msg_health_status), msg);
/* don't resend recovery messages */
if (msg->msg_recovery) {
CDEBUG(D_NET, "msg %s->%s is a recovery ping. retry# %d\n",
- libcfs_nid2str(msg->msg_from),
- libcfs_nid2str(msg->msg_target.nid),
+ libcfs_nidstr(&msg->msg_from),
+ libcfs_nidstr(&msg->msg_target.nid),
msg->msg_retry_count);
return -ENOTRECOVERABLE;
}
*/
if (msg->msg_no_resend) {
CDEBUG(D_NET, "msg %s->%s requested no resend. retry# %d\n",
- libcfs_nid2str(msg->msg_from),
- libcfs_nid2str(msg->msg_target.nid),
+ libcfs_nidstr(&msg->msg_from),
+ libcfs_nidstr(&msg->msg_target.nid),
msg->msg_retry_count);
return -ENOTRECOVERABLE;
}
/* check if the message has exceeded the number of retries */
if (msg->msg_retry_count >= lnet_retry_count) {
CNETERR("msg %s->%s exceeded retry count %d\n",
- libcfs_nid2str(msg->msg_from),
- libcfs_nid2str(msg->msg_target.nid),
+ libcfs_nidstr(&msg->msg_from),
+ libcfs_nidstr(&msg->msg_target.nid),
msg->msg_retry_count);
return -ENOTRECOVERABLE;
}
return 0;
}
- while (!list_empty(&container->msc_resending)) {
- msg = list_entry(container->msc_resending.next,
- struct lnet_msg, msg_list);
+ while ((msg = list_first_entry_or_null(&container->msc_resending,
+ struct lnet_msg,
+ msg_list)) != NULL) {
list_del(&msg->msg_list);
/*
CDEBUG(D_NET, "health check: %s->%s: %s: %s\n",
libcfs_nidstr(&ni->ni_nid),
- (lo) ? "self" : libcfs_nid2str(lpni->lpni_nid),
+ (lo) ? "self" : libcfs_nidstr(&lpni->lpni_nid),
lnet_msgtyp2str(msg->msg_type),
lnet_health_error2str(hstatus));
if (!lnet_isrouter(lpni))
handle_remote_health = false;
}
+ /* Do not put my interfaces into peer NI recovery. They should
+ * be handled with local NI recovery.
+ */
+ if (handle_remote_health && lpni &&
+ lnet_nid_to_ni_locked(&lpni->lpni_nid, 0))
+ handle_remote_health = false;
lnet_net_unlock(0);
}
* faster recovery.
*/
lnet_inc_healthv(&ni->ni_healthv, lnet_health_sensitivity);
- lnet_net_lock(0);
- ni->ni_ping_count = 0;
/*
* It's possible msg_txpeer is NULL in the LOLND
* case. Only increment the peer's health if we're
* as indication that the router is fully healthy.
*/
if (lpni && msg->msg_rx_committed) {
+ lnet_net_lock(0);
lpni->lpni_ping_count = 0;
+ ni->ni_ping_count = 0;
/*
* If we're receiving a message from the router or
* I'm a router, then set that lpni's health to
&the_lnet.ln_mt_peerNIRecovq,
ktime_get_seconds());
}
+ lnet_net_unlock(0);
}
- lnet_net_unlock(0);
/* we can finalize this message */
return -1;
return false;
/* match only health rules */
- if (!lnet_drop_rule_match(&msg->msg_hdr, LNET_NID_ANY,
- hstatus))
+ if (!lnet_drop_rule_match(&msg->msg_hdr, NULL, hstatus))
return false;
CDEBUG(D_NET, "src %s(%s)->dst %s: %s simulate health error: %s\n",
- libcfs_nid2str(msg->msg_hdr.src_nid),
+ libcfs_nidstr(&msg->msg_hdr.src_nid),
libcfs_nidstr(&msg->msg_txni->ni_nid),
- libcfs_nid2str(msg->msg_hdr.dest_nid),
+ libcfs_nidstr(&msg->msg_hdr.dest_nid),
lnet_msgtyp2str(msg->msg_type),
lnet_health_error2str(*hstatus));
}
rc = 0;
- while (!list_empty(&container->msc_finalizing)) {
- msg = list_entry(container->msc_finalizing.next,
- struct lnet_msg, msg_list);
-
+ while ((msg = list_first_entry_or_null(&container->msc_finalizing,
+ struct lnet_msg,
+ msg_list)) != NULL) {
list_del_init(&msg->msg_list);
/* NB drops and regains the lnet lock if it actually does
void
lnet_msg_container_cleanup(struct lnet_msg_container *container)
{
- int count = 0;
+ struct lnet_msg *msg;
+ int count = 0;
if (container->msc_init == 0)
return;
- while (!list_empty(&container->msc_active)) {
- struct lnet_msg *msg;
-
- msg = list_entry(container->msc_active.next,
- struct lnet_msg, msg_activelist);
+ while ((msg = list_first_entry_or_null(&container->msc_active,
+ struct lnet_msg,
+ msg_activelist)) != NULL) {
LASSERT(msg->msg_onactivelist);
msg->msg_onactivelist = 0;
list_del_init(&msg->msg_activelist);