for (j = 0; j < LNET_PEER_HASH_SIZE; j++)
LASSERT(list_empty(&hash[j]));
- LIBCFS_FREE(hash, LNET_PEER_HASH_SIZE * sizeof(*hash));
+ CFS_FREE_PTR_ARRAY(hash, LNET_PEER_HASH_SIZE);
}
cfs_percpt_free(the_lnet.ln_peer_tables);
init_waitqueue_head(&lp->lp_dc_waitq);
spin_lock_init(&lp->lp_lock);
lp->lp_primary_nid = nid;
+ if (lnet_peers_start_down())
+ lp->lp_alive = false;
+ else
+ lp->lp_alive = true;
/*
* all peers created on a router should have health on
/* decrement the ref count on the peer table */
ptable = the_lnet.ln_peer_tables[lpni->lpni_cpt];
- LASSERT(ptable->pt_number > 0);
- ptable->pt_number--;
/*
* The peer_ni can no longer be found with a lookup. But there
"Waiting for %d zombies on peer table\n",
ptable->pt_zombies);
}
- set_current_state(TASK_UNINTERRUPTIBLE);
- schedule_timeout(cfs_time_seconds(1) >> 1);
+ schedule_timeout_uninterruptible(cfs_time_seconds(1) >> 1);
spin_lock(&ptable->pt_zombie_lock);
}
spin_unlock(&ptable->pt_zombie_lock);
struct list_head *peers;
struct lnet_peer_ni *lp;
- LASSERT(the_lnet.ln_state == LNET_STATE_RUNNING);
+ if (the_lnet.ln_state != LNET_STATE_RUNNING)
+ return NULL;
peers = &ptable->pt_hash[lnet_nid2peerhash(nid)];
list_for_each_entry(lp, peers, lpni_hashlist) {
if (oldnids) {
size = sizeof(*nids) * (lpni->lpni_pref_nnids - 1);
- LIBCFS_FREE(oldnids, sizeof(*oldnids) * size);
+ CFS_FREE_PTR_ARRAY(oldnids, size);
}
out:
if (rc == -EEXIST && (lpni->lpni_state & LNET_PEER_NI_NON_MR_PREF)) {
if (oldnids) {
size = sizeof(*nids) * (lpni->lpni_pref_nnids + 1);
- LIBCFS_FREE(oldnids, sizeof(*oldnids) * size);
+ CFS_FREE_PTR_ARRAY(oldnids, size);
}
out:
CDEBUG(D_NET, "peer %s nid %s: %d\n",
bool
lnet_is_discovery_disabled_locked(struct lnet_peer *lp)
+__must_hold(&lp->lp_lock)
{
if (lnet_peer_discovery_disabled)
return true;
ptable = the_lnet.ln_peer_tables[lpni->lpni_cpt];
list_add_tail(&lpni->lpni_hashlist, &ptable->pt_hash[hash]);
ptable->pt_version++;
- ptable->pt_number++;
/* This is the 1st refcount on lpni. */
atomic_inc(&lpni->lpni_refcount);
}
/* Add peer_ni to peer_net */
lpni->lpni_peer_net = lpn;
list_add_tail(&lpni->lpni_peer_nis, &lpn->lpn_peer_nis);
+ lnet_update_peer_net_healthv(lpni);
lnet_peer_net_addref_locked(lpn);
/* Add peer_net to peer */
struct lnet_peer *lp;
struct lnet_peer_net *lpn;
struct lnet_peer_ni *lpni;
- /*
- * Assume peer is Multi-Rail capable and let discovery find out
- * otherwise.
- */
- unsigned flags = LNET_PEER_MULTI_RAIL;
+ unsigned flags = 0;
int rc = 0;
if (nid == LNET_NID_ANY) {
ptable->pt_zombies--;
spin_unlock(&ptable->pt_zombie_lock);
- if (lpni->lpni_pref_nnids > 1) {
- LIBCFS_FREE(lpni->lpni_pref.nids,
- sizeof(*lpni->lpni_pref.nids) * lpni->lpni_pref_nnids);
- }
+ if (lpni->lpni_pref_nnids > 1)
+ CFS_FREE_PTR_ARRAY(lpni->lpni_pref.nids, lpni->lpni_pref_nnids);
+
LIBCFS_FREE(lpni, sizeof(*lpni));
lnet_peer_net_decref_locked(lpn);
return rc;
}
+bool
+lnet_peer_is_uptodate(struct lnet_peer *lp)
+{
+ bool rc;
+
+ spin_lock(&lp->lp_lock);
+ rc = lnet_peer_is_uptodate_locked(lp);
+ spin_unlock(&lp->lp_lock);
+ return rc;
+}
+
/*
* Is a peer uptodate from the point of view of discovery?
*
* Otherwise look at whether the peer needs rediscovering.
*/
bool
-lnet_peer_is_uptodate(struct lnet_peer *lp)
+lnet_peer_is_uptodate_locked(struct lnet_peer *lp)
+__must_hold(&lp->lp_lock)
{
bool rc;
- spin_lock(&lp->lp_lock);
if (lp->lp_state & (LNET_PEER_DISCOVERING |
LNET_PEER_FORCE_PING |
LNET_PEER_FORCE_PUSH)) {
} else {
rc = false;
}
- spin_unlock(&lp->lp_lock);
return rc;
}
{
struct lnet_msg *msg, *tmp;
int rc = 0;
- struct list_head pending_msgs;
-
- INIT_LIST_HEAD(&pending_msgs);
+ LIST_HEAD(pending_msgs);
CDEBUG(D_NET, "Discovery complete. Dequeue peer %s\n",
libcfs_nid2str(lp->lp_primary_nid));
/*
- * Only enable the multi-rail feature on the peer if both sides of
- * the connection have discovery on
- */
- if (pbuf->pb_info.pi_features & LNET_PING_FEAT_MULTI_RAIL) {
- CDEBUG(D_NET, "Peer %s has Multi-Rail feature enabled\n",
- libcfs_nid2str(lp->lp_primary_nid));
- lp->lp_state |= LNET_PEER_MULTI_RAIL;
- } else {
- CDEBUG(D_NET, "Peer %s has Multi-Rail feature disabled\n",
- libcfs_nid2str(lp->lp_primary_nid));
- lp->lp_state &= ~LNET_PEER_MULTI_RAIL;
- }
-
- /*
* The peer may have discovery disabled at its end. Set
* NO_DISCOVERY as appropriate.
*/
*/
if (pbuf->pb_info.pi_features & LNET_PING_FEAT_MULTI_RAIL) {
if (lp->lp_state & LNET_PEER_MULTI_RAIL) {
- /* Everything's fine */
+ CDEBUG(D_NET, "peer %s(%p) is MR\n",
+ libcfs_nid2str(lp->lp_primary_nid), lp);
} else if (lp->lp_state & LNET_PEER_CONFIGURED) {
CWARN("Reply says %s is Multi-Rail, DLC says not\n",
libcfs_nid2str(lp->lp_primary_nid));
+ } else if (lnet_peer_discovery_disabled) {
+ CDEBUG(D_NET,
+ "peer %s(%p) not MR: DD disabled locally\n",
+ libcfs_nid2str(lp->lp_primary_nid), lp);
+ } else if (lp->lp_state & LNET_PEER_NO_DISCOVERY) {
+ CDEBUG(D_NET,
+ "peer %s(%p) not MR: DD disabled remotely\n",
+ libcfs_nid2str(lp->lp_primary_nid), lp);
} else {
- /*
- * if discovery is disabled then we don't want to
- * update the state of the peer. All we'll do is
- * update the peer_nis which were reported back in
- * the initial ping
- */
-
- if (!lnet_is_discovery_disabled_locked(lp)) {
- lp->lp_state |= LNET_PEER_MULTI_RAIL;
- lnet_peer_clr_non_mr_pref_nids(lp);
- }
+ CDEBUG(D_NET, "peer %s(%p) is MR capable\n",
+ libcfs_nid2str(lp->lp_primary_nid), lp);
+ lp->lp_state |= LNET_PEER_MULTI_RAIL;
+ lnet_peer_clr_non_mr_pref_nids(lp);
}
} else if (lp->lp_state & LNET_PEER_MULTI_RAIL) {
if (lp->lp_state & LNET_PEER_CONFIGURED) {
out:
lp->lp_state &= ~LNET_PEER_PING_SENT;
spin_unlock(&lp->lp_lock);
+
+ lnet_net_lock(LNET_LOCK_EX);
+ /*
+ * If this peer is a gateway, call the routing callback to
+ * handle the ping reply
+ */
+ if (lp->lp_rtr_refcount > 0)
+ lnet_router_discovery_ping_reply(lp);
+ lnet_net_unlock(LNET_LOCK_EX);
}
/*
lp->lp_state &= ~LNET_PEER_ROUTER_ENABLED;
spin_unlock(&lp->lp_lock);
- nnis = MAX(lp->lp_nnis, pbuf->pb_info.pi_nnis);
- LIBCFS_ALLOC(curnis, nnis * sizeof(*curnis));
- LIBCFS_ALLOC(addnis, nnis * sizeof(*addnis));
- LIBCFS_ALLOC(delnis, nnis * sizeof(*delnis));
+ nnis = max_t(int, lp->lp_nnis, pbuf->pb_info.pi_nnis);
+ CFS_ALLOC_PTR_ARRAY(curnis, nnis);
+ CFS_ALLOC_PTR_ARRAY(addnis, nnis);
+ CFS_ALLOC_PTR_ARRAY(delnis, nnis);
if (!curnis || !addnis || !delnis) {
rc = -ENOMEM;
goto out;
*/
rc = 0;
out:
- LIBCFS_FREE(curnis, nnis * sizeof(*curnis));
- LIBCFS_FREE(addnis, nnis * sizeof(*addnis));
- LIBCFS_FREE(delnis, nnis * sizeof(*delnis));
+ CFS_FREE_PTR_ARRAY(curnis, nnis);
+ CFS_FREE_PTR_ARRAY(addnis, nnis);
+ CFS_FREE_PTR_ARRAY(delnis, nnis);
lnet_ping_buffer_decref(pbuf);
CDEBUG(D_NET, "peer %s (%p): %d\n", libcfs_nid2str(lp->lp_primary_nid), lp, rc);
pnid = lnet_peer_select_nid(lp);
lnet_net_unlock(cpt);
- nnis = MAX(lp->lp_data_nnis, LNET_INTERFACES_MIN);
+ nnis = max(lp->lp_data_nnis, LNET_INTERFACES_MIN);
rc = lnet_send_ping(pnid, &lp->lp_ping_mdh, nnis, lp,
- the_lnet.ln_dc_eqh, false);
+ the_lnet.ln_dc_eq, false);
/*
* if LNetMDBind in lnet_send_ping fails we need to decrement the
md.threshold = 2; /* Put/Ack */
md.max_size = 0;
md.options = 0;
- md.eq_handle = the_lnet.ln_dc_eqh;
+ md.eq_handle = the_lnet.ln_dc_eq;
md.user_ptr = lp;
rc = LNetMDBind(md, LNET_UNLINK, &lp->lp_push_mdh);
static void lnet_resend_msgs(void)
{
struct lnet_msg *msg, *tmp;
- struct list_head resend;
+ LIST_HEAD(resend);
int rc;
- INIT_LIST_HEAD(&resend);
-
spin_lock(&the_lnet.ln_msg_resend_lock);
list_splice(&the_lnet.ln_msg_resend, &resend);
spin_unlock(&the_lnet.ln_msg_resend_lock);
struct lnet_peer *lp;
int rc;
+ wait_for_completion(&the_lnet.ln_started);
+
CDEBUG(D_NET, "started\n");
- cfs_block_allsigs();
for (;;) {
if (lnet_peer_discovery_wait_for_work())
lnet_push_target_resize();
lnet_net_lock(LNET_LOCK_EX);
- if (the_lnet.ln_dc_state == LNET_DC_STATE_STOPPING)
+ if (the_lnet.ln_dc_state == LNET_DC_STATE_STOPPING) {
+ lnet_net_unlock(LNET_LOCK_EX);
break;
+ }
/*
* Process all incoming discovery work requests. When
/* Queue cleanup 2: wait for the expired queue to clear. */
while (!list_empty(&the_lnet.ln_dc_expired))
- schedule_timeout(cfs_time_seconds(1));
+ schedule_timeout_uninterruptible(cfs_time_seconds(1));
/* Queue cleanup 3: clear the request queue. */
lnet_net_lock(LNET_LOCK_EX);
}
lnet_net_unlock(LNET_LOCK_EX);
- LNetEQFree(the_lnet.ln_dc_eqh);
- LNetInvalidateEQHandle(&the_lnet.ln_dc_eqh);
+ LNetEQFree(the_lnet.ln_dc_eq);
+ the_lnet.ln_dc_eq = NULL;
the_lnet.ln_dc_state = LNET_DC_STATE_SHUTDOWN;
wake_up(&the_lnet.ln_dc_waitq);
int lnet_peer_discovery_start(void)
{
struct task_struct *task;
- int rc;
+ int rc = 0;
if (the_lnet.ln_dc_state != LNET_DC_STATE_SHUTDOWN)
return -EALREADY;
- rc = LNetEQAlloc(0, lnet_discovery_event_handler, &the_lnet.ln_dc_eqh);
- if (rc != 0) {
+ the_lnet.ln_dc_eq = LNetEQAlloc(lnet_discovery_event_handler);
+ if (IS_ERR(the_lnet.ln_dc_eq)) {
+ rc = PTR_ERR(the_lnet.ln_dc_eq);
CERROR("Can't allocate discovery EQ: %d\n", rc);
return rc;
}
rc = PTR_ERR(task);
CERROR("Can't start peer discovery thread: %d\n", rc);
- LNetEQFree(the_lnet.ln_dc_eqh);
- LNetInvalidateEQHandle(&the_lnet.ln_dc_eqh);
+ LNetEQFree(the_lnet.ln_dc_eq);
+ the_lnet.ln_dc_eq = NULL;
the_lnet.ln_dc_state = LNET_DC_STATE_SHUTDOWN;
}
LASSERT(the_lnet.ln_dc_state == LNET_DC_STATE_RUNNING);
the_lnet.ln_dc_state = LNET_DC_STATE_STOPPING;
- wake_up(&the_lnet.ln_dc_waitq);
+
+ /* In the LNetNIInit() path we may be stopping discovery before it
+ * entered its work loop
+ */
+ if (!completion_done(&the_lnet.ln_started))
+ complete(&the_lnet.ln_started);
+ else
+ wake_up(&the_lnet.ln_dc_waitq);
wait_event(the_lnet.ln_dc_waitq,
the_lnet.ln_dc_state == LNET_DC_STATE_SHUTDOWN);
if (list_empty(&lpni->lpni_recovery) &&
atomic_read(&lpni->lpni_healthv) < LNET_MAX_HEALTH_VALUE) {
- CERROR("lpni %s added to recovery queue. Health = %d\n",
+ CDEBUG(D_NET, "lpni %s added to recovery queue. Health = %d\n",
libcfs_nid2str(lpni->lpni_nid),
atomic_read(&lpni->lpni_healthv));
list_add_tail(&lpni->lpni_recovery, &the_lnet.ln_mt_peerNIRecovq);
git://git.whamcloud.com / fs / lustre-release.git / blobdiff