MODULE_PARM_DESC(lnet_recovery_interval,
"Interval to recover unhealthy interfaces in seconds");
+unsigned int lnet_recovery_limit;
+module_param(lnet_recovery_limit, uint, 0644);
+MODULE_PARM_DESC(lnet_recovery_limit,
+ "How long to attempt recovery of unhealthy peer interfaces in seconds. Set to 0 to allow indefinite recovery");
+
static int lnet_interfaces_max = LNET_INTERFACES_MAX_DEFAULT;
static int intf_max_set(const char *val, cfs_kernel_param_arg_t *kp);
MODULE_PARM_DESC(lnet_drop_asym_route,
"Set to 1 to drop asymmetrical route messages.");
-#define LNET_TRANSACTION_TIMEOUT_NO_HEALTH_DEFAULT 50
-#define LNET_TRANSACTION_TIMEOUT_HEALTH_DEFAULT 50
-
-unsigned lnet_transaction_timeout = LNET_TRANSACTION_TIMEOUT_HEALTH_DEFAULT;
+#define LNET_TRANSACTION_TIMEOUT_DEFAULT 50
+unsigned int lnet_transaction_timeout = LNET_TRANSACTION_TIMEOUT_DEFAULT;
static int transaction_to_set(const char *val, cfs_kernel_param_arg_t *kp);
#ifdef HAVE_KERNEL_PARAM_OPS
static struct kernel_param_ops param_ops_transaction_timeout = {
MODULE_PARM_DESC(lnet_transaction_timeout,
"Maximum number of seconds to wait for a peer response.");
-#define LNET_RETRY_COUNT_HEALTH_DEFAULT 2
-unsigned lnet_retry_count = LNET_RETRY_COUNT_HEALTH_DEFAULT;
+#define LNET_RETRY_COUNT_DEFAULT 2
+unsigned int lnet_retry_count = LNET_RETRY_COUNT_DEFAULT;
static int retry_count_set(const char *val, cfs_kernel_param_arg_t *kp);
#ifdef HAVE_KERNEL_PARAM_OPS
static struct kernel_param_ops param_ops_retry_count = {
MODULE_PARM_DESC(lnet_retry_count,
"Maximum number of times to retry transmitting a message");
+unsigned int lnet_response_tracking = 3;
+static int response_tracking_set(const char *val, cfs_kernel_param_arg_t *kp);
+
+#ifdef HAVE_KERNEL_PARAM_OPS
+static struct kernel_param_ops param_ops_response_tracking = {
+ .set = response_tracking_set,
+ .get = param_get_int,
+};
+
+#define param_check_response_tracking(name, p) \
+ __param_check(name, p, int)
+module_param(lnet_response_tracking, response_tracking, 0644);
+#else
+module_param_call(lnet_response_tracking, response_tracking_set, param_get_int,
+ &lnet_response_tracking, 0644);
+#endif
+MODULE_PARM_DESC(lnet_response_tracking,
+ "(0|1|2|3) LNet Internal Only|GET Reply only|PUT ACK only|Full Tracking (default)");
+
+#define LNET_LND_TIMEOUT_DEFAULT ((LNET_TRANSACTION_TIMEOUT_DEFAULT - 1) / \
+ (LNET_RETRY_COUNT_DEFAULT + 1))
+unsigned int lnet_lnd_timeout = LNET_LND_TIMEOUT_DEFAULT;
+static void lnet_set_lnd_timeout(void)
+{
+ lnet_lnd_timeout = (lnet_transaction_timeout - 1) /
+ (lnet_retry_count + 1);
+}
-unsigned lnet_lnd_timeout = LNET_LND_DEFAULT_TIMEOUT;
unsigned int lnet_current_net_count;
/*
return -EINVAL;
}
- /*
- * if we're turning on health then use the health timeout
- * defaults.
- */
- if (*sensitivity == 0 && value != 0) {
- lnet_transaction_timeout = LNET_TRANSACTION_TIMEOUT_HEALTH_DEFAULT;
- lnet_retry_count = LNET_RETRY_COUNT_HEALTH_DEFAULT;
- /*
- * if we're turning off health then use the no health timeout
- * default.
- */
- } else if (*sensitivity != 0 && value == 0) {
- lnet_transaction_timeout =
- LNET_TRANSACTION_TIMEOUT_NO_HEALTH_DEFAULT;
+ if (*sensitivity != 0 && value == 0 && lnet_retry_count != 0) {
lnet_retry_count = 0;
+ lnet_set_lnd_timeout();
}
*sensitivity = value;
discovery_set(const char *val, cfs_kernel_param_arg_t *kp)
{
int rc;
- unsigned *discovery = (unsigned *)kp->arg;
+ unsigned *discovery_off = (unsigned *)kp->arg;
unsigned long value;
struct lnet_ping_buffer *pbuf;
*/
mutex_lock(&the_lnet.ln_api_mutex);
- if (value == *discovery) {
+ if (value == *discovery_off) {
mutex_unlock(&the_lnet.ln_api_mutex);
return 0;
}
* updating the peers
*/
if (the_lnet.ln_state != LNET_STATE_RUNNING) {
- *discovery = value;
+ *discovery_off = value;
mutex_unlock(&the_lnet.ln_api_mutex);
return 0;
}
pbuf->pb_info.pi_features |= LNET_PING_FEAT_DISCOVERY;
lnet_net_unlock(LNET_LOCK_EX);
- /*
- * Always update the peers. This will result in a push to the
- * peers with the updated capabilities feature mask. The peer can
- * then take appropriate action to update its representation of
- * the node.
- *
- * If discovery is already off, turn it on first before pushing
- * the update. The discovery flag must be on before pushing.
- * otherwise if the flag is on and we're turning it off then push
- * first before turning the flag off. In the former case the flag
- * is being set twice, but I find it's better to do that rather
- * than have duplicate code in an if/else statement.
- */
- if (*discovery > 0 && value == 0)
- *discovery = value;
- lnet_push_update_to_peers(1);
- *discovery = value;
+ /* only send a push when we're turning off discovery */
+ if (*discovery_off <= 0 && value > 0)
+ lnet_push_update_to_peers(1);
+ *discovery_off = value;
mutex_unlock(&the_lnet.ln_api_mutex);
*/
mutex_lock(&the_lnet.ln_api_mutex);
- if (value < lnet_retry_count || value == 0) {
+ if (value <= lnet_retry_count || value == 0) {
mutex_unlock(&the_lnet.ln_api_mutex);
CERROR("Invalid value for lnet_transaction_timeout (%lu). "
"Has to be greater than lnet_retry_count (%u)\n",
}
*transaction_to = value;
- if (lnet_retry_count == 0)
- lnet_lnd_timeout = value;
- else
- lnet_lnd_timeout = value / lnet_retry_count;
+ /* Update the lnet_lnd_timeout now that we've modified the
+ * transaction timeout
+ */
+ lnet_set_lnd_timeout();
mutex_unlock(&the_lnet.ln_api_mutex);
*/
mutex_lock(&the_lnet.ln_api_mutex);
- if (lnet_health_sensitivity == 0) {
+ if (lnet_health_sensitivity == 0 && value > 0) {
mutex_unlock(&the_lnet.ln_api_mutex);
- CERROR("Can not set retry_count when health feature is turned off\n");
+ CERROR("Can not set lnet_retry_count when health feature is turned off\n");
return -EINVAL;
}
*retry_count = value;
- if (value == 0)
- lnet_lnd_timeout = lnet_transaction_timeout;
- else
- lnet_lnd_timeout = lnet_transaction_timeout / value;
+ /* Update the lnet_lnd_timeout now that we've modified the
+ * retry count
+ */
+ lnet_set_lnd_timeout();
mutex_unlock(&the_lnet.ln_api_mutex);
return 0;
}
+static int
+response_tracking_set(const char *val, cfs_kernel_param_arg_t *kp)
+{
+ int rc;
+ unsigned long new_value;
+
+ rc = kstrtoul(val, 0, &new_value);
+ if (rc) {
+ CERROR("Invalid value for 'lnet_response_tracking'\n");
+ return -EINVAL;
+ }
+
+ if (new_value < 0 || new_value > 3) {
+ CWARN("Invalid value (%lu) for 'lnet_response_tracking'\n",
+ new_value);
+ return -EINVAL;
+ }
+
+ lnet_response_tracking = new_value;
+
+ return 0;
+}
+
static const char *
lnet_get_routes(void)
{
}
EXPORT_SYMBOL(lnet_unregister_lnd);
-void
-lnet_counters_get_common(struct lnet_counters_common *common)
+static void
+lnet_counters_get_common_locked(struct lnet_counters_common *common)
{
struct lnet_counters *ctr;
int i;
+ /* FIXME !!! Their is no assert_lnet_net_locked() to ensure this
+ * actually called under the protection of the lnet_net_lock.
+ */
memset(common, 0, sizeof(*common));
- lnet_net_lock(LNET_LOCK_EX);
-
cfs_percpt_for_each(ctr, i, the_lnet.ln_counters) {
common->lcc_msgs_max += ctr->lct_common.lcc_msgs_max;
common->lcc_msgs_alloc += ctr->lct_common.lcc_msgs_alloc;
common->lcc_route_length += ctr->lct_common.lcc_route_length;
common->lcc_drop_length += ctr->lct_common.lcc_drop_length;
}
+}
+
+void
+lnet_counters_get_common(struct lnet_counters_common *common)
+{
+ lnet_net_lock(LNET_LOCK_EX);
+ lnet_counters_get_common_locked(common);
lnet_net_unlock(LNET_LOCK_EX);
}
EXPORT_SYMBOL(lnet_counters_get_common);
-void
+int
lnet_counters_get(struct lnet_counters *counters)
{
struct lnet_counters *ctr;
struct lnet_counters_health *health = &counters->lct_health;
- int i;
+ int i, rc = 0;
memset(counters, 0, sizeof(*counters));
- lnet_counters_get_common(&counters->lct_common);
-
lnet_net_lock(LNET_LOCK_EX);
+ if (the_lnet.ln_state != LNET_STATE_RUNNING)
+ GOTO(out_unlock, rc = -ENODEV);
+
+ lnet_counters_get_common_locked(&counters->lct_common);
+
cfs_percpt_for_each(ctr, i, the_lnet.ln_counters) {
health->lch_rst_alloc += ctr->lct_health.lch_rst_alloc;
health->lch_resend_count += ctr->lct_health.lch_resend_count;
health->lch_network_timeout_count +=
ctr->lct_health.lch_network_timeout_count;
}
+out_unlock:
lnet_net_unlock(LNET_LOCK_EX);
+ return rc;
}
EXPORT_SYMBOL(lnet_counters_get);
lnet_net_lock(LNET_LOCK_EX);
+ if (the_lnet.ln_state != LNET_STATE_RUNNING)
+ goto avoid_reset;
+
cfs_percpt_for_each(counters, i, the_lnet.ln_counters)
memset(counters, 0, sizeof(struct lnet_counters));
-
+avoid_reset:
lnet_net_unlock(LNET_LOCK_EX);
}
md.handler = the_lnet.ln_ping_target_handler;
md.user_ptr = *ppbuf;
- rc = LNetMDAttach(me, md, LNET_RETAIN, ping_mdh);
+ rc = LNetMDAttach(me, &md, LNET_RETAIN, ping_mdh);
if (rc != 0) {
CERROR("Can't attach ping target MD: %d\n", rc);
- goto fail_unlink_ping_me;
+ goto fail_decref_ping_buffer;
}
lnet_ping_buffer_addref(*ppbuf);
return 0;
-fail_unlink_ping_me:
- LNetMEUnlink(me);
fail_decref_ping_buffer:
LASSERT(atomic_read(&(*ppbuf)->pb_refcnt) == 1);
lnet_ping_buffer_decref(*ppbuf);
md.user_ptr = pbuf;
md.handler = the_lnet.ln_push_target_handler;
- rc = LNetMDAttach(me, md, LNET_UNLINK, mdhp);
+ rc = LNetMDAttach(me, &md, LNET_UNLINK, mdhp);
if (rc) {
CERROR("Can't attach push MD: %d\n", rc);
- LNetMEUnlink(me);
lnet_ping_buffer_decref(pbuf);
pbuf->pb_needs_post = true;
return rc;
}
if (!list_empty(&ni->ni_netlist)) {
+ /* Unlock mutex while waiting to allow other
+ * threads to read the LNet state and fall through
+ * to avoid deadlock
+ */
lnet_net_unlock(LNET_LOCK_EX);
+ mutex_unlock(&the_lnet.ln_api_mutex);
+
++i;
if ((i & (-i)) == i) {
CDEBUG(D_WARNING,
libcfs_nid2str(ni->ni_nid));
}
schedule_timeout_uninterruptible(cfs_time_seconds(1));
+
+ mutex_lock(&the_lnet.ln_api_mutex);
lnet_net_lock(LNET_LOCK_EX);
continue;
}
return rc;
}
+static void
+lnet_set_tune_defaults(struct lnet_ioctl_config_lnd_tunables *tun)
+{
+ if (tun) {
+ if (!tun->lt_cmn.lct_peer_timeout)
+ tun->lt_cmn.lct_peer_timeout = DEFAULT_PEER_TIMEOUT;
+ if (!tun->lt_cmn.lct_peer_tx_credits)
+ tun->lt_cmn.lct_peer_tx_credits = DEFAULT_PEER_CREDITS;
+ if (!tun->lt_cmn.lct_max_tx_credits)
+ tun->lt_cmn.lct_max_tx_credits = DEFAULT_CREDITS;
+ }
+}
+
static int lnet_handle_legacy_ip2nets(char *ip2nets,
struct lnet_ioctl_config_lnd_tunables *tun)
{
if (rc < 0)
return rc;
+ lnet_set_tune_defaults(tun);
+
mutex_lock(&the_lnet.ln_api_mutex);
while (!list_empty(&net_head)) {
net = list_entry(net_head.next, struct lnet_net, net_list);
if (!ni)
return -ENOMEM;
+ lnet_set_tune_defaults(tun);
+
mutex_lock(&the_lnet.ln_api_mutex);
rc = lnet_add_net_common(net, tun);
memset(&tun, 0, sizeof(tun));
tun.lt_cmn.lct_peer_timeout =
- conf->cfg_config_u.cfg_net.net_peer_timeout;
+ (!conf->cfg_config_u.cfg_net.net_peer_timeout) ? DEFAULT_PEER_TIMEOUT :
+ conf->cfg_config_u.cfg_net.net_peer_timeout;
tun.lt_cmn.lct_peer_tx_credits =
- conf->cfg_config_u.cfg_net.net_peer_tx_credits;
+ (!conf->cfg_config_u.cfg_net.net_peer_tx_credits) ? DEFAULT_PEER_CREDITS :
+ conf->cfg_config_u.cfg_net.net_peer_tx_credits;
tun.lt_cmn.lct_peer_rtr_credits =
conf->cfg_config_u.cfg_net.net_peer_rtr_credits;
tun.lt_cmn.lct_max_tx_credits =
- conf->cfg_config_u.cfg_net.net_max_tx_credits;
+ (!conf->cfg_config_u.cfg_net.net_max_tx_credits) ? DEFAULT_CREDITS :
+ conf->cfg_config_u.cfg_net.net_max_tx_credits;
rc = lnet_add_net_common(net, &tun);
return -EINVAL;
mutex_lock(&the_lnet.ln_api_mutex);
- lnet_counters_get(&lnet_stats->st_cntrs);
+ rc = lnet_counters_get(&lnet_stats->st_cntrs);
mutex_unlock(&the_lnet.ln_api_mutex);
- return 0;
+ return rc;
}
case IOC_LIBCFS_CONFIG_RTR:
init_completion(&pd.completion);
- rc = LNetMDBind(md, LNET_UNLINK, &pd.mdh);
+ rc = LNetMDBind(&md, LNET_UNLINK, &pd.mdh);
if (rc != 0) {
CERROR("Can't bind MD: %d\n", rc);
goto fail_ping_buffer_decref;