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_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_HEALTH_DEFAULT - 1) / \
- (LNET_RETRY_COUNT_HEALTH_DEFAULT + 1))
+#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)
{
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;
- lnet_set_lnd_timeout();
- /*
- * 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();
}
*/
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",
*/
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;
}
}
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);
}
}
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 -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:
git://git.whamcloud.com / fs / lustre-release.git / blobdiff