/*
* lnet_health_sensitivity determines by how much we decrement the health
- * value on sending error. The value defaults to 0, which means health
- * checking is turned off by default.
+ * value on sending error. The value defaults to 100, which means health
+ * interface health is decremented by 100 points every failure.
*/
-unsigned int lnet_health_sensitivity = 0;
+unsigned int lnet_health_sensitivity = 100;
static int sensitivity_set(const char *val, cfs_kernel_param_arg_t *kp);
#ifdef HAVE_KERNEL_PARAM_OPS
static struct kernel_param_ops param_ops_health_sensitivity = {
MODULE_PARM_DESC(lnet_drop_asym_route,
"Set to 1 to drop asymmetrical route messages.");
-unsigned lnet_transaction_timeout = 50;
+#define LNET_TRANSACTION_TIMEOUT_NO_HEALTH_DEFAULT 50
+#define LNET_TRANSACTION_TIMEOUT_HEALTH_DEFAULT 10
+
+unsigned lnet_transaction_timeout = LNET_TRANSACTION_TIMEOUT_HEALTH_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.");
-unsigned lnet_retry_count = 0;
+#define LNET_RETRY_COUNT_HEALTH_DEFAULT 3
+unsigned lnet_retry_count = LNET_RETRY_COUNT_HEALTH_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 = {
unsigned lnet_lnd_timeout = LNET_LND_DEFAULT_TIMEOUT;
+unsigned int lnet_current_net_count;
/*
* This sequence number keeps track of how many times DLC was used to
*/
mutex_lock(&the_lnet.ln_api_mutex);
- if (the_lnet.ln_state != LNET_STATE_RUNNING) {
- mutex_unlock(&the_lnet.ln_api_mutex);
- return 0;
- }
-
if (value > LNET_MAX_HEALTH_VALUE) {
mutex_unlock(&the_lnet.ln_api_mutex);
CERROR("Invalid health value. Maximum: %d value = %lu\n",
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;
+ lnet_retry_count = 0;
+ }
+
*sensitivity = value;
mutex_unlock(&the_lnet.ln_api_mutex);
*/
mutex_lock(&the_lnet.ln_api_mutex);
- if (the_lnet.ln_state != LNET_STATE_RUNNING) {
- mutex_unlock(&the_lnet.ln_api_mutex);
- return 0;
- }
-
*interval = value;
mutex_unlock(&the_lnet.ln_api_mutex);
*/
mutex_lock(&the_lnet.ln_api_mutex);
- if (the_lnet.ln_state != LNET_STATE_RUNNING) {
- mutex_unlock(&the_lnet.ln_api_mutex);
- return 0;
- }
-
if (value < lnet_retry_count || value == 0) {
mutex_unlock(&the_lnet.ln_api_mutex);
CERROR("Invalid value for lnet_transaction_timeout (%lu). "
*/
mutex_lock(&the_lnet.ln_api_mutex);
- if (the_lnet.ln_state != LNET_STATE_RUNNING) {
+ if (lnet_health_sensitivity == 0) {
mutex_unlock(&the_lnet.ln_api_mutex);
- return 0;
+ CERROR("Can not set retry_count when health feature is turned off\n");
+ return -EINVAL;
}
if (value > lnet_transaction_timeout) {
return -EINVAL;
}
- if (value == *retry_count) {
- mutex_unlock(&the_lnet.ln_api_mutex);
- return 0;
- }
-
*retry_count = value;
if (value == 0)
spin_lock_init(&the_lnet.ln_eq_wait_lock);
spin_lock_init(&the_lnet.ln_msg_resend_lock);
init_waitqueue_head(&the_lnet.ln_eq_waitq);
- init_waitqueue_head(&the_lnet.ln_mt_waitq);
+ init_completion(&the_lnet.ln_mt_wait_complete);
mutex_init(&the_lnet.ln_lnd_mutex);
}
-static void
-lnet_fini_locks(void)
-{
-}
-
struct kmem_cache *lnet_mes_cachep; /* MEs kmem_cache */
struct kmem_cache *lnet_small_mds_cachep; /* <= LNET_SMALL_MD_SIZE bytes
* MDs kmem_cache */
cfs_percpt_lock_free(the_lnet.ln_net_lock);
the_lnet.ln_net_lock = NULL;
}
-
- lnet_fini_locks();
}
static int
* with gcc version 3.3.3 20040412 (Red Hat Linux 3.3.3-7) */
/* Constants... */
- CLASSERT(LNET_PROTO_TCP_MAGIC == 0xeebc0ded);
- CLASSERT(LNET_PROTO_TCP_VERSION_MAJOR == 1);
- CLASSERT(LNET_PROTO_TCP_VERSION_MINOR == 0);
- CLASSERT(LNET_MSG_ACK == 0);
- CLASSERT(LNET_MSG_PUT == 1);
- CLASSERT(LNET_MSG_GET == 2);
- CLASSERT(LNET_MSG_REPLY == 3);
- CLASSERT(LNET_MSG_HELLO == 4);
+ BUILD_BUG_ON(LNET_PROTO_TCP_MAGIC != 0xeebc0ded);
+ BUILD_BUG_ON(LNET_PROTO_TCP_VERSION_MAJOR != 1);
+ BUILD_BUG_ON(LNET_PROTO_TCP_VERSION_MINOR != 0);
+ BUILD_BUG_ON(LNET_MSG_ACK != 0);
+ BUILD_BUG_ON(LNET_MSG_PUT != 1);
+ BUILD_BUG_ON(LNET_MSG_GET != 2);
+ BUILD_BUG_ON(LNET_MSG_REPLY != 3);
+ BUILD_BUG_ON(LNET_MSG_HELLO != 4);
/* Checks for struct lnet_handle_wire */
- CLASSERT((int)sizeof(struct lnet_handle_wire) == 16);
- CLASSERT((int)offsetof(struct lnet_handle_wire, wh_interface_cookie) == 0);
- CLASSERT((int)sizeof(((struct lnet_handle_wire *)0)->wh_interface_cookie) == 8);
- CLASSERT((int)offsetof(struct lnet_handle_wire, wh_object_cookie) == 8);
- CLASSERT((int)sizeof(((struct lnet_handle_wire *)0)->wh_object_cookie) == 8);
+ BUILD_BUG_ON((int)sizeof(struct lnet_handle_wire) != 16);
+ BUILD_BUG_ON((int)offsetof(struct lnet_handle_wire,
+ wh_interface_cookie) != 0);
+ BUILD_BUG_ON((int)sizeof(((struct lnet_handle_wire *)0)->wh_interface_cookie) != 8);
+ BUILD_BUG_ON((int)offsetof(struct lnet_handle_wire,
+ wh_object_cookie) != 8);
+ BUILD_BUG_ON((int)sizeof(((struct lnet_handle_wire *)0)->wh_object_cookie) != 8);
/* Checks for struct struct lnet_magicversion */
- CLASSERT((int)sizeof(struct lnet_magicversion) == 8);
- CLASSERT((int)offsetof(struct lnet_magicversion, magic) == 0);
- CLASSERT((int)sizeof(((struct lnet_magicversion *)0)->magic) == 4);
- CLASSERT((int)offsetof(struct lnet_magicversion, version_major) == 4);
- CLASSERT((int)sizeof(((struct lnet_magicversion *)0)->version_major) == 2);
- CLASSERT((int)offsetof(struct lnet_magicversion, version_minor) == 6);
- CLASSERT((int)sizeof(((struct lnet_magicversion *)0)->version_minor) == 2);
+ BUILD_BUG_ON((int)sizeof(struct lnet_magicversion) != 8);
+ BUILD_BUG_ON((int)offsetof(struct lnet_magicversion, magic) != 0);
+ BUILD_BUG_ON((int)sizeof(((struct lnet_magicversion *)0)->magic) != 4);
+ BUILD_BUG_ON((int)offsetof(struct lnet_magicversion, version_major) != 4);
+ BUILD_BUG_ON((int)sizeof(((struct lnet_magicversion *)0)->version_major) != 2);
+ BUILD_BUG_ON((int)offsetof(struct lnet_magicversion,
+ version_minor) != 6);
+ BUILD_BUG_ON((int)sizeof(((struct lnet_magicversion *)0)->version_minor) != 2);
/* Checks for struct struct lnet_hdr */
- CLASSERT((int)sizeof(struct lnet_hdr) == 72);
- CLASSERT((int)offsetof(struct lnet_hdr, dest_nid) == 0);
- CLASSERT((int)sizeof(((struct lnet_hdr *)0)->dest_nid) == 8);
- CLASSERT((int)offsetof(struct lnet_hdr, src_nid) == 8);
- CLASSERT((int)sizeof(((struct lnet_hdr *)0)->src_nid) == 8);
- CLASSERT((int)offsetof(struct lnet_hdr, dest_pid) == 16);
- CLASSERT((int)sizeof(((struct lnet_hdr *)0)->dest_pid) == 4);
- CLASSERT((int)offsetof(struct lnet_hdr, src_pid) == 20);
- CLASSERT((int)sizeof(((struct lnet_hdr *)0)->src_pid) == 4);
- CLASSERT((int)offsetof(struct lnet_hdr, type) == 24);
- CLASSERT((int)sizeof(((struct lnet_hdr *)0)->type) == 4);
- CLASSERT((int)offsetof(struct lnet_hdr, payload_length) == 28);
- CLASSERT((int)sizeof(((struct lnet_hdr *)0)->payload_length) == 4);
- CLASSERT((int)offsetof(struct lnet_hdr, msg) == 32);
- CLASSERT((int)sizeof(((struct lnet_hdr *)0)->msg) == 40);
+ BUILD_BUG_ON((int)sizeof(struct lnet_hdr) != 72);
+ BUILD_BUG_ON((int)offsetof(struct lnet_hdr, dest_nid) != 0);
+ BUILD_BUG_ON((int)sizeof(((struct lnet_hdr *)0)->dest_nid) != 8);
+ BUILD_BUG_ON((int)offsetof(struct lnet_hdr, src_nid) != 8);
+ BUILD_BUG_ON((int)sizeof(((struct lnet_hdr *)0)->src_nid) != 8);
+ BUILD_BUG_ON((int)offsetof(struct lnet_hdr, dest_pid) != 16);
+ BUILD_BUG_ON((int)sizeof(((struct lnet_hdr *)0)->dest_pid) != 4);
+ BUILD_BUG_ON((int)offsetof(struct lnet_hdr, src_pid) != 20);
+ BUILD_BUG_ON((int)sizeof(((struct lnet_hdr *)0)->src_pid) != 4);
+ BUILD_BUG_ON((int)offsetof(struct lnet_hdr, type) != 24);
+ BUILD_BUG_ON((int)sizeof(((struct lnet_hdr *)0)->type) != 4);
+ BUILD_BUG_ON((int)offsetof(struct lnet_hdr, payload_length) != 28);
+ BUILD_BUG_ON((int)sizeof(((struct lnet_hdr *)0)->payload_length) != 4);
+ BUILD_BUG_ON((int)offsetof(struct lnet_hdr, msg) != 32);
+ BUILD_BUG_ON((int)sizeof(((struct lnet_hdr *)0)->msg) != 40);
/* Ack */
- CLASSERT((int)offsetof(struct lnet_hdr, msg.ack.dst_wmd) == 32);
- CLASSERT((int)sizeof(((struct lnet_hdr *)0)->msg.ack.dst_wmd) == 16);
- CLASSERT((int)offsetof(struct lnet_hdr, msg.ack.match_bits) == 48);
- CLASSERT((int)sizeof(((struct lnet_hdr *)0)->msg.ack.match_bits) == 8);
- CLASSERT((int)offsetof(struct lnet_hdr, msg.ack.mlength) == 56);
- CLASSERT((int)sizeof(((struct lnet_hdr *)0)->msg.ack.mlength) == 4);
+ BUILD_BUG_ON((int)offsetof(struct lnet_hdr, msg.ack.dst_wmd) != 32);
+ BUILD_BUG_ON((int)sizeof(((struct lnet_hdr *)0)->msg.ack.dst_wmd) != 16);
+ BUILD_BUG_ON((int)offsetof(struct lnet_hdr, msg.ack.match_bits) != 48);
+ BUILD_BUG_ON((int)sizeof(((struct lnet_hdr *)0)->msg.ack.match_bits) != 8);
+ BUILD_BUG_ON((int)offsetof(struct lnet_hdr, msg.ack.mlength) != 56);
+ BUILD_BUG_ON((int)sizeof(((struct lnet_hdr *)0)->msg.ack.mlength) != 4);
/* Put */
- CLASSERT((int)offsetof(struct lnet_hdr, msg.put.ack_wmd) == 32);
- CLASSERT((int)sizeof(((struct lnet_hdr *)0)->msg.put.ack_wmd) == 16);
- CLASSERT((int)offsetof(struct lnet_hdr, msg.put.match_bits) == 48);
- CLASSERT((int)sizeof(((struct lnet_hdr *)0)->msg.put.match_bits) == 8);
- CLASSERT((int)offsetof(struct lnet_hdr, msg.put.hdr_data) == 56);
- CLASSERT((int)sizeof(((struct lnet_hdr *)0)->msg.put.hdr_data) == 8);
- CLASSERT((int)offsetof(struct lnet_hdr, msg.put.ptl_index) == 64);
- CLASSERT((int)sizeof(((struct lnet_hdr *)0)->msg.put.ptl_index) == 4);
- CLASSERT((int)offsetof(struct lnet_hdr, msg.put.offset) == 68);
- CLASSERT((int)sizeof(((struct lnet_hdr *)0)->msg.put.offset) == 4);
+ BUILD_BUG_ON((int)offsetof(struct lnet_hdr, msg.put.ack_wmd) != 32);
+ BUILD_BUG_ON((int)sizeof(((struct lnet_hdr *)0)->msg.put.ack_wmd) != 16);
+ BUILD_BUG_ON((int)offsetof(struct lnet_hdr, msg.put.match_bits) != 48);
+ BUILD_BUG_ON((int)sizeof(((struct lnet_hdr *)0)->msg.put.match_bits) != 8);
+ BUILD_BUG_ON((int)offsetof(struct lnet_hdr, msg.put.hdr_data) != 56);
+ BUILD_BUG_ON((int)sizeof(((struct lnet_hdr *)0)->msg.put.hdr_data) != 8);
+ BUILD_BUG_ON((int)offsetof(struct lnet_hdr, msg.put.ptl_index) != 64);
+ BUILD_BUG_ON((int)sizeof(((struct lnet_hdr *)0)->msg.put.ptl_index) != 4);
+ BUILD_BUG_ON((int)offsetof(struct lnet_hdr, msg.put.offset) != 68);
+ BUILD_BUG_ON((int)sizeof(((struct lnet_hdr *)0)->msg.put.offset) != 4);
/* Get */
- CLASSERT((int)offsetof(struct lnet_hdr, msg.get.return_wmd) == 32);
- CLASSERT((int)sizeof(((struct lnet_hdr *)0)->msg.get.return_wmd) == 16);
- CLASSERT((int)offsetof(struct lnet_hdr, msg.get.match_bits) == 48);
- CLASSERT((int)sizeof(((struct lnet_hdr *)0)->msg.get.match_bits) == 8);
- CLASSERT((int)offsetof(struct lnet_hdr, msg.get.ptl_index) == 56);
- CLASSERT((int)sizeof(((struct lnet_hdr *)0)->msg.get.ptl_index) == 4);
- CLASSERT((int)offsetof(struct lnet_hdr, msg.get.src_offset) == 60);
- CLASSERT((int)sizeof(((struct lnet_hdr *)0)->msg.get.src_offset) == 4);
- CLASSERT((int)offsetof(struct lnet_hdr, msg.get.sink_length) == 64);
- CLASSERT((int)sizeof(((struct lnet_hdr *)0)->msg.get.sink_length) == 4);
+ BUILD_BUG_ON((int)offsetof(struct lnet_hdr, msg.get.return_wmd) != 32);
+ BUILD_BUG_ON((int)sizeof(((struct lnet_hdr *)0)->msg.get.return_wmd) != 16);
+ BUILD_BUG_ON((int)offsetof(struct lnet_hdr, msg.get.match_bits) != 48);
+ BUILD_BUG_ON((int)sizeof(((struct lnet_hdr *)0)->msg.get.match_bits) != 8);
+ BUILD_BUG_ON((int)offsetof(struct lnet_hdr, msg.get.ptl_index) != 56);
+ BUILD_BUG_ON((int)sizeof(((struct lnet_hdr *)0)->msg.get.ptl_index) != 4);
+ BUILD_BUG_ON((int)offsetof(struct lnet_hdr, msg.get.src_offset) != 60);
+ BUILD_BUG_ON((int)sizeof(((struct lnet_hdr *)0)->msg.get.src_offset) != 4);
+ BUILD_BUG_ON((int)offsetof(struct lnet_hdr, msg.get.sink_length) != 64);
+ BUILD_BUG_ON((int)sizeof(((struct lnet_hdr *)0)->msg.get.sink_length) != 4);
/* Reply */
- CLASSERT((int)offsetof(struct lnet_hdr, msg.reply.dst_wmd) == 32);
- CLASSERT((int)sizeof(((struct lnet_hdr *)0)->msg.reply.dst_wmd) == 16);
+ BUILD_BUG_ON((int)offsetof(struct lnet_hdr, msg.reply.dst_wmd) != 32);
+ BUILD_BUG_ON((int)sizeof(((struct lnet_hdr *)0)->msg.reply.dst_wmd) != 16);
/* Hello */
- CLASSERT((int)offsetof(struct lnet_hdr, msg.hello.incarnation) == 32);
- CLASSERT((int)sizeof(((struct lnet_hdr *)0)->msg.hello.incarnation) == 8);
- CLASSERT((int)offsetof(struct lnet_hdr, msg.hello.type) == 40);
- CLASSERT((int)sizeof(((struct lnet_hdr *)0)->msg.hello.type) == 4);
+ BUILD_BUG_ON((int)offsetof(struct lnet_hdr, msg.hello.incarnation) != 32);
+ BUILD_BUG_ON((int)sizeof(((struct lnet_hdr *)0)->msg.hello.incarnation) != 8);
+ BUILD_BUG_ON((int)offsetof(struct lnet_hdr, msg.hello.type) != 40);
+ BUILD_BUG_ON((int)sizeof(((struct lnet_hdr *)0)->msg.hello.type) != 4);
/* Checks for struct lnet_ni_status and related constants */
- CLASSERT(LNET_NI_STATUS_INVALID == 0x00000000);
- CLASSERT(LNET_NI_STATUS_UP == 0x15aac0de);
- CLASSERT(LNET_NI_STATUS_DOWN == 0xdeadface);
+ BUILD_BUG_ON(LNET_NI_STATUS_INVALID != 0x00000000);
+ BUILD_BUG_ON(LNET_NI_STATUS_UP != 0x15aac0de);
+ BUILD_BUG_ON(LNET_NI_STATUS_DOWN != 0xdeadface);
/* Checks for struct lnet_ni_status */
- CLASSERT((int)sizeof(struct lnet_ni_status) == 16);
- CLASSERT((int)offsetof(struct lnet_ni_status, ns_nid) == 0);
- CLASSERT((int)sizeof(((struct lnet_ni_status *)0)->ns_nid) == 8);
- CLASSERT((int)offsetof(struct lnet_ni_status, ns_status) == 8);
- CLASSERT((int)sizeof(((struct lnet_ni_status *)0)->ns_status) == 4);
- CLASSERT((int)offsetof(struct lnet_ni_status, ns_unused) == 12);
- CLASSERT((int)sizeof(((struct lnet_ni_status *)0)->ns_unused) == 4);
+ BUILD_BUG_ON((int)sizeof(struct lnet_ni_status) != 16);
+ BUILD_BUG_ON((int)offsetof(struct lnet_ni_status, ns_nid) != 0);
+ BUILD_BUG_ON((int)sizeof(((struct lnet_ni_status *)0)->ns_nid) != 8);
+ BUILD_BUG_ON((int)offsetof(struct lnet_ni_status, ns_status) != 8);
+ BUILD_BUG_ON((int)sizeof(((struct lnet_ni_status *)0)->ns_status) != 4);
+ BUILD_BUG_ON((int)offsetof(struct lnet_ni_status, ns_unused) != 12);
+ BUILD_BUG_ON((int)sizeof(((struct lnet_ni_status *)0)->ns_unused) != 4);
/* Checks for struct lnet_ping_info and related constants */
- CLASSERT(LNET_PROTO_PING_MAGIC == 0x70696E67);
- CLASSERT(LNET_PING_FEAT_INVAL == 0);
- CLASSERT(LNET_PING_FEAT_BASE == 1);
- CLASSERT(LNET_PING_FEAT_NI_STATUS == 2);
- CLASSERT(LNET_PING_FEAT_RTE_DISABLED == 4);
- CLASSERT(LNET_PING_FEAT_MULTI_RAIL == 8);
- CLASSERT(LNET_PING_FEAT_DISCOVERY == 16);
- CLASSERT(LNET_PING_FEAT_BITS == 31);
+ BUILD_BUG_ON(LNET_PROTO_PING_MAGIC != 0x70696E67);
+ BUILD_BUG_ON(LNET_PING_FEAT_INVAL != 0);
+ BUILD_BUG_ON(LNET_PING_FEAT_BASE != 1);
+ BUILD_BUG_ON(LNET_PING_FEAT_NI_STATUS != 2);
+ BUILD_BUG_ON(LNET_PING_FEAT_RTE_DISABLED != 4);
+ BUILD_BUG_ON(LNET_PING_FEAT_MULTI_RAIL != 8);
+ BUILD_BUG_ON(LNET_PING_FEAT_DISCOVERY != 16);
+ BUILD_BUG_ON(LNET_PING_FEAT_BITS != 31);
/* Checks for struct lnet_ping_info */
- CLASSERT((int)sizeof(struct lnet_ping_info) == 16);
- CLASSERT((int)offsetof(struct lnet_ping_info, pi_magic) == 0);
- CLASSERT((int)sizeof(((struct lnet_ping_info *)0)->pi_magic) == 4);
- CLASSERT((int)offsetof(struct lnet_ping_info, pi_features) == 4);
- CLASSERT((int)sizeof(((struct lnet_ping_info *)0)->pi_features) == 4);
- CLASSERT((int)offsetof(struct lnet_ping_info, pi_pid) == 8);
- CLASSERT((int)sizeof(((struct lnet_ping_info *)0)->pi_pid) == 4);
- CLASSERT((int)offsetof(struct lnet_ping_info, pi_nnis) == 12);
- CLASSERT((int)sizeof(((struct lnet_ping_info *)0)->pi_nnis) == 4);
- CLASSERT((int)offsetof(struct lnet_ping_info, pi_ni) == 16);
- CLASSERT((int)sizeof(((struct lnet_ping_info *)0)->pi_ni) == 0);
+ BUILD_BUG_ON((int)sizeof(struct lnet_ping_info) != 16);
+ BUILD_BUG_ON((int)offsetof(struct lnet_ping_info, pi_magic) != 0);
+ BUILD_BUG_ON((int)sizeof(((struct lnet_ping_info *)0)->pi_magic) != 4);
+ BUILD_BUG_ON((int)offsetof(struct lnet_ping_info, pi_features) != 4);
+ BUILD_BUG_ON((int)sizeof(((struct lnet_ping_info *)0)->pi_features) != 4);
+ BUILD_BUG_ON((int)offsetof(struct lnet_ping_info, pi_pid) != 8);
+ BUILD_BUG_ON((int)sizeof(((struct lnet_ping_info *)0)->pi_pid) != 4);
+ BUILD_BUG_ON((int)offsetof(struct lnet_ping_info, pi_nnis) != 12);
+ BUILD_BUG_ON((int)sizeof(((struct lnet_ping_info *)0)->pi_nnis) != 4);
+ BUILD_BUG_ON((int)offsetof(struct lnet_ping_info, pi_ni) != 16);
+ BUILD_BUG_ON((int)sizeof(((struct lnet_ping_info *)0)->pi_ni) != 0);
}
-static struct lnet_lnd *lnet_find_lnd_by_type(__u32 type)
+static const struct lnet_lnd *lnet_find_lnd_by_type(__u32 type)
{
- struct lnet_lnd *lnd;
- struct list_head *tmp;
+ const struct lnet_lnd *lnd;
/* holding lnd mutex */
- list_for_each(tmp, &the_lnet.ln_lnds) {
- lnd = list_entry(tmp, struct lnet_lnd, lnd_list);
+ if (type >= NUM_LNDS)
+ return NULL;
+ lnd = the_lnet.ln_lnds[type];
+ LASSERT(!lnd || lnd->lnd_type == type);
- if (lnd->lnd_type == type)
- return lnd;
- }
- return NULL;
+ return lnd;
}
unsigned int
EXPORT_SYMBOL(lnet_get_lnd_timeout);
void
-lnet_register_lnd(struct lnet_lnd *lnd)
+lnet_register_lnd(const struct lnet_lnd *lnd)
{
mutex_lock(&the_lnet.ln_lnd_mutex);
LASSERT(libcfs_isknown_lnd(lnd->lnd_type));
LASSERT(lnet_find_lnd_by_type(lnd->lnd_type) == NULL);
- list_add_tail(&lnd->lnd_list, &the_lnet.ln_lnds);
- lnd->lnd_refcount = 0;
+ the_lnet.ln_lnds[lnd->lnd_type] = lnd;
CDEBUG(D_NET, "%s LND registered\n", libcfs_lnd2str(lnd->lnd_type));
EXPORT_SYMBOL(lnet_register_lnd);
void
-lnet_unregister_lnd(struct lnet_lnd *lnd)
+lnet_unregister_lnd(const struct lnet_lnd *lnd)
{
mutex_lock(&the_lnet.ln_lnd_mutex);
LASSERT(lnet_find_lnd_by_type(lnd->lnd_type) == lnd);
- LASSERT(lnd->lnd_refcount == 0);
- list_del(&lnd->lnd_list);
+ the_lnet.ln_lnds[lnd->lnd_type] = NULL;
CDEBUG(D_NET, "%s LND unregistered\n", libcfs_lnd2str(lnd->lnd_type));
mutex_unlock(&the_lnet.ln_lnd_mutex);
list_add(&lh->lh_hash_chain, &rec->rec_lh_hash[hash]);
}
+struct list_head **
+lnet_create_array_of_queues(void)
+{
+ struct list_head **qs;
+ struct list_head *q;
+ int i;
+
+ qs = cfs_percpt_alloc(lnet_cpt_table(),
+ sizeof(struct list_head));
+ if (!qs) {
+ CERROR("Failed to allocate queues\n");
+ return NULL;
+ }
+
+ cfs_percpt_for_each(q, i, qs)
+ INIT_LIST_HEAD(q);
+
+ return qs;
+}
+
static int lnet_unprepare(void);
static int
INIT_LIST_HEAD(&the_lnet.ln_mt_localNIRecovq);
INIT_LIST_HEAD(&the_lnet.ln_mt_peerNIRecovq);
init_waitqueue_head(&the_lnet.ln_dc_waitq);
+ LNetInvalidateEQHandle(&the_lnet.ln_mt_eqh);
+ init_completion(&the_lnet.ln_started);
rc = lnet_descriptor_setup();
if (rc != 0)
goto failed;
}
+ the_lnet.ln_mt_zombie_rstqs = lnet_create_array_of_queues();
+ if (!the_lnet.ln_mt_zombie_rstqs) {
+ rc = -ENOMEM;
+ goto failed;
+ }
+
return 0;
failed:
static int
lnet_unprepare (void)
{
+ int rc;
+
/* NB no LNET_LOCK since this is the last reference. All LND instances
* have shut down already, so it is safe to unlink and free all
* descriptors, even those that appear committed to a network op (eg MD
LASSERT(list_empty(&the_lnet.ln_test_peers));
LASSERT(list_empty(&the_lnet.ln_nets));
+ if (the_lnet.ln_mt_zombie_rstqs) {
+ lnet_clean_zombie_rstqs();
+ the_lnet.ln_mt_zombie_rstqs = NULL;
+ }
+
+ if (!LNetEQHandleIsInvalid(the_lnet.ln_mt_eqh)) {
+ rc = LNetEQFree(the_lnet.ln_mt_eqh);
+ LNetInvalidateEQHandle(&the_lnet.ln_mt_eqh);
+ LASSERT(rc == 0);
+ }
+
lnet_portals_destroy();
if (the_lnet.ln_md_containers != NULL) {
EXPORT_SYMBOL(lnet_cpt_of_nid);
int
-lnet_islocalnet(__u32 net_id)
+lnet_islocalnet_locked(__u32 net_id)
{
struct lnet_net *net;
- int cpt;
- bool local;
-
- cpt = lnet_net_lock_current();
+ bool local;
net = lnet_get_net_locked(net_id);
local = net != NULL;
+ return local;
+}
+
+int
+lnet_islocalnet(__u32 net_id)
+{
+ int cpt;
+ bool local;
+
+ cpt = lnet_net_lock_current();
+
+ local = lnet_islocalnet_locked(net_id);
+
lnet_net_unlock(cpt);
return local;
}
int
+lnet_get_net_count(void)
+{
+ struct lnet_net *net;
+ int count = 0;
+
+ lnet_net_lock(0);
+
+ list_for_each_entry(net, &the_lnet.ln_nets, net_list) {
+ count++;
+ }
+
+ lnet_net_unlock(0);
+
+ return count;
+}
+
+void
+lnet_swap_pinginfo(struct lnet_ping_buffer *pbuf)
+{
+ struct lnet_ni_status *stat;
+ int nnis;
+ int i;
+
+ __swab32s(&pbuf->pb_info.pi_magic);
+ __swab32s(&pbuf->pb_info.pi_features);
+ __swab32s(&pbuf->pb_info.pi_pid);
+ __swab32s(&pbuf->pb_info.pi_nnis);
+ nnis = pbuf->pb_info.pi_nnis;
+ if (nnis > pbuf->pb_nnis)
+ nnis = pbuf->pb_nnis;
+ for (i = 0; i < nnis; i++) {
+ stat = &pbuf->pb_info.pi_ni[i];
+ __swab64s(&stat->ns_nid);
+ __swab32s(&stat->ns_status);
+ }
+}
+
+int
lnet_ping_info_validate(struct lnet_ping_info *pinfo)
{
if (!pinfo)
islo = ni->ni_net->net_lnd->lnd_type == LOLND;
LASSERT(!in_interrupt());
+ /* Holding the mutex makes it safe for lnd_shutdown
+ * to call module_put(). Module unload cannot finish
+ * until lnet_unregister_lnd() completes, and that
+ * requires the mutex.
+ */
+ mutex_lock(&the_lnet.ln_lnd_mutex);
(net->net_lnd->lnd_shutdown)(ni);
+ mutex_unlock(&the_lnet.ln_lnd_mutex);
if (!islo)
CDEBUG(D_LNI, "Removed LNI %s\n",
lnet_net_lock(LNET_LOCK_EX);
- net->net_state = LNET_NET_STATE_DELETING;
-
list_del_init(&net->net_list);
while (!list_empty(&net->net_ni_list)) {
/* Do peer table cleanup for this net */
lnet_peer_tables_cleanup(net);
- lnet_net_lock(LNET_LOCK_EX);
- /*
- * decrement ref count on lnd only when the entire network goes
- * away
- */
- net->net_lnd->lnd_refcount--;
-
- lnet_net_unlock(LNET_LOCK_EX);
-
lnet_net_free(net);
}
if (rc != 0) {
LCONSOLE_ERROR_MSG(0x105, "Error %d starting up LNI %s\n",
rc, libcfs_lnd2str(net->net_lnd->lnd_type));
- lnet_net_lock(LNET_LOCK_EX);
- net->net_lnd->lnd_refcount--;
- lnet_net_unlock(LNET_LOCK_EX);
goto failed0;
}
int rc;
int ni_count = 0;
__u32 lnd_type;
- struct lnet_lnd *lnd;
+ const struct lnet_lnd *lnd;
int peer_timeout =
net->net_tunables.lct_peer_timeout;
int maxtxcredits =
}
}
- lnet_net_lock(LNET_LOCK_EX);
- lnd->lnd_refcount++;
- lnet_net_unlock(LNET_LOCK_EX);
-
net->net_lnd = lnd;
mutex_unlock(&the_lnet.ln_lnd_mutex);
* up is actually unique. if it's not fail. */
if (!lnet_ni_unique_net(&net_l->net_ni_list,
ni->ni_interfaces[0])) {
- rc = -EINVAL;
+ rc = -EEXIST;
goto failed1;
}
rc = lnet_startup_lndni(ni, tun);
- LASSERT(ni->ni_net->net_tunables.lct_peer_timeout <= 0 ||
- ni->ni_net->net_lnd->lnd_query != NULL);
-
if (rc < 0)
goto failed1;
+ LASSERT(ni->ni_net->net_tunables.lct_peer_timeout <= 0 ||
+ ni->ni_net->net_lnd->lnd_query != NULL);
+
lnet_ni_addref(ni);
list_add_tail(&ni->ni_netlist, &local_ni_list);
*/
lnet_net_free(net);
} else {
- net->net_state = LNET_NET_STATE_ACTIVE;
/*
* restore tunables after it has been overwitten by the
* lnd
lnet_net_unlock(LNET_LOCK_EX);
}
+ /* update net count */
+ lnet_current_net_count = lnet_get_net_count();
+
return ni_count;
failed1:
}
the_lnet.ln_refcount = 0;
- LNetInvalidateEQHandle(&the_lnet.ln_rc_eqh);
- INIT_LIST_HEAD(&the_lnet.ln_lnds);
INIT_LIST_HEAD(&the_lnet.ln_net_zombie);
- INIT_LIST_HEAD(&the_lnet.ln_rcd_zombie);
INIT_LIST_HEAD(&the_lnet.ln_msg_resend);
- INIT_LIST_HEAD(&the_lnet.ln_rcd_deathrow);
/* The hash table size is the number of bits it takes to express the set
* ln_num_routes, minus 1 (better to under estimate than over so we
*
* \pre lnet_lib_init() called with success.
* \pre All LNet users called LNetNIFini() for matching LNetNIInit() calls.
+ *
+ * As this happens at module-unload, all lnds must already be unloaded,
+ * so they must already be unregistered.
*/
void lnet_lib_exit(void)
{
- LASSERT(the_lnet.ln_refcount == 0);
+ int i;
- while (!list_empty(&the_lnet.ln_lnds))
- lnet_unregister_lnd(list_entry(the_lnet.ln_lnds.next,
- struct lnet_lnd, lnd_list));
+ LASSERT(the_lnet.ln_refcount == 0);
+ lnet_unregister_lnd(&the_lolnd);
+ for (i = 0; i < NUM_LNDS; i++)
+ LASSERT(!the_lnet.ln_lnds[i]);
lnet_destroy_locks();
}
if (rc != 0)
goto err_shutdown_lndnis;
- rc = lnet_check_routes();
- if (rc != 0)
- goto err_destroy_routes;
-
rc = lnet_rtrpools_alloc(im_a_router);
if (rc != 0)
goto err_destroy_routes;
lnet_ping_target_update(pbuf, ping_mdh);
- rc = lnet_monitor_thr_start();
- if (rc != 0)
+ rc = LNetEQAlloc(0, lnet_mt_event_handler, &the_lnet.ln_mt_eqh);
+ if (rc != 0) {
+ CERROR("Can't allocate monitor thread EQ: %d\n", rc);
goto err_stop_ping;
+ }
rc = lnet_push_target_init();
if (rc != 0)
- goto err_stop_monitor_thr;
+ goto err_stop_ping;
rc = lnet_peer_discovery_start();
if (rc != 0)
goto err_destroy_push_target;
+ rc = lnet_monitor_thr_start();
+ if (rc != 0)
+ goto err_stop_discovery_thr;
+
lnet_fault_init();
lnet_router_debugfs_init();
mutex_unlock(&the_lnet.ln_api_mutex);
+ complete_all(&the_lnet.ln_started);
+
+ /* wait for all routers to start */
+ lnet_wait_router_start();
+
return 0;
+err_stop_discovery_thr:
+ lnet_peer_discovery_stop();
err_destroy_push_target:
lnet_push_target_fini();
-err_stop_monitor_thr:
- lnet_monitor_thr_stop();
err_stop_ping:
lnet_ping_target_fini();
err_acceptor_stop:
* \return always 0 for current implementation.
*/
int
-LNetNIFini()
+LNetNIFini(void)
{
mutex_lock(&the_lnet.ln_api_mutex);
lnet_fault_fini();
- lnet_router_debugfs_init();
+ lnet_router_debugfs_fini();
+ lnet_monitor_thr_stop();
lnet_peer_discovery_stop();
lnet_push_target_fini();
- lnet_monitor_thr_stop();
lnet_ping_target_fini();
/* Teardown fns that use my own API functions BEFORE here */
case IOC_LIBCFS_FAIL_NID:
return lnet_fail_nid(data->ioc_nid, data->ioc_count);
- case IOC_LIBCFS_ADD_ROUTE:
+ case IOC_LIBCFS_ADD_ROUTE: {
+ /* default router sensitivity to 1 */
+ unsigned int sensitivity = 1;
config = arg;
if (config->cfg_hdr.ioc_len < sizeof(*config))
return -EINVAL;
+ if (config->cfg_config_u.cfg_route.rtr_sensitivity) {
+ sensitivity =
+ config->cfg_config_u.cfg_route.rtr_sensitivity;
+ }
+
mutex_lock(&the_lnet.ln_api_mutex);
rc = lnet_add_route(config->cfg_net,
config->cfg_config_u.cfg_route.rtr_hop,
config->cfg_nid,
config->cfg_config_u.cfg_route.
- rtr_priority);
- if (rc == 0) {
- rc = lnet_check_routes();
- if (rc != 0)
- lnet_del_route(config->cfg_net,
- config->cfg_nid);
- }
+ rtr_priority, sensitivity);
mutex_unlock(&the_lnet.ln_api_mutex);
return rc;
+ }
case IOC_LIBCFS_DEL_ROUTE:
config = arg;
&config->cfg_nid,
&config->cfg_config_u.cfg_route.rtr_flags,
&config->cfg_config_u.cfg_route.
- rtr_priority);
+ rtr_priority,
+ &config->cfg_config_u.cfg_route.
+ rtr_sensitivity);
mutex_unlock(&the_lnet.ln_api_mutex);
return rc;
* that deadline to the wall clock.
*/
deadline += ktime_get_seconds();
- return lnet_notify(NULL, data->ioc_nid, data->ioc_flags,
+ return lnet_notify(NULL, data->ioc_nid, data->ioc_flags, false,
deadline);
}
return 0;
case IOC_LIBCFS_TESTPROTOCOMPAT:
- lnet_net_lock(LNET_LOCK_EX);
the_lnet.ln_testprotocompat = data->ioc_flags;
- lnet_net_unlock(LNET_LOCK_EX);
return 0;
case IOC_LIBCFS_LNET_FAULT:
/* If timeout is negative then set default of 3 minutes */
if (((s32)data->ioc_u32[1] <= 0) ||
data->ioc_u32[1] > (DEFAULT_PEER_TIMEOUT * MSEC_PER_SEC))
- timeout = msecs_to_jiffies(DEFAULT_PEER_TIMEOUT * MSEC_PER_SEC);
+ timeout = cfs_time_seconds(DEFAULT_PEER_TIMEOUT);
else
- timeout = msecs_to_jiffies(data->ioc_u32[1]);
+ timeout = nsecs_to_jiffies(data->ioc_u32[1] * NSEC_PER_MSEC);
rc = lnet_ping(id, timeout, data->ioc_pbuf1,
data->ioc_plen1 / sizeof(struct lnet_process_id));
/* If timeout is negative then set default of 3 minutes */
if (((s32)ping->op_param) <= 0 ||
ping->op_param > (DEFAULT_PEER_TIMEOUT * MSEC_PER_SEC))
- timeout = msecs_to_jiffies(DEFAULT_PEER_TIMEOUT * MSEC_PER_SEC);
+ timeout = cfs_time_seconds(DEFAULT_PEER_TIMEOUT);
else
- timeout = msecs_to_jiffies(ping->op_param);
+ timeout = nsecs_to_jiffies(ping->op_param * NSEC_PER_MSEC);
rc = lnet_ping(ping->ping_id, timeout,
ping->ping_buf,
int which;
int unlinked = 0;
int replied = 0;
- const signed long a_long_time = msecs_to_jiffies(60 * MSEC_PER_SEC);
+ const signed long a_long_time = cfs_time_seconds(60);
struct lnet_ping_buffer *pbuf;
struct lnet_process_id tmpid;
int i;
git://git.whamcloud.com / fs / lustre-release.git / blobdiff