lnet_nid_t msg_from;
__u32 msg_type;
+ /*
+ * hold parameters in case message is with held due
+ * to discovery
+ */
+ lnet_nid_t msg_src_nid_param;
+ lnet_nid_t msg_rtr_nid_param;
+
/* committed for sending */
unsigned int msg_tx_committed:1;
/* CPT # this message committed for sending */
LNET_NI_STATE_DELETING
};
+enum lnet_stats_type {
+ LNET_STATS_TYPE_SEND = 0,
+ LNET_STATS_TYPE_RECV,
+ LNET_STATS_TYPE_DROP
+};
+
+struct lnet_comm_count {
+ atomic_t co_get_count;
+ atomic_t co_put_count;
+ atomic_t co_reply_count;
+ atomic_t co_ack_count;
+ atomic_t co_hello_count;
+};
+
struct lnet_element_stats {
- atomic_t send_count;
- atomic_t recv_count;
- atomic_t drop_count;
+ struct lnet_comm_count el_send_stats;
+ struct lnet_comm_count el_recv_stats;
+ struct lnet_comm_count el_drop_stats;
};
struct lnet_net {
#define LNET_PING_BUFFER_LONI(PBUF) ((PBUF)->pb_info.pi_ni[0].ns_nid)
#define LNET_PING_BUFFER_SEQNO(PBUF) ((PBUF)->pb_info.pi_ni[0].ns_status)
+#define LNET_PING_INFO_TO_BUFFER(PINFO) \
+ container_of((PINFO), struct lnet_ping_buffer, pb_info)
/* router checker data, per router */
typedef struct lnet_rc_data {
/* list of peer nets */
struct list_head lp_peer_nets;
+ /* list of messages pending discovery*/
+ struct list_head lp_dc_pendq;
+
/* primary NID of the peer */
lnet_nid_t lp_primary_nid;
/* peer state flags */
unsigned lp_state;
+
+ /* buffer for data pushed by peer */
+ struct lnet_ping_buffer *lp_data;
+
+ /* MD handle for ping in progress */
+ lnet_handle_md_t lp_ping_mdh;
+
+ /* MD handle for push in progress */
+ lnet_handle_md_t lp_push_mdh;
+
+ /* number of NIDs for sizing push data */
+ int lp_data_nnis;
+
+ /* NI config sequence number of peer */
+ __u32 lp_peer_seqno;
+
+ /* Local NI config sequence number acked by peer */
+ __u32 lp_node_seqno;
+
+ /* Local NI config sequence number sent to peer */
+ __u32 lp_node_seqno_sent;
+
+ /* Ping error encountered during discovery. */
+ int lp_ping_error;
+
+ /* Push error encountered during discovery. */
+ int lp_push_error;
+
+ /* Error encountered during discovery. */
+ int lp_dc_error;
+
+ /* time it was put on the ln_dc_working queue */
+ time64_t lp_last_queued;
+
+ /* link on discovery-related lists */
+ struct list_head lp_dc_list;
+
+ /* tasks waiting on discovery of this peer */
+ wait_queue_head_t lp_dc_waitq;
};
-#define LNET_PEER_MULTI_RAIL (1 << 0)
-#define LNET_PEER_CONFIGURED (1 << 1)
+/*
+ * The status flags in lp_state. Their semantics have chosen so that
+ * lp_state can be zero-initialized.
+ *
+ * A peer is marked MULTI_RAIL in two cases: it was configured using DLC
+ * as multi-rail aware, or the LNET_PING_FEAT_MULTI_RAIL bit was set.
+ *
+ * A peer is marked NO_DISCOVERY if the LNET_PING_FEAT_DISCOVERY bit was
+ * NOT set when the peer was pinged by discovery.
+ */
+#define LNET_PEER_MULTI_RAIL (1 << 0) /* Multi-rail aware */
+#define LNET_PEER_NO_DISCOVERY (1 << 1) /* Peer disabled discovery */
+/*
+ * A peer is marked CONFIGURED if it was configured by DLC.
+ *
+ * In addition, a peer is marked DISCOVERED if it has fully passed
+ * through Peer Discovery.
+ *
+ * When Peer Discovery is disabled, the discovery thread will mark
+ * peers REDISCOVER to indicate that they should be re-examined if
+ * discovery is (re)enabled on the node.
+ *
+ * A peer that was created as the result of inbound traffic will not
+ * be marked at all.
+ */
+#define LNET_PEER_CONFIGURED (1 << 2) /* Configured via DLC */
+#define LNET_PEER_DISCOVERED (1 << 3) /* Peer was discovered */
+#define LNET_PEER_REDISCOVER (1 << 4) /* Discovery was disabled */
+/*
+ * A peer is marked DISCOVERING when discovery is in progress.
+ * The other flags below correspond to stages of discovery.
+ */
+#define LNET_PEER_DISCOVERING (1 << 5) /* Discovering */
+#define LNET_PEER_DATA_PRESENT (1 << 6) /* Remote peer data present */
+#define LNET_PEER_NIDS_UPTODATE (1 << 7) /* Remote peer info uptodate */
+#define LNET_PEER_PING_SENT (1 << 8) /* Waiting for REPLY to Ping */
+#define LNET_PEER_PUSH_SENT (1 << 9) /* Waiting for ACK of Push */
+#define LNET_PEER_PING_FAILED (1 << 10) /* Ping send failure */
+#define LNET_PEER_PUSH_FAILED (1 << 11) /* Push send failure */
+/*
+ * A ping can be forced as a way to fix up state, or as a manual
+ * intervention by an admin.
+ * A push can be forced in circumstances that would normally not
+ * allow for one to happen.
+ */
+#define LNET_PEER_FORCE_PING (1 << 12) /* Forced Ping */
+#define LNET_PEER_FORCE_PUSH (1 << 13) /* Forced Push */
struct lnet_peer_net {
/* chain on lp_peer_nets */
* pt_hash[...]
* pt_peer_list
* pt_peers
- * pt_peer_nnids
* protected by pt_zombie_lock:
* pt_zombie_list
* pt_zombies
struct list_head *pt_hash; /* NID->peer hash */
struct list_head pt_peer_list; /* peers */
int pt_peers; /* # peers */
- int pt_peer_nnids; /* # NIDS on listed peers */
struct list_head pt_zombie_list; /* zombie peer_ni */
int pt_zombies; /* # zombie peers_ni */
spinlock_t pt_zombie_lock; /* protect list and count */
#define LNET_CREDIT_OK 0
/** lnet message is waiting for credit */
#define LNET_CREDIT_WAIT 1
+/** lnet message is waiting for discovery */
+#define LNET_DC_WAIT 2
typedef struct lnet_rtrbufpool {
/* my free buffer pool */
void **msc_finalizers;
};
+/* Peer Discovery states */
+#define LNET_DC_STATE_SHUTDOWN 0 /* not started */
+#define LNET_DC_STATE_RUNNING 1 /* started up OK */
+#define LNET_DC_STATE_STOPPING 2 /* telling thread to stop */
+
/* Router Checker states */
#define LNET_RC_STATE_SHUTDOWN 0 /* not started */
#define LNET_RC_STATE_RUNNING 1 /* started up OK */
struct lnet_ping_buffer *ln_ping_target;
atomic_t ln_ping_target_seqno;
+ /*
+ * Push Target
+ *
+ * ln_push_nnis contains the desired size of the push target.
+ * The lnet_net_lock is used to handle update races. The old
+ * buffer may linger a while after it has been unlinked, in
+ * which case the event handler cleans up.
+ */
+ lnet_handle_eq_t ln_push_target_eq;
+ lnet_handle_md_t ln_push_target_md;
+ struct lnet_ping_buffer *ln_push_target;
+ int ln_push_target_nnis;
+
+ /* discovery event queue handle */
+ lnet_handle_eq_t ln_dc_eqh;
+ /* discovery requests */
+ struct list_head ln_dc_request;
+ /* discovery working list */
+ struct list_head ln_dc_working;
+ /* discovery expired list */
+ struct list_head ln_dc_expired;
+ /* discovery thread wait queue */
+ wait_queue_head_t ln_dc_waitq;
+ /* discovery startup/shutdown state */
+ int ln_dc_state;
+
/* router checker startup/shutdown state */
int ln_rc_state;
/* router checker's event queue */