LU-11514 lnet: separate ni state from recovery

[fs/lustre-release.git] / lnet / include / lnet / lib-types.h

diff --git a/lnet/include/lnet/lib-types.h b/lnet/include/lnet/lib-types.h
index fdb1784..bd1df1e 100644 (file)
--- a/lnet/include/lnet/lib-types.h
+++ b/lnet/include/lnet/lib-types.h
@@ -75,7 +75,8 @@ enum lnet_msg_hstatus {
        LNET_MSG_STATUS_REMOTE_ERROR,
        LNET_MSG_STATUS_REMOTE_DROPPED,
        LNET_MSG_STATUS_REMOTE_TIMEOUT,
-       LNET_MSG_STATUS_NETWORK_TIMEOUT
+       LNET_MSG_STATUS_NETWORK_TIMEOUT,
+       LNET_MSG_STATUS_END,
 };
 
 struct lnet_rsp_tracker {
@@ -83,6 +84,8 @@ struct lnet_rsp_tracker {
        struct list_head rspt_on_list;
        /* cpt to lock */
        int rspt_cpt;
+       /* nid of next hop */
+       lnet_nid_t rspt_next_hop_nid;
        /* deadline of the REPLY/ACK */
        ktime_t rspt_deadline;
        /* parent MD */
@@ -322,11 +325,17 @@ enum lnet_net_state {
        LNET_NET_STATE_DELETING
 };
 
-#define LNET_NI_STATE_INIT             (1 << 0)
-#define LNET_NI_STATE_ACTIVE           (1 << 1)
-#define LNET_NI_STATE_FAILED           (1 << 2)
-#define LNET_NI_STATE_RECOVERY_PENDING (1 << 3)
-#define LNET_NI_STATE_DELETING         (1 << 4)
+enum lnet_ni_state {
+       /* initial state when NI is created */
+       LNET_NI_STATE_INIT = 0,
+       /* set when NI is brought up */
+       LNET_NI_STATE_ACTIVE,
+       /* set when NI is being shutdown */
+       LNET_NI_STATE_DELETING,
+};
+
+#define LNET_NI_RECOVERY_PENDING       BIT(0)
+#define LNET_NI_RECOVERY_FAILED                BIT(1)
 
 enum lnet_stats_type {
        LNET_STATS_TYPE_SEND = 0,
@@ -348,6 +357,22 @@ struct lnet_element_stats {
        struct lnet_comm_count el_drop_stats;
 };
 
+struct lnet_health_local_stats {
+       atomic_t hlt_local_interrupt;
+       atomic_t hlt_local_dropped;
+       atomic_t hlt_local_aborted;
+       atomic_t hlt_local_no_route;
+       atomic_t hlt_local_timeout;
+       atomic_t hlt_local_error;
+};
+
+struct lnet_health_remote_stats {
+       atomic_t hlt_remote_dropped;
+       atomic_t hlt_remote_timeout;
+       atomic_t hlt_remote_error;
+       atomic_t hlt_network_timeout;
+};
+
 struct lnet_net {
        /* chain on the ln_nets */
        struct list_head        net_list;
@@ -396,9 +421,6 @@ struct lnet_ni {
        /* chain on the lnet_net structure */
        struct list_head        ni_netlist;
 
-       /* chain on net_ni_cpt */
-       struct list_head        ni_cptlist;
-
        /* chain on the recovery queue */
        struct list_head        ni_recovery;
 
@@ -437,8 +459,11 @@ struct lnet_ni {
        /* my health status */
        struct lnet_ni_status   *ni_status;
 
-       /* NI FSM */
-       __u32                   ni_state;
+       /* NI FSM. Protected by lnet_ni_lock() */
+       enum lnet_ni_state      ni_state;
+
+       /* Recovery state. Protected by lnet_ni_lock() */
+       __u32                   ni_recovery_state;
 
        /* per NI LND tunables */
        struct lnet_lnd_tunables ni_lnd_tunables;
@@ -448,6 +473,7 @@ struct lnet_ni {
 
        /* NI statistics */
        struct lnet_element_stats ni_stats;
+       struct lnet_health_local_stats ni_hstats;
 
        /* physical device CPT */
        int                     ni_dev_cpt;
@@ -530,6 +556,7 @@ struct lnet_peer_ni {
        struct lnet_peer_net    *lpni_peer_net;
        /* statistics kept on each peer NI */
        struct lnet_element_stats lpni_stats;
+       struct lnet_health_remote_stats lpni_hstats;
        /* spin lock protecting credits and lpni_txq / lpni_rtrq */
        spinlock_t              lpni_lock;
        /* # tx credits available */
@@ -605,8 +632,10 @@ struct lnet_peer_ni {
 #define LNET_PEER_NI_NON_MR_PREF       (1 << 0)
 /* peer is being recovered. */
 #define LNET_PEER_NI_RECOVERY_PENDING  (1 << 1)
+/* recovery ping failed */
+#define LNET_PEER_NI_RECOVERY_FAILED   (1 << 2)
 /* peer is being deleted */
-#define LNET_PEER_NI_DELETING          (1 << 2)
+#define LNET_PEER_NI_DELETING          (1 << 3)
 
 struct lnet_peer {
        /* chain on pt_peer_list */