X-Git-Url: https://git.whamcloud.com/?p=fs%2Flustre-release.git;a=blobdiff_plain;f=lnet%2Finclude%2Flnet%2Flib-lnet.h;h=52aeb92f74a3fde9239f6f66e3c87205e702487c;hp=359a2b4fe1182d342ee755657bd1bb5b007033e1;hb=1aae733c16161513b07d7f8cc046299e2de5aad3;hpb=ccabce23bd9e366c345c852f565766a799f61238;ds=sidebyside diff --git a/lnet/include/lnet/lib-lnet.h b/lnet/include/lnet/lib-lnet.h index 359a2b4..52aeb92 100644 --- a/lnet/include/lnet/lib-lnet.h +++ b/lnet/include/lnet/lib-lnet.h @@ -37,6 +37,9 @@ #ifndef __LNET_LIB_LNET_H__ #define __LNET_LIB_LNET_H__ +/* LNET has 0xeXXX */ +#define CFS_FAIL_PTLRPC_OST_BULK_CB2 0xe000 + #ifndef __KERNEL__ # error This include is only for kernel use. #endif @@ -75,17 +78,22 @@ extern struct lnet the_lnet; /* THE network */ /* default timeout */ #define DEFAULT_PEER_TIMEOUT 180 +#define LNET_LND_DEFAULT_TIMEOUT 5 + +#ifdef HAVE_KERN_SOCK_GETNAME_2ARGS +#define lnet_kernel_getpeername(sock, addr, addrlen) \ + kernel_getpeername(sock, addr) +#define lnet_kernel_getsockname(sock, addr, addrlen) \ + kernel_getsockname(sock, addr) +#else +#define lnet_kernel_getpeername(sock, addr, addrlen) \ + kernel_getpeername(sock, addr, addrlen) +#define lnet_kernel_getsockname(sock, addr, addrlen) \ + kernel_getsockname(sock, addr, addrlen) +#endif -static inline int lnet_is_route_alive(struct lnet_route *route) -{ - if (!route->lr_gateway->lpni_alive) - return 0; /* gateway is down */ - if ((route->lr_gateway->lpni_ping_feats & - LNET_PING_FEAT_NI_STATUS) == 0) - return 1; /* no NI status, assume it's alive */ - /* has NI status, check # down NIs */ - return route->lr_downis == 0; -} +bool lnet_is_route_alive(struct lnet_route *route); +bool lnet_is_gateway_alive(struct lnet_peer *gw); static inline int lnet_is_wire_handle_none(struct lnet_handle_wire *wh) { @@ -432,9 +440,9 @@ lnet_peer_ni_decref_locked(struct lnet_peer_ni *lp) } static inline int -lnet_isrouter(struct lnet_peer_ni *lp) +lnet_isrouter(struct lnet_peer_ni *lpni) { - return lp->lpni_rtr_refcount != 0; + return lpni->lpni_peer_net->lpn_peer->lp_rtr_refcount != 0; } static inline void @@ -489,6 +497,26 @@ lnet_msg_free(struct lnet_msg *msg) LIBCFS_FREE(msg, sizeof(*msg)); } +static inline struct lnet_rsp_tracker * +lnet_rspt_alloc(int cpt) +{ + struct lnet_rsp_tracker *rspt; + LIBCFS_ALLOC(rspt, sizeof(*rspt)); + lnet_net_lock(cpt); + the_lnet.ln_counters[cpt]->lct_health.lch_rst_alloc++; + lnet_net_unlock(cpt); + return rspt; +} + +static inline void +lnet_rspt_free(struct lnet_rsp_tracker *rspt, int cpt) +{ + LIBCFS_FREE(rspt, sizeof(*rspt)); + lnet_net_lock(cpt); + the_lnet.ln_counters[cpt]->lct_health.lch_rst_alloc--; + lnet_net_unlock(cpt); +} + void lnet_ni_free(struct lnet_ni *ni); void lnet_net_free(struct lnet_net *net); @@ -526,49 +554,46 @@ extern struct lnet_ni *lnet_nid2ni_locked(lnet_nid_t nid, int cpt); extern struct lnet_ni *lnet_nid2ni_addref(lnet_nid_t nid); extern struct lnet_ni *lnet_net2ni_locked(__u32 net, int cpt); extern struct lnet_ni *lnet_net2ni_addref(__u32 net); -bool lnet_is_ni_healthy_locked(struct lnet_ni *ni); struct lnet_net *lnet_get_net_locked(__u32 net_id); int lnet_lib_init(void); void lnet_lib_exit(void); +extern unsigned lnet_transaction_timeout; +extern unsigned lnet_retry_count; extern unsigned int lnet_numa_range; +extern unsigned int lnet_health_sensitivity; +extern unsigned int lnet_recovery_interval; extern unsigned int lnet_peer_discovery_disabled; +extern unsigned int lnet_drop_asym_route; +extern unsigned int router_sensitivity_percentage; +extern int alive_router_check_interval; extern int portal_rotor; -int lnet_notify(struct lnet_ni *ni, lnet_nid_t peer, int alive, - cfs_time_t when); +void lnet_mt_event_handler(struct lnet_event *event); + +int lnet_notify(struct lnet_ni *ni, lnet_nid_t peer, bool alive, bool reset, + time64_t when); void lnet_notify_locked(struct lnet_peer_ni *lp, int notifylnd, int alive, - cfs_time_t when); + time64_t when); int lnet_add_route(__u32 net, __u32 hops, lnet_nid_t gateway_nid, - unsigned int priority); -int lnet_check_routes(void); + __u32 priority, __u32 sensitivity); int lnet_del_route(__u32 net, lnet_nid_t gw_nid); void lnet_destroy_routes(void); int lnet_get_route(int idx, __u32 *net, __u32 *hops, - lnet_nid_t *gateway, __u32 *alive, __u32 *priority); + lnet_nid_t *gateway, __u32 *alive, __u32 *priority, + __u32 *sensitivity); int lnet_get_rtr_pool_cfg(int idx, struct lnet_ioctl_pool_cfg *pool_cfg); struct lnet_ni *lnet_get_next_ni_locked(struct lnet_net *mynet, struct lnet_ni *prev); struct lnet_ni *lnet_get_ni_idx_locked(int idx); -struct libcfs_ioctl_handler { - struct list_head item; - int (*handle_ioctl)(unsigned int cmd, struct libcfs_ioctl_hdr *hdr); -}; - -#define DECLARE_IOCTL_HANDLER(ident, func) \ - static struct libcfs_ioctl_handler ident = { \ - .item = LIST_HEAD_INIT(ident.item), \ - .handle_ioctl = func \ - } - -extern int libcfs_register_ioctl(struct libcfs_ioctl_handler *hand); -extern int libcfs_deregister_ioctl(struct libcfs_ioctl_handler *hand); extern int libcfs_ioctl_getdata(struct libcfs_ioctl_hdr **hdr_pp, struct libcfs_ioctl_hdr __user *uparam); extern int lnet_get_peer_list(__u32 *countp, __u32 *sizep, struct lnet_process_id __user *ids); +extern void lnet_peer_ni_set_healthv(lnet_nid_t nid, int value, bool all); +extern void lnet_peer_ni_add_to_recoveryq_locked(struct lnet_peer_ni *lpni); void lnet_router_debugfs_init(void); void lnet_router_debugfs_fini(void); @@ -578,6 +603,8 @@ int lnet_rtrpools_adjust(int tiny, int small, int large); int lnet_rtrpools_enable(void); void lnet_rtrpools_disable(void); void lnet_rtrpools_free(int keep_pools); +void lnet_rtr_transfer_to_peer(struct lnet_peer *src, + struct lnet_peer *target); struct lnet_remotenet *lnet_find_rnet_locked(__u32 net); int lnet_dyn_add_net(struct lnet_ioctl_config_data *conf); int lnet_dyn_del_net(__u32 net); @@ -588,10 +615,10 @@ struct lnet_net *lnet_get_net_locked(__u32 net_id); int lnet_islocalnid(lnet_nid_t nid); int lnet_islocalnet(__u32 net); +int lnet_islocalnet_locked(__u32 net); void lnet_msg_attach_md(struct lnet_msg *msg, struct lnet_libmd *md, unsigned int offset, unsigned int mlen); -void lnet_msg_detach_md(struct lnet_msg *msg, int status); void lnet_build_unlink_event(struct lnet_libmd *md, struct lnet_event *ev); void lnet_build_msg_event(struct lnet_msg *msg, enum lnet_event_kind ev_type); void lnet_msg_commit(struct lnet_msg *msg, int cpt); @@ -602,6 +629,8 @@ void lnet_prep_send(struct lnet_msg *msg, int type, struct lnet_process_id target, unsigned int offset, unsigned int len); int lnet_send(lnet_nid_t nid, struct lnet_msg *msg, lnet_nid_t rtr_nid); +int lnet_send_ping(lnet_nid_t dest_nid, struct lnet_handle_md *mdh, int nnis, + void *user_ptr, struct lnet_handle_eq eqh, bool recovery); void lnet_return_tx_credits_locked(struct lnet_msg *msg); void lnet_return_rx_credits_locked(struct lnet_msg *msg); void lnet_schedule_blocked_locked(struct lnet_rtrbufpool *rbp); @@ -676,8 +705,12 @@ struct lnet_msg *lnet_create_reply_msg(struct lnet_ni *ni, struct lnet_msg *get_msg); void lnet_set_reply_msg_len(struct lnet_ni *ni, struct lnet_msg *msg, unsigned int len); +void lnet_detach_rsp_tracker(struct lnet_libmd *md, int cpt); void lnet_finalize(struct lnet_msg *msg, int rc); +bool lnet_send_error_simulation(struct lnet_msg *msg, + enum lnet_msg_hstatus *hstatus); +void lnet_handle_remote_failure_locked(struct lnet_peer_ni *lpni); void lnet_drop_message(struct lnet_ni *ni, int cpt, void *private, unsigned int nob, __u32 msg_type); @@ -689,6 +722,7 @@ void lnet_msg_container_cleanup(struct lnet_msg_container *container); void lnet_msg_containers_destroy(void); int lnet_msg_containers_create(void); +char *lnet_health_error2str(enum lnet_msg_hstatus hstatus); char *lnet_msgtyp2str(int type); void lnet_print_hdr(struct lnet_hdr *hdr); int lnet_fail_nid(lnet_nid_t nid, unsigned int threshold); @@ -699,7 +733,8 @@ int lnet_fault_ctl(int cmd, struct libcfs_ioctl_data *data); int lnet_fault_init(void); void lnet_fault_fini(void); -bool lnet_drop_rule_match(struct lnet_hdr *hdr); +bool lnet_drop_rule_match(struct lnet_hdr *hdr, lnet_nid_t local_nid, + enum lnet_msg_hstatus *hstatus); int lnet_delay_rule_add(struct lnet_fault_attr *attr); int lnet_delay_rule_del(lnet_nid_t src, lnet_nid_t dst, bool shutdown); @@ -711,6 +746,7 @@ bool lnet_delay_rule_match_locked(struct lnet_hdr *hdr, struct lnet_msg *msg); /** @} lnet_fault_simulation */ +void lnet_counters_get_common(struct lnet_counters_common *common); void lnet_counters_get(struct lnet_counters *counters); void lnet_counters_reset(void); @@ -790,6 +826,7 @@ void lnet_md_deconstruct(struct lnet_libmd *lmd, struct lnet_md *umd); struct page *lnet_kvaddr_to_page(unsigned long vaddr); int lnet_cpt_of_md(struct lnet_libmd *md, unsigned int offset); +unsigned int lnet_get_lnd_timeout(void); void lnet_register_lnd(struct lnet_lnd *lnd); void lnet_unregister_lnd(struct lnet_lnd *lnd); @@ -803,9 +840,6 @@ int lnet_acceptor_port(void); int lnet_acceptor_start(void); void lnet_acceptor_stop(void); -int lnet_ipif_query(char *name, int *up, __u32 *ip, __u32 *mask); -int lnet_ipif_enumerate(char ***names); -void lnet_ipif_free_enumeration(char **names, int n); int lnet_sock_setbuf(struct socket *socket, int txbufsize, int rxbufsize); int lnet_sock_getbuf(struct socket *socket, int *txbufsize, int *rxbufsize); int lnet_sock_getaddr(struct socket *socket, bool remote, __u32 *ip, int *port); @@ -820,10 +854,16 @@ int lnet_sock_connect(struct socket **sockp, int *fatal, int lnet_peers_start_down(void); int lnet_peer_buffer_credits(struct lnet_net *net); +void lnet_consolidate_routes_locked(struct lnet_peer *orig_lp, + struct lnet_peer *new_lp); +void lnet_router_discovery_complete(struct lnet_peer *lp); -int lnet_router_checker_start(void); -void lnet_router_checker_stop(void); -void lnet_router_ni_update_locked(struct lnet_peer_ni *gw, __u32 net); +int lnet_monitor_thr_start(void); +void lnet_monitor_thr_stop(void); + +bool lnet_router_checker_active(void); +void lnet_check_routers(void); +void lnet_wait_router_start(void); void lnet_swap_pinginfo(struct lnet_ping_buffer *pbuf); int lnet_ping_info_validate(struct lnet_ping_info *pinfo); @@ -863,13 +903,18 @@ bool lnet_net_unique(__u32 net_id, struct list_head *nilist, bool lnet_ni_unique_net(struct list_head *nilist, char *iface); void lnet_incr_dlc_seq(void); __u32 lnet_get_dlc_seq_locked(void); +int lnet_get_net_count(void); +struct lnet_peer_net *lnet_get_next_peer_net_locked(struct lnet_peer *lp, + __u32 prev_lpn_id); struct lnet_peer_ni *lnet_get_next_peer_ni_locked(struct lnet_peer *peer, struct lnet_peer_net *peer_net, struct lnet_peer_ni *prev); struct lnet_peer_ni *lnet_nid2peerni_locked(lnet_nid_t nid, lnet_nid_t pref, int cpt); struct lnet_peer_ni *lnet_nid2peerni_ex(lnet_nid_t nid, int cpt); +struct lnet_peer_ni *lnet_peer_get_ni_locked(struct lnet_peer *lp, + lnet_nid_t nid); struct lnet_peer_ni *lnet_find_peer_ni_locked(lnet_nid_t nid); struct lnet_peer *lnet_find_peer(lnet_nid_t nid); void lnet_peer_net_added(struct lnet_net *net); @@ -895,53 +940,19 @@ int lnet_get_peer_ni_info(__u32 peer_index, __u64 *nid, __u32 *ni_peer_tx_credits, __u32 *peer_tx_credits, __u32 *peer_rtr_credits, __u32 *peer_min_rtr_credtis, __u32 *peer_tx_qnob); +int lnet_get_peer_ni_hstats(struct lnet_ioctl_peer_ni_hstats *stats); - -static inline bool -lnet_is_peer_ni_healthy_locked(struct lnet_peer_ni *lpni) -{ - return lpni->lpni_healthy; -} - -static inline void -lnet_set_peer_ni_health_locked(struct lnet_peer_ni *lpni, bool health) -{ - lpni->lpni_healthy = health; -} - -static inline bool -lnet_is_peer_net_healthy_locked(struct lnet_peer_net *peer_net) -{ - struct lnet_peer_ni *lpni; - - list_for_each_entry(lpni, &peer_net->lpn_peer_nis, - lpni_peer_nis) { - if (lnet_is_peer_ni_healthy_locked(lpni)) - return true; - } - - return false; -} - -static inline bool -lnet_is_peer_healthy_locked(struct lnet_peer *peer) +static inline struct lnet_peer_net * +lnet_find_peer_net_locked(struct lnet_peer *peer, __u32 net_id) { struct lnet_peer_net *peer_net; list_for_each_entry(peer_net, &peer->lp_peer_nets, lpn_peer_nets) { - if (lnet_is_peer_net_healthy_locked(peer_net)) - return true; + if (peer_net->lpn_net_id == net_id) + return peer_net; } - return false; -} - -static inline void -lnet_peer_set_alive(struct lnet_peer_ni *lp) -{ - lp->lpni_last_alive = lp->lpni_last_query = cfs_time_current(); - if (!lp->lpni_alive) - lnet_notify_locked(lp, 0, 1, lp->lpni_last_alive); + return NULL; } static inline bool @@ -967,6 +978,8 @@ lnet_peer_ni_is_primary(struct lnet_peer_ni *lpni) } bool lnet_peer_is_uptodate(struct lnet_peer *lp); +bool lnet_is_discovery_disabled(struct lnet_peer *lp); +bool lnet_peer_gw_discovery(struct lnet_peer *lp); static inline bool lnet_peer_needs_push(struct lnet_peer *lp) @@ -977,11 +990,42 @@ lnet_peer_needs_push(struct lnet_peer *lp) return true; if (lp->lp_state & LNET_PEER_NO_DISCOVERY) return false; + /* if discovery is not enabled then no need to push */ + if (lnet_peer_discovery_disabled) + return false; if (lp->lp_node_seqno < atomic_read(&the_lnet.ln_ping_target_seqno)) return true; return false; } +/* + * A peer is alive if it satisfies the following two conditions: + * 1. peer health >= LNET_MAX_HEALTH_VALUE * router_sensitivity_percentage + * 2. the cached NI status received when we discover the peer is UP + */ +static inline bool +lnet_is_peer_ni_alive(struct lnet_peer_ni *lpni) +{ + bool halive = false; + + halive = (atomic_read(&lpni->lpni_healthv) >= + (LNET_MAX_HEALTH_VALUE * router_sensitivity_percentage / 100)); + + return halive && lpni->lpni_ns_status == LNET_NI_STATUS_UP; +} + +static inline void +lnet_set_healthv(atomic_t *healthv, int value) +{ + atomic_set(healthv, value); +} + +static inline void +lnet_inc_healthv(atomic_t *healthv) +{ + atomic_add_unless(healthv, 1, LNET_MAX_HEALTH_VALUE); +} + void lnet_incr_stats(struct lnet_element_stats *stats, enum lnet_msg_type msg_type, enum lnet_stats_type stats_type);