From cab57464e17b9d21f37f7234bb3d54451a7829fc Mon Sep 17 00:00:00 2001 From: Amir Shehata Date: Wed, 27 Mar 2019 19:32:45 -0700 Subject: [PATCH] LU-11475 lnet: transfer routers When a primary NID of a peer is about to be deleted because it's being transfered to another peer, if that peer is a gateway then transfer all gateway properties to the new peer. Test-Parameters: forbuildonly Signed-off-by: Amir Shehata Change-Id: Ib475c389ca5630906416a5112b3088f6f5d03950 Reviewed-on: https://review.whamcloud.com/34539 Reviewed-by: Sebastien Buisson Reviewed-by: Olaf Weber Tested-by: Jenkins --- lnet/include/lnet/lib-lnet.h | 2 ++ lnet/lnet/peer.c | 12 ++++++++++++ lnet/lnet/router.c | 29 +++++++++++++++++++++++++++++ 3 files changed, 43 insertions(+) diff --git a/lnet/include/lnet/lib-lnet.h b/lnet/include/lnet/lib-lnet.h index 494325e..f1dbbff 100644 --- a/lnet/include/lnet/lib-lnet.h +++ b/lnet/include/lnet/lib-lnet.h @@ -602,6 +602,8 @@ 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); diff --git a/lnet/lnet/peer.c b/lnet/lnet/peer.c index 0ef30b5..73d86d5 100644 --- a/lnet/lnet/peer.c +++ b/lnet/lnet/peer.c @@ -1362,6 +1362,18 @@ lnet_peer_add_nid(struct lnet_peer *lp, lnet_nid_t nid, unsigned flags) } /* If this is the primary NID, destroy the peer. */ if (lnet_peer_ni_is_primary(lpni)) { + struct lnet_peer *rtr_lp = + lpni->lpni_peer_net->lpn_peer; + int rtr_refcount = rtr_lp->lp_rtr_refcount; + /* + * if we're trying to delete a router it means + * we're moving this peer NI to a new peer so must + * transfer router properties to the new peer + */ + if (rtr_refcount > 0) { + flags |= LNET_PEER_RTR_NI_FORCE_DEL; + lnet_rtr_transfer_to_peer(rtr_lp, lp); + } lnet_peer_del(lpni->lpni_peer_net->lpn_peer); lpni = lnet_peer_ni_alloc(nid); if (!lpni) { diff --git a/lnet/lnet/router.c b/lnet/lnet/router.c index 9ac6de1..0346cf0 100644 --- a/lnet/lnet/router.c +++ b/lnet/lnet/router.c @@ -141,6 +141,35 @@ rtr_sensitivity_set(const char *val, cfs_kernel_param_arg_t *kp) return 0; } +void +lnet_rtr_transfer_to_peer(struct lnet_peer *src, struct lnet_peer *target) +{ + struct lnet_route *route; + + lnet_net_lock(LNET_LOCK_EX); + target->lp_rtr_refcount += src->lp_rtr_refcount; + /* move the list of queued messages to the new peer */ + list_splice_init(&src->lp_rtrq, &target->lp_rtrq); + /* move all the routes that reference the peer */ + list_splice_init(&src->lp_routes, &target->lp_routes); + /* update all the routes to point to the new peer */ + list_for_each_entry(route, &target->lp_routes, lr_gwlist) + route->lr_gateway = target; + /* remove the old peer from the ln_routers list */ + list_del_init(&src->lp_rtr_list); + /* add the new peer to the ln_routers list */ + if (list_empty(&target->lp_rtr_list)) { + lnet_peer_addref_locked(target); + list_add_tail(&target->lp_rtr_list, &the_lnet.ln_routers); + } + /* reset the ref count on the old peer and decrement its ref count */ + src->lp_rtr_refcount = 0; + lnet_peer_decref_locked(src); + /* update the router version */ + the_lnet.ln_routers_version++; + lnet_net_unlock(LNET_LOCK_EX); +} + int lnet_peers_start_down(void) { -- 1.8.3.1