diff --git a/lustre/ChangeLog b/lustre/ChangeLog index e9a30134da2aa771ddb896e549b9f88e26facb5d..d51c83dee22db9b58781a80c3165a0e809f30854 100644 --- a/lustre/ChangeLog +++ b/lustre/ChangeLog @@ -771,6 +771,14 @@ read status of conflictness, since we are guaranteed there are no conflicting locks in the rest of the list. +Severity : normal +Bugzilla : 14774 +Description: Time out and refuse to reconnect +Details : When the failover node is the primary node, it is possible + to have two identical connections in imp_conn_list. We must + compare not conn's pointers but NIDs, otherwise we can defeat + connection throttling. + -------------------------------------------------------------------------------- 2007-08-10 Cluster File Systems, Inc. <info@clusterfs.com> diff --git a/lustre/ptlrpc/import.c b/lustre/ptlrpc/import.c index 5082bc5b60c4ec69a760fc381b4afaa932fb4d5a..1dfd0a578b69023536384dd06ba56b03e888a360 100644 --- a/lustre/ptlrpc/import.c +++ b/lustre/ptlrpc/import.c @@ -536,7 +536,12 @@ static void ptlrpc_maybe_ping_import_soon(struct obd_import *imp) struct obd_import_conn, oic_item); - if (imp->imp_conn_current != imp_conn) { + /* XXX: When the failover node is the primary node, it is possible + * to have two identical connections in imp_conn_list. We must + * compare not conn's pointers but NIDs, otherwise we can defeat + * connection throttling. (See bug 14774.) */ + if (imp->imp_conn_current->oic_conn->c_self != + imp_conn->oic_conn->c_self) { ptlrpc_ping_import_soon(imp); wake_pinger = 1; }