i=liangzhen,i=maxim,b=16338:

-   fixed a connection reference count leak.

diff --git a/lnet/ChangeLog b/lnet/ChangeLog
index 7241c42..1b1c107 100644 (file)
--- a/lnet/ChangeLog
+++ b/lnet/ChangeLog
@@ -17,6 +17,13 @@ Bugzilla   :
 Description: 
 Details    : 
 
+Severity   : major
+Bugzilla   : 16338
+Description: Continuous recovery on 33 of 413 nodes after lustre oss failure
+Details    : Lost reference on conn prevents peer from being destroyed, which
+             could prevent new peer creation if peer count has reached upper
+            limit.
+
 Severity   : normal
 Bugzilla   : 16102
 Description: LNET Selftest results in Soft lockup on OSS CPU

diff --git a/lnet/klnds/viblnd/viblnd_cb.c b/lnet/klnds/viblnd/viblnd_cb.c
index 0c7e323..a9efca1 100644 (file)
--- a/lnet/klnds/viblnd/viblnd_cb.c
+++ b/lnet/klnds/viblnd/viblnd_cb.c
@@ -2614,6 +2614,7 @@ kibnal_recv_connreq(cm_cep_handle_t *cep, cm_request_data_t *cmreq)
         if (conn != NULL) {
                 LASSERT (rc != 0);
                 kibnal_connreq_done(conn, 0, rc);
+                kibnal_conn_decref(conn);
         } else {
                 cm_destroy_cep(cep);
         }