summaryrefslogtreecommitdiff
path: root/src
diff options
context:
space:
mode:
authorSimon MacMullen <simon@rabbitmq.com>2014-10-09 16:09:48 +0100
committerSimon MacMullen <simon@rabbitmq.com>2014-10-09 16:09:48 +0100
commitc3ef17d9515ab2cd949f82cc2a6e0bb0662aea78 (patch)
treee6424c13c8cbf32ab92a37eb589831798255a3a0 /src
parentb0f2c4644801a1116fbe17adba57c65e87f863ea (diff)
downloadrabbitmq-server-git-c3ef17d9515ab2cd949f82cc2a6e0bb0662aea78.tar.gz
Slightly more accurate comment.
Diffstat (limited to 'src')
-rw-r--r--src/rabbit_node_monitor.erl9
1 files changed, 5 insertions, 4 deletions
diff --git a/src/rabbit_node_monitor.erl b/src/rabbit_node_monitor.erl
index fdda62528f..933beed77b 100644
--- a/src/rabbit_node_monitor.erl
+++ b/src/rabbit_node_monitor.erl
@@ -622,10 +622,11 @@ cast(Node, Msg) -> gen_server:cast({?SERVER, Node}, Msg).
%%--------------------------------------------------------------------
%% mnesia:system_info(db_nodes) (and hence
-%% rabbit_mnesia:cluster_nodes(running)) does not give reliable
-%% results when partitioned. So we have a small set of replacement
-%% functions here. "rabbit" in a function's name implies we test if
-%% the rabbit application is up, not just the node.
+%% rabbit_mnesia:cluster_nodes(running)) does not return all nodes
+%% when partitioned, just those that we are sharing Mnesia state
+%% with. So we have a small set of replacement functions
+%% here. "rabbit" in a function's name implies we test if the rabbit
+%% application is up, not just the node.
%% As we use these functions to decide what to do in pause_minority
%% state, they *must* be fast, even in the case where TCP connections