Stop responding to ping requests before master abdication (#27329)

When the current master node is shutting down, it sends a leave request to the other nodes so that they can eagerly start a fresh master election. Unfortunately, it was still possible for the master node that was shutting down to respond to ping requests, possibly influencing the election decision as it still appeared as an active master in the ping responses. This commit ensures that UnicastZenPing does not respond to ping requests once it's been closed. ZenDiscovery.doStop() continues to ensure that the pinging component is first closed before it triggers a master election. Closes #27328
elastic · Nov 13, 2017 · 70b62a2 · 70b62a2
1 parent d4b7f7a
commit 70b62a2
Show file tree

Hide file tree

Showing 2 changed files with 15 additions and 1 deletion.
diff --git a/core/src/main/java/org/elasticsearch/discovery/zen/UnicastZenPing.java b/core/src/main/java/org/elasticsearch/discovery/zen/UnicastZenPing.java
@@ -575,7 +575,8 @@ public void handleResponse(UnicastPingResponse response) {
 
             @Override
             public void handleException(TransportException exp) {
-                if (exp instanceof ConnectTransportException || exp.getCause() instanceof ConnectTransportException) {
+                if (exp instanceof ConnectTransportException || exp.getCause() instanceof ConnectTransportException ||
+                    exp.getCause() instanceof AlreadyClosedException) {
                     // ok, not connected...
                     logger.trace((Supplier<?>) () -> new ParameterizedMessage("failed to connect to {}", node), exp);
                 } else if (closed == false) {
@@ -608,6 +609,9 @@ class UnicastPingRequestHandler implements TransportRequestHandler<UnicastPingRe
 
         @Override
         public void messageReceived(UnicastPingRequest request, TransportChannel channel) throws Exception {
+            if (closed) {
+                throw new AlreadyClosedException("node is shutting down");
+            }
             if (request.pingResponse.clusterName().equals(clusterName)) {
                 channel.sendResponse(handlePingRequest(request));
             } else {

diff --git a/core/src/test/java/org/elasticsearch/discovery/zen/UnicastZenPingTests.java b/core/src/test/java/org/elasticsearch/discovery/zen/UnicastZenPingTests.java
@@ -258,6 +258,16 @@ protected Version getVersion() {
         assertPingCount(handleD, handleA, 0);
         assertPingCount(handleD, handleB, 0);
         assertPingCount(handleD, handleC, 3);
+
+        zenPingC.close();
+        handleD.counters.clear();
+        logger.info("ping from UZP_D after closing UZP_C");
+        pingResponses = zenPingD.pingAndWait().toList();
+        // check that node does not respond to pings anymore after the ping service has been closed
+        assertThat(pingResponses.size(), equalTo(0));
+        assertPingCount(handleD, handleA, 0);
+        assertPingCount(handleD, handleB, 0);
+        assertPingCount(handleD, handleC, 3);
     }
 
     public void testUnknownHostNotCached() throws ExecutionException, InterruptedException {