From a94d24ae5ad2f7a1695cf83c2ad191c456c7dab4 Mon Sep 17 00:00:00 2001
From: Armin Braun <me@obrown.io>
Date: Mon, 27 May 2019 13:57:17 +0200
Subject: [PATCH] Fix RareClusterStateIT (#42430) (#42580)

* It looks like we might be cancelling a previous publication instead of
the one triggered by the given request with a very low likelihood.
   * Fixed by adding a wait for no in-progress publications
   * Also added debug logging that would've identified this problem
* Closes #36813
---
 .../cluster/coordination/Coordinator.java              | 10 +++++++---
 .../cluster/coordination/RareClusterStateIT.java       |  4 ++++
 2 files changed, 11 insertions(+), 3 deletions(-)

diff --git a/server/src/main/java/org/elasticsearch/cluster/coordination/Coordinator.java b/server/src/main/java/org/elasticsearch/cluster/coordination/Coordinator.java
index e6acac17da9..af9a38bec49 100644
--- a/server/src/main/java/org/elasticsearch/cluster/coordination/Coordinator.java
+++ b/server/src/main/java/org/elasticsearch/cluster/coordination/Coordinator.java
@@ -1198,9 +1198,13 @@ public class Coordinator extends AbstractLifecycleComponent implements Discovery
      */
     boolean cancelCommittedPublication() {
         synchronized (mutex) {
-            if (currentPublication.isPresent() && currentPublication.get().isCommitted()) {
-                currentPublication.get().cancel("cancelCommittedPublication");
-                return true;
+            if (currentPublication.isPresent()) {
+                final CoordinatorPublication publication = currentPublication.get();
+                if (publication.isCommitted()) {
+                    publication.cancel("cancelCommittedPublication");
+                    logger.debug("Cancelled publication of [{}].", publication);
+                    return true;
+                }
             }
             return false;
         }
diff --git a/server/src/test/java/org/elasticsearch/cluster/coordination/RareClusterStateIT.java b/server/src/test/java/org/elasticsearch/cluster/coordination/RareClusterStateIT.java
index 4c0168c6e3a..614bede3288 100644
--- a/server/src/test/java/org/elasticsearch/cluster/coordination/RareClusterStateIT.java
+++ b/server/src/test/java/org/elasticsearch/cluster/coordination/RareClusterStateIT.java
@@ -141,6 +141,10 @@ public class RareClusterStateIT extends ESIntegTestCase {
 
     private <Req extends ActionRequest, Res extends ActionResponse> ActionFuture<Res> executeAndCancelCommittedPublication(
             ActionRequestBuilder<Req, Res> req) throws Exception {
+        // Wait for no publication in progress to not accidentally cancel a publication different from the one triggered by the given
+        // request.
+        assertBusy(
+            () -> assertFalse(((Coordinator) internalCluster().getCurrentMasterNodeInstance(Discovery.class)).publicationInProgress()));
         ActionFuture<Res> future = req.execute();
         assertBusy(
             () -> assertTrue(((Coordinator)internalCluster().getCurrentMasterNodeInstance(Discovery.class)).cancelCommittedPublication()));