Log running tasks in EsqlDisruptionIT (#108440) (#108467)

This PR logs tasks that are running after the disruption is cleared, allowing us to investigate why the disruption tests failed in #107347. Relates #107347
elastic · May 9, 2024 · 1d99311 · 1d99311
1 parent ee58956
commit 1d99311
Show file tree

Hide file tree

Showing 2 changed files with 17 additions and 1 deletion.
diff --git a/...n/esql/src/internalClusterTest/java/org/elasticsearch/xpack/esql/action/EsqlActionIT.java b/...n/esql/src/internalClusterTest/java/org/elasticsearch/xpack/esql/action/EsqlActionIT.java
@@ -121,7 +121,6 @@ public void testRow() {
         }
     }
 
-    @AwaitsFix(bugUrl = "https://github.com/elastic/elasticsearch/issues/107347")
     public void testFromStatsGroupingAvgWithSort() {
         testFromStatsGroupingAvgImpl("from test | stats avg(count) by data | sort data | limit 2", "data", "avg(count)");
     }

diff --git a/...ql/src/internalClusterTest/java/org/elasticsearch/xpack/esql/action/EsqlDisruptionIT.java b/...ql/src/internalClusterTest/java/org/elasticsearch/xpack/esql/action/EsqlDisruptionIT.java
@@ -8,12 +8,14 @@
 package org.elasticsearch.xpack.esql.action;
 
 import org.elasticsearch.action.ActionFuture;
+import org.elasticsearch.action.admin.cluster.node.tasks.list.TransportListTasksAction;
 import org.elasticsearch.cluster.coordination.Coordinator;
 import org.elasticsearch.cluster.coordination.FollowersChecker;
 import org.elasticsearch.cluster.coordination.LeaderChecker;
 import org.elasticsearch.common.settings.Settings;
 import org.elasticsearch.compute.operator.exchange.ExchangeService;
 import org.elasticsearch.core.TimeValue;
+import org.elasticsearch.health.node.selection.HealthNode;
 import org.elasticsearch.plugins.Plugin;
 import org.elasticsearch.test.ESIntegTestCase;
 import org.elasticsearch.test.disruption.NetworkDisruption;
@@ -91,6 +93,21 @@ private EsqlQueryResponse runQueryWithDisruption(EsqlQueryRequest request) {
         try {
             return future.actionGet(2, TimeUnit.MINUTES);
         } catch (Exception e) {
+            logger.info(
+                "running tasks: {}",
+                client().admin()
+                    .cluster()
+                    .prepareListTasks()
+                    .get()
+                    .getTasks()
+                    .stream()
+                    .filter(
+                        // Skip the tasks we that'd get in the way while debugging
+                        t -> false == t.action().contains(TransportListTasksAction.TYPE.name())
+                            && false == t.action().contains(HealthNode.TASK_NAME)
+                    )
+                    .toList()
+            );
             assertTrue("request must be failed or completed after clearing disruption", future.isDone());
             ensureBlocksReleased();
             logger.info("--> failed to execute esql query with disruption; retrying...", e);