zentol closed pull request #7119: [FLINK-10907] Fix Flink JobManager metrics 
from getting stuck after a job recovery.
URL: https://github.com/apache/flink/pull/7119
 
 
   

This is a PR merged from a forked repository.
As GitHub hides the original diff on merge, it is displayed below for
the sake of provenance:

As this is a foreign pull request (from a fork), the diff is supplied
below (as it won't show otherwise due to GitHub magic):

diff --git 
a/flink-runtime/src/main/java/org/apache/flink/runtime/metrics/groups/JobManagerMetricGroup.java
 
b/flink-runtime/src/main/java/org/apache/flink/runtime/metrics/groups/JobManagerMetricGroup.java
index e09051d7160..f67b49d6745 100644
--- 
a/flink-runtime/src/main/java/org/apache/flink/runtime/metrics/groups/JobManagerMetricGroup.java
+++ 
b/flink-runtime/src/main/java/org/apache/flink/runtime/metrics/groups/JobManagerMetricGroup.java
@@ -61,16 +61,17 @@ public String hostname() {
        public JobManagerJobMetricGroup addJob(JobGraph job) {
                JobID jobId = job.getJobID();
                String jobName = job.getName();
-               // get or create a jobs metric group
-               JobManagerJobMetricGroup currentJobGroup;
                synchronized (this) {
                        if (!isClosed()) {
-                               currentJobGroup = jobs.get(jobId);
+                               JobManagerJobMetricGroup currentJobGroup = 
jobs.get(jobId);
 
-                               if (currentJobGroup == null || 
currentJobGroup.isClosed()) {
-                                       currentJobGroup = new 
JobManagerJobMetricGroup(registry, this, jobId, jobName);
-                                       jobs.put(jobId, currentJobGroup);
+                               if (currentJobGroup != null) {
+                                       currentJobGroup.close();
                                }
+
+                               currentJobGroup = new 
JobManagerJobMetricGroup(registry, this, jobId, jobName);
+                               jobs.put(jobId, currentJobGroup);
+
                                return currentJobGroup;
                        } else {
                                return null;
diff --git 
a/flink-runtime/src/test/java/org/apache/flink/runtime/metrics/groups/JobManagerGroupTest.java
 
b/flink-runtime/src/test/java/org/apache/flink/runtime/metrics/groups/JobManagerGroupTest.java
index cb5ec67c97c..146fb3b1f45 100644
--- 
a/flink-runtime/src/test/java/org/apache/flink/runtime/metrics/groups/JobManagerGroupTest.java
+++ 
b/flink-runtime/src/test/java/org/apache/flink/runtime/metrics/groups/JobManagerGroupTest.java
@@ -32,6 +32,7 @@
 
 import static org.junit.Assert.assertArrayEquals;
 import static org.junit.Assert.assertEquals;
+import static org.junit.Assert.assertNotEquals;
 import static org.junit.Assert.assertTrue;
 
 /**
@@ -58,13 +59,15 @@ public void addAndRemoveJobs() throws Exception {
                JobManagerJobMetricGroup jmJobGroup12 = group.addJob(new 
JobGraph(jid1, jobName1));
                JobManagerJobMetricGroup jmJobGroup21 = group.addJob(new 
JobGraph(jid2, jobName2));
 
-               assertEquals(jmJobGroup11, jmJobGroup12);
+               assertNotEquals(jmJobGroup11, jmJobGroup12);
+               assertTrue(jmJobGroup11.isClosed());
+               assertTrue(!jmJobGroup12.isClosed());
 
                assertEquals(2, group.numRegisteredJobMetricGroups());
 
                group.removeJob(jid1);
 
-               assertTrue(jmJobGroup11.isClosed());
+               assertTrue(jmJobGroup12.isClosed());
                assertEquals(1, group.numRegisteredJobMetricGroups());
 
                group.removeJob(jid2);


 

----------------------------------------------------------------
This is an automated message from the Apache Git Service.
To respond to the message, please log on GitHub and use the
URL above to go to the specific comment.
 
For queries about this service, please contact Infrastructure at:
[email protected]


With regards,
Apache Git Services

Reply via email to