Myracle commented on code in PR #21347:
URL: https://github.com/apache/flink/pull/21347#discussion_r1039490326
##########
flink-runtime/src/main/java/org/apache/flink/runtime/dispatcher/Dispatcher.java:
##########
@@ -1016,6 +1034,47 @@ public CompletableFuture<CoordinationResponse>
deliverCoordinationRequestToCoord
operatorId, serializedRequest, timeout));
}
+ @Override
+ public CompletableFuture<Void> reportJobClientHeartbeat(JobID jobId, Time
timeout) {
+ if (!getJobManagerRunner(jobId).isPresent()) {
+ log.warn("Fail to find job {} for client.", jobId);
+ } else {
+ log.debug("Job {} receives client's heartbeat.", jobId);
+ markJobClientAliveness(jobId);
+ resetJobClientAlivenessCheck(jobId);
+ }
+ return CompletableFuture.completedFuture(null);
+ }
+
+ private void markJobClientAliveness(JobID jobId) {
+ if (jobClientAlivenessFutures.containsKey(jobId)) {
+ jobClientAlivenessFutures.get(jobId).complete(null);
+ }
+ }
+
+ private void resetJobClientAlivenessCheck(JobID jobId) {
+ CompletableFuture<Void> clientAlivenessFuture = new
CompletableFuture<>();
+ jobClientAlivenessFutures.put(jobId, clientAlivenessFuture);
+ FutureUtils.orTimeout(
+ clientAlivenessFuture,
+ jobClientHeartbeatTimeout,
+ TimeUnit.MILLISECONDS,
+ getMainThreadExecutor());
+ clientAlivenessFuture.whenComplete(
+ (t, throwable) -> {
+ if (throwable != null) {
+ if (throwable instanceof TimeoutException) {
+ log.warn(
+ "Haven't receive aliveness from job client
and cancel the job {}.",
+ jobId);
+ cancelJob(jobId, webTimeout);
Review Comment:
@xintongsong Agree with you and fixed.
--
This is an automated message from the Apache Git Service.
To respond to the message, please log on to GitHub and use the
URL above to go to the specific comment.
To unsubscribe, e-mail: [email protected]
For queries about this service, please contact Infrastructure at:
[email protected]
