afterincomparableyum commented on code in PR #3737:
URL: https://github.com/apache/celeborn/pull/3737#discussion_r3489414645
##########
worker/src/test/scala/org/apache/celeborn/service/deploy/MiniClusterFeature.scala:
##########
@@ -225,17 +236,30 @@ trait MiniClusterFeature extends Logging {
workerStarted = true
worker.initialize()
} catch {
+ case ie: InterruptedException =>
+
Utils.tryLogNonFatalError(worker.stop(CelebornExitKind.EXIT_IMMEDIATELY))
+ Utils.tryLogNonFatalError(worker.rpcEnv.shutdown())
+ Thread.currentThread().interrupt()
+ throw ie
case ex: Exception =>
- if (workers(i - 1) != null) {
- workers(i - 1).shutdownGracefully()
- }
+ Utils.tryLogNonFatalError(worker.exitImmediately())
+
Utils.tryLogNonFatalError(worker.stop(CelebornExitKind.EXIT_IMMEDIATELY))
+ Utils.tryLogNonFatalError(worker.rpcEnv.shutdown())
workerStarted = false
workerStartRetry += 1
logError(s"cannot start worker $i, retrying: ", ex)
if (workerStartRetry == maxRetries) {
logError(s"cannot start worker $i, reached to max retrying",
ex)
throw ex
}
+ try {
+ TimeUnit.SECONDS.sleep(Math.pow(2, workerStartRetry).toLong)
+ } catch {
+ case ie: InterruptedException =>
+ Thread.currentThread().interrupt()
+ throw ie
+ }
+ worker = createWorker(workerConf)
Review Comment:
This will be flaky then. let's keep it as is.
--
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]
