holdenk commented on a change in pull request #28370:
URL: https://github.com/apache/spark/pull/28370#discussion_r417656267
##########
File path: core/src/main/scala/org/apache/spark/storage/BlockManager.scala
##########
@@ -1829,7 +1895,52 @@ private[spark] class BlockManager(
data.dispose()
}
+ /**
+ * Class to handle block manager decommissioning retries
+ * It creates a Thread to retry offloading all RDD cache blocks
+ */
+ private class BlockManagerDecommissionManager(conf: SparkConf) {
+ @volatile private var stopped = false
+ private val blockReplicationThread = new Thread {
+ override def run(): Unit = {
+ while (blockManagerDecommissioning && !stopped) {
+ try {
+ logDebug("Attempting to replicate all cached RDD blocks")
+ decommissionRddCacheBlocks()
+ logInfo("Attempt to replicate all cached blocks done")
+ val sleepInterval = conf.get(
+ config.STORAGE_DECOMMISSION_REPLICATION_REATTEMPT_INTERVAL)
+ Thread.sleep(sleepInterval)
+ } catch {
+ case _: InterruptedException =>
+ // no-op
+ case NonFatal(e) =>
+ logError("Error occurred while trying to " +
+ "replicate cached RDD blocks for block manager
decommissioning", e)
+ }
+ }
+ }
+ }
+ blockReplicationThread.setDaemon(true)
+ blockReplicationThread.setName("block-replication-thread")
+
+ def start(): Unit = {
+ logInfo("Starting block replication thread")
+ blockReplicationThread.start()
+ }
+
+ def stop(): Unit = {
+ if (!stopped) {
+ stopped = true
+ logInfo("Stopping block replication thread")
+ blockReplicationThread.interrupt()
+ blockReplicationThread.join()
Review comment:
So it's hanging with remaining alive workers. Try taking this out and
see if it makes a difference.
----------------------------------------------------------------
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.
For queries about this service, please contact Infrastructure at:
[email protected]
---------------------------------------------------------------------
To unsubscribe, e-mail: [email protected]
For additional commands, e-mail: [email protected]
