holdenk commented on a change in pull request #28370:
URL: https://github.com/apache/spark/pull/28370#discussion_r425949927



##########
File path: core/src/main/scala/org/apache/spark/storage/BlockManager.scala
##########
@@ -1829,7 +1901,58 @@ 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 sleepInterval = conf.get(
+      config.STORAGE_DECOMMISSION_REPLICATION_REATTEMPT_INTERVAL)
+
+    private val blockReplicationThread = new Thread {
+      override def run(): Unit = {
+        var failures = 0
+        while (blockManagerDecommissioning
+          && !stopped
+          && !Thread.interrupted()
+          && failures < 20) {
+          try {
+            logDebug("Attempting to replicate all cached RDD blocks")
+            decommissionRddCacheBlocks()
+            logInfo("Attempt to replicate all cached blocks done")
+            Thread.sleep(sleepInterval)
+          } catch {
+            case _: InterruptedException =>
+              logInfo("Interrupted during migration, will not refresh 
migrations.")
+              stopped = true
+            case NonFatal(e) =>
+              failures += 1
+              logError("Error occurred while trying to replicate cached RDD 
blocks" +
+                s" for block manager decommissioning (failure count: 
$failures)", e)
+          }
+        }
+      }
+    }
+    blockReplicationThread.setDaemon(true)
+    blockReplicationThread.setName("block-replication-thread")

Review comment:
       `grep -r "new Thread" ./core/src/main | wc -l` returns 36
   `grep -r ThreadUtils.newDaemonSingleThreadExecutor ./core/src/main |wc -l` 
returns 4




----------------------------------------------------------------
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:
us...@infra.apache.org



---------------------------------------------------------------------
To unsubscribe, e-mail: reviews-unsubscr...@spark.apache.org
For additional commands, e-mail: reviews-h...@spark.apache.org

Reply via email to