Github user henryr commented on a diff in the pull request:
https://github.com/apache/spark/pull/21068#discussion_r181908529
--- Diff:
resource-managers/yarn/src/main/scala/org/apache/spark/deploy/yarn/YarnAllocatorBlacklistTracker.scala
---
@@ -0,0 +1,155 @@
+/*
+ * Licensed to the Apache Software Foundation (ASF) under one or more
+ * contributor license agreements. See the NOTICE file distributed with
+ * this work for additional information regarding copyright ownership.
+ * The ASF licenses this file to You under the Apache License, Version 2.0
+ * (the "License"); you may not use this file except in compliance with
+ * the License. You may obtain a copy of the License at
+ *
+ * http://www.apache.org/licenses/LICENSE-2.0
+ *
+ * Unless required by applicable law or agreed to in writing, software
+ * distributed under the License is distributed on an "AS IS" BASIS,
+ * WITHOUT WARRANTIES OR CONDITIONS OF ANY KIND, either express or implied.
+ * See the License for the specific language governing permissions and
+ * limitations under the License.
+ */
+package org.apache.spark.deploy.yarn
+
+import scala.collection.JavaConverters._
+import scala.collection.mutable.HashMap
+
+import org.apache.hadoop.yarn.client.api.AMRMClient
+import org.apache.hadoop.yarn.client.api.AMRMClient.ContainerRequest
+
+import org.apache.spark.SparkConf
+import org.apache.spark.deploy.yarn.config._
+import org.apache.spark.internal.Logging
+import org.apache.spark.internal.config._
+import org.apache.spark.util.{Clock, SystemClock, Utils}
+
+private[spark] class YarnAllocatorBlacklistTracker(
+ sparkConf: SparkConf,
+ amClient: AMRMClient[ContainerRequest],
+ failureWithinTimeIntervalTracker: FailureWithinTimeIntervalTracker)
+ extends Logging {
+
+ private val DEFAULT_TIMEOUT = "1h"
+
+ private val BLACKLIST_TIMEOUT_MILLIS =
+
sparkConf.get(BLACKLIST_TIMEOUT_CONF).getOrElse(Utils.timeStringAsMs(DEFAULT_TIMEOUT))
+
+ private val IS_YARN_ALLOCATION_BLACKLIST_ENABLED =
+ sparkConf.get(YARN_ALLOCATION_BLACKLIST_ENABLED).getOrElse(false)
+
+ private val BLACKLIST_MAX_FAILED_EXEC_PER_NODE =
sparkConf.get(MAX_FAILED_EXEC_PER_NODE)
+
+ private val BLACKLIST_SIZE_LIMIT =
sparkConf.get(YARN_BLACKLIST_SIZE_LIMIT)
+
+ private val BLACKLIST_SIZE_DEFAULT_WEIGHT =
sparkConf.get(YARN_BLACKLIST_SIZE_DEFAULT_WEIGHT)
+
+ private var clock: Clock = new SystemClock
+
+ private val allocationBlacklistedNodesWithExpiry = new HashMap[String,
Long]()
+
+ private var currentBlacklistedYarnNodes = Set.empty[String]
+
+ private var schedulerBlacklistedNodesWithExpiry = Map.empty[String, Long]
--- End diff --
Do you need to keep a separate data structure for the scheduler and
allocator blacklisted nodes? Instead, could you add the scheduler ones into a
shared map when `setSchedulerBlacklistedNodes` is called?
---
---------------------------------------------------------------------
To unsubscribe, e-mail: reviews-unsubscr...@spark.apache.org
For additional commands, e-mail: reviews-h...@spark.apache.org
