Github user kayousterhout commented on a diff in the pull request:
https://github.com/apache/spark/pull/1762#discussion_r15742607
--- Diff:
yarn/common/src/main/scala/org/apache/spark/scheduler/cluster/YarnSchedulerBackend.scala
---
@@ -0,0 +1,63 @@
+/*
+ * 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.scheduler.cluster
+
+import akka.actor.ActorSystem
+
+import org.apache.spark.SparkContext
+import org.apache.spark.scheduler.TaskSchedulerImpl
+
+/**
+ * Subclass of CoarseGrainedSchedulerBackend that handles waiting until
sufficient resources
+ * are registered before beginning to schedule tasks (needed by both Yarn
scheduler backends).
+ */
+private[spark] class YarnSchedulerBackend(
+ scheduler: TaskSchedulerImpl,
+ actorSystem: ActorSystem)
+ extends CoarseGrainedSchedulerBackend(scheduler, actorSystem) {
+
+ // Submit tasks only after (registered executors / total expected
executors)
+ // is equal to at least this value (expected to be a double between 0
and 1, inclusive).
+ var minRegisteredRatio =
conf.getDouble("spark.scheduler.minRegisteredExecutorsRatio", 0.8)
+ if (minRegisteredRatio > 1) minRegisteredRatio = 1
+ // Regardless of whether the required number of executors have
registered, return true from
+ // isReady() after this amount of time has elapsed.
+ val maxRegisteredWaitingTime =
+ conf.getInt("spark.scheduler.maxRegisteredExecutorsWaitingTime", 30000)
+ private val createTime = System.currentTimeMillis()
+
+ var totalExpectedExecutors: Int = _
+
+ override def isReady(): Boolean = {
--- End diff --
Realized I should fix this to only print the log message once -- will do
this if we decide to use this PR
---
If your project is set up for it, you can reply to this email and have your
reply appear on GitHub as well. If your project does not have this feature
enabled and wishes so, or if the feature is enabled but not working, please
contact infrastructure at [email protected] or file a JIRA ticket
with INFRA.
---
---------------------------------------------------------------------
To unsubscribe, e-mail: [email protected]
For additional commands, e-mail: [email protected]
