# 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. Index: core/src/main/scala/org/apache/spark/util/Utils.scala IDEA additional info: Subsystem: com.intellij.openapi.diff.impl.patch.CharsetEP <+>UTF-8 =================================================================== diff --git a/core/src/main/scala/org/apache/spark/util/Utils.scala b/core/src/main/scala/org/apache/spark/util/Utils.scala --- a/core/src/main/scala/org/apache/spark/util/Utils.scala (revision d1cae9c5ac5393243d2f9661dc7957d0ebccb1d6) +++ b/core/src/main/scala/org/apache/spark/util/Utils.scala (date 1652322540231) @@ -3222,6 +3222,9 @@ } files.toSeq } + + def isCelebornEnabled(conf: SparkConf): Boolean = + conf.get("spark.shuffle.manager", "sort").contains("celeborn") } private[util] object CallerContext extends Logging { Index: core/src/main/scala/org/apache/spark/ExecutorAllocationManager.scala IDEA additional info: Subsystem: com.intellij.openapi.diff.impl.patch.CharsetEP <+>UTF-8 =================================================================== diff --git a/core/src/main/scala/org/apache/spark/ExecutorAllocationManager.scala b/core/src/main/scala/org/apache/spark/ExecutorAllocationManager.scala --- a/core/src/main/scala/org/apache/spark/ExecutorAllocationManager.scala (revision d1cae9c5ac5393243d2f9661dc7957d0ebccb1d6) +++ b/core/src/main/scala/org/apache/spark/ExecutorAllocationManager.scala (date 1652322692344) @@ -211,7 +211,7 @@ (decommissionEnabled && conf.get(config.STORAGE_DECOMMISSION_SHUFFLE_BLOCKS_ENABLED))) { logWarning("Dynamic allocation without a shuffle service is an experimental feature.") - } else if (!testing) { + } else if (!testing && !Utils.isCelebornEnabled(conf)) { throw new SparkException("Dynamic allocation of executors requires the external " + "shuffle service. You may enable this through spark.shuffle.service.enabled.") } Index: core/src/main/scala/org/apache/spark/scheduler/TaskSetManager.scala IDEA additional info: Subsystem: com.intellij.openapi.diff.impl.patch.CharsetEP <+>UTF-8 =================================================================== diff --git a/core/src/main/scala/org/apache/spark/scheduler/TaskSetManager.scala b/core/src/main/scala/org/apache/spark/scheduler/TaskSetManager.scala --- a/core/src/main/scala/org/apache/spark/scheduler/TaskSetManager.scala (revision d1cae9c5ac5393243d2f9661dc7957d0ebccb1d6) +++ b/core/src/main/scala/org/apache/spark/scheduler/TaskSetManager.scala (date 1652323382069) @@ -1015,7 +1015,8 @@ // and we are not using an external shuffle server which could serve the shuffle outputs. // The reason is the next stage wouldn't be able to fetch the data from this dead executor // so we would need to rerun these tasks on other executors. - if (isShuffleMapTasks && !env.blockManager.externalShuffleServiceEnabled && !isZombie) { + if (isShuffleMapTasks && !env.blockManager.externalShuffleServiceEnabled && !isZombie && + !Utils.isCelebornEnabled(conf)) { for ((tid, info) <- taskInfos if info.executorId == execId) { val index = taskInfos(tid).index // We may have a running task whose partition has been marked as successful, Index: core/src/main/scala/org/apache/spark/scheduler/DAGScheduler.scala IDEA additional info: Subsystem: com.intellij.openapi.diff.impl.patch.CharsetEP <+>UTF-8 =================================================================== diff --git a/core/src/main/scala/org/apache/spark/scheduler/DAGScheduler.scala b/core/src/main/scala/org/apache/spark/scheduler/DAGScheduler.scala --- a/core/src/main/scala/org/apache/spark/scheduler/DAGScheduler.scala (revision d1cae9c5ac5393243d2f9661dc7957d0ebccb1d6) +++ b/core/src/main/scala/org/apache/spark/scheduler/DAGScheduler.scala (date 1652322695806) @@ -2231,7 +2231,8 @@ // if the cluster manager explicitly tells us that the entire worker was lost, then // we know to unregister shuffle output. (Note that "worker" specifically refers to the process // from a Standalone cluster, where the shuffle service lives in the Worker.) - val fileLost = workerHost.isDefined || !env.blockManager.externalShuffleServiceEnabled + val fileLost = !Utils.isCelebornEnabled(sc.getConf) && + (workerHost.isDefined || !env.blockManager.externalShuffleServiceEnabled) removeExecutorAndUnregisterOutputs( execId = execId, fileLost = fileLost,