[SPARK-44442][MESOS] Remove Mesos support

.github/labeler.yml

@@ -136,9 +136,6 @@ R:
   - "bin/sparkR*"
 YARN:
   - "resource-managers/yarn/**/*"
-MESOS:
-  - "resource-managers/mesos/**/*"
-  - "sbin/*mesos*.sh"
 KUBERNETES:
   - "resource-managers/kubernetes/**/*"
 WINDOWS:

.github/workflows/benchmark.yml

@@ -170,7 +170,7 @@ jobs:
         key: tpcds-${{ hashFiles('.github/workflows/benchmark.yml', 'sql/core/src/test/scala/org/apache/spark/sql/TPCDSSchema.scala') }}
     - name: Run benchmarks
       run: |
-        ./build/sbt -Pscala-${{ github.event.inputs.scala }} -Pyarn -Pmesos -Pkubernetes -Phive -Phive-thriftserver -Phadoop-cloud -Pkinesis-asl -Pspark-ganglia-lgpl Test/package
+        ./build/sbt -Pscala-${{ github.event.inputs.scala }} -Pyarn -Pkubernetes -Phive -Phive-thriftserver -Phadoop-cloud -Pkinesis-asl -Pspark-ganglia-lgpl Test/package
         # Make less noisy
         cp conf/log4j2.properties.template conf/log4j2.properties
         sed -i 's/rootLogger.level = info/rootLogger.level = warn/g' conf/log4j2.properties

.github/workflows/build_and_test.yml

@@ -149,7 +149,7 @@ jobs:
           - >-
             streaming, sql-kafka-0-10, streaming-kafka-0-10,
             mllib-local, mllib,
-            yarn, mesos, kubernetes, hadoop-cloud, spark-ganglia-lgpl,
+            yarn, kubernetes, hadoop-cloud, spark-ganglia-lgpl,
             connect, protobuf
         # Here, we split Hive and SQL tests into some of slow ones and the rest of them.
         included-tags: [""]
@@ -823,7 +823,7 @@ jobs:
         export MAVEN_CLI_OPTS="--no-transfer-progress"
         export JAVA_VERSION=${{ matrix.java }}
         # It uses Maven's 'install' intentionally, see https://github.com/apache/spark/pull/26414.
-        ./build/mvn $MAVEN_CLI_OPTS -DskipTests -Pyarn -Pmesos -Pkubernetes -Pvolcano -Phive -Phive-thriftserver -Phadoop-cloud -Djava.version=${JAVA_VERSION/-ea} install
+        ./build/mvn $MAVEN_CLI_OPTS -DskipTests -Pyarn -Pkubernetes -Pvolcano -Phive -Phive-thriftserver -Phadoop-cloud -Djava.version=${JAVA_VERSION/-ea} install
         rm -rf ~/.m2/repository/org/apache/spark
 
   # Any TPC-DS related updates on this job need to be applied to tpcds-1g-gen job of benchmark.yml as well

.github/workflows/maven_test.yml

@@ -65,7 +65,7 @@ jobs:
           - >-
             connector#kafka-0-10,connector#kafka-0-10-sql,connector#kafka-0-10-token-provider,connector#spark-ganglia-lgpl,connector#protobuf,connector#avro
           - >-
-            sql#catalyst,resource-managers#yarn,resource-managers#mesos,resource-managers#kubernetes#core
+            sql#catalyst,resource-managers#yarn,resource-managers#kubernetes#core
           - >-
             connect
         # Here, we split Hive and SQL tests into some of slow ones and the rest of them.
@@ -180,18 +180,18 @@ jobs:
           export JAVA_VERSION=${{ matrix.java }}
           # Replace with the real module name, for example, connector#kafka-0-10 -> connector/kafka-0-10
           export TEST_MODULES=`echo "$MODULES_TO_TEST" | sed -e "s%#%/%g"`
-          ./build/mvn $MAVEN_CLI_OPTS -DskipTests -Pyarn -Pmesos -Pkubernetes -Pvolcano -Phive -Phive-thriftserver -Phadoop-cloud -Pspark-ganglia-lgpl -Djava.version=${JAVA_VERSION/-ea} clean install
+          ./build/mvn $MAVEN_CLI_OPTS -DskipTests -Pyarn -Pkubernetes -Pvolcano -Phive -Phive-thriftserver -Phadoop-cloud -Pspark-ganglia-lgpl -Djava.version=${JAVA_VERSION/-ea} clean install
           if [[ "$INCLUDED_TAGS" != "" ]]; then
-            ./build/mvn $MAVEN_CLI_OPTS -pl "$TEST_MODULES" -Pyarn -Pmesos -Pkubernetes -Pvolcano -Phive -Phive-thriftserver -Phadoop-cloud -Pspark-ganglia-lgpl -Djava.version=${JAVA_VERSION/-ea} -Dtest.include.tags="$INCLUDED_TAGS" test -fae
+            ./build/mvn $MAVEN_CLI_OPTS -pl "$TEST_MODULES" -Pyarn -Pkubernetes -Pvolcano -Phive -Phive-thriftserver -Phadoop-cloud -Pspark-ganglia-lgpl -Djava.version=${JAVA_VERSION/-ea} -Dtest.include.tags="$INCLUDED_TAGS" test -fae
           elif [[ "$EXCLUDED_TAGS" != "" ]]; then
-            ./build/mvn $MAVEN_CLI_OPTS -pl "$TEST_MODULES" -Pyarn -Pmesos -Pkubernetes -Pvolcano -Phive -Phive-thriftserver -Phadoop-cloud -Pspark-ganglia-lgpl -Djava.version=${JAVA_VERSION/-ea} -Dtest.exclude.tags="$EXCLUDED_TAGS" test -fae
+            ./build/mvn $MAVEN_CLI_OPTS -pl "$TEST_MODULES" -Pyarn -Pkubernetes -Pvolcano -Phive -Phive-thriftserver -Phadoop-cloud -Pspark-ganglia-lgpl -Djava.version=${JAVA_VERSION/-ea} -Dtest.exclude.tags="$EXCLUDED_TAGS" test -fae
           elif [[ "$MODULES_TO_TEST" == "connect" ]]; then
             ./build/mvn $MAVEN_CLI_OPTS -Djava.version=${JAVA_VERSION/-ea} -pl connector/connect/client/jvm,connector/connect/common,connector/connect/server test -fae
           elif [[ "$MODULES_TO_TEST" == *"sql#hive-thriftserver"* ]]; then
             # To avoid a compilation loop, for the `sql/hive-thriftserver` module, run `clean install` instead
-            ./build/mvn $MAVEN_CLI_OPTS -pl "$TEST_MODULES" -Pyarn -Pmesos -Pkubernetes -Pvolcano -Phive -Phive-thriftserver -Phadoop-cloud -Pspark-ganglia-lgpl -Djava.version=${JAVA_VERSION/-ea} clean install -fae
+            ./build/mvn $MAVEN_CLI_OPTS -pl "$TEST_MODULES" -Pyarn -Pkubernetes -Pvolcano -Phive -Phive-thriftserver -Phadoop-cloud -Pspark-ganglia-lgpl -Djava.version=${JAVA_VERSION/-ea} clean install -fae
           else
-            ./build/mvn $MAVEN_CLI_OPTS -pl "$TEST_MODULES" -Pyarn -Pmesos -Pkubernetes -Pvolcano -Phive -Phive-thriftserver -Pspark-ganglia-lgpl -Phadoop-cloud -Djava.version=${JAVA_VERSION/-ea} test -fae
+            ./build/mvn $MAVEN_CLI_OPTS -pl "$TEST_MODULES" -Pyarn -Pkubernetes -Pvolcano -Phive -Phive-thriftserver -Pspark-ganglia-lgpl -Phadoop-cloud -Djava.version=${JAVA_VERSION/-ea} test -fae
           fi
       - name: Clean up local Maven repository
         run: |  

LICENSE-binary

@@ -348,8 +348,7 @@ org.apache.directory.server:apacheds-i18n
 org.apache.directory.server:apacheds-kerberos-codec
 org.apache.htrace:htrace-core
 org.apache.ivy:ivy
-org.apache.mesos:mesos
-org.apache.parquet:parquet-column
+=org.apache.parquet:parquet-column
 org.apache.parquet:parquet-common
 org.apache.parquet:parquet-encoding
 org.apache.parquet:parquet-format

NOTICE-binary

@@ -673,9 +673,6 @@ Copyright 2002-2012 The Apache Software Foundation
 Google Guice - Core Library
 Copyright 2006-2011 Google, Inc.
 
-mesos
-Copyright 2017 The Apache Software Foundation
-
 Apache Parquet Hadoop Bundle (Incubating)
 Copyright 2015 The Apache Software Foundation
 

R/pkg/tests/fulltests/test_sparkR.R

@@ -18,7 +18,7 @@
 context("functions in sparkR.R")
 
 test_that("sparkCheckInstall", {
-  # "local, yarn-client, mesos-client" mode, SPARK_HOME was set correctly,
+  # "local, yarn-client" mode, SPARK_HOME was set correctly,
   # and the SparkR job was submitted by "spark-submit"
   sparkHome <- paste0(tempdir(), "/", "sparkHome")
   dir.create(sparkHome)
@@ -27,14 +27,14 @@ test_that("sparkCheckInstall", {
   expect_true(is.null(sparkCheckInstall(sparkHome, master, deployMode)))
   unlink(sparkHome, recursive = TRUE)
 
-  # "yarn-cluster, mesos-cluster" mode, SPARK_HOME was not set,
+  # "yarn-cluster" mode, SPARK_HOME was not set,
   # and the SparkR job was submitted by "spark-submit"
   sparkHome <- ""
   master <- ""
   deployMode <- ""
   expect_true(is.null(sparkCheckInstall(sparkHome, master, deployMode)))
 
-  # "yarn-client, mesos-client" mode, SPARK_HOME was not set
+  # "yarn-client" mode, SPARK_HOME was not set
   sparkHome <- ""
   master <- "yarn"
   deployMode <- "client"

README.md

@@ -77,7 +77,7 @@ To run one of them, use `./bin/run-example <class> [params]`. For example:
 will run the Pi example locally.
 
 You can set the MASTER environment variable when running examples to submit
-examples to a cluster. This can be a mesos:// or spark:// URL,
+examples to a cluster. This can be spark:// URL,
 "yarn" to run on YARN, and "local" to run
 locally with one thread, or "local[N]" to run locally with N threads. You
 can also use an abbreviated class name if the class is in the `examples`

assembly/pom.xml

@@ -142,16 +142,6 @@
         </dependency>
       </dependencies>
     </profile>
-    <profile>
-      <id>mesos</id>
-      <dependencies>
-        <dependency>
-          <groupId>org.apache.spark</groupId>
-          <artifactId>spark-mesos_${scala.binary.version}</artifactId>
-          <version>${project.version}</version>
-        </dependency>
-      </dependencies>
-    </profile>
     <profile>
       <id>connect</id>
       <dependencies>

common/network-shuffle/src/main/java/org/apache/spark/network/shuffle/protocol/BlockTransferMessage.java

@@ -24,8 +24,6 @@
 
 import org.apache.spark.network.protocol.Encodable;
 import org.apache.spark.network.shuffle.ExternalBlockHandler;
-import org.apache.spark.network.shuffle.protocol.mesos.RegisterDriver;
-import org.apache.spark.network.shuffle.protocol.mesos.ShuffleServiceHeartbeat;
 
 /**
  * Messages handled by the {@link ExternalBlockHandler}, or
@@ -73,8 +71,6 @@ public static BlockTransferMessage fromByteBuffer(ByteBuffer msg) {
         case 1: return UploadBlock.decode(buf);
         case 2: return RegisterExecutor.decode(buf);
         case 3: return StreamHandle.decode(buf);
-        case 4: return RegisterDriver.decode(buf);
-        case 5: return ShuffleServiceHeartbeat.decode(buf);
         case 6: return UploadBlockStream.decode(buf);
         case 7: return RemoveBlocks.decode(buf);
         case 8: return BlocksRemoved.decode(buf);

conf/spark-env.sh.template

@@ -30,7 +30,6 @@
 # - SPARK_LOCAL_IP, to set the IP address Spark binds to on this node
 # - SPARK_PUBLIC_DNS, to set the public DNS name of the driver program
 # - SPARK_LOCAL_DIRS, storage directories to use on this node for shuffle and RDD data
-# - MESOS_NATIVE_JAVA_LIBRARY, to point to your libmesos.so if you use Mesos
 
 # Options read in any mode
 # - SPARK_CONF_DIR, Alternate conf dir. (Default: ${SPARK_HOME}/conf)

core/src/main/scala/org/apache/spark/SparkConf.scala

@@ -498,7 +498,7 @@ class SparkConf(loadDefaults: Boolean) extends Cloneable with Logging with Seria
   private[spark] def validateSettings(): Unit = {
     if (contains("spark.local.dir")) {
       val msg = "Note that spark.local.dir will be overridden by the value set by " +
-        "the cluster manager (via SPARK_LOCAL_DIRS in mesos/standalone/kubernetes and LOCAL_DIRS" +
+        "the cluster manager (via SPARK_LOCAL_DIRS in standalone/kubernetes and LOCAL_DIRS" +
         " in YARN)."
       logWarning(msg)
     }

core/src/main/scala/org/apache/spark/SparkContext.scala

@@ -132,7 +132,7 @@ class SparkContext(config: SparkConf) extends Logging {
   /**
    * Alternative constructor that allows setting common Spark properties directly
    *
-   * @param master Cluster URL to connect to (e.g. mesos://host:port, spark://host:port, local[4]).
+   * @param master Cluster URL to connect to (e.g. spark://host:port, local[4]).
    * @param appName A name for your application, to display on the cluster web UI
    * @param conf a [[org.apache.spark.SparkConf]] object specifying other Spark parameters
    */
@@ -142,7 +142,7 @@ class SparkContext(config: SparkConf) extends Logging {
   /**
    * Alternative constructor that allows setting common Spark properties directly
    *
-   * @param master Cluster URL to connect to (e.g. mesos://host:port, spark://host:port, local[4]).
+   * @param master Cluster URL to connect to (e.g. spark://host:port, local[4]).
    * @param appName A name for your application, to display on the cluster web UI.
    * @param sparkHome Location where Spark is installed on cluster nodes.
    * @param jars Collection of JARs to send to the cluster. These can be paths on the local file
@@ -164,7 +164,7 @@ class SparkContext(config: SparkConf) extends Logging {
   /**
    * Alternative constructor that allows setting common Spark properties directly
    *
-   * @param master Cluster URL to connect to (e.g. mesos://host:port, spark://host:port, local[4]).
+   * @param master Cluster URL to connect to (e.g. spark://host:port, local[4]).
    * @param appName A name for your application, to display on the cluster web UI.
    */
   private[spark] def this(master: String, appName: String) =
@@ -173,7 +173,7 @@ class SparkContext(config: SparkConf) extends Logging {
   /**
    * Alternative constructor that allows setting common Spark properties directly
    *
-   * @param master Cluster URL to connect to (e.g. mesos://host:port, spark://host:port, local[4]).
+   * @param master Cluster URL to connect to (e.g. spark://host:port, local[4]).
    * @param appName A name for your application, to display on the cluster web UI.
    * @param sparkHome Location where Spark is installed on cluster nodes.
    */
@@ -183,7 +183,7 @@ class SparkContext(config: SparkConf) extends Logging {
   /**
    * Alternative constructor that allows setting common Spark properties directly
    *
-   * @param master Cluster URL to connect to (e.g. mesos://host:port, spark://host:port, local[4]).
+   * @param master Cluster URL to connect to (e.g. spark://host:port, local[4]).
    * @param appName A name for your application, to display on the cluster web UI.
    * @param sparkHome Location where Spark is installed on cluster nodes.
    * @param jars Collection of JARs to send to the cluster. These can be paths on the local file
@@ -352,7 +352,6 @@ class SparkContext(config: SparkConf) extends Logging {
    * (i.e.
    *  in case of local spark app something like 'local-1433865536131'
    *  in case of YARN something like 'application_1433865536131_34483'
-   *  in case of MESOS something like 'driver-20170926223339-0001'
    * )
    */
   def applicationId: String = _applicationId
@@ -557,9 +556,6 @@ class SparkContext(config: SparkConf) extends Logging {
     Option(System.getenv("SPARK_PREPEND_CLASSES")).foreach { v =>
       executorEnvs("SPARK_PREPEND_CLASSES") = v
     }
-    // The Mesos scheduler backend relies on this environment variable to set executor memory.
-    // TODO: Set this only in the Mesos scheduler.
-    executorEnvs("SPARK_EXECUTOR_MEMORY") = executorMemory + "m"
     executorEnvs ++= _conf.getExecutorEnv
     executorEnvs("SPARK_USER") = sparkUser