diff options
77 files changed, 1824 insertions, 465 deletions
diff --git a/assembly/pom.xml b/assembly/pom.xml index d19f44d292..808a829e19 100644 --- a/assembly/pom.xml +++ b/assembly/pom.xml @@ -106,6 +106,12 @@ <transformers> <transformer implementation="org.apache.maven.plugins.shade.resource.ServicesResourceTransformer"/> <transformer implementation="org.apache.maven.plugins.shade.resource.AppendingTransformer"> + <resource>META-INF/services/org.apache.hadoop.fs.FileSystem</resource> + </transformer> + </transformers> + <transformers> + <transformer implementation="org.apache.maven.plugins.shade.resource.ServicesResourceTransformer"/> + <transformer implementation="org.apache.maven.plugins.shade.resource.AppendingTransformer"> <resource>reference.conf</resource> </transformer> </transformers> diff --git a/conf/fairscheduler.xml.template b/conf/fairscheduler.xml.template index 04a6b418dc..acf59e2a35 100644 --- a/conf/fairscheduler.xml.template +++ b/conf/fairscheduler.xml.template @@ -1,15 +1,13 @@ <?xml version="1.0"?> <allocations> -<pool name="production"> - <minShare>2</minShare> - <weight>1</weight> + <pool name="production"> <schedulingMode>FAIR</schedulingMode> -</pool> -<pool name="test"> - <minShare>3</minShare> - <weight>2</weight> + <weight>1</weight> + <minShare>2</minShare> + </pool> + <pool name="test"> <schedulingMode>FIFO</schedulingMode> -</pool> -<pool name="data"> -</pool> + <weight>2</weight> + <minShare>3</minShare> + </pool> </allocations> diff --git a/conf/metrics.properties.template b/conf/metrics.properties.template index 6c36f3cca4..ae10f615d1 100644 --- a/conf/metrics.properties.template +++ b/conf/metrics.properties.template @@ -31,7 +31,7 @@ # 1. To add a new sink, set the "class" option to a fully qualified class # name (see examples below). # 2. Some sinks involve a polling period. The minimum allowed polling period -# is 1 second. +# is 1 second. # 3. Wild card properties can be overridden by more specific properties. # For example, master.sink.console.period takes precedence over # *.sink.console.period. @@ -47,11 +47,45 @@ # instance master and applications. MetricsServlet may not be configured by self. # +## List of available sinks and their properties. + +# org.apache.spark.metrics.sink.ConsoleSink +# Name: Default: Description: +# period 10 Poll period +# unit seconds Units of poll period + +# org.apache.spark.metrics.sink.CSVSink +# Name: Default: Description: +# period 10 Poll period +# unit seconds Units of poll period +# directory /tmp Where to store CSV files + +# org.apache.spark.metrics.sink.GangliaSink +# Name: Default: Description: +# host NONE Hostname or multicast group of Ganglia server +# port NONE Port of Ganglia server(s) +# period 10 Poll period +# unit seconds Units of poll period +# ttl 1 TTL of messages sent by Ganglia +# mode multicast Ganglia network mode ('unicast' or 'mulitcast') + +# org.apache.spark.metrics.sink.JmxSink + +# org.apache.spark.metrics.sink.MetricsServlet +# Name: Default: Description: +# path VARIES* Path prefix from the web server root +# sample false Whether to show entire set of samples for histograms ('false' or 'true') +# +# * Default path is /metrics/json for all instances except the master. The master has two paths: +# /metrics/aplications/json # App information +# /metrics/master/json # Master information + +## Examples # Enable JmxSink for all instances by class name -#*.sink.jmx.class=spark.metrics.sink.JmxSink +#*.sink.jmx.class=org.apache.spark.metrics.sink.JmxSink # Enable ConsoleSink for all instances by class name -#*.sink.console.class=spark.metrics.sink.ConsoleSink +#*.sink.console.class=org.apache.spark.metrics.sink.ConsoleSink # Polling period for ConsoleSink #*.sink.console.period=10 @@ -64,7 +98,7 @@ #master.sink.console.unit=seconds # Enable CsvSink for all instances -#*.sink.csv.class=spark.metrics.sink.CsvSink +#*.sink.csv.class=org.apache.spark.metrics.sink.CsvSink # Polling period for CsvSink #*.sink.csv.period=1 @@ -80,11 +114,11 @@ #worker.sink.csv.unit=minutes # Enable jvm source for instance master, worker, driver and executor -#master.source.jvm.class=spark.metrics.source.JvmSource +#master.source.jvm.class=org.apache.spark.metrics.source.JvmSource -#worker.source.jvm.class=spark.metrics.source.JvmSource +#worker.source.jvm.class=org.apache.spark.metrics.source.JvmSource -#driver.source.jvm.class=spark.metrics.source.JvmSource +#driver.source.jvm.class=org.apache.spark.metrics.source.JvmSource -#executor.source.jvm.class=spark.metrics.source.JvmSource +#executor.source.jvm.class=org.apache.spark.metrics.source.JvmSource diff --git a/core/pom.xml b/core/pom.xml index 076236e20a..382473a3b3 100644 --- a/core/pom.xml +++ b/core/pom.xml @@ -37,6 +37,11 @@ <artifactId>hadoop-client</artifactId> </dependency> <dependency> + <groupId>net.java.dev.jets3t</groupId> + <artifactId>jets3t</artifactId> + <version>0.7.1</version> + </dependency> + <dependency> <groupId>org.apache.avro</groupId> <artifactId>avro</artifactId> </dependency> @@ -147,6 +152,10 @@ <artifactId>metrics-json</artifactId> </dependency> <dependency> + <groupId>com.codahale.metrics</groupId> + <artifactId>metrics-ganglia</artifactId> + </dependency> + <dependency> <groupId>org.apache.derby</groupId> <artifactId>derby</artifactId> <scope>test</scope> diff --git a/core/src/main/scala/org/apache/spark/CacheManager.scala b/core/src/main/scala/org/apache/spark/CacheManager.scala index e299a106ee..68b99ca125 100644 --- a/core/src/main/scala/org/apache/spark/CacheManager.scala +++ b/core/src/main/scala/org/apache/spark/CacheManager.scala @@ -66,10 +66,12 @@ private[spark] class CacheManager(blockManager: BlockManager) extends Logging { } try { // If we got here, we have to load the split - val elements = new ArrayBuffer[Any] logInfo("Computing partition " + split) - elements ++= rdd.computeOrReadCheckpoint(split, context) - // Try to put this block in the blockManager + val computedValues = rdd.computeOrReadCheckpoint(split, context) + // Persist the result, so long as the task is not running locally + if (context.runningLocally) { return computedValues } + val elements = new ArrayBuffer[Any] + elements ++= computedValues blockManager.put(key, elements, storageLevel, true) return elements.iterator.asInstanceOf[Iterator[T]] } finally { diff --git a/core/src/main/scala/org/apache/spark/SparkContext.scala b/core/src/main/scala/org/apache/spark/SparkContext.scala index 04d172a989..882bc506b4 100644 --- a/core/src/main/scala/org/apache/spark/SparkContext.scala +++ b/core/src/main/scala/org/apache/spark/SparkContext.scala @@ -258,20 +258,20 @@ class SparkContext( private[spark] var checkpointDir: Option[String] = None // Thread Local variable that can be used by users to pass information down the stack - private val localProperties = new DynamicVariable[Properties](null) + private val localProperties = new ThreadLocal[Properties] def initLocalProperties() { - localProperties.value = new Properties() + localProperties.set(new Properties()) } def setLocalProperty(key: String, value: String) { - if (localProperties.value == null) { - localProperties.value = new Properties() + if (localProperties.get() == null) { + localProperties.set(new Properties()) } if (value == null) { - localProperties.value.remove(key) + localProperties.get.remove(key) } else { - localProperties.value.setProperty(key, value) + localProperties.get.setProperty(key, value) } } @@ -283,8 +283,8 @@ class SparkContext( // Post init taskScheduler.postStartHook() - val dagSchedulerSource = new DAGSchedulerSource(this.dagScheduler) - val blockManagerSource = new BlockManagerSource(SparkEnv.get.blockManager) + val dagSchedulerSource = new DAGSchedulerSource(this.dagScheduler, this) + val blockManagerSource = new BlockManagerSource(SparkEnv.get.blockManager, this) def initDriverMetrics() { SparkEnv.get.metricsSystem.registerSource(dagSchedulerSource) @@ -724,7 +724,8 @@ class SparkContext( val callSite = Utils.formatSparkCallSite logInfo("Starting job: " + callSite) val start = System.nanoTime - val result = dagScheduler.runJob(rdd, func, partitions, callSite, allowLocal, resultHandler, localProperties.value) + val result = dagScheduler.runJob(rdd, func, partitions, callSite, allowLocal, resultHandler, + localProperties.get) logInfo("Job finished: " + callSite + ", took " + (System.nanoTime - start) / 1e9 + " s") rdd.doCheckpoint() result @@ -807,7 +808,8 @@ class SparkContext( val callSite = Utils.formatSparkCallSite logInfo("Starting job: " + callSite) val start = System.nanoTime - val result = dagScheduler.runApproximateJob(rdd, func, evaluator, callSite, timeout, localProperties.value) + val result = dagScheduler.runApproximateJob(rdd, func, evaluator, callSite, timeout, + localProperties.get) logInfo("Job finished: " + callSite + ", took " + (System.nanoTime - start) / 1e9 + " s") result } diff --git a/core/src/main/scala/org/apache/spark/TaskContext.scala b/core/src/main/scala/org/apache/spark/TaskContext.scala index b2dd668330..c2c358c7ad 100644 --- a/core/src/main/scala/org/apache/spark/TaskContext.scala +++ b/core/src/main/scala/org/apache/spark/TaskContext.scala @@ -24,6 +24,7 @@ class TaskContext( val stageId: Int, val splitId: Int, val attemptId: Long, + val runningLocally: Boolean = false, val taskMetrics: TaskMetrics = TaskMetrics.empty() ) extends Serializable { diff --git a/core/src/main/scala/org/apache/spark/deploy/JsonProtocol.scala b/core/src/main/scala/org/apache/spark/deploy/JsonProtocol.scala index a6be8efef1..87a703427c 100644 --- a/core/src/main/scala/org/apache/spark/deploy/JsonProtocol.scala +++ b/core/src/main/scala/org/apache/spark/deploy/JsonProtocol.scala @@ -44,7 +44,9 @@ private[spark] object JsonProtocol { ("cores" -> obj.desc.maxCores) ~ ("user" -> obj.desc.user) ~ ("memoryperslave" -> obj.desc.memoryPerSlave) ~ - ("submitdate" -> obj.submitDate.toString) + ("submitdate" -> obj.submitDate.toString) ~ + ("state" -> obj.state.toString) ~ + ("duration" -> obj.duration) } def writeApplicationDescription(obj: ApplicationDescription) = { diff --git a/core/src/main/scala/org/apache/spark/executor/Executor.scala b/core/src/main/scala/org/apache/spark/executor/Executor.scala index d365804994..ceae3b8289 100644 --- a/core/src/main/scala/org/apache/spark/executor/Executor.scala +++ b/core/src/main/scala/org/apache/spark/executor/Executor.scala @@ -98,7 +98,7 @@ private[spark] class Executor( } ) - val executorSource = new ExecutorSource(this) + val executorSource = new ExecutorSource(this, executorId) // Initialize Spark environment (using system properties read above) val env = SparkEnv.createFromSystemProperties(executorId, slaveHostname, 0, false, false) diff --git a/core/src/main/scala/org/apache/spark/executor/ExecutorSource.scala b/core/src/main/scala/org/apache/spark/executor/ExecutorSource.scala index bf8fb4fd21..18c9dc1c0a 100644 --- a/core/src/main/scala/org/apache/spark/executor/ExecutorSource.scala +++ b/core/src/main/scala/org/apache/spark/executor/ExecutorSource.scala @@ -27,7 +27,7 @@ import scala.collection.JavaConversions._ import org.apache.spark.metrics.source.Source -class ExecutorSource(val executor: Executor) extends Source { +class ExecutorSource(val executor: Executor, executorId: String) extends Source { private def fileStats(scheme: String) : Option[FileSystem.Statistics] = FileSystem.getAllStatistics().filter(s => s.getScheme.equals(scheme)).headOption @@ -39,7 +39,8 @@ class ExecutorSource(val executor: Executor) extends Source { } val metricRegistry = new MetricRegistry() - val sourceName = "executor" + // TODO: It would be nice to pass the application name here + val sourceName = "executor.%s".format(executorId) // Gauge for executor thread pool's actively executing task counts metricRegistry.register(MetricRegistry.name("threadpool", "activeTask", "count"), new Gauge[Int] { diff --git a/core/src/main/scala/org/apache/spark/metrics/MetricsConfig.scala b/core/src/main/scala/org/apache/spark/metrics/MetricsConfig.scala index 0f9c4e00b1..caab748d60 100644 --- a/core/src/main/scala/org/apache/spark/metrics/MetricsConfig.scala +++ b/core/src/main/scala/org/apache/spark/metrics/MetricsConfig.scala @@ -37,10 +37,9 @@ private[spark] class MetricsConfig(val configFile: Option[String]) extends Loggi private def setDefaultProperties(prop: Properties) { prop.setProperty("*.sink.servlet.class", "org.apache.spark.metrics.sink.MetricsServlet") - prop.setProperty("*.sink.servlet.uri", "/metrics/json") - prop.setProperty("*.sink.servlet.sample", "false") - prop.setProperty("master.sink.servlet.uri", "/metrics/master/json") - prop.setProperty("applications.sink.servlet.uri", "/metrics/applications/json") + prop.setProperty("*.sink.servlet.path", "/metrics/json") + prop.setProperty("master.sink.servlet.path", "/metrics/master/json") + prop.setProperty("applications.sink.servlet.path", "/metrics/applications/json") } def initialize() { diff --git a/core/src/main/scala/org/apache/spark/metrics/sink/GangliaSink.scala b/core/src/main/scala/org/apache/spark/metrics/sink/GangliaSink.scala new file mode 100644 index 0000000000..b924907070 --- /dev/null +++ b/core/src/main/scala/org/apache/spark/metrics/sink/GangliaSink.scala @@ -0,0 +1,82 @@ +/* + * 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.metrics.sink + +import java.util.Properties +import java.util.concurrent.TimeUnit + +import com.codahale.metrics.ganglia.GangliaReporter +import com.codahale.metrics.MetricRegistry +import info.ganglia.gmetric4j.gmetric.GMetric + +import org.apache.spark.metrics.MetricsSystem + +class GangliaSink(val property: Properties, val registry: MetricRegistry) extends Sink { + val GANGLIA_KEY_PERIOD = "period" + val GANGLIA_DEFAULT_PERIOD = 10 + + val GANGLIA_KEY_UNIT = "unit" + val GANGLIA_DEFAULT_UNIT = TimeUnit.SECONDS + + val GANGLIA_KEY_MODE = "mode" + val GANGLIA_DEFAULT_MODE = GMetric.UDPAddressingMode.MULTICAST + + // TTL for multicast messages. If listeners are X hops away in network, must be at least X. + val GANGLIA_KEY_TTL = "ttl" + val GANGLIA_DEFAULT_TTL = 1 + + val GANGLIA_KEY_HOST = "host" + val GANGLIA_KEY_PORT = "port" + + def propertyToOption(prop: String) = Option(property.getProperty(prop)) + + if (!propertyToOption(GANGLIA_KEY_HOST).isDefined) { + throw new Exception("Ganglia sink requires 'host' property.") + } + + if (!propertyToOption(GANGLIA_KEY_PORT).isDefined) { + throw new Exception("Ganglia sink requires 'port' property.") + } + + val host = propertyToOption(GANGLIA_KEY_HOST).get + val port = propertyToOption(GANGLIA_KEY_PORT).get.toInt + val ttl = propertyToOption(GANGLIA_KEY_TTL).map(_.toInt).getOrElse(GANGLIA_DEFAULT_TTL) + val mode = propertyToOption(GANGLIA_KEY_MODE) + .map(u => GMetric.UDPAddressingMode.valueOf(u.toUpperCase)).getOrElse(GANGLIA_DEFAULT_MODE) + val pollPeriod = propertyToOption(GANGLIA_KEY_PERIOD).map(_.toInt) + .getOrElse(GANGLIA_DEFAULT_PERIOD) + val pollUnit = propertyToOption(GANGLIA_KEY_UNIT).map(u => TimeUnit.valueOf(u.toUpperCase)) + .getOrElse(GANGLIA_DEFAULT_UNIT) + + MetricsSystem.checkMinimalPollingPeriod(pollUnit, pollPeriod) + + val ganglia = new GMetric(host, port, mode, ttl) + val reporter: GangliaReporter = GangliaReporter.forRegistry(registry) + .convertDurationsTo(TimeUnit.MILLISECONDS) + .convertRatesTo(TimeUnit.SECONDS) + .build(ganglia) + + override def start() { + reporter.start(pollPeriod, pollUnit) + } + + override def stop() { + reporter.stop() + } +} + diff --git a/core/src/main/scala/org/apache/spark/metrics/sink/MetricsServlet.scala b/core/src/main/scala/org/apache/spark/metrics/sink/MetricsServlet.scala index 4e90dd4323..99357fede6 100644 --- a/core/src/main/scala/org/apache/spark/metrics/sink/MetricsServlet.scala +++ b/core/src/main/scala/org/apache/spark/metrics/sink/MetricsServlet.scala @@ -31,18 +31,21 @@ import org.eclipse.jetty.server.Handler import org.apache.spark.ui.JettyUtils class MetricsServlet(val property: Properties, val registry: MetricRegistry) extends Sink { - val SERVLET_KEY_URI = "uri" + val SERVLET_KEY_PATH = "path" val SERVLET_KEY_SAMPLE = "sample" - val servletURI = property.getProperty(SERVLET_KEY_URI) + val SERVLET_DEFAULT_SAMPLE = false - val servletShowSample = property.getProperty(SERVLET_KEY_SAMPLE).toBoolean + val servletPath = property.getProperty(SERVLET_KEY_PATH) + + val servletShowSample = Option(property.getProperty(SERVLET_KEY_SAMPLE)).map(_.toBoolean) + .getOrElse(SERVLET_DEFAULT_SAMPLE) val mapper = new ObjectMapper().registerModule( new MetricsModule(TimeUnit.SECONDS, TimeUnit.MILLISECONDS, servletShowSample)) def getHandlers = Array[(String, Handler)]( - (servletURI, JettyUtils.createHandler(request => getMetricsSnapshot(request), "text/json")) + (servletPath, JettyUtils.createHandler(request => getMetricsSnapshot(request), "text/json")) ) def getMetricsSnapshot(request: HttpServletRequest): String = { diff --git a/core/src/main/scala/org/apache/spark/network/netty/ShuffleSender.scala b/core/src/main/scala/org/apache/spark/network/netty/ShuffleSender.scala index 537f225469..8afcbe190a 100644 --- a/core/src/main/scala/org/apache/spark/network/netty/ShuffleSender.scala +++ b/core/src/main/scala/org/apache/spark/network/netty/ShuffleSender.scala @@ -20,6 +20,7 @@ package org.apache.spark.network.netty import java.io.File import org.apache.spark.Logging +import org.apache.spark.util.Utils private[spark] class ShuffleSender(portIn: Int, val pResolver: PathResolver) extends Logging { @@ -57,7 +58,7 @@ private[spark] object ShuffleSender { throw new Exception("Block " + blockId + " is not a shuffle block") } // Figure out which local directory it hashes to, and which subdirectory in that - val hash = math.abs(blockId.hashCode) + val hash = Utils.nonNegativeHash(blockId) val dirId = hash % localDirs.length val subDirId = (hash / localDirs.length) % subDirsPerLocalDir val subDir = new File(localDirs(dirId), "%02x".format(subDirId)) diff --git a/core/src/main/scala/org/apache/spark/rdd/RDD.scala b/core/src/main/scala/org/apache/spark/rdd/RDD.scala index 70c967f4bf..ea4eeb7dbf 100644 --- a/core/src/main/scala/org/apache/spark/rdd/RDD.scala +++ b/core/src/main/scala/org/apache/spark/rdd/RDD.scala @@ -270,6 +270,23 @@ abstract class RDD[T: ClassTag]( /** * Return a new RDD that is reduced into `numPartitions` partitions. + * + * This results in a narrow dependency, e.g. if you go from 1000 partitions + * to 100 partitions, there will not be a shuffle, instead each of the 100 + * new partitions will claim 10 of the current partitions. + * + * However, if you're doing a drastic coalesce, e.g. to numPartitions = 1, + * this may result in your computation taking place on fewer nodes than + * you like (e.g. one node in the case of numPartitions = 1). To avoid this, + * you can pass shuffle = true. This will add a shuffle step, but means the + * current upstream partitions will be executed in parallel (per whatever + * the current partitioning is). + * + * Note: With shuffle = true, you can actually coalesce to a larger number + * of partitions. This is useful if you have a small number of partitions, + * say 100, potentially with a few partitions being abnormally large. Calling + * coalesce(1000, shuffle = true) will result in 1000 partitions with the + * data distributed using a hash partitioner. */ def coalesce(numPartitions: Int, shuffle: Boolean = false): RDD[T] = { if (shuffle) { diff --git a/core/src/main/scala/org/apache/spark/scheduler/DAGScheduler.scala b/core/src/main/scala/org/apache/spark/scheduler/DAGScheduler.scala index 854dbfee09..dca84db597 100644 --- a/core/src/main/scala/org/apache/spark/scheduler/DAGScheduler.scala +++ b/core/src/main/scala/org/apache/spark/scheduler/DAGScheduler.scala @@ -479,7 +479,8 @@ class DAGScheduler( SparkEnv.set(env) val rdd = job.finalStage.rdd val split = rdd.partitions(job.partitions(0)) - val taskContext = new TaskContext(job.finalStage.id, job.partitions(0), 0) + val taskContext = + new TaskContext(job.finalStage.id, job.partitions(0), 0, runningLocally = true) try { val result = job.func(taskContext, rdd.iterator(split, taskContext)) job.listener.taskSucceeded(0, result) @@ -532,9 +533,16 @@ class DAGScheduler( tasks += new ResultTask(stage.id, stage.rdd, job.func, partition, locs, id) } } + + val properties = if (idToActiveJob.contains(stage.jobId)) { + idToActiveJob(stage.jobId).properties + } else { + //this stage will be assigned to "default" pool + null + } + // must be run listener before possible NotSerializableException // should be "StageSubmitted" first and then "JobEnded" - val properties = idToActiveJob(stage.jobId).properties listenerBus.post(SparkListenerStageSubmitted(stage, tasks.size, properties)) if (tasks.size > 0) { diff --git a/core/src/main/scala/org/apache/spark/scheduler/DAGSchedulerSource.scala b/core/src/main/scala/org/apache/spark/scheduler/DAGSchedulerSource.scala index 22e3723ac8..446d490cc9 100644 --- a/core/src/main/scala/org/apache/spark/scheduler/DAGSchedulerSource.scala +++ b/core/src/main/scala/org/apache/spark/scheduler/DAGSchedulerSource.scala @@ -20,10 +20,12 @@ package org.apache.spark.scheduler import com.codahale.metrics.{Gauge,MetricRegistry} import org.apache.spark.metrics.source.Source +import org.apache.spark.SparkContext -private[spark] class DAGSchedulerSource(val dagScheduler: DAGScheduler) extends Source { +private[spark] class DAGSchedulerSource(val dagScheduler: DAGScheduler, sc: SparkContext) + extends Source { val metricRegistry = new MetricRegistry() - val sourceName = "DAGScheduler" + val sourceName = "%s.DAGScheduler".format(sc.appName) metricRegistry.register(MetricRegistry.name("stage", "failedStages", "number"), new Gauge[Int] { override def getValue: Int = dagScheduler.failed.size diff --git a/core/src/main/scala/org/apache/spark/scheduler/ResultTask.scala b/core/src/main/scala/org/apache/spark/scheduler/ResultTask.scala index 2b007cbe82..07e8317e3a 100644 --- a/core/src/main/scala/org/apache/spark/scheduler/ResultTask.scala +++ b/core/src/main/scala/org/apache/spark/scheduler/ResultTask.scala @@ -77,7 +77,7 @@ private[spark] class ResultTask[T, U]( var func: (TaskContext, Iterator[T]) => U, var partition: Int, @transient locs: Seq[TaskLocation], - val outputId: Int) + var outputId: Int) extends Task[U](stageId) with Externalizable { def this() = this(0, null, null, 0, null, 0) @@ -93,7 +93,7 @@ private[spark] class ResultTask[T, U]( } override def run(attemptId: Long): U = { - val context = new TaskContext(stageId, partition, attemptId) + val context = new TaskContext(stageId, partition, attemptId, runningLocally = false) metrics = Some(context.taskMetrics) try { func(context, rdd.iterator(split, context)) @@ -130,7 +130,7 @@ private[spark] class ResultTask[T, U]( rdd = rdd_.asInstanceOf[RDD[T]] func = func_.asInstanceOf[(TaskContext, Iterator[T]) => U] partition = in.readInt() - val outputId = in.readInt() + outputId = in.readInt() epoch = in.readLong() split = in.readObject().asInstanceOf[Partition] } diff --git a/core/src/main/scala/org/apache/spark/scheduler/ShuffleMapTask.scala b/core/src/main/scala/org/apache/spark/scheduler/ShuffleMapTask.scala index 764775fede..d23df0dd2b 100644 --- a/core/src/main/scala/org/apache/spark/scheduler/ShuffleMapTask.scala +++ b/core/src/main/scala/org/apache/spark/scheduler/ShuffleMapTask.scala @@ -132,7 +132,7 @@ private[spark] class ShuffleMapTask( override def run(attemptId: Long): MapStatus = { val numOutputSplits = dep.partitioner.numPartitions - val taskContext = new TaskContext(stageId, partition, attemptId) + val taskContext = new TaskContext(stageId, partition, attemptId, runningLocally = false) metrics = Some(taskContext.taskMetrics) val blockManager = SparkEnv.get.blockManager diff --git a/core/src/main/scala/org/apache/spark/scheduler/cluster/ClusterScheduler.scala b/core/src/main/scala/org/apache/spark/scheduler/cluster/ClusterScheduler.scala index 3196ab5022..919acce828 100644 --- a/core/src/main/scala/org/apache/spark/scheduler/cluster/ClusterScheduler.scala +++ b/core/src/main/scala/org/apache/spark/scheduler/cluster/ClusterScheduler.scala @@ -94,7 +94,7 @@ private[spark] class ClusterScheduler(val sc: SparkContext) var rootPool: Pool = null // default scheduler is FIFO val schedulingMode: SchedulingMode = SchedulingMode.withName( - System.getProperty("spark.cluster.schedulingmode", "FIFO")) + System.getProperty("spark.scheduler.mode", "FIFO")) override def setListener(listener: TaskSchedulerListener) { this.listener = listener diff --git a/core/src/main/scala/org/apache/spark/scheduler/cluster/ClusterTaskSetManager.scala b/core/src/main/scala/org/apache/spark/scheduler/cluster/ClusterTaskSetManager.scala index 1b31c8c57e..0ac3d7bcfd 100644 --- a/core/src/main/scala/org/apache/spark/scheduler/cluster/ClusterTaskSetManager.scala +++ b/core/src/main/scala/org/apache/spark/scheduler/cluster/ClusterTaskSetManager.scala @@ -335,7 +335,7 @@ private[spark] class ClusterTaskSetManager( } /** - * Respond to an offer of a single slave from the scheduler by finding a task + * Respond to an offer of a single executor from the scheduler by finding a task */ override def resourceOffer( execId: String, @@ -358,7 +358,7 @@ private[spark] class ClusterTaskSetManager( val task = tasks(index) val taskId = sched.newTaskId() // Figure out whether this should count as a preferred launch - logInfo("Starting task %s:%d as TID %s on slave %s: %s (%s)".format( + logInfo("Starting task %s:%d as TID %s on executor %s: %s (%s)".format( taskSet.id, index, taskId, execId, host, taskLocality)) // Do various bookkeeping copiesRunning(index) += 1 diff --git a/core/src/main/scala/org/apache/spark/scheduler/cluster/SchedulableBuilder.scala b/core/src/main/scala/org/apache/spark/scheduler/cluster/SchedulableBuilder.scala index d04eeb6b98..f80823317b 100644 --- a/core/src/main/scala/org/apache/spark/scheduler/cluster/SchedulableBuilder.scala +++ b/core/src/main/scala/org/apache/spark/scheduler/cluster/SchedulableBuilder.scala @@ -51,8 +51,8 @@ private[spark] class FIFOSchedulableBuilder(val rootPool: Pool) private[spark] class FairSchedulableBuilder(val rootPool: Pool) extends SchedulableBuilder with Logging { - val schedulerAllocFile = System.getProperty("spark.fairscheduler.allocation.file") - val FAIR_SCHEDULER_PROPERTIES = "spark.scheduler.cluster.fair.pool" + val schedulerAllocFile = System.getProperty("spark.scheduler.allocation.file") + val FAIR_SCHEDULER_PROPERTIES = "spark.scheduler.pool" val DEFAULT_POOL_NAME = "default" val MINIMUM_SHARES_PROPERTY = "minShare" val SCHEDULING_MODE_PROPERTY = "schedulingMode" @@ -60,7 +60,7 @@ private[spark] class FairSchedulableBuilder(val rootPool: Pool) val POOL_NAME_PROPERTY = "@name" val POOLS_PROPERTY = "pool" val DEFAULT_SCHEDULING_MODE = SchedulingMode.FIFO - val DEFAULT_MINIMUM_SHARE = 2 + val DEFAULT_MINIMUM_SHARE = 0 val DEFAULT_WEIGHT = 1 override def buildPools() { diff --git a/core/src/main/scala/org/apache/spark/scheduler/cluster/SparkDeploySchedulerBackend.scala b/core/src/main/scala/org/apache/spark/scheduler/cluster/SparkDeploySchedulerBackend.scala index 9a2cf20de7..9c49768c0c 100644 --- a/core/src/main/scala/org/apache/spark/scheduler/cluster/SparkDeploySchedulerBackend.scala +++ b/core/src/main/scala/org/apache/spark/scheduler/cluster/SparkDeploySchedulerBackend.scala @@ -76,17 +76,17 @@ private[spark] class SparkDeploySchedulerBackend( } } - override def executorAdded(executorId: String, workerId: String, hostPort: String, cores: Int, memory: Int) { + override def executorAdded(fullId: String, workerId: String, hostPort: String, cores: Int, memory: Int) { logInfo("Granted executor ID %s on hostPort %s with %d cores, %s RAM".format( - executorId, hostPort, cores, Utils.megabytesToString(memory))) + fullId, hostPort, cores, Utils.megabytesToString(memory))) } - override def executorRemoved(executorId: String, message: String, exitStatus: Option[Int]) { + override def executorRemoved(fullId: String, message: String, exitStatus: Option[Int]) { val reason: ExecutorLossReason = exitStatus match { case Some(code) => ExecutorExited(code) case None => SlaveLost(message) } - logInfo("Executor %s removed: %s".format(executorId, message)) - removeExecutor(executorId, reason.toString) + logInfo("Executor %s removed: %s".format(fullId, message)) + removeExecutor(fullId.split("/")(1), reason.toString) } } diff --git a/core/src/main/scala/org/apache/spark/scheduler/local/LocalScheduler.scala b/core/src/main/scala/org/apache/spark/scheduler/local/LocalScheduler.scala index e8fa5e2f17..8cb4d1396f 100644 --- a/core/src/main/scala/org/apache/spark/scheduler/local/LocalScheduler.scala +++ b/core/src/main/scala/org/apache/spark/scheduler/local/LocalScheduler.scala @@ -91,7 +91,7 @@ private[spark] class LocalScheduler(threads: Int, val maxFailures: Int, val sc: var schedulableBuilder: SchedulableBuilder = null var rootPool: Pool = null val schedulingMode: SchedulingMode = SchedulingMode.withName( - System.getProperty("spark.cluster.schedulingmode", "FIFO")) + System.getProperty("spark.scheduler.mode", "FIFO")) val activeTaskSets = new HashMap[String, TaskSetManager] val taskIdToTaskSetId = new HashMap[Long, String] val taskSetTaskIds = new HashMap[String, HashSet[Long]] diff --git a/core/src/main/scala/org/apache/spark/storage/BlockManagerSource.scala b/core/src/main/scala/org/apache/spark/storage/BlockManagerSource.scala index 3d709cfde4..acc3951088 100644 --- a/core/src/main/scala/org/apache/spark/storage/BlockManagerSource.scala +++ b/core/src/main/scala/org/apache/spark/storage/BlockManagerSource.scala @@ -20,11 +20,13 @@ package org.apache.spark.storage import com.codahale.metrics.{Gauge,MetricRegistry} import org.apache.spark.metrics.source.Source +import org.apache.spark.SparkContext -private[spark] class BlockManagerSource(val blockManager: BlockManager) extends Source { +private[spark] class BlockManagerSource(val blockManager: BlockManager, sc: SparkContext) + extends Source { val metricRegistry = new MetricRegistry() - val sourceName = "BlockManager" + val sourceName = "%s.BlockManager".format(sc.appName) metricRegistry.register(MetricRegistry.name("memory", "maxMem", "MBytes"), new Gauge[Long] { override def getValue: Long = { diff --git a/core/src/main/scala/org/apache/spark/storage/DiskStore.scala b/core/src/main/scala/org/apache/spark/storage/DiskStore.scala index fc25ef0fae..63447baf8c 100644 --- a/core/src/main/scala/org/apache/spark/storage/DiskStore.scala +++ b/core/src/main/scala/org/apache/spark/storage/DiskStore.scala @@ -238,7 +238,7 @@ private class DiskStore(blockManager: BlockManager, rootDirs: String) logDebug("Getting file for block " + blockId) // Figure out which local directory it hashes to, and which subdirectory in that - val hash = math.abs(blockId.hashCode) + val hash = Utils.nonNegativeHash(blockId) val dirId = hash % localDirs.length val subDirId = (hash / localDirs.length) % subDirsPerLocalDir diff --git a/core/src/main/scala/org/apache/spark/storage/StorageLevel.scala b/core/src/main/scala/org/apache/spark/storage/StorageLevel.scala index 755f1a760e..632ff047d1 100644 --- a/core/src/main/scala/org/apache/spark/storage/StorageLevel.scala +++ b/core/src/main/scala/org/apache/spark/storage/StorageLevel.scala @@ -23,9 +23,9 @@ import java.io.{Externalizable, IOException, ObjectInput, ObjectOutput} * Flags for controlling the storage of an RDD. Each StorageLevel records whether to use memory, * whether to drop the RDD to disk if it falls out of memory, whether to keep the data in memory * in a serialized format, and whether to replicate the RDD partitions on multiple nodes. - * The [[org.apache.spark.storage.StorageLevel$]] singleton object contains some static constants for - * commonly useful storage levels. To create your own storage level object, use the factor method - * of the singleton object (`StorageLevel(...)`). + * The [[org.apache.spark.storage.StorageLevel$]] singleton object contains some static constants + * for commonly useful storage levels. To create your own storage level object, use the + * factory method of the singleton object (`StorageLevel(...)`). */ class StorageLevel private( private var useDisk_ : Boolean, diff --git a/core/src/main/scala/org/apache/spark/ui/SparkUI.scala b/core/src/main/scala/org/apache/spark/ui/SparkUI.scala index 48eb096063..f1d86c0221 100644 --- a/core/src/main/scala/org/apache/spark/ui/SparkUI.scala +++ b/core/src/main/scala/org/apache/spark/ui/SparkUI.scala @@ -84,6 +84,6 @@ private[spark] class SparkUI(sc: SparkContext) extends Logging { } private[spark] object SparkUI { - val DEFAULT_PORT = "3030" + val DEFAULT_PORT = "4040" val STATIC_RESOURCE_DIR = "org/apache/spark/ui/static" } diff --git a/core/src/main/scala/org/apache/spark/ui/UIWorkloadGenerator.scala b/core/src/main/scala/org/apache/spark/ui/UIWorkloadGenerator.scala index 0ecb22d2f9..3ec9760ed0 100644 --- a/core/src/main/scala/org/apache/spark/ui/UIWorkloadGenerator.scala +++ b/core/src/main/scala/org/apache/spark/ui/UIWorkloadGenerator.scala @@ -43,13 +43,13 @@ private[spark] object UIWorkloadGenerator { val appName = "Spark UI Tester" if (schedulingMode == SchedulingMode.FAIR) { - System.setProperty("spark.cluster.schedulingmode", "FAIR") + System.setProperty("spark.scheduler.mode", "FAIR") } val sc = new SparkContext(master, appName) def setProperties(s: String) = { if(schedulingMode == SchedulingMode.FAIR) { - sc.setLocalProperty("spark.scheduler.cluster.fair.pool", s) + sc.setLocalProperty("spark.scheduler.pool", s) } sc.setLocalProperty(SparkContext.SPARK_JOB_DESCRIPTION, s) } diff --git a/core/src/main/scala/org/apache/spark/ui/jobs/JobProgressListener.scala b/core/src/main/scala/org/apache/spark/ui/jobs/JobProgressListener.scala index e2bcd98545..5d46f38a2a 100644 --- a/core/src/main/scala/org/apache/spark/ui/jobs/JobProgressListener.scala +++ b/core/src/main/scala/org/apache/spark/ui/jobs/JobProgressListener.scala @@ -95,7 +95,7 @@ private[spark] class JobProgressListener(val sc: SparkContext) extends SparkList activeStages += stage val poolName = Option(stageSubmitted.properties).map { - p => p.getProperty("spark.scheduler.cluster.fair.pool", DEFAULT_POOL_NAME) + p => p.getProperty("spark.scheduler.pool", DEFAULT_POOL_NAME) }.getOrElse(DEFAULT_POOL_NAME) stageToPool(stage) = poolName diff --git a/core/src/main/scala/org/apache/spark/util/Utils.scala b/core/src/main/scala/org/apache/spark/util/Utils.scala index d8d014de7d..be215fc127 100644 --- a/core/src/main/scala/org/apache/spark/util/Utils.scala +++ b/core/src/main/scala/org/apache/spark/util/Utils.scala @@ -464,12 +464,20 @@ private[spark] object Utils extends Logging { def newDaemonFixedThreadPool(nThreads: Int): ThreadPoolExecutor = Executors.newFixedThreadPool(nThreads, daemonThreadFactory).asInstanceOf[ThreadPoolExecutor] + private def listFilesSafely(file: File): Seq[File] = { + val files = file.listFiles() + if (files == null) { + throw new IOException("Failed to list files for dir: " + file) + } + files + } + /** * Delete a file or directory and its contents recursively. */ def deleteRecursively(file: File) { if (file.isDirectory) { - for (child <- file.listFiles()) { + for (child <- listFilesSafely(file)) { deleteRecursively(child) } } @@ -785,4 +793,18 @@ private[spark] object Utils extends Logging { val rawMod = x % mod rawMod + (if (rawMod < 0) mod else 0) } + + // Handles idiosyncracies with hash (add more as required) + def nonNegativeHash(obj: AnyRef): Int = { + + // Required ? + if (obj eq null) return 0 + + val hash = obj.hashCode + // math.abs fails for Int.MinValue + val hashAbs = if (Int.MinValue != hash) math.abs(hash) else 0 + + // Nothing else to guard against ? + hashAbs + } } diff --git a/core/src/test/scala/org/apache/spark/CacheManagerSuite.scala b/core/src/test/scala/org/apache/spark/CacheManagerSuite.scala new file mode 100644 index 0000000000..3a7171c488 --- /dev/null +++ b/core/src/test/scala/org/apache/spark/CacheManagerSuite.scala @@ -0,0 +1,91 @@ +/* + * 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 + +import scala.collection.mutable.ArrayBuffer + +import org.scalatest.{BeforeAndAfter, FunSuite} +import org.scalatest.mock.EasyMockSugar + +import org.apache.spark.rdd.RDD +import org.apache.spark.storage.{BlockManager, StorageLevel} + +// TODO: Test the CacheManager's thread-safety aspects +class CacheManagerSuite extends FunSuite with BeforeAndAfter with EasyMockSugar { + var sc : SparkContext = _ + var blockManager: BlockManager = _ + var cacheManager: CacheManager = _ + var split: Partition = _ + /** An RDD which returns the values [1, 2, 3, 4]. */ + var rdd: RDD[Int] = _ + + before { + sc = new SparkContext("local", "test") + blockManager = mock[BlockManager] + cacheManager = new CacheManager(blockManager) + split = new Partition { override def index: Int = 0 } + rdd = new RDD[Int](sc, Nil) { + override def getPartitions: Array[Partition] = Array(split) + override val getDependencies = List[Dependency[_]]() + override def compute(split: Partition, context: TaskContext) = Array(1, 2, 3, 4).iterator + } + } + + after { + sc.stop() + } + + test("get uncached rdd") { + expecting { + blockManager.get("rdd_0_0").andReturn(None) + blockManager.put("rdd_0_0", ArrayBuffer[Any](1, 2, 3, 4), StorageLevel.MEMORY_ONLY, true). + andReturn(0) + } + + whenExecuting(blockManager) { + val context = new TaskContext(0, 0, 0, runningLocally = false, null) + val value = cacheManager.getOrCompute(rdd, split, context, StorageLevel.MEMORY_ONLY) + assert(value.toList === List(1, 2, 3, 4)) + } + } + + test("get cached rdd") { + expecting { + blockManager.get("rdd_0_0").andReturn(Some(ArrayBuffer(5, 6, 7).iterator)) + } + + whenExecuting(blockManager) { + val context = new TaskContext(0, 0, 0, runningLocally = false, null) + val value = cacheManager.getOrCompute(rdd, split, context, StorageLevel.MEMORY_ONLY) + assert(value.toList === List(5, 6, 7)) + } + } + + test("get uncached local rdd") { + expecting { + // Local computation should not persist the resulting value, so don't expect a put(). + blockManager.get("rdd_0_0").andReturn(None) + } + + whenExecuting(blockManager) { + val context = new TaskContext(0, 0, 0, runningLocally = true, null) + val value = cacheManager.getOrCompute(rdd, split, context, StorageLevel.MEMORY_ONLY) + assert(value.toList === List(1, 2, 3, 4)) + } + } +} diff --git a/core/src/test/scala/org/apache/spark/JavaAPISuite.java b/core/src/test/scala/org/apache/spark/JavaAPISuite.java index 8a869c9005..591c1d498d 100644 --- a/core/src/test/scala/org/apache/spark/JavaAPISuite.java +++ b/core/src/test/scala/org/apache/spark/JavaAPISuite.java @@ -495,7 +495,7 @@ public class JavaAPISuite implements Serializable { @Test public void iterator() { JavaRDD<Integer> rdd = sc.parallelize(Arrays.asList(1, 2, 3, 4, 5), 2); - TaskContext context = new TaskContext(0, 0, 0, null); + TaskContext context = new TaskContext(0, 0, 0, false, null); Assert.assertEquals(1, rdd.iterator(rdd.splits().get(0), context).next().intValue()); } diff --git a/core/src/test/scala/org/apache/spark/metrics/MetricsConfigSuite.scala b/core/src/test/scala/org/apache/spark/metrics/MetricsConfigSuite.scala index 58c94a162d..1a9ce8c607 100644 --- a/core/src/test/scala/org/apache/spark/metrics/MetricsConfigSuite.scala +++ b/core/src/test/scala/org/apache/spark/metrics/MetricsConfigSuite.scala @@ -30,14 +30,13 @@ class MetricsConfigSuite extends FunSuite with BeforeAndAfter { val conf = new MetricsConfig(Option("dummy-file")) conf.initialize() - assert(conf.properties.size() === 5) + assert(conf.properties.size() === 4) assert(conf.properties.getProperty("test-for-dummy") === null) val property = conf.getInstance("random") - assert(property.size() === 3) + assert(property.size() === 2) assert(property.getProperty("sink.servlet.class") === "org.apache.spark.metrics.sink.MetricsServlet") - assert(property.getProperty("sink.servlet.uri") === "/metrics/json") - assert(property.getProperty("sink.servlet.sample") === "false") + assert(property.getProperty("sink.servlet.path") === "/metrics/json") } test("MetricsConfig with properties set") { @@ -45,22 +44,20 @@ class MetricsConfigSuite extends FunSuite with BeforeAndAfter { conf.initialize() val masterProp = conf.getInstance("master") - assert(masterProp.size() === 6) + assert(masterProp.size() === 5) assert(masterProp.getProperty("sink.console.period") === "20") assert(masterProp.getProperty("sink.console.unit") === "minutes") assert(masterProp.getProperty("source.jvm.class") === "org.apache.spark.metrics.source.JvmSource") assert(masterProp.getProperty("sink.servlet.class") === "org.apache.spark.metrics.sink.MetricsServlet") - assert(masterProp.getProperty("sink.servlet.uri") === "/metrics/master/json") - assert(masterProp.getProperty("sink.servlet.sample") === "false") + assert(masterProp.getProperty("sink.servlet.path") === "/metrics/master/json") val workerProp = conf.getInstance("worker") - assert(workerProp.size() === 6) + assert(workerProp.size() === 5) assert(workerProp.getProperty("sink.console.period") === "10") assert(workerProp.getProperty("sink.console.unit") === "seconds") assert(workerProp.getProperty("source.jvm.class") === "org.apache.spark.metrics.source.JvmSource") assert(workerProp.getProperty("sink.servlet.class") === "org.apache.spark.metrics.sink.MetricsServlet") - assert(workerProp.getProperty("sink.servlet.uri") === "/metrics/json") - assert(workerProp.getProperty("sink.servlet.sample") === "false") + assert(workerProp.getProperty("sink.servlet.path") === "/metrics/json") } test("MetricsConfig with subProperties") { @@ -84,6 +81,6 @@ class MetricsConfigSuite extends FunSuite with BeforeAndAfter { assert(consoleProps.size() === 2) val servletProps = sinkProps("servlet") - assert(servletProps.size() === 3) + assert(servletProps.size() === 2) } } diff --git a/core/src/test/scala/org/apache/spark/rdd/RDDSuite.scala b/core/src/test/scala/org/apache/spark/rdd/RDDSuite.scala index adc971050e..c1df5e151e 100644 --- a/core/src/test/scala/org/apache/spark/rdd/RDDSuite.scala +++ b/core/src/test/scala/org/apache/spark/rdd/RDDSuite.scala @@ -140,7 +140,7 @@ class RDDSuite extends FunSuite with SharedSparkContext { assert(rdd.union(emptyKv).collect().size === 2) } - test("cogrouped RDDs") { + test("coalesced RDDs") { val data = sc.parallelize(1 to 10, 10) val coalesced1 = data.coalesce(2) @@ -175,8 +175,14 @@ class RDDSuite extends FunSuite with SharedSparkContext { val coalesced5 = data.coalesce(1, shuffle = true) assert(coalesced5.dependencies.head.rdd.dependencies.head.rdd.asInstanceOf[ShuffledRDD[_, _, _]] != null) + + // when shuffling, we can increase the number of partitions + val coalesced6 = data.coalesce(20, shuffle = true) + assert(coalesced6.partitions.size === 20) + assert(coalesced6.collect().toSet === (1 to 10).toSet) } - test("cogrouped RDDs with locality") { + + test("coalesced RDDs with locality") { val data3 = sc.makeRDD(List((1,List("a","c")), (2,List("a","b","c")), (3,List("b")))) val coal3 = data3.coalesce(3) val list3 = coal3.partitions.map(p => p.asInstanceOf[CoalescedRDDPartition].preferredLocation) @@ -197,11 +203,11 @@ class RDDSuite extends FunSuite with SharedSparkContext { val coalesced4 = data.coalesce(20) val listOfLists = coalesced4.glom().collect().map(_.toList).toList val sortedList = listOfLists.sortWith{ (x, y) => !x.isEmpty && (y.isEmpty || (x(0) < y(0))) } - assert( sortedList === (1 to 9). + assert(sortedList === (1 to 9). map{x => List(x)}.toList, "Tried coalescing 9 partitions to 20 but didn't get 9 back") } - test("cogrouped RDDs with locality, large scale (10K partitions)") { + test("coalesced RDDs with locality, large scale (10K partitions)") { // large scale experiment import collection.mutable val rnd = scala.util.Random diff --git a/core/src/test/scala/org/apache/spark/scheduler/cluster/ClusterSchedulerSuite.scala b/core/src/test/scala/org/apache/spark/scheduler/cluster/ClusterSchedulerSuite.scala index 92ad9f09b2..1b50ce06b3 100644 --- a/core/src/test/scala/org/apache/spark/scheduler/cluster/ClusterSchedulerSuite.scala +++ b/core/src/test/scala/org/apache/spark/scheduler/cluster/ClusterSchedulerSuite.scala @@ -166,7 +166,7 @@ class ClusterSchedulerSuite extends FunSuite with LocalSparkContext with Logging val taskSet = new TaskSet(tasks.toArray,0,0,0,null) val xmlPath = getClass.getClassLoader.getResource("fairscheduler.xml").getFile() - System.setProperty("spark.fairscheduler.allocation.file", xmlPath) + System.setProperty("spark.scheduler.allocation.file", xmlPath) val rootPool = new Pool("", SchedulingMode.FAIR, 0, 0) val schedulableBuilder = new FairSchedulableBuilder(rootPool) schedulableBuilder.buildPools() @@ -179,13 +179,13 @@ class ClusterSchedulerSuite extends FunSuite with LocalSparkContext with Logging assert(rootPool.getSchedulableByName("1").weight === 1) assert(rootPool.getSchedulableByName("2").minShare === 3) assert(rootPool.getSchedulableByName("2").weight === 1) - assert(rootPool.getSchedulableByName("3").minShare === 2) + assert(rootPool.getSchedulableByName("3").minShare === 0) assert(rootPool.getSchedulableByName("3").weight === 1) val properties1 = new Properties() - properties1.setProperty("spark.scheduler.cluster.fair.pool","1") + properties1.setProperty("spark.scheduler.pool","1") val properties2 = new Properties() - properties2.setProperty("spark.scheduler.cluster.fair.pool","2") + properties2.setProperty("spark.scheduler.pool","2") val taskSetManager10 = createDummyTaskSetManager(1, 0, 1, clusterScheduler, taskSet) val taskSetManager11 = createDummyTaskSetManager(1, 1, 1, clusterScheduler, taskSet) diff --git a/core/src/test/scala/org/apache/spark/scheduler/local/LocalSchedulerSuite.scala b/core/src/test/scala/org/apache/spark/scheduler/local/LocalSchedulerSuite.scala index 111340a65c..af76c843e8 100644 --- a/core/src/test/scala/org/apache/spark/scheduler/local/LocalSchedulerSuite.scala +++ b/core/src/test/scala/org/apache/spark/scheduler/local/LocalSchedulerSuite.scala @@ -73,7 +73,7 @@ class LocalSchedulerSuite extends FunSuite with LocalSparkContext { TaskThreadInfo.threadToStarted(threadIndex) = new CountDownLatch(1) new Thread { if (poolName != null) { - sc.setLocalProperty("spark.scheduler.cluster.fair.pool", poolName) + sc.setLocalProperty("spark.scheduler.pool", poolName) } override def run() { val ans = nums.map(number => { @@ -90,7 +90,7 @@ class LocalSchedulerSuite extends FunSuite with LocalSparkContext { } test("Local FIFO scheduler end-to-end test") { - System.setProperty("spark.cluster.schedulingmode", "FIFO") + System.setProperty("spark.scheduler.mode", "FIFO") sc = new SparkContext("local[4]", "test") val sem = new Semaphore(0) @@ -150,9 +150,9 @@ class LocalSchedulerSuite extends FunSuite with LocalSparkContext { test("Local fair scheduler end-to-end test") { sc = new SparkContext("local[8]", "LocalSchedulerSuite") val sem = new Semaphore(0) - System.setProperty("spark.cluster.schedulingmode", "FAIR") + System.setProperty("spark.scheduler.mode", "FAIR") val xmlPath = getClass.getClassLoader.getResource("fairscheduler.xml").getFile() - System.setProperty("spark.fairscheduler.allocation.file", xmlPath) + System.setProperty("spark.scheduler.allocation.file", xmlPath) createThread(10,"1",sc,sem) TaskThreadInfo.threadToStarted(10).await() diff --git a/core/src/test/scala/org/apache/spark/ui/UISuite.scala b/core/src/test/scala/org/apache/spark/ui/UISuite.scala index 3321fb5eb7..07c9f2382b 100644 --- a/core/src/test/scala/org/apache/spark/ui/UISuite.scala +++ b/core/src/test/scala/org/apache/spark/ui/UISuite.scala @@ -24,7 +24,7 @@ import org.eclipse.jetty.server.Server class UISuite extends FunSuite { test("jetty port increases under contention") { - val startPort = 3030 + val startPort = 4040 val server = new Server(startPort) server.start() val (jettyServer1, boundPort1) = JettyUtils.startJettyServer("localhost", startPort, Seq()) diff --git a/docs/_layouts/global.html b/docs/_layouts/global.html index 84749fda4e..238ad26de0 100755 --- a/docs/_layouts/global.html +++ b/docs/_layouts/global.html @@ -51,7 +51,7 @@ <div class="navbar-inner"> <div class="container"> <div class="brand"><a href="index.html"> - <img src="img/spark-logo-77x50px-hd.png" /></a><span class="version">{{site.SPARK_VERSION_SHORT}}</span> + <img src="img/spark-logo-hd.png" style="height:50px;"/></a><span class="version">{{site.SPARK_VERSION_SHORT}}</span> </div> <ul class="nav"> <!--TODO(andyk): Add class="active" attribute to li some how.--> @@ -86,6 +86,7 @@ <li class="dropdown"> <a href="#" class="dropdown-toggle" data-toggle="dropdown">Deploying<b class="caret"></b></a> <ul class="dropdown-menu"> + <li><a href="cluster-overview.html">Overview</a></li> <li><a href="ec2-scripts.html">Amazon EC2</a></li> <li><a href="spark-standalone.html">Standalone Mode</a></li> <li><a href="running-on-mesos.html">Mesos</a></li> @@ -97,10 +98,14 @@ <a href="api.html" class="dropdown-toggle" data-toggle="dropdown">More<b class="caret"></b></a> <ul class="dropdown-menu"> <li><a href="configuration.html">Configuration</a></li> + <li><a href="monitoring.html">Monitoring</a></li> <li><a href="tuning.html">Tuning Guide</a></li> + <li><a href="hadoop-third-party-distributions.html">Running with CDH/HDP</a></li> <li><a href="hardware-provisioning.html">Hardware Provisioning</a></li> + <li><a href="job-scheduling.html">Job Scheduling</a></li> + <li class="divider"></li> <li><a href="building-with-maven.html">Building Spark with Maven</a></li> - <li><a href="contributing-to-spark.html">Contributing to Spark</a></li> + <li><a href="https://cwiki.apache.org/confluence/display/SPARK/Contributing+to+Spark">Contributing to Spark</a></li> </ul> </li> </ul> diff --git a/docs/cluster-overview.md b/docs/cluster-overview.md new file mode 100644 index 0000000000..f679cad713 --- /dev/null +++ b/docs/cluster-overview.md @@ -0,0 +1,117 @@ +--- +layout: global +title: Cluster Mode Overview +--- + +This document gives a short overview of how Spark runs on clusters, to make it easier to understand +the components involved. + +# Components + +Spark applications run as independent sets of processes on a cluster, coordinated by the SparkContext +object in your main program (called the _driver program_). +Specifically, to run on a cluster, the SparkContext can connect to several types of _cluster managers_ +(either Spark's own standalone cluster manager or Mesos/YARN), which allocate resources across +applications. Once connected, Spark acquires *executors* on nodes in the cluster, which are +worker processes that run computations and store data for your application. +Next, it sends your application code (defined by JAR or Python files passed to SparkContext) to +the executors. Finally, SparkContext sends *tasks* for the executors to run. + +<p style="text-align: center;"> + <img src="img/cluster-overview.png" title="Spark cluster components" alt="Spark cluster components" /> +</p> + +There are several useful things to note about this architecture: + +1. Each application gets its own executor processes, which stay up for the duration of the whole + application and run tasks in multiple threads. This has the benefit of isolating applications + from each other, on both the scheduling side (each driver schedules its own tasks) and executor + side (tasks from different applications run in different JVMs). However, it also means that + data cannot be shared across different Spark applications (instances of SparkContext) without + writing it to an external storage system. +2. Spark is agnostic to the underlying cluster manager. As long as it can acquire executor + processes, and these communicate with each other, it is relatively easy to run it even on a + cluster manager that also supports other applications (e.g. Mesos/YARN). +3. Because the driver schedules tasks on the cluster, it should be run close to the worker + nodes, preferably on the same local area network. If you'd like to send requests to the + cluster remotely, it's better to open an RPC to the driver and have it submit operations + from nearby than to run a driver far away from the worker nodes. + +# Cluster Manager Types + +The system currently supports three cluster managers: + +* [Standalone](spark-standalone.html) -- a simple cluster manager included with Spark that makes it + easy to set up a cluster. +* [Apache Mesos](running-on-mesos.html) -- a general cluster manager that can also run Hadoop MapReduce + and service applications. +* [Hadoop YARN](running-on-yarn.html) -- the resource manager in Hadoop 2.0. + +In addition, Spark's [EC2 launch scripts](ec2-scripts.html) make it easy to launch a standalone +cluster on Amazon EC2. + +# Shipping Code to the Cluster + +The recommended way to ship your code to the cluster is to pass it through SparkContext's constructor, +which takes a list of JAR files (Java/Scala) or .egg and .zip libraries (Python) to disseminate to +worker nodes. You can also dynamically add new files to be sent to executors with `SparkContext.addJar` +and `addFile`. + +# Monitoring + +Each driver program has a web UI, typically on port 4040, that displays information about running +tasks, executors, and storage usage. Simply go to `http://<driver-node>:4040` in a web browser to +access this UI. The [monitoring guide](monitoring.html) also describes other monitoring options. + +# Job Scheduling + +Spark gives control over resource allocation both _across_ applications (at the level of the cluster +manager) and _within_ applications (if multiple computations are happening on the same SparkContext). +The [job scheduling overview](job-scheduling.html) describes this in more detail. + +# Glossary + +The following table summarizes terms you'll see used to refer to cluster concepts: + +<table class="table"> + <thead> + <tr><th style="width: 130px;">Term</th><th>Meaning</th></tr> + </thead> + <tbody> + <tr> + <td>Application</td> + <td>User program built on Spark. Consists of a <em>driver program</em> and <em>executors</em> on the cluster.</td> + </tr> + <tr> + <td>Driver program</td> + <td>The process running the main() function of the application and creating the SparkContext</td> + </tr> + <tr> + <td>Cluster manager</td> + <td>An external service for acquiring resources on the cluster (e.g. standalone manager, Mesos, YARN)</td> + </tr> + <tr> + <td>Worker node</td> + <td>Any node that can run application code in the cluster</td> + </tr> + <tr> + <td>Executor</td> + <td>A process launched for an application on a worker node, that runs tasks and keeps data in memory + or disk storage across them. Each application has its own executors.</td> + </tr> + <tr> + <td>Task</td> + <td>A unit of work that will be sent to one executor</td> + </tr> + <tr> + <td>Job</td> + <td>A parallel computation consisting of multiple tasks that gets spawned in response to a Spark action + (e.g. <code>save</code>, <code>collect</code>); you'll see this term used in the driver's logs.</td> + </tr> + <tr> + <td>Stage</td> + <td>Each job gets divided into smaller sets of tasks called <em>stages</em> that depend on each other + (similar to the map and reduce stages in MapReduce); you'll see this term used in the driver's logs.</td> + </tr> + </tbody> +</table> diff --git a/docs/configuration.md b/docs/configuration.md index 310e78a9eb..7940d41a27 100644 --- a/docs/configuration.md +++ b/docs/configuration.md @@ -82,17 +82,6 @@ Apart from these, the following properties are also available, and may be useful <table class="table"> <tr><th>Property Name</th><th>Default</th><th>Meaning</th></tr> <tr> - <td>spark.mesos.coarse</td> - <td>false</td> - <td> - If set to "true", runs over Mesos clusters in - <a href="running-on-mesos.html#mesos-run-modes">"coarse-grained" sharing mode</a>, - where Spark acquires one long-lived Mesos task on each machine instead of one Mesos task per Spark task. - This gives lower-latency scheduling for short queries, but leaves resources in use for the whole - duration of the Spark job. - </td> -</tr> -<tr> <td>spark.default.parallelism</td> <td>8</td> <td> @@ -110,8 +99,19 @@ Apart from these, the following properties are also available, and may be useful </td> </tr> <tr> + <td>spark.mesos.coarse</td> + <td>false</td> + <td> + If set to "true", runs over Mesos clusters in + <a href="running-on-mesos.html#mesos-run-modes">"coarse-grained" sharing mode</a>, + where Spark acquires one long-lived Mesos task on each machine instead of one Mesos task per Spark task. + This gives lower-latency scheduling for short queries, but leaves resources in use for the whole + duration of the Spark job. + </td> +</tr> +<tr> <td>spark.ui.port</td> - <td>3030</td> + <td>4040</td> <td> Port for your application's dashboard, which shows memory and workload data </td> @@ -161,6 +161,16 @@ Apart from these, the following properties are also available, and may be useful </td> </tr> <tr> + <td>spark.scheduler.mode</td> + <td>FIFO</td> + <td> + The <a href="job-scheduling.html#scheduling-within-an-application">scheduling mode</a> between + jobs submitted to the same SparkContext. Can be set to <code>FAIR</code> + to use fair sharing instead of queueing jobs one after another. Useful for + multi-user services. + </td> +</tr> +<tr> <td>spark.reducer.maxMbInFlight</td> <td>48</td> <td> diff --git a/docs/contributing-to-spark.md b/docs/contributing-to-spark.md index 50feeb2d6c..ef1b3ad6da 100644 --- a/docs/contributing-to-spark.md +++ b/docs/contributing-to-spark.md @@ -3,24 +3,6 @@ layout: global title: Contributing to Spark --- -The Spark team welcomes contributions in the form of GitHub pull requests. Here are a few tips to get your contribution in: - -- Break your work into small, single-purpose patches if possible. It's much harder to merge in a large change with a lot of disjoint features. -- Submit the patch as a GitHub pull request. For a tutorial, see the GitHub guides on [forking a repo](https://help.github.com/articles/fork-a-repo) and [sending a pull request](https://help.github.com/articles/using-pull-requests). -- Follow the style of the existing codebase. Specifically, we use [standard Scala style guide](http://docs.scala-lang.org/style/), but with the following changes: - * Maximum line length of 100 characters. - * Always import packages using absolute paths (e.g. `scala.collection.Map` instead of `collection.Map`). - * No "infix" syntax for methods other than operators. For example, don't write `table containsKey myKey`; replace it with `table.containsKey(myKey)`. -- Make sure that your code passes the unit tests. You can run the tests with `sbt/sbt test` in the root directory of Spark. - But first, make sure that you have [configured a spark-env.sh](configuration.html) with at least - `SCALA_HOME`, as some of the tests try to spawn subprocesses using this. -- Add new unit tests for your code. We use [ScalaTest](http://www.scalatest.org/) for testing. Just add a new Suite in `core/src/test`, or methods to an existing Suite. -- If you'd like to report a bug but don't have time to fix it, you can still post it to our [issue tracker]({{site.SPARK_ISSUE_TRACKER_URL}}), or email the [mailing list](http://www.spark-project.org/mailing-lists.html). - -# Licensing of Contributions - -Contributions via GitHub pull requests are gladly accepted from their original author. Along with any pull requests, please -state that the contribution is your original work and that you license the work to the project under the project's open source -license. *Whether or not you state this explicitly, by submitting any copyrighted material via pull request, email, or other -means you agree to license the material under the project's open source license and warrant that you have the legal authority -to do so.* +The Spark team welcomes all forms of contributions, including bug reports, documentation or patches. +For the newest information on how to contribute to the project, please read the +[wiki page on contributing to Spark](https://cwiki.apache.org/confluence/display/SPARK/Contributing+to+Spark). diff --git a/docs/ec2-scripts.md b/docs/ec2-scripts.md index da0c06e2a6..1e5575d657 100644 --- a/docs/ec2-scripts.md +++ b/docs/ec2-scripts.md @@ -80,7 +80,7 @@ another. permissions on your private key file, you can run `launch` with the `--resume` option to restart the setup process on an existing cluster. -# Running Jobs +# Running Applications - Go into the `ec2` directory in the release of Spark you downloaded. - Run `./spark-ec2 -k <keypair> -i <key-file> login <cluster-name>` to @@ -90,7 +90,7 @@ permissions on your private key file, you can run `launch` with the - To deploy code or data within your cluster, you can log in and use the provided script `~/spark-ec2/copy-dir`, which, given a directory path, RSYNCs it to the same location on all the slaves. -- If your job needs to access large datasets, the fastest way to do +- If your application needs to access large datasets, the fastest way to do that is to load them from Amazon S3 or an Amazon EBS device into an instance of the Hadoop Distributed File System (HDFS) on your nodes. The `spark-ec2` script already sets up a HDFS instance for you. It's @@ -103,8 +103,8 @@ permissions on your private key file, you can run `launch` with the (about 3 GB), but you can use the `--ebs-vol-size` option to `spark-ec2` to attach a persistent EBS volume to each node for storing the persistent HDFS. -- Finally, if you get errors while running your jobs, look at the slave's logs - for that job inside of the scheduler work directory (/root/spark/work). You can +- Finally, if you get errors while running your application, look at the slave's logs + for that application inside of the scheduler work directory (/root/spark/work). You can also view the status of the cluster using the web UI: `http://<master-hostname>:8080`. # Configuration diff --git a/docs/hadoop-third-party-distributions.md b/docs/hadoop-third-party-distributions.md new file mode 100644 index 0000000000..f706625fe9 --- /dev/null +++ b/docs/hadoop-third-party-distributions.md @@ -0,0 +1,118 @@ +--- +layout: global +title: Running with Cloudera and HortonWorks +--- + +Spark can run against all versions of Cloudera's Distribution Including Apache Hadoop (CDH) and +the Hortonworks Data Platform (HDP). There are a few things to keep in mind when using Spark +with these distributions: + +# Compile-time Hadoop Version + +When compiling Spark, you'll need to +[set the SPARK_HADOOP_VERSION flag](http://localhost:4000/index.html#a-note-about-hadoop-versions): + + SPARK_HADOOP_VERSION=1.0.4 sbt/sbt assembly + +The table below lists the corresponding `SPARK_HADOOP_VERSION` code for each CDH/HDP release. Note that +some Hadoop releases are binary compatible across client versions. This means the pre-built Spark +distribution may "just work" without you needing to compile. That said, we recommend compiling with +the _exact_ Hadoop version you are running to avoid any compatibility errors. + +<table> + <tr valign="top"> + <td> + <h3>CDH Releases</h3> + <table class="table" style="width:350px; margin-right: 20px;"> + <tr><th>Release</th><th>Version code</th></tr> + <tr><td>CDH 4.X.X (YARN mode)</td><td>2.0.0-chd4.X.X</td></tr> + <tr><td>CDH 4.X.X</td><td>2.0.0-mr1-chd4.X.X</td></tr> + <tr><td>CDH 3u6</td><td>0.20.2-cdh3u6</td></tr> + <tr><td>CDH 3u5</td><td>0.20.2-cdh3u5</td></tr> + <tr><td>CDH 3u4</td><td>0.20.2-cdh3u4</td></tr> + </table> + </td> + <td> + <h3>HDP Releases</h3> + <table class="table" style="width:350px;"> + <tr><th>Release</th><th>Version code</th></tr> + <tr><td>HDP 1.3</td><td>1.2.0</td></tr> + <tr><td>HDP 1.2</td><td>1.1.2</td></tr> + <tr><td>HDP 1.1</td><td>1.0.3</td></tr> + <tr><td>HDP 1.0</td><td>1.0.3</td></tr> + </table> + </td> + </tr> +</table> + +# Linking Applications to the Hadoop Version + +In addition to compiling Spark itself against the right version, you need to add a Maven dependency on that +version of `hadoop-client` to any Spark applications you run, so they can also talk to the HDFS version +on the cluster. If you are using CDH, you also need to add the Cloudera Maven repository. +This looks as follows in SBT: + +{% highlight scala %} +libraryDependencies += "org.apache.hadoop" % "hadoop-client" % "<version>" + +// If using CDH, also add Cloudera repo +resolvers += "Cloudera Repository" at "https://repository.cloudera.com/artifactory/cloudera-repos/" +{% endhighlight %} + +Or in Maven: + +{% highlight xml %} +<project> + <dependencies> + ... + <dependency> + <groupId>org.apache.hadoop</groupId> + <artifactId>hadoop-client</artifactId> + <version>[version]</version> + </dependency> + </dependencies> + + <!-- If using CDH, also add Cloudera repo --> + <repositories> + ... + <repository> + <id>Cloudera repository</id> + <url>https://repository.cloudera.com/artifactory/cloudera-repos/</url> + </repository> + </repositories> +</project> + +{% endhighlight %} + +# Where to Run Spark + +As described in the [Hardware Provisioning](hardware-provisioning.html#storage-systems) guide, +Spark can run in a variety of deployment modes: + +* Using dedicated set of Spark nodes in your cluster. These nodes should be co-located with your + Hadoop installation. +* Running on the same nodes as an existing Hadoop installation, with a fixed amount memory and + cores dedicated to Spark on each node. +* Run Spark alongside Hadoop using a cluster resource manager, such as YARN or Mesos. + +These options are identical for those using CDH and HDP. + +# Inheriting Cluster Configuration + +If you plan to read and write from HDFS using Spark, there are two Hadoop configuration files that +should be included on Spark's classpath: + +* `hdfs-site.xml`, which provides default behaviors for the HDFS client. +* `core-site.xml`, which sets the default filesystem name. + +The location of these configuration files varies across CDH and HDP versions, but +a common location is inside of `/etc/hadoop/conf`. Some tools, such as Cloudera Manager, create +configurations on-the-fly, but offer a mechanisms to download copies of them. + +There are a few ways to make these files visible to Spark: + +* You can copy these files into `$SPARK_HOME/conf` and they will be included in Spark's +classpath automatically. +* If you are running Spark on the same nodes as Hadoop _and_ your distribution includes both +`hdfs-site.xml` and `core-site.xml` in the same directory, you can set `HADOOP_CONF_DIR` +in `$SPARK_HOME/spark-env.sh` to that directory. diff --git a/docs/hardware-provisioning.md b/docs/hardware-provisioning.md index e5f054cb14..790220500a 100644 --- a/docs/hardware-provisioning.md +++ b/docs/hardware-provisioning.md @@ -43,7 +43,7 @@ rest for the operating system and buffer cache. How much memory you will need will depend on your application. To determine how much your application uses for a certain dataset size, load part of your dataset in a Spark RDD and use the -Storage tab of Spark's monitoring UI (`http://<driver-node>:3030`) to see its size in memory. +Storage tab of Spark's monitoring UI (`http://<driver-node>:4040`) to see its size in memory. Note that memory usage is greatly affected by storage level and serialization format -- see the [tuning guide](tuning.html) for tips on how to reduce it. @@ -59,7 +59,7 @@ In our experience, when the data is in memory, a lot of Spark applications are n Using a **10 Gigabit** or higher network is the best way to make these applications faster. This is especially true for "distributed reduce" applications such as group-bys, reduce-bys, and SQL joins. In any given application, you can see how much data Spark shuffles across the network -from the application's monitoring UI (`http://<driver-node>:3030`). +from the application's monitoring UI (`http://<driver-node>:4040`). # CPU Cores diff --git a/docs/img/cluster-overview.png b/docs/img/cluster-overview.png Binary files differnew file mode 100644 index 0000000000..368274068e --- /dev/null +++ b/docs/img/cluster-overview.png diff --git a/docs/img/cluster-overview.pptx b/docs/img/cluster-overview.pptx Binary files differnew file mode 100644 index 0000000000..af3c462cd9 --- /dev/null +++ b/docs/img/cluster-overview.pptx diff --git a/docs/img/spark-logo-hd.png b/docs/img/spark-logo-hd.png Binary files differnew file mode 100644 index 0000000000..1381e3004d --- /dev/null +++ b/docs/img/spark-logo-hd.png diff --git a/docs/index.md b/docs/index.md index 7d73929940..bd386a8a8f 100644 --- a/docs/index.md +++ b/docs/index.md @@ -21,7 +21,7 @@ Spark uses [Simple Build Tool](http://www.scala-sbt.org), which is bundled with For its Scala API, Spark {{site.SPARK_VERSION}} depends on Scala {{site.SCALA_VERSION}}. If you write applications in Scala, you will need to use this same version of Scala in your own program -- newer major versions may not work. You can get the right version of Scala from [scala-lang.org](http://www.scala-lang.org/download/). -# Testing the Build +# Running the Examples and Shell Spark comes with several sample programs in the `examples` directory. To run one of the samples, use `./run-example <class> <params>` in the top-level Spark directory @@ -34,14 +34,16 @@ to connect to. This can be a [URL for a distributed cluster](scala-programming-g or `local` to run locally with one thread, or `local[N]` to run locally with N threads. You should start by using `local` for testing. -Finally, Spark can be used interactively through modified versions of the Scala shell (`./spark-shell`) or -Python interpreter (`./pyspark`). These are a great way to learn Spark. +Finally, you can run Spark interactively through modified versions of the Scala shell (`./spark-shell`) or +Python interpreter (`./pyspark`). These are a great way to learn the framework. -# Running on a Cluster +# Launching on a Cluster -Spark supports several options for deployment: +The Spark [cluster mode overview](cluster-overview.html) explains the key concepts in running on a cluster. +Spark can run both by itself, or over several existing cluster managers. It currently provides several +options for deployment: -* [Amazon EC2](ec2-scripts.html): our scripts let you launch a cluster in about 5 minutes +* [Amazon EC2](ec2-scripts.html): our EC2 scripts let you launch a cluster in about 5 minutes * [Standalone Deploy Mode](spark-standalone.html): simplest way to deploy Spark on a private cluster * [Apache Mesos](running-on-mesos.html) * [Hadoop YARN](running-on-yarn.html) @@ -86,19 +88,21 @@ In addition, if you wish to run Spark on [YARN](running-on-yarn.md), set **Deployment guides:** -* [Running Spark on Amazon EC2](ec2-scripts.html): scripts that let you launch a cluster on EC2 in about 5 minutes +* [Cluster Overview](cluster-overview.html): overview of concepts and components when running on a cluster +* [Amazon EC2](ec2-scripts.html): scripts that let you launch a cluster on EC2 in about 5 minutes * [Standalone Deploy Mode](spark-standalone.html): launch a standalone cluster quickly without a third-party cluster manager -* [Running Spark on Mesos](running-on-mesos.html): deploy a private cluster using +* [Mesos](running-on-mesos.html): deploy a private cluster using [Apache Mesos](http://incubator.apache.org/mesos) -* [Running Spark on YARN](running-on-yarn.html): deploy Spark on top of Hadoop NextGen (YARN) +* [YARN](running-on-yarn.html): deploy Spark on top of Hadoop NextGen (YARN) **Other documents:** * [Configuration](configuration.html): customize Spark via its configuration system * [Tuning Guide](tuning.html): best practices to optimize performance and memory use * [Hardware Provisioning](hardware-provisioning.html): recommendations for cluster hardware -* [Building Spark with Maven](building-with-maven.html): Build Spark using the Maven build tool -* [Contributing to Spark](contributing-to-spark.html) +* [Job Scheduling](job-scheduling.html): scheduling resources across and within Spark applications +* [Building Spark with Maven](building-with-maven.html): build Spark using the Maven system +* [Contributing to Spark](https://cwiki.apache.org/confluence/display/SPARK/Contributing+to+Spark) **External resources:** diff --git a/docs/job-scheduling.md b/docs/job-scheduling.md new file mode 100644 index 0000000000..d304c5497b --- /dev/null +++ b/docs/job-scheduling.md @@ -0,0 +1,168 @@ +--- +layout: global +title: Job Scheduling +--- + +* This will become a table of contents (this text will be scraped). +{:toc} + +# Overview + +Spark has several facilities for scheduling resources between computations. First, recall that, as described +in the [cluster mode overview](cluster-overview.html), each Spark application (instance of SparkContext) +runs an independent set of executor processes. The cluster managers that Spark runs on provide +facilities for [scheduling across applications](#scheduling-across-applications). Second, +_within_ each Spark application, multiple "jobs" (Spark actions) may be running concurrently +if they were submitted by different threads. This is common if your application is serving requests +over the network; for example, the [Shark](http://shark.cs.berkeley.edu) server works this way. Spark +includes a [fair scheduler](#scheduling-within-an-application) to schedule resources within each SparkContext. + +# Scheduling Across Applications + +When running on a cluster, each Spark application gets an independent set of executor JVMs that only +run tasks and store data for that application. If multiple users need to share your cluster, there are +different options to manage allocation, depending on the cluster manager. + +The simplest option, available on all cluster managers, is _static partitioning_ of resources. With +this approach, each application is given a maximum amount of resources it can use, and holds onto them +for its whole duration. This is the approach used in Spark's [standalone](spark-standalone.html) +and [YARN](running-on-yarn.html) modes, as well as the +[coarse-grained Mesos mode](running-on-mesos.html#mesos-run-modes). +Resource allocation can be configured as follows, based on the cluster type: + +* **Standalone mode:** By default, applications submitted to the standalone mode cluster will run in + FIFO (first-in-first-out) order, and each application will try to use all available nodes. You can limit + the number of nodes an application uses by setting the `spark.cores.max` system property in it. This + will allow multiple users/applications to run concurrently. For example, you might launch a long-running + server that uses 10 cores, and allow users to launch shells that use 20 cores each. + Finally, in addition to controlling cores, each application's `spark.executor.memory` setting controls + its memory use. +* **Mesos:** To use static partitioning on Mesos, set the `spark.mesos.coarse` system property to `true`, + and optionally set `spark.cores.max` to limit each application's resource share as in the standalone mode. + You should also set `spark.executor.memory` to control the executor memory. +* **YARN:** The `--num-workers` option to the Spark YARN client controls how many workers it will allocate + on the cluster, while `--worker-memory` and `--worker-cores` control the resources per worker. + +A second option available on Mesos is _dynamic sharing_ of CPU cores. In this mode, each Spark application +still has a fixed and independent memory allocation (set by `spark.executor.memory`), but when the +application is not running tasks on a machine, other applications may run tasks on those cores. This mode +is useful when you expect large numbers of not overly active applications, such as shell sessions from +separate users. However, it comes with a risk of less predictable latency, because it may take a while for +an application to gain back cores on one node when it has work to do. To use this mode, simply use a +`mesos://` URL without setting `spark.mesos.coarse` to true. + +Note that none of the modes currently provide memory sharing across applications. If you would like to share +data this way, we recommend running a single server application that can serve multiple requests by querying +the same RDDs. For example, the [Shark](http://shark.cs.berkeley.edu) JDBC server works this way for SQL +queries. In future releases, in-memory storage systems such as [Tachyon](http://tachyon-project.org) will +provide another approach to share RDDs. + + +# Scheduling Within an Application + +Inside a given Spark application (SparkContext instance), multiple parallel jobs can run simultaneously if +they were submitted from separate threads. By "job", in this section, we mean a Spark action (e.g. `save`, +`collect`) and any tasks that need to run to evaluate that action. Spark's scheduler is fully thread-safe +and supports this use case to enable applications that serve multiple requests (e.g. queries for +multiple users). + +By default, Spark's scheduler runs jobs in FIFO fashion. Each job is divided into "stages" (e.g. map and +reduce phases), and the first job gets priority on all available resources while its stages have tasks to +launch, then the second job gets priority, etc. If the jobs at the head of the queue don't need to use +the whole cluster, later jobs can start to run right away, but if the jobs at the head of the queue are +large, then later jobs may be delayed significantly. + +Starting in Spark 0.8, it is also possible to configure fair sharing between jobs. Under fair sharing, +Spark assigns tasks between jobs in a "round robin" fashion, so that all jobs get a roughly equal share +of cluster resources. This means that short jobs submitted while a long job is running can start receiving +resources right away and still get good response times, without waiting for the long job to finish. This +mode is best for multi-user settings. + +To enable the fair scheduler, simply set the `spark.scheduler.mode` to `FAIR` before creating +a SparkContext: + +{% highlight scala %} +System.setProperty("spark.scheduler.mode", "FAIR") +{% endhighlight %} + +## Fair Scheduler Pools + +The fair scheduler also supports grouping jobs into _pools_, and setting different scheduling options +(e.g. weight) for each pool. This can be useful to create a "high-priority" pool for more important jobs, +for example, or to group the jobs of each user together and give _users_ equal shares regardless of how +many concurrent jobs they have instead of giving _jobs_ equal shares. This approach is modeled after the +[Hadoop Fair Scheduler](http://hadoop.apache.org/docs/stable/fair_scheduler.html). + +Without any intervention, newly submitted jobs go into a _default pool_, but jobs' pools can be set by +adding the `spark.scheduler.pool` "local property" to the SparkContext in the thread that's submitting them. +This is done as follows: + +{% highlight scala %} +// Assuming context is your SparkContext variable +context.setLocalProperty("spark.scheduler.pool", "pool1") +{% endhighlight %} + +After setting this local property, _all_ jobs submitted within this thread (by calls in this thread +to `RDD.save`, `count`, `collect`, etc) will use this pool name. The setting is per-thread to make +it easy to have a thread run multiple jobs on behalf of the same user. If you'd like to clear the +pool that a thread is associated with, simply call: + +{% highlight scala %} +context.setLocalProperty("spark.scheduler.pool", null) +{% endhighlight %} + +## Default Behavior of Pools + +By default, each pool gets an equal share of the cluster (also equal in share to each job in the default +pool), but inside each pool, jobs run in FIFO order. For example, if you create one pool per user, this +means that each user will get an equal share of the cluster, and that each user's queries will run in +order instead of later queries taking resources from that user's earlier ones. + +## Configuring Pool Properties + +Specific pools' properties can also be modified through a configuration file. Each pool supports three +properties: + +* `schedulingMode`: This can be FIFO or FAIR, to control whether jobs within the pool queue up behind + each other (the default) or share the pool's resources fairly. +* `weight`: This controls the pool's share of the cluster relative to other pools. By default, all pools + have a weight of 1. If you give a specific pool a weight of 2, for example, it will get 2x more + resources as other active pools. Setting a high weight such as 1000 also makes it possible to implement + _priority_ between pools---in essence, the weight-1000 pool will always get to launch tasks first + whenever it has jobs active. +* `minShare`: Apart from an overall weight, each pool can be given a _minimum shares_ (as a number of + CPU cores) that the administrator would like it to have. The fair scheduler always attempts to meet + all active pools' minimum shares before redistributing extra resources according to the weights. + The `minShare` property can therefore be another way to ensure that a pool can always get up to a + certain number of resources (e.g. 10 cores) quickly without giving it a high priority for the rest + of the cluster. By default, each pool's `minShare` is 0. + +The pool properties can be set by creating an XML file, similar to `conf/fairscheduler.xml.template`, +and setting the `spark.scheduler.allocation.file` property: + +{% highlight scala %} +System.setProperty("spark.scheduler.allocation.file", "/path/to/file") +{% endhighlight %} + +The format of the XML file is simply a `<pool>` element for each pool, with different elements +within it for the various settings. For example: + +{% highlight xml %} +<?xml version="1.0"?> +<allocations> + <pool name="production"> + <schedulingMode>FAIR</schedulingMode> + <weight>1</weight> + <minShare>2</minShare> + </pool> + <pool name="test"> + <schedulingMode>FIFO</schedulingMode> + <weight>2</weight> + <minShare>3</minShare> + </pool> +</allocations> +{% endhighlight %} + +A full example is also available in `conf/fairscheduler.xml.template`. Note that any pools not +configured in the XML file will simply get default values for all settings (scheduling mode FIFO, +weight 1, and minShare 0). diff --git a/docs/mllib-guide.md b/docs/mllib-guide.md index c897f8b36c..f991d86c8d 100644 --- a/docs/mllib-guide.md +++ b/docs/mllib-guide.md @@ -3,4 +3,194 @@ layout: global title: Machine Learning Library (MLlib) --- -Coming soon. +MLlib is a Spark implementation of some common machine learning (ML) +functionality, as well associated tests and data generators. MLlib +currently supports four common types of machine learning problem settings, +namely, binary classification, regression, clustering and collaborative +filtering, as well as an underlying gradient descent optimization primitive. +This guide will outline the functionality supported in MLlib and also provides +an example of invoking MLlib. + +# Dependencies +MLlib uses the [jblas](https://github.com/mikiobraun/jblas) linear algebra library, which itself +depends on native Fortran routines. You may need to install the +[gfortran runtime library](https://github.com/mikiobraun/jblas/wiki/Missing-Libraries) +if it is not already present on your nodes. MLlib will throw a linking error if it cannot +detect these libraries automatically. + +# Binary Classification + +Binary classification is a supervised learning problem in which we want to +classify entities into one of two distinct categories or labels, e.g., +predicting whether or not emails are spam. This problem involves executing a +learning *Algorithm* on a set of *labeled* examples, i.e., a set of entities +represented via (numerical) features along with underlying category labels. +The algorithm returns a trained *Model* that can predict the label for new +entities for which the underlying label is unknown. + +MLlib currently supports two standard model families for binary classification, +namely [Linear Support Vector Machines +(SVMs)](http://en.wikipedia.org/wiki/Support_vector_machine) and [Logistic +Regression](http://en.wikipedia.org/wiki/Logistic_regression), along with [L1 +and L2 regularized](http://en.wikipedia.org/wiki/Regularization_(mathematics)) +variants of each model family. The training algorithms all leverage an +underlying gradient descent primitive (described +[below](#gradient-descent-primitive)), and take as input a regularization +parameter (*regParam*) along with various parameters associated with gradient +descent (*stepSize*, *numIterations*, *miniBatchFraction*). + +The following code snippet illustrates how to load a sample dataset, execute a +training algorithm on this training data using a static method in the algorithm +object, and make predictions with the resulting model to compute the training +error. + +{% highlight scala %} +import org.apache.spark.SparkContext +import org.apache.spark.mllib.classification.SVMWithSGD +import org.apache.spark.mllib.regression.LabeledPoint + +// Load and parse the data file +val data = sc.textFile("mllib/data/sample_svm_data.txt") +val parsedData = data.map { line => + val parts = line.split(' ') + LabeledPoint(parts(0).toDouble, parts.tail.map(x => x.toDouble).toArray) +} + +// Run training algorithm +val numIterations = 20 +val model = SVMWithSGD.train(parsedData, numIterations) + +// Evaluate model on training examples and compute training error +val labelAndPreds = parsedData.map { point => + val prediction = model.predict(point.features) + (point.label, prediction) +} +val trainErr = labelAndPreds.filter(r => r._1 != r._2).count.toDouble / parsedData.count +println("trainError = " + trainErr) +{% endhighlight %} + +The `SVMWithSGD.train()` method by default performs L2 regularization with the +regularization parameter set to 1.0. If we want to configure this algorithm, we +can customize `SVMWithSGD` further by creating a new object directly and +calling setter methods. All other MLlib algorithms support customization in +this way as well. For example, the following code produces an L1 regularized +variant of SVMs with regularization parameter set to 0.1, and runs the training +algorithm for 200 iterations. + +{% highlight scala %} +import org.apache.spark.mllib.optimization.L1Updater + +val svmAlg = new SVMWithSGD() +svmAlg.optimizer.setNumIterations(200) + .setRegParam(0.1) + .setUpdater(new L1Updater) +val modelL1 = svmAlg.run(parsedData) +{% endhighlight %} + +Both of the code snippets above can be executed in `spark-shell` to generate a +classifier for the provided dataset. + +Available algorithms for binary classification: + +* [SVMWithSGD](api/mllib/index.html#org.apache.spark.mllib.classification.SVMWithSGD) +* [LogisticRegressionWithSGD](api/mllib/index.html#org.apache.spark.mllib.classification.LogisticRegressionWithSGD) + +# Linear Regression + +Linear regression is another classical supervised learning setting. In this +problem, each entity is associated with a real-valued label (as opposed to a +binary label as in binary classification), and we want to predict labels as +closely as possible given numerical features representing entities. MLlib +supports linear regression as well as L1 +([lasso](http://en.wikipedia.org/wiki/Lasso_(statistics)#Lasso_method)) and L2 +([ridge](http://en.wikipedia.org/wiki/Ridge_regression)) regularized variants. +The regression algorithms in MLlib also leverage the underlying gradient +descent primitive (described [below](#gradient-descent-primitive)), and have +the same parameters as the binary classification algorithms described above. + +Available algorithms for linear regression: + +* [LinearRegressionWithSGD](api/mllib/index.html#org.apache.spark.mllib.regression.LinearRegressionWithSGD) +* [RidgeRegressionWithSGD](api/mllib/index.html#org.apache.spark.mllib.regression.RidgeRegressionWithSGD) +* [LassoWithSGD](api/mllib/index.html#org.apache.spark.mllib.regression.LassoWithSGD) + +# Clustering + +Clustering is an unsupervised learning problem whereby we aim to group subsets +of entities with one another based on some notion of similarity. Clustering is +often used for exploratory analysis and/or as a component of a hierarchical +supervised learning pipeline (in which distinct classifiers or regression +models are trained for each cluster). MLlib supports +[k-means](http://en.wikipedia.org/wiki/K-means_clustering) clustering, arguably +the most commonly used clustering approach that clusters the data points into +*k* clusters. The MLlib implementation includes a parallelized +variant of the [k-means++](http://en.wikipedia.org/wiki/K-means%2B%2B) method +called [kmeans||](http://theory.stanford.edu/~sergei/papers/vldb12-kmpar.pdf). +The implementation in MLlib has the following parameters: + +* *k* is the number of clusters. +* *maxIterations* is the maximum number of iterations to run. +* *initializationMode* specifies either random initialization or +initialization via k-means\|\|. +* *runs* is the number of times to run the k-means algorithm (k-means is not +guaranteed to find a globally optimal solution, and when run multiple times on +a given dataset, the algorithm returns the best clustering result). +* *initializiationSteps* determines the number of steps in the k-means\|\| algorithm. +* *epsilon* determines the distance threshold within which we consider k-means to have converged. + +Available algorithms for clustering: + +* [KMeans](api/mllib/index.html#org.apache.spark.mllib.clustering.KMeans) + +# Collaborative Filtering + +[Collaborative +filtering](http://en.wikipedia.org/wiki/Recommender_system#Collaborative_filtering) +is commonly used for recommender systems. These techniques aim to fill in the +missing entries of a user-product association matrix. MLlib currently supports +model-based collaborative filtering, in which users and products are described +by a small set of latent factors that can be used to predict missing entries. +In particular, we implement the [alternating least squares +(ALS)](http://www2.research.att.com/~volinsky/papers/ieeecomputer.pdf) +algorithm to learn these latent factors. The implementation in MLlib has the +following parameters: + +* *numBlocks* is the number of blacks used to parallelize computation (set to -1 to auto-configure). +* *rank* is the number of latent factors in our model. +* *iterations* is the number of iterations to run. +* *lambda* specifies the regularization parameter in ALS. + +Available algorithms for collaborative filtering: + +* [ALS](api/mllib/index.html#org.apache.spark.mllib.recommendation.ALS) + +# Gradient Descent Primitive + +[Gradient descent](http://en.wikipedia.org/wiki/Gradient_descent) (along with +stochastic variants thereof) are first-order optimization methods that are +well-suited for large-scale and distributed computation. Gradient descent +methods aim to find a local minimum of a function by iteratively taking steps +in the direction of the negative gradient of the function at the current point, +i.e., the current parameter value. Gradient descent is included as a low-level +primitive in MLlib, upon which various ML algorithms are developed, and has the +following parameters: + +* *gradient* is a class that computes the stochastic gradient of the function +being optimized, i.e., with respect to a single training example, at the +current parameter value. MLlib includes gradient classes for common loss +functions, e.g., hinge, logistic, least-squares. The gradient class takes as +input a training example, its label, and the current parameter value. +* *updater* is a class that updates weights in each iteration of gradient +descent. MLlib includes updaters for cases without regularization, as well as +L1 and L2 regularizers. +* *stepSize* is a scalar value denoting the initial step size for gradient +descent. All updaters in MLlib use a step size at the t-th step equal to +stepSize / sqrt(t). +* *numIterations* is the number of iterations to run. +* *regParam* is the regularization parameter when using L1 or L2 regularization. +* *miniBatchFraction* is the fraction of the data used to compute the gradient +at each iteration. + +Available algorithms for gradient descent: + +* [GradientDescent](api/mllib/index.html#org.apache.spark.mllib.optimization.GradientDescent) diff --git a/docs/monitoring.md b/docs/monitoring.md new file mode 100644 index 0000000000..5f456b999b --- /dev/null +++ b/docs/monitoring.md @@ -0,0 +1,70 @@ +--- +layout: global +title: Monitoring and Instrumentation +--- + +There are several ways to monitor Spark applications. + +# Web Interfaces + +Every SparkContext launches a web UI, by default on port 4040, that +displays useful information about the application. This includes: + +* A list of scheduler stages and tasks +* A summary of RDD sizes and memory usage +* Information about the running executors +* Environmental information. + +You can access this interface by simply opening `http://<driver-node>:4040` in a web browser. +If multiple SparkContexts are running on the same host, they will bind to succesive ports +beginning with 4040 (4041, 4042, etc). + +Spark's Standlone Mode cluster manager also has its own +[web UI](spark-standalone.html#monitoring-and-logging). + +Note that in both of these UIs, the tables are sortable by clicking their headers, +making it easy to identify slow tasks, data skew, etc. + +# Metrics + +Spark has a configurable metrics system based on the +[Coda Hale Metrics Library](http://metrics.codahale.com/). +This allows users to report Spark metrics to a variety of sinks including HTTP, JMX, and CSV +files. The metrics system is configured via a configuration file that Spark expects to be present +at `$SPARK_HOME/conf/metrics.conf`. A custom file location can be specified via the +`spark.metrics.conf` Java system property. Spark's metrics are decoupled into different +_instances_ corresponding to Spark components. Within each instance, you can configure a +set of sinks to which metrics are reported. The following instances are currently supported: + +* `master`: The Spark standalone master process. +* `applications`: A component within the master which reports on various applications. +* `worker`: A Spark standalone worker process. +* `executor`: A Spark executor. +* `driver`: The Spark driver process (the process in which your SparkContext is created). + +Each instance can report to zero or more _sinks_. Sinks are contained in the +`org.apache.spark.metrics.sink` package: + +* `ConsoleSink`: Logs metrics information to the console. +* `CSVSink`: Exports metrics data to CSV files at regular intervals. +* `GangliaSink`: Sends metrics to a Ganglia node or multicast group. +* `JmxSink`: Registers metrics for viewing in a JXM console. +* `MetricsServlet`: Adds a servlet within the existing Spark UI to serve metrics data as JSON data. + +The syntax of the metrics configuration file is defined in an example configuration file, +`$SPARK_HOME/conf/metrics.conf.template`. + +# Advanced Instrumentation + +Several external tools can be used to help profile the performance of Spark jobs: + +* Cluster-wide monitoring tools, such as [Ganglia](http://ganglia.sourceforge.net/), can provide +insight into overall cluster utilization and resource bottlenecks. For instance, a Ganglia +dashboard can quickly reveal whether a particular workload is disk bound, network bound, or +CPU bound. +* OS profiling tools such as [dstat](http://dag.wieers.com/home-made/dstat/), +[iostat](http://linux.die.net/man/1/iostat), and [iotop](http://linux.die.net/man/1/iotop) +can provide fine-grained profiling on individual nodes. +* JVM utilities such as `jstack` for providing stack traces, `jmap` for creating heap-dumps, +`jstat` for reporting time-series statistics and `jconsole` for visually exploring various JVM +properties are useful for those comfortable with JVM internals. diff --git a/docs/python-programming-guide.md b/docs/python-programming-guide.md index 8c33a953a4..f67a1cc49c 100644 --- a/docs/python-programming-guide.md +++ b/docs/python-programming-guide.md @@ -16,7 +16,7 @@ This guide will show how to use the Spark features described there in Python. There are a few key differences between the Python and Scala APIs: * Python is dynamically typed, so RDDs can hold objects of multiple types. -* PySpark does not yet support a few API calls, such as `lookup`, `sort`, and `persist` at custom storage levels. See the [API docs](api/pyspark/index.html) for details. +* PySpark does not yet support a few API calls, such as `lookup`, `sort`, and non-text input files, though these will be added in future releases. In PySpark, RDDs support the same methods as their Scala counterparts but take Python functions and return Python collection types. Short functions can be passed to RDD methods using Python's [`lambda`](http://www.diveintopython.net/power_of_introspection/lambda_functions.html) syntax: @@ -53,20 +53,20 @@ In addition, PySpark fully supports interactive use---simply run `./pyspark` to # Installing and Configuring PySpark PySpark requires Python 2.6 or higher. -PySpark jobs are executed using a standard CPython interpreter in order to support Python modules that use C extensions. +PySpark applications are executed using a standard CPython interpreter in order to support Python modules that use C extensions. We have not tested PySpark with Python 3 or with alternative Python interpreters, such as [PyPy](http://pypy.org/) or [Jython](http://www.jython.org/). By default, PySpark requires `python` to be available on the system `PATH` and use it to run programs; an alternate Python executable may be specified by setting the `PYSPARK_PYTHON` environment variable in `conf/spark-env.sh` (or `.cmd` on Windows). All of PySpark's library dependencies, including [Py4J](http://py4j.sourceforge.net/), are bundled with PySpark and automatically imported. -Standalone PySpark jobs should be run using the `pyspark` script, which automatically configures the Java and Python environment using the settings in `conf/spark-env.sh` or `.cmd`. +Standalone PySpark applications should be run using the `pyspark` script, which automatically configures the Java and Python environment using the settings in `conf/spark-env.sh` or `.cmd`. The script automatically adds the `pyspark` package to the `PYTHONPATH`. # Interactive Use -The `pyspark` script launches a Python interpreter that is configured to run PySpark jobs. To use `pyspark` interactively, first build Spark, then launch it directly from the command line without any options: +The `pyspark` script launches a Python interpreter that is configured to run PySpark applications. To use `pyspark` interactively, first build Spark, then launch it directly from the command line without any options: {% highlight bash %} $ sbt/sbt assembly @@ -82,7 +82,7 @@ The Python shell can be used explore data interactively and is a simple way to l >>> help(pyspark) # Show all pyspark functions {% endhighlight %} -By default, the `pyspark` shell creates SparkContext that runs jobs locally on a single core. +By default, the `pyspark` shell creates SparkContext that runs applications locally on a single core. To connect to a non-local cluster, or use multiple cores, set the `MASTER` environment variable. For example, to use the `pyspark` shell with a [standalone Spark cluster](spark-standalone.html): @@ -119,13 +119,13 @@ IPython also works on a cluster or on multiple cores if you set the `MASTER` env # Standalone Programs PySpark can also be used from standalone Python scripts by creating a SparkContext in your script and running the script using `pyspark`. -The Quick Start guide includes a [complete example](quick-start.html#a-standalone-job-in-python) of a standalone Python job. +The Quick Start guide includes a [complete example](quick-start.html#a-standalone-app-in-python) of a standalone Python application. Code dependencies can be deployed by listing them in the `pyFiles` option in the SparkContext constructor: {% highlight python %} from pyspark import SparkContext -sc = SparkContext("local", "Job Name", pyFiles=['MyFile.py', 'lib.zip', 'app.egg']) +sc = SparkContext("local", "App Name", pyFiles=['MyFile.py', 'lib.zip', 'app.egg']) {% endhighlight %} Files listed here will be added to the `PYTHONPATH` and shipped to remote worker machines. diff --git a/docs/quick-start.md b/docs/quick-start.md index 70c3df8095..8f782db5b8 100644 --- a/docs/quick-start.md +++ b/docs/quick-start.md @@ -6,7 +6,7 @@ title: Quick Start * This will become a table of contents (this text will be scraped). {:toc} -This tutorial provides a quick introduction to using Spark. We will first introduce the API through Spark's interactive Scala shell (don't worry if you don't know Scala -- you will not need much for this), then show how to write standalone jobs in Scala, Java, and Python. +This tutorial provides a quick introduction to using Spark. We will first introduce the API through Spark's interactive Scala shell (don't worry if you don't know Scala -- you will not need much for this), then show how to write standalone applications in Scala, Java, and Python. See the [programming guide](scala-programming-guide.html) for a more complete reference. To follow along with this guide, you only need to have successfully built Spark on one machine. Simply go into your Spark directory and run: @@ -36,7 +36,7 @@ scala> textFile.count() // Number of items in this RDD res0: Long = 74 scala> textFile.first() // First item in this RDD -res1: String = # Spark +res1: String = # Apache Spark {% endhighlight %} Now let's use a transformation. We will use the [`filter`](scala-programming-guide.html#transformations) transformation to return a new RDD with a subset of the items in the file. @@ -101,20 +101,20 @@ res9: Long = 15 It may seem silly to use Spark to explore and cache a 30-line text file. The interesting part is that these same functions can be used on very large data sets, even when they are striped across tens or hundreds of nodes. You can also do this interactively by connecting `spark-shell` to a cluster, as described in the [programming guide](scala-programming-guide.html#initializing-spark). -# A Standalone Job in Scala -Now say we wanted to write a standalone job using the Spark API. We will walk through a simple job in both Scala (with sbt) and Java (with maven). If you are using other build systems, consider using the Spark assembly JAR described in the developer guide. +# A Standalone App in Scala +Now say we wanted to write a standalone application using the Spark API. We will walk through a simple application in both Scala (with SBT), Java (with Maven), and Python. If you are using other build systems, consider using the Spark assembly JAR described in the developer guide. -We'll create a very simple Spark job in Scala. So simple, in fact, that it's named `SimpleJob.scala`: +We'll create a very simple Spark application in Scala. So simple, in fact, that it's named `SimpleApp.scala`: {% highlight scala %} -/*** SimpleJob.scala ***/ +/*** SimpleApp.scala ***/ import org.apache.spark.SparkContext import org.apache.spark.SparkContext._ -object SimpleJob { +object SimpleApp { def main(args: Array[String]) { val logFile = "$YOUR_SPARK_HOME/README.md" // Should be some file on your system - val sc = new SparkContext("local", "Simple Job", "YOUR_SPARK_HOME", + val sc = new SparkContext("local", "Simple App", "YOUR_SPARK_HOME", List("target/scala-{{site.SCALA_VERSION}}/simple-project_{{site.SCALA_VERSION}}-1.0.jar")) val logData = sc.textFile(logFile, 2).cache() val numAs = logData.filter(line => line.contains("a")).count() @@ -124,7 +124,7 @@ object SimpleJob { } {% endhighlight %} -This job simply counts the number of lines containing 'a' and the number containing 'b' in the Spark README. Note that you'll need to replace $YOUR_SPARK_HOME with the location where Spark is installed. Unlike the earlier examples with the Spark shell, which initializes its own SparkContext, we initialize a SparkContext as part of the job. We pass the SparkContext constructor four arguments, the type of scheduler we want to use (in this case, a local scheduler), a name for the job, the directory where Spark is installed, and a name for the jar file containing the job's sources. The final two arguments are needed in a distributed setting, where Spark is running across several nodes, so we include them for completeness. Spark will automatically ship the jar files you list to slave nodes. +This program simply counts the number of lines containing 'a' and the number containing 'b' in the Spark README. Note that you'll need to replace $YOUR_SPARK_HOME with the location where Spark is installed. Unlike the earlier examples with the Spark shell, which initializes its own SparkContext, we initialize a SparkContext as part of the proogram. We pass the SparkContext constructor four arguments, the type of scheduler we want to use (in this case, a local scheduler), a name for the application, the directory where Spark is installed, and a name for the jar file containing the application's code. The final two arguments are needed in a distributed setting, where Spark is running across several nodes, so we include them for completeness. Spark will automatically ship the jar files you list to slave nodes. This file depends on the Spark API, so we'll also include an sbt configuration file, `simple.sbt` which explains that Spark is a dependency. This file also adds a repository that Spark depends on: @@ -146,7 +146,7 @@ If you also wish to read data from Hadoop's HDFS, you will also need to add a de libraryDependencies += "org.apache.hadoop" % "hadoop-client" % "<your-hdfs-version>" {% endhighlight %} -Finally, for sbt to work correctly, we'll need to layout `SimpleJob.scala` and `simple.sbt` according to the typical directory structure. Once that is in place, we can create a JAR package containing the job's code, then use `sbt run` to execute our example job. +Finally, for sbt to work correctly, we'll need to layout `SimpleApp.scala` and `simple.sbt` according to the typical directory structure. Once that is in place, we can create a JAR package containing the application's code, then use `sbt run` to execute our program. {% highlight bash %} $ find . @@ -155,7 +155,7 @@ $ find . ./src ./src/main ./src/main/scala -./src/main/scala/SimpleJob.scala +./src/main/scala/SimpleApp.scala $ sbt package $ sbt run @@ -163,20 +163,20 @@ $ sbt run Lines with a: 46, Lines with b: 23 {% endhighlight %} -# A Standalone Job In Java -Now say we wanted to write a standalone job using the Java API. We will walk through doing this with Maven. If you are using other build systems, consider using the Spark assembly JAR described in the developer guide. +# A Standalone App in Java +Now say we wanted to write a standalone application using the Java API. We will walk through doing this with Maven. If you are using other build systems, consider using the Spark assembly JAR described in the developer guide. -We'll create a very simple Spark job, `SimpleJob.java`: +We'll create a very simple Spark application, `SimpleApp.java`: {% highlight java %} -/*** SimpleJob.java ***/ +/*** SimpleApp.java ***/ import org.apache.spark.api.java.*; import org.apache.spark.api.java.function.Function; -public class SimpleJob { +public class SimpleApp { public static void main(String[] args) { String logFile = "$YOUR_SPARK_HOME/README.md"; // Should be some file on your system - JavaSparkContext sc = new JavaSparkContext("local", "Simple Job", + JavaSparkContext sc = new JavaSparkContext("local", "Simple App", "$YOUR_SPARK_HOME", new String[]{"target/simple-project-1.0.jar"}); JavaRDD<String> logData = sc.textFile(logFile).cache(); @@ -193,9 +193,9 @@ public class SimpleJob { } {% endhighlight %} -This job simply counts the number of lines containing 'a' and the number containing 'b' in a system log file. Note that you'll need to replace $YOUR_SPARK_HOME with the location where Spark is installed. As with the Scala example, we initialize a SparkContext, though we use the special `JavaSparkContext` class to get a Java-friendly one. We also create RDDs (represented by `JavaRDD`) and run transformations on them. Finally, we pass functions to Spark by creating classes that extend `spark.api.java.function.Function`. The [Java programming guide](java-programming-guide.html) describes these differences in more detail. +This program simply counts the number of lines containing 'a' and the number containing 'b' in a system log file. Note that you'll need to replace $YOUR_SPARK_HOME with the location where Spark is installed. As with the Scala example, we initialize a SparkContext, though we use the special `JavaSparkContext` class to get a Java-friendly one. We also create RDDs (represented by `JavaRDD`) and run transformations on them. Finally, we pass functions to Spark by creating classes that extend `spark.api.java.function.Function`. The [Java programming guide](java-programming-guide.html) describes these differences in more detail. -To build the job, we also write a Maven `pom.xml` file that lists Spark as a dependency. Note that Spark artifacts are tagged with a Scala version. +To build the program, we also write a Maven `pom.xml` file that lists Spark as a dependency. Note that Spark artifacts are tagged with a Scala version. {% highlight xml %} <project> @@ -238,29 +238,29 @@ $ find . ./src ./src/main ./src/main/java -./src/main/java/SimpleJob.java +./src/main/java/SimpleApp.java {% endhighlight %} -Now, we can execute the job using Maven: +Now, we can execute the application using Maven: {% highlight bash %} $ mvn package -$ mvn exec:java -Dexec.mainClass="SimpleJob" +$ mvn exec:java -Dexec.mainClass="SimpleApp" ... Lines with a: 46, Lines with b: 23 {% endhighlight %} -# A Standalone Job In Python -Now we will show how to write a standalone job using the Python API (PySpark). +# A Standalone App in Python +Now we will show how to write a standalone application using the Python API (PySpark). -As an example, we'll create a simple Spark job, `SimpleJob.py`: +As an example, we'll create a simple Spark application, `SimpleApp.py`: {% highlight python %} -"""SimpleJob.py""" +"""SimpleApp.py""" from pyspark import SparkContext logFile = "$YOUR_SPARK_HOME/README.md" # Should be some file on your system -sc = SparkContext("local", "Simple job") +sc = SparkContext("local", "Simple App") logData = sc.textFile(logFile).cache() numAs = logData.filter(lambda s: 'a' in s).count() @@ -270,25 +270,25 @@ print "Lines with a: %i, lines with b: %i" % (numAs, numBs) {% endhighlight %} -This job simply counts the number of lines containing 'a' and the number containing 'b' in a system log file. +This program simply counts the number of lines containing 'a' and the number containing 'b' in a system log file. Note that you'll need to replace $YOUR_SPARK_HOME with the location where Spark is installed. As with the Scala and Java examples, we use a SparkContext to create RDDs. We can pass Python functions to Spark, which are automatically serialized along with any variables that they reference. -For jobs that use custom classes or third-party libraries, we can add those code dependencies to SparkContext to ensure that they will be available on remote machines; this is described in more detail in the [Python programming guide](python-programming-guide.html). -`SimpleJob` is simple enough that we do not need to specify any code dependencies. +For applications that use custom classes or third-party libraries, we can add those code dependencies to SparkContext to ensure that they will be available on remote machines; this is described in more detail in the [Python programming guide](python-programming-guide.html). +`SimpleApp` is simple enough that we do not need to specify any code dependencies. -We can run this job using the `pyspark` script: +We can run this application using the `pyspark` script: {% highlight python %} $ cd $SPARK_HOME -$ ./pyspark SimpleJob.py +$ ./pyspark SimpleApp.py ... Lines with a: 46, Lines with b: 23 {% endhighlight python %} -# Running Jobs on a Cluster +# Running on a Cluster -There are a few additional considerations when running jobs on a +There are a few additional considerations when running applicaitons on a [Spark](spark-standalone.html), [YARN](running-on-yarn.html), or [Mesos](running-on-mesos.html) cluster. @@ -306,7 +306,7 @@ your dependent jars one-by-one when creating a SparkContext. ### Setting Configuration Options Spark includes several configuration options which influence the behavior -of your job. These should be set as +of your application. These should be set as [JVM system properties](configuration.html#system-properties) in your program. The options will be captured and shipped to all slave nodes. diff --git a/docs/running-on-mesos.md b/docs/running-on-mesos.md index b31f78e8bf..322ff585f1 100644 --- a/docs/running-on-mesos.md +++ b/docs/running-on-mesos.md @@ -3,24 +3,23 @@ layout: global title: Running Spark on Mesos --- -Spark can run on private clusters managed by the [Apache Mesos](http://incubator.apache.org/mesos/) resource manager. Follow the steps below to install Mesos and Spark: - -1. Download and build Spark using the instructions [here](index.html). -2. Download Mesos {{site.MESOS_VERSION}} from a [mirror](http://www.apache.org/dyn/closer.cgi/incubator/mesos/mesos-{{site.MESOS_VERSION}}/). -3. Configure Mesos using the `configure` script, passing the location of your `JAVA_HOME` using `--with-java-home`. Mesos comes with "template" configure scripts for different platforms, such as `configure.macosx`, that you can run. See the README file in Mesos for other options. **Note:** If you want to run Mesos without installing it into the default paths on your system (e.g. if you don't have administrative privileges to install it), you should also pass the `--prefix` option to `configure` to tell it where to install. For example, pass `--prefix=/home/user/mesos`. By default the prefix is `/usr/local`. -4. Build Mesos using `make`, and then install it using `make install`. -5. Create a file called `spark-env.sh` in Spark's `conf` directory, by copying `conf/spark-env.sh.template`, and add the following lines it: - * `export MESOS_NATIVE_LIBRARY=<path to libmesos.so>`. This path is usually `<prefix>/lib/libmesos.so` (where the prefix is `/usr/local` by default). Also, on Mac OS X, the library is called `libmesos.dylib` instead of `.so`. -6. Copy Spark and Mesos to the _same_ paths on all the nodes in the cluster (or, for Mesos, `make install` on every node). -7. Configure Mesos for deployment: - * On your master node, edit `<prefix>/var/mesos/deploy/masters` to list your master and `<prefix>/var/mesos/deploy/slaves` to list the slaves, where `<prefix>` is the prefix where you installed Mesos (`/usr/local` by default). - * On all nodes, edit `<prefix>/var/mesos/conf/mesos.conf` and add the line `master=HOST:5050`, where HOST is your master node. - * Run `<prefix>/sbin/mesos-start-cluster.sh` on your master to start Mesos. If all goes well, you should see Mesos's web UI on port 8080 of the master machine. - * See Mesos's README file for more information on deploying it. -8. To run a Spark job against the cluster, when you create your `SparkContext`, pass the string `mesos://HOST:5050` as the first parameter, where `HOST` is the machine running your Mesos master. In addition, pass the location of Spark on your nodes as the third parameter, and a list of JAR files containing your JAR's code as the fourth (these will automatically get copied to the workers). For example: +Spark can run on clusters managed by [Apache Mesos](http://mesos.apache.org/). Follow the steps below to install Mesos and Spark: + +1. Download and build Spark using the instructions [here](index.html). **Note:** Don't forget to consider what version of HDFS you might want to use! +2. Download, build, install, and start Mesos {{site.MESOS_VERSION}} on your cluster. You can download the Mesos distribution from a [mirror](http://www.apache.org/dyn/closer.cgi/mesos/{{site.MESOS_VERSION}}/). See the Mesos [Getting Started](http://mesos.apache.org/gettingstarted) page for more information. **Note:** If you want to run Mesos without installing it into the default paths on your system (e.g., if you don't have administrative privileges to install it), you should also pass the `--prefix` option to `configure` to tell it where to install. For example, pass `--prefix=/home/user/mesos`. By default the prefix is `/usr/local`. +3. Create a Spark "distribution" using `make-distribution.sh`. +4. Rename the `dist` directory created from `make-distribution.sh` to `spark-{{site.SPARK_VERSION}}`. +5. Create a `tar` archive: `tar czf spark-{{site.SPARK_VERSION}}.tar.gz spark-{{site.SPARK_VERSION}}` +6. Upload this archive to HDFS or another place accessible from Mesos via `http://`, e.g., [Amazon Simple Storage Service](http://aws.amazon.com/s3): `hadoop fs -put spark-{{site.SPARK_VERSION}}.tar.gz /path/to/spark-{{site.SPARK_VERSION}}.tar.gz` +7. Create a file called `spark-env.sh` in Spark's `conf` directory, by copying `conf/spark-env.sh.template`, and add the following lines to it: + * `export MESOS_NATIVE_LIBRARY=<path to libmesos.so>`. This path is usually `<prefix>/lib/libmesos.so` (where the prefix is `/usr/local` by default, see above). Also, on Mac OS X, the library is called `libmesos.dylib` instead of `libmesos.so`. + * `export SPARK_EXECUTOR_URI=<path to spark-{{site.SPARK_VERSION}}.tar.gz uploaded above>`. + * `export MASTER=mesos://HOST:PORT` where HOST:PORT is the host and port (default: 5050) of your Mesos master (or `zk://...` if using Mesos with ZooKeeper). +8. To run a Spark application against the cluster, when you create your `SparkContext`, pass the string `mesos://HOST:PORT` as the first parameter. In addition, you'll need to set the `spark.executor.uri` property. For example: {% highlight scala %} -new SparkContext("mesos://HOST:5050", "My Job Name", "/home/user/spark", List("my-job.jar")) +System.setProperty("spark.executor.uri", "<path to spark-{{site.SPARK_VERSION}}.tar.gz uploaded above>") +val sc = new SparkContext("mesos://HOST:5050", "App Name", ...) {% endhighlight %} If you want to run Spark on Amazon EC2, you can use the Spark [EC2 launch scripts](ec2-scripts.html), which provide an easy way to launch a cluster with Mesos, Spark, and HDFS pre-configured. This will get you a cluster in about five minutes without any configuration on your part. @@ -28,24 +27,23 @@ If you want to run Spark on Amazon EC2, you can use the Spark [EC2 launch script # Mesos Run Modes Spark can run over Mesos in two modes: "fine-grained" and "coarse-grained". In fine-grained mode, which is the default, -each Spark task runs as a separate Mesos task. This allows multiple instances of Spark (and other applications) to share -machines at a very fine granularity, where each job gets more or fewer machines as it ramps up, but it comes with an -additional overhead in launching each task, which may be inappropriate for low-latency applications that aim for -sub-second Spark operations (e.g. interactive queries or serving web requests). The coarse-grained mode will instead +each Spark task runs as a separate Mesos task. This allows multiple instances of Spark (and other frameworks) to share +machines at a very fine granularity, where each application gets more or fewer machines as it ramps up, but it comes with an +additional overhead in launching each task, which may be inappropriate for low-latency applications (e.g. interactive queries or serving web requests). The coarse-grained mode will instead launch only *one* long-running Spark task on each Mesos machine, and dynamically schedule its own "mini-tasks" within it. The benefit is much lower startup overhead, but at the cost of reserving the Mesos resources for the complete duration -of the job. +of the application. To run in coarse-grained mode, set the `spark.mesos.coarse` system property to true *before* creating your SparkContext: {% highlight scala %} System.setProperty("spark.mesos.coarse", "true") -val sc = new SparkContext("mesos://HOST:5050", "Job Name", ...) +val sc = new SparkContext("mesos://HOST:5050", "App Name", ...) {% endhighlight %} In addition, for coarse-grained mode, you can control the maximum number of resources Spark will acquire. By default, -it will acquire *all* cores in the cluster (that get offered by Mesos), which only makes sense if you run just a single -job at a time. You can cap the maximum number of cores using `System.setProperty("spark.cores.max", "10")` (for example). +it will acquire *all* cores in the cluster (that get offered by Mesos), which only makes sense if you run just one +application at a time. You can cap the maximum number of cores using `System.setProperty("spark.cores.max", "10")` (for example). Again, this must be done *before* initializing a SparkContext. @@ -53,6 +51,6 @@ Again, this must be done *before* initializing a SparkContext. You can run Spark and Mesos alongside your existing Hadoop cluster by just launching them as a separate service on the machines. To access Hadoop data from Spark, just use a hdfs:// URL (typically `hdfs://<namenode>:9000/path`, but you can find the right URL on your Hadoop Namenode's web UI). -In addition, it is possible to also run Hadoop MapReduce on Mesos, to get better resource isolation and sharing between the two. In this case, Mesos will act as a unified scheduler that assigns cores to either Hadoop or Spark, as opposed to having them share resources via the Linux scheduler on each node. Please refer to the Mesos wiki page on [Running Hadoop on Mesos](https://github.com/mesos/mesos/wiki/Running-Hadoop-on-Mesos). +In addition, it is possible to also run Hadoop MapReduce on Mesos, to get better resource isolation and sharing between the two. In this case, Mesos will act as a unified scheduler that assigns cores to either Hadoop or Spark, as opposed to having them share resources via the Linux scheduler on each node. Please refer to [Hadoop on Mesos](https://github.com/mesos/hadoop). In either case, HDFS runs separately from Hadoop MapReduce, without going through Mesos. diff --git a/docs/running-on-yarn.md b/docs/running-on-yarn.md index 93421efcbc..c611db0af4 100644 --- a/docs/running-on-yarn.md +++ b/docs/running-on-yarn.md @@ -42,7 +42,7 @@ This would be used to connect to the cluster, write to the dfs and submit jobs t The command to launch the YARN Client is as follows: - SPARK_JAR=<SPARK_YARN_JAR_FILE> ./spark-class org.apache.spark.deploy.yarn.Client \ + SPARK_JAR=<SPARK_ASSEMBLY_JAR_FILE> ./spark-class org.apache.spark.deploy.yarn.Client \ --jar <YOUR_APP_JAR_FILE> \ --class <APP_MAIN_CLASS> \ --args <APP_MAIN_ARGUMENTS> \ @@ -54,14 +54,27 @@ The command to launch the YARN Client is as follows: For example: - SPARK_JAR=./yarn/target/spark-yarn-assembly-{{site.SPARK_VERSION}}.jar ./spark-class org.apache.spark.deploy.yarn.Client \ - --jar examples/target/scala-{{site.SCALA_VERSION}}/spark-examples_{{site.SCALA_VERSION}}-{{site.SPARK_VERSION}}.jar \ - --class org.apache.spark.examples.SparkPi \ - --args yarn-standalone \ - --num-workers 3 \ - --master-memory 4g \ - --worker-memory 2g \ - --worker-cores 1 + # Build the Spark assembly JAR and the Spark examples JAR + $ SPARK_HADOOP_VERSION=2.0.5-alpha SPARK_YARN=true ./sbt/sbt assembly + + # Configure logging + $ cp conf/log4j.properties.template conf/log4j.properties + + # Submit Spark's ApplicationMaster to YARN's ResourceManager, and instruct Spark to run the SparkPi example + $ SPARK_JAR=./assembly/target/scala-{{site.SCALA_VERSION}}/spark-assembly-{{site.SPARK_VERSION}}-hadoop2.0.5-alpha.jar \ + ./spark-class org.apache.spark.deploy.yarn.Client \ + --jar examples/target/scala-{{site.SCALA_VERSION}}/spark-examples-assembly-{{site.SPARK_VERSION}}.jar \ + --class org.apache.spark.examples.SparkPi \ + --args yarn-standalone \ + --num-workers 3 \ + --master-memory 4g \ + --worker-memory 2g \ + --worker-cores 1 + + # Examine the output (replace $YARN_APP_ID in the following with the "application identifier" output by the previous command) + # (Note: YARN_APP_LOGS_DIR is usually /tmp/logs or $HADOOP_HOME/logs/userlogs depending on the Hadoop version.) + $ cat $YARN_APP_LOGS_DIR/$YARN_APP_ID/container*_000001/stdout + Pi is roughly 3.13794 The above starts a YARN Client programs which periodically polls the Application Master for status updates and displays them in the console. The client will exit once your application has finished running. diff --git a/docs/scala-programming-guide.md b/docs/scala-programming-guide.md index f7768e55fc..03647a2ad2 100644 --- a/docs/scala-programming-guide.md +++ b/docs/scala-programming-guide.md @@ -87,10 +87,10 @@ For running on YARN, Spark launches an instance of the standalone deploy cluster ### Deploying Code on a Cluster -If you want to run your job on a cluster, you will need to specify the two optional parameters to `SparkContext` to let it find your code: +If you want to run your application on a cluster, you will need to specify the two optional parameters to `SparkContext` to let it find your code: * `sparkHome`: The path at which Spark is installed on your worker machines (it should be the same on all of them). -* `jars`: A list of JAR files on the local machine containing your job's code and any dependencies, which Spark will deploy to all the worker nodes. You'll need to package your job into a set of JARs using your build system. For example, if you're using SBT, the [sbt-assembly](https://github.com/sbt/sbt-assembly) plugin is a good way to make a single JAR with your code and dependencies. +* `jars`: A list of JAR files on the local machine containing your application's code and any dependencies, which Spark will deploy to all the worker nodes. You'll need to package your application into a set of JARs using your build system. For example, if you're using SBT, the [sbt-assembly](https://github.com/sbt/sbt-assembly) plugin is a good way to make a single JAR with your code and dependencies. If you run `spark-shell` on a cluster, you can add JARs to it by specifying the `ADD_JARS` environment variable before you launch it. This variable should contain a comma-separated list of JARs. For example, `ADD_JARS=a.jar,b.jar ./spark-shell` will launch a shell with `a.jar` and `b.jar` on its classpath. In addition, any new classes you define in the shell will automatically be distributed. diff --git a/docs/spark-standalone.md b/docs/spark-standalone.md index 994a96f2c9..81cdbefd0c 100644 --- a/docs/spark-standalone.md +++ b/docs/spark-standalone.md @@ -3,13 +3,21 @@ layout: global title: Spark Standalone Mode --- -In addition to running on the Mesos or YARN cluster managers, Spark also provides a simple standalone deploy mode. You can launch a standalone cluster either manually, by starting a master and workers by hand, or use our provided [deploy scripts](#cluster-launch-scripts). It is also possible to run these daemons on a single machine for testing. +In addition to running on the Mesos or YARN cluster managers, Spark also provides a simple standalone deploy mode. You can launch a standalone cluster either manually, by starting a master and workers by hand, or use our provided [launch scripts](#cluster-launch-scripts). It is also possible to run these daemons on a single machine for testing. + +# Installing Spark Standalone to a Cluster + +The easiest way to deploy Spark is by running the `./make-distribution.sh` script to create a binary distribution. +This distribution can be deployed to any machine with the Java runtime installed; there is no need to install Scala. + +The recommended procedure is to deploy and start the master on one node first, get the master spark URL, +then modify `conf/spark-env.sh` in the `dist/` directory before deploying to all the other nodes. # Starting a Cluster Manually You can start a standalone master server by executing: - ./spark-class org.apache.spark.deploy.master.Master + ./bin/start-master.sh Once started, the master will print out a `spark://HOST:PORT` URL for itself, which you can use to connect workers to it, or pass as the "master" argument to `SparkContext`. You can also find this URL on @@ -22,7 +30,7 @@ Similarly, you can start one or more workers and connect them to the master via: Once you have started a worker, look at the master's web UI ([http://localhost:8080](http://localhost:8080) by default). You should see the new node listed there, along with its number of CPUs and memory (minus one gigabyte left for the OS). -Finally, the following configuration options can be passed to the master and worker: +Finally, the following configuration options can be passed to the master and worker: <table class="table"> <tr><th style="width:21%">Argument</th><th>Meaning</th></tr> @@ -40,11 +48,11 @@ Finally, the following configuration options can be passed to the master and wor </tr> <tr> <td><code>-c CORES</code>, <code>--cores CORES</code></td> - <td>Total CPU cores to allow Spark jobs to use on the machine (default: all available); only on worker</td> + <td>Total CPU cores to allow Spark applicatons to use on the machine (default: all available); only on worker</td> </tr> <tr> <td><code>-m MEM</code>, <code>--memory MEM</code></td> - <td>Total amount of memory to allow Spark jobs to use on the machine, in a format like 1000M or 2G (default: your machine's total RAM minus 1 GB); only on worker</td> + <td>Total amount of memory to allow Spark applicatons to use on the machine, in a format like 1000M or 2G (default: your machine's total RAM minus 1 GB); only on worker</td> </tr> <tr> <td><code>-d DIR</code>, <code>--work-dir DIR</code></td> @@ -55,7 +63,7 @@ Finally, the following configuration options can be passed to the master and wor # Cluster Launch Scripts -To launch a Spark standalone cluster with the deploy scripts, you need to create a file called `conf/slaves` in your Spark directory, which should contain the hostnames of all the machines where you would like to start Spark workers, one per line. The master machine must be able to access each of the slave machines via password-less `ssh` (using a private key). For testing, you can just put `localhost` in this file. +To launch a Spark standalone cluster with the launch scripts, you need to create a file called `conf/slaves` in your Spark directory, which should contain the hostnames of all the machines where you would like to start Spark workers, one per line. The master machine must be able to access each of the slave machines via password-less `ssh` (using a private key). For testing, you can just put `localhost` in this file. Once you've set up this file, you can launch or stop your cluster with the following shell scripts, based on Hadoop's deploy scripts, and available in `SPARK_HOME/bin`: @@ -90,15 +98,15 @@ You can optionally configure the cluster further by setting environment variable </tr> <tr> <td><code>SPARK_WORKER_DIR</code></td> - <td>Directory to run jobs in, which will include both logs and scratch space (default: SPARK_HOME/work).</td> + <td>Directory to run applications in, which will include both logs and scratch space (default: SPARK_HOME/work).</td> </tr> <tr> <td><code>SPARK_WORKER_CORES</code></td> - <td>Total number of cores to allow Spark jobs to use on the machine (default: all available cores).</td> + <td>Total number of cores to allow Spark applications to use on the machine (default: all available cores).</td> </tr> <tr> <td><code>SPARK_WORKER_MEMORY</code></td> - <td>Total amount of memory to allow Spark jobs to use on the machine, e.g. <code>1000m</code>, <code>2g</code> (default: total memory minus 1 GB); note that each job's <i>individual</i> memory is configured using its <code>spark.executor.memory</code> property.</td> + <td>Total amount of memory to allow Spark applications to use on the machine, e.g. <code>1000m</code>, <code>2g</code> (default: total memory minus 1 GB); note that each application's <i>individual</i> memory is configured using its <code>spark.executor.memory</code> property.</td> </tr> <tr> <td><code>SPARK_WORKER_WEBUI_PORT</code></td> @@ -125,22 +133,28 @@ You can optionally configure the cluster further by setting environment variable **Note:** The launch scripts do not currently support Windows. To run a Spark cluster on Windows, start the master and workers by hand. -# Connecting a Job to the Cluster +# Connecting an Application to the Cluster -To run a job on the Spark cluster, simply pass the `spark://IP:PORT` URL of the master as to the [`SparkContext` +To run an application on the Spark cluster, simply pass the `spark://IP:PORT` URL of the master as to the [`SparkContext` constructor](scala-programming-guide.html#initializing-spark). To run an interactive Spark shell against the cluster, run the following command: MASTER=spark://IP:PORT ./spark-shell +Note that if you are running spark-shell from one of the spark cluster machines, the `spark-shell` script will +automatically set MASTER from the `SPARK_MASTER_IP` and `SPARK_MASTER_PORT` variables in `conf/spark-env.sh`. + +You can also pass an option `-c <numCores>` to control the number of cores that spark-shell uses on the cluster. -# Job Scheduling +# Resource Scheduling -The standalone cluster mode currently only supports a simple FIFO scheduler across jobs. -However, to allow multiple concurrent jobs, you can control the maximum number of resources each Spark job will acquire. -By default, it will acquire *all* the cores in the cluster, which only makes sense if you run just a single -job at a time. You can cap the number of cores using `System.setProperty("spark.cores.max", "10")` (for example). +The standalone cluster mode currently only supports a simple FIFO scheduler across applications. +However, to allow multiple concurrent users, you can control the maximum number of resources each +application will acquire. +By default, it will acquire *all* cores in the cluster, which only makes sense if you just run one +application at a time. You can cap the number of cores using +`System.setProperty("spark.cores.max", "10")` (for example). This value must be set *before* initializing your SparkContext. diff --git a/ec2/deploy.generic/root/spark-ec2/ec2-variables.sh b/ec2/deploy.generic/root/spark-ec2/ec2-variables.sh index 675429c57e..42e8faa26e 100644 --- a/ec2/deploy.generic/root/spark-ec2/ec2-variables.sh +++ b/ec2/deploy.generic/root/spark-ec2/ec2-variables.sh @@ -1,5 +1,22 @@ #!/usr/bin/env bash +# +# 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. +# + # These variables are automatically filled in by the spark-ec2 script. export MASTERS="{{master_list}}" export SLAVES="{{slave_list}}" diff --git a/ec2/spark_ec2.py b/ec2/spark_ec2.py index 932e70db96..419d0fe13f 100755 --- a/ec2/spark_ec2.py +++ b/ec2/spark_ec2.py @@ -215,11 +215,10 @@ def launch_cluster(conn, opts, cluster_name): master_group.authorize(src_group=slave_group) master_group.authorize('tcp', 22, 22, '0.0.0.0/0') master_group.authorize('tcp', 8080, 8081, '0.0.0.0/0') - master_group.authorize('tcp', 33000, 33000, '0.0.0.0/0') master_group.authorize('tcp', 50030, 50030, '0.0.0.0/0') master_group.authorize('tcp', 50070, 50070, '0.0.0.0/0') master_group.authorize('tcp', 60070, 60070, '0.0.0.0/0') - master_group.authorize('tcp', 3030, 3035, '0.0.0.0/0') + master_group.authorize('tcp', 4040, 4045, '0.0.0.0/0') if opts.ganglia: master_group.authorize('tcp', 5080, 5080, '0.0.0.0/0') if slave_group.rules == []: # Group was just now created diff --git a/examples/pom.xml b/examples/pom.xml index 740d3be242..9eb6c8a77f 100644 --- a/examples/pom.xml +++ b/examples/pom.xml @@ -127,20 +127,6 @@ </dependency> </dependencies> - <profiles> - <profile> - <id>hadoop2-yarn</id> - <dependencies> - <dependency> - <groupId>org.apache.spark</groupId> - <artifactId>spark-yarn</artifactId> - <version>${project.version}</version> - <scope>provided</scope> - </dependency> - </dependencies> - </profile> - </profiles> - <build> <outputDirectory>target/scala-${scala.version}/classes</outputDirectory> <testOutputDirectory>target/scala-${scala.version}/test-classes</testOutputDirectory> diff --git a/make-distribution.sh b/make-distribution.sh index 91f6278491..bffb19843c 100755 --- a/make-distribution.sh +++ b/make-distribution.sh @@ -95,7 +95,7 @@ cp $FWDIR/assembly/target/scala*/*assembly*hadoop*.jar "$DISTDIR/jars/" # Copy other things mkdir "$DISTDIR"/conf -cp -r "$FWDIR/conf/*.template" "$DISTDIR" +cp "$FWDIR/conf/*.template" "$DISTDIR"/conf cp -r "$FWDIR/bin" "$DISTDIR" cp -r "$FWDIR/python" "$DISTDIR" cp "$FWDIR/spark-class" "$DISTDIR" diff --git a/mllib/data/sample_svm_data.txt b/mllib/data/sample_svm_data.txt new file mode 100644 index 0000000000..7ab30bd93c --- /dev/null +++ b/mllib/data/sample_svm_data.txt @@ -0,0 +1,322 @@ +1 0 2.52078447201548 0 0 0 2.004684436494304 2.000347299268466 0 2.228387042742021 2.228387042742023 0 0 0 0 0 0 +0 2.857738033247042 0 0 2.619965104088255 0 2.004684436494304 2.000347299268466 0 2.228387042742021 2.228387042742023 0 0 0 0 0 0 +0 2.857738033247042 0 2.061393766919624 0 0 2.004684436494304 0 0 2.228387042742021 2.228387042742023 0 0 0 0 0 0 +1 0 0 2.061393766919624 2.619965104088255 0 2.004684436494304 2.000347299268466 0 0 0 0 2.055002875864414 0 0 0 0 +1 2.857738033247042 0 2.061393766919624 2.619965104088255 0 2.004684436494304 0 0 0 0 0 2.055002875864414 0 0 0 0 +0 2.857738033247042 0 2.061393766919624 2.619965104088255 0 2.004684436494304 2.000347299268466 0 2.228387042742021 2.228387042742023 0 0 0 0 0 0 +1 0 0 0 2.619965104088255 0 2.004684436494304 0 0 2.228387042742021 2.228387042742023 0 2.055002875864414 0 0 0 0 +1 0 0 0 2.619965104088255 0 2.004684436494304 0 0 2.228387042742021 2.228387042742023 0 2.055002875864414 0 0 0 0 +0 2.857738033247042 0 2.061393766919624 2.619965104088255 0 2.004684436494304 2.000347299268466 2.122974378789621 2.228387042742021 2.228387042742023 0 0 0 0 12.72816758217773 0 +0 2.857738033247042 0 0 2.619965104088255 0 0 0 0 2.228387042742021 2.228387042742023 0 2.055002875864414 0 0 0 0 +1 2.857738033247042 0 0 2.619965104088255 0 0 2.000347299268466 0 2.228387042742021 2.228387042742023 0 0 0 0 0 0 +1 2.857738033247042 0 0 2.619965104088255 0 2.004684436494304 2.000347299268466 2.122974378789621 0 0 0 0 0 0 0 0 +1 0 0 0 0 4.745052855503306 2.004684436494304 0 2.122974378789621 2.228387042742021 2.228387042742023 0 0 0 0 0 0 +1 2.857738033247042 0 0 2.619965104088255 0 2.004684436494304 0 2.122974378789621 2.228387042742021 2.228387042742023 0 2.055002875864414 0 0 0 0 +0 2.857738033247042 0 0 2.619965104088255 0 0 0 0 2.228387042742021 2.228387042742023 0 2.055002875864414 0 0 0 0 +0 0 0 2.061393766919624 2.619965104088255 0 0 0 2.122974378789621 2.228387042742021 2.228387042742023 0 0 0 0 0 0 +0 2.857738033247042 0 0 0 0 2.004684436494304 0 2.122974378789621 2.228387042742021 2.228387042742023 0 0 0 0 0 0 +0 2.857738033247042 0 0 2.619965104088255 0 0 2.000347299268466 0 2.228387042742021 2.228387042742023 0 2.055002875864414 0 0 0 0 +0 2.857738033247042 0 0 2.619965104088255 0 2.004684436494304 0 0 2.228387042742021 2.228387042742023 0 2.055002875864414 0 0 0 0 +1 2.857738033247042 0 0 2.619965104088255 0 0 2.000347299268466 0 2.228387042742021 2.228387042742023 0 0 0 0 0 0 +0 2.857738033247042 0 0 2.619965104088255 0 2.004684436494304 2.000347299268466 0 2.228387042742021 2.228387042742023 0 0 0 0 0 0 +0 2.857738033247042 0 0 0 0 2.004684436494304 0 0 2.228387042742021 2.228387042742023 0 2.055002875864414 0 0 0 0 +0 2.857738033247042 0 0 2.619965104088255 0 2.004684436494304 2.000347299268466 2.122974378789621 2.228387042742021 2.228387042742023 0 0 0 0 0 0 +1 2.857738033247042 0 2.061393766919624 2.619965104088255 0 0 0 0 2.228387042742021 2.228387042742023 0 2.055002875864414 0 0 0 0 +1 2.857738033247042 0 0 2.619965104088255 0 2.004684436494304 2.000347299268466 0 2.228387042742021 2.228387042742023 0 0 0 0 0 0 +1 2.857738033247042 0 2.061393766919624 2.619965104088255 0 2.004684436494304 2.000347299268466 2.122974378789621 2.228387042742021 2.228387042742023 0 0 0 0 0 0 +0 2.857738033247042 0 2.061393766919624 2.619965104088255 0 0 2.000347299268466 2.122974378789621 2.228387042742021 2.228387042742023 0 0 0 0 0 0 +1 2.857738033247042 0 2.061393766919624 2.619965104088255 0 2.004684436494304 2.000347299268466 0 0 0 0 0 0 0 0 0 +0 2.857738033247042 0 0 2.619965104088255 0 2.004684436494304 0 0 2.228387042742021 2.228387042742023 0 0 0 0 0 0 +1 2.857738033247042 0 0 2.619965104088255 0 2.004684436494304 2.000347299268466 0 0 0 0 2.055002875864414 0 0 0 0 +1 2.857738033247042 2.52078447201548 0 2.619965104088255 0 2.004684436494304 2.000347299268466 0 2.228387042742021 2.228387042742023 0 0 0 0 0 0 +0 0 0 0 2.619965104088255 0 0 2.000347299268466 0 2.228387042742021 2.228387042742023 0 2.055002875864414 0 0 0 0 +1 2.857738033247042 0 2.061393766919624 2.619965104088255 0 0 0 0 2.228387042742021 2.228387042742023 0 2.055002875864414 0 0 0 0 +0 2.857738033247042 0 0 2.619965104088255 0 2.004684436494304 0 2.122974378789621 0 0 0 2.055002875864414 0 0 0 0 +1 2.857738033247042 2.52078447201548 2.061393766919624 2.619965104088255 0 0 0 0 2.228387042742021 2.228387042742023 0 0 0 0 0 0 +0 2.857738033247042 2.52078447201548 0 2.619965104088255 0 0 0 0 2.228387042742021 2.228387042742023 0 0 0 0 0 0 +1 0 0 2.061393766919624 2.619965104088255 0 2.004684436494304 0 0 2.228387042742021 2.228387042742023 0 0 0 0 0 0 +1 2.857738033247042 0 2.061393766919624 0 0 2.004684436494304 2.000347299268466 0 2.228387042742021 2.228387042742023 0 2.055002875864414 0 0 0 0 +1 0 0 0 2.619965104088255 0 2.004684436494304 0 2.122974378789621 2.228387042742021 2.228387042742023 0 0 0 0 0 0 +0 2.857738033247042 0 0 2.619965104088255 0 2.004684436494304 2.000347299268466 0 2.228387042742021 2.228387042742023 0 2.055002875864414 0 0 0 0 +1 2.857738033247042 0 0 2.619965104088255 0 0 2.000347299268466 0 2.228387042742021 2.228387042742023 0 0 0 0 0 0 +0 2.857738033247042 0 0 2.619965104088255 0 2.004684436494304 0 2.122974378789621 2.228387042742021 2.228387042742023 0 0 0 0 0 0 +0 2.857738033247042 0 0 2.619965104088255 0 2.004684436494304 2.000347299268466 0 2.228387042742021 2.228387042742023 0 2.055002875864414 0 0 0 0 +1 2.857738033247042 2.52078447201548 0 2.619965104088255 0 2.004684436494304 2.000347299268466 0 0 0 0 0 0 0 0 0 +1 0 0 0 2.619965104088255 0 2.004684436494304 0 0 2.228387042742021 2.228387042742023 0 2.055002875864414 0 0 0 0 +0 2.857738033247042 0 0 2.619965104088255 0 2.004684436494304 2.000347299268466 0 0 0 0 2.055002875864414 0 0 0 0 +1 2.857738033247042 0 2.061393766919624 2.619965104088255 0 2.004684436494304 2.000347299268466 0 0 0 0 2.055002875864414 0 0 0 0 +0 2.857738033247042 2.52078447201548 0 0 0 2.004684436494304 0 2.122974378789621 0 0 0 2.055002875864414 0 0 0 0 +1 2.857738033247042 0 0 2.619965104088255 0 2.004684436494304 2.000347299268466 2.122974378789621 2.228387042742021 2.228387042742023 6.857275130999357 2.055002875864414 0 0 0 0 +1 2.857738033247042 0 2.061393766919624 2.619965104088255 0 0 2.000347299268466 0 0 0 0 2.055002875864414 0 0 0 0 +0 2.857738033247042 0 2.061393766919624 0 0 0 2.000347299268466 0 2.228387042742021 2.228387042742023 0 0 0 0 0 0 +0 2.857738033247042 0 0 2.619965104088255 0 0 0 0 2.228387042742021 2.228387042742023 0 2.055002875864414 0 0 0 0 +0 0 0 0 2.619965104088255 0 2.004684436494304 2.000347299268466 2.122974378789621 0 0 0 0 0 10.4087817597473 0 0 +1 2.857738033247042 0 0 2.619965104088255 0 2.004684436494304 2.000347299268466 2.122974378789621 2.228387042742021 2.228387042742023 0 0 0 0 0 0 +1 2.857738033247042 0 0 2.619965104088255 0 0 2.000347299268466 0 2.228387042742021 2.228387042742023 0 0 0 0 0 0 +0 2.857738033247042 2.52078447201548 0 2.619965104088255 0 0 0 0 2.228387042742021 2.228387042742023 0 0 0 0 0 0 +0 2.857738033247042 0 0 2.619965104088255 0 2.004684436494304 2.000347299268466 0 2.228387042742021 2.228387042742023 0 0 0 0 0 0 +0 2.857738033247042 0 0 2.619965104088255 0 2.004684436494304 0 0 2.228387042742021 2.228387042742023 0 2.055002875864414 0 0 0 0 +1 2.857738033247042 0 2.061393766919624 2.619965104088255 0 0 0 2.122974378789621 0 0 0 2.055002875864414 0 0 0 0 +1 2.857738033247042 2.52078447201548 2.061393766919624 2.619965104088255 0 2.004684436494304 0 0 0 0 0 0 0 0 0 0 +0 2.857738033247042 0 0 2.619965104088255 0 0 0 0 2.228387042742021 2.228387042742023 0 2.055002875864414 0 0 0 0 +0 2.857738033247042 0 0 2.619965104088255 0 2.004684436494304 2.000347299268466 0 2.228387042742021 2.228387042742023 0 2.055002875864414 0 0 0 0 +1 2.857738033247042 0 2.061393766919624 2.619965104088255 0 0 2.000347299268466 0 2.228387042742021 2.228387042742023 0 2.055002875864414 0 0 0 0 +1 2.857738033247042 0 2.061393766919624 2.619965104088255 0 0 2.000347299268466 0 2.228387042742021 2.228387042742023 0 2.055002875864414 0 0 0 0 +1 2.857738033247042 0 0 2.619965104088255 0 0 2.000347299268466 0 2.228387042742021 2.228387042742023 0 0 0 0 0 0 +0 2.857738033247042 0 2.061393766919624 2.619965104088255 0 2.004684436494304 0 0 2.228387042742021 2.228387042742023 0 2.055002875864414 0 0 0 0 +0 0 0 2.061393766919624 0 0 0 2.000347299268466 0 2.228387042742021 2.228387042742023 0 2.055002875864414 0 0 0 0 +0 2.857738033247042 2.52078447201548 0 2.619965104088255 0 0 0 0 2.228387042742021 2.228387042742023 0 0 0 0 0 0 +1 2.857738033247042 0 2.061393766919624 0 0 2.004684436494304 0 0 2.228387042742021 2.228387042742023 0 0 0 0 0 0 +1 2.857738033247042 0 2.061393766919624 2.619965104088255 0 2.004684436494304 2.000347299268466 2.122974378789621 2.228387042742021 2.228387042742023 0 0 12.72816758217773 0 0 0 +0 2.857738033247042 0 2.061393766919624 2.619965104088255 0 2.004684436494304 0 0 0 0 0 2.055002875864414 0 0 0 0 +0 2.857738033247042 0 2.061393766919624 0 0 0 2.000347299268466 0 2.228387042742021 2.228387042742023 0 0 0 0 0 0 +0 2.857738033247042 0 0 2.619965104088255 4.745052855503306 0 2.000347299268466 0 0 0 0 2.055002875864414 0 0 0 0 +0 2.857738033247042 0 2.061393766919624 2.619965104088255 0 0 2.000347299268466 0 2.228387042742021 2.228387042742023 0 2.055002875864414 0 0 0 0 +1 2.857738033247042 0 0 2.619965104088255 0 2.004684436494304 0 0 2.228387042742021 2.228387042742023 0 0 0 0 0 0 +1 2.857738033247042 0 0 2.619965104088255 0 2.004684436494304 2.000347299268466 0 2.228387042742021 2.228387042742023 0 0 0 0 0 0 +1 0 2.52078447201548 2.061393766919624 2.619965104088255 0 2.004684436494304 2.000347299268466 0 0 0 0 0 0 0 0 0 +1 2.857738033247042 0 0 2.619965104088255 0 2.004684436494304 2.000347299268466 0 0 0 0 2.055002875864414 0 0 0 0 +1 0 0 2.061393766919624 2.619965104088255 0 2.004684436494304 0 0 2.228387042742021 2.228387042742023 0 0 0 0 0 0 +0 2.857738033247042 0 0 2.619965104088255 0 0 0 0 2.228387042742021 2.228387042742023 0 2.055002875864414 0 0 0 0 +1 2.857738033247042 2.52078447201548 0 2.619965104088255 0 2.004684436494304 0 0 2.228387042742021 2.228387042742023 0 0 0 0 0 0 +0 2.857738033247042 0 0 2.619965104088255 0 2.004684436494304 2.000347299268466 0 2.228387042742021 2.228387042742023 0 0 0 0 0 0 +1 2.857738033247042 0 0 2.619965104088255 0 0 0 0 2.228387042742021 2.228387042742023 0 2.055002875864414 0 0 0 0 +1 2.857738033247042 0 2.061393766919624 0 0 0 0 2.122974378789621 2.228387042742021 2.228387042742023 0 0 0 0 0 0 +1 2.857738033247042 0 0 2.619965104088255 0 0 2.000347299268466 0 2.228387042742021 2.228387042742023 0 0 0 0 0 0 +0 2.857738033247042 0 0 0 0 2.004684436494304 2.000347299268466 0 2.228387042742021 2.228387042742023 0 0 0 0 0 0 +1 2.857738033247042 0 0 2.619965104088255 0 0 2.000347299268466 2.122974378789621 2.228387042742021 2.228387042742023 0 0 0 0 0 0 +1 2.857738033247042 0 0 2.619965104088255 0 2.004684436494304 2.000347299268466 0 2.228387042742021 2.228387042742023 0 2.055002875864414 0 0 0 0 +0 2.857738033247042 0 0 2.619965104088255 0 2.004684436494304 2.000347299268466 2.122974378789621 0 0 0 2.055002875864414 0 0 0 0 +1 0 2.52078447201548 0 2.619965104088255 0 2.004684436494304 0 0 2.228387042742021 2.228387042742023 0 0 0 0 0 0 +1 2.857738033247042 2.52078447201548 0 2.619965104088255 0 2.004684436494304 2.000347299268466 0 2.228387042742021 2.228387042742023 0 0 0 0 0 0 +0 2.857738033247042 0 0 2.619965104088255 0 0 2.000347299268466 0 2.228387042742021 2.228387042742023 0 0 0 0 0 0 +0 2.857738033247042 0 0 2.619965104088255 0 2.004684436494304 0 2.122974378789621 2.228387042742021 2.228387042742023 0 0 0 0 0 0 +1 2.857738033247042 0 0 2.619965104088255 0 2.004684436494304 2.000347299268466 2.122974378789621 0 0 0 0 0 0 0 0 +0 0 2.52078447201548 2.061393766919624 2.619965104088255 0 0 0 0 2.228387042742021 2.228387042742023 0 0 0 0 0 0 +1 2.857738033247042 0 0 2.619965104088255 0 2.004684436494304 0 2.122974378789621 2.228387042742021 2.228387042742023 0 0 0 0 0 0 +0 2.857738033247042 2.52078447201548 2.061393766919624 0 0 2.004684436494304 0 2.122974378789621 0 0 0 0 0 0 0 0 +1 2.857738033247042 0 0 2.619965104088255 0 0 2.000347299268466 2.122974378789621 2.228387042742021 2.228387042742023 0 0 0 0 0 0 +1 2.857738033247042 0 2.061393766919624 2.619965104088255 0 2.004684436494304 2.000347299268466 0 0 0 0 2.055002875864414 0 0 0 0 +1 2.857738033247042 0 0 2.619965104088255 0 0 2.000347299268466 0 2.228387042742021 2.228387042742023 0 0 0 0 0 0 +0 2.857738033247042 0 2.061393766919624 2.619965104088255 0 2.004684436494304 0 2.122974378789621 0 0 0 2.055002875864414 0 0 0 0 +1 2.857738033247042 0 2.061393766919624 2.619965104088255 0 2.004684436494304 0 0 0 0 0 2.055002875864414 0 0 0 0 +1 2.857738033247042 0 0 0 0 0 2.000347299268466 0 2.228387042742021 2.228387042742023 0 2.055002875864414 0 0 0 0 +1 2.857738033247042 0 2.061393766919624 2.619965104088255 0 2.004684436494304 0 2.122974378789621 0 0 0 0 0 0 0 0 +0 2.857738033247042 0 0 2.619965104088255 4.745052855503306 0 0 0 2.228387042742021 2.228387042742023 0 0 0 0 0 0 +1 2.857738033247042 0 0 2.619965104088255 0 2.004684436494304 0 0 2.228387042742021 2.228387042742023 0 0 0 0 0 0 +0 2.857738033247042 0 0 2.619965104088255 0 2.004684436494304 2.000347299268466 0 0 0 0 2.055002875864414 0 0 0 0 +0 2.857738033247042 0 0 2.619965104088255 0 2.004684436494304 0 2.122974378789621 2.228387042742021 2.228387042742023 0 2.055002875864414 0 0 0 0 +0 2.857738033247042 0 2.061393766919624 2.619965104088255 0 2.004684436494304 0 2.122974378789621 2.228387042742021 2.228387042742023 0 0 0 0 0 0 +1 0 2.52078447201548 2.061393766919624 2.619965104088255 0 0 0 0 2.228387042742021 2.228387042742023 0 0 0 0 0 0 +1 2.857738033247042 0 0 2.619965104088255 0 0 0 0 2.228387042742021 2.228387042742023 0 2.055002875864414 0 0 0 0 +0 2.857738033247042 0 0 2.619965104088255 0 0 0 0 2.228387042742021 2.228387042742023 0 2.055002875864414 0 0 0 0 +0 2.857738033247042 0 0 0 0 0 2.000347299268466 0 2.228387042742021 2.228387042742023 0 2.055002875864414 0 0 0 0 +1 2.857738033247042 0 0 2.619965104088255 0 2.004684436494304 2.000347299268466 0 2.228387042742021 2.228387042742023 0 2.055002875864414 0 0 0 0 +0 0 0 2.061393766919624 2.619965104088255 0 2.004684436494304 0 2.122974378789621 2.228387042742021 2.228387042742023 0 0 0 0 0 0 +0 2.857738033247042 0 2.061393766919624 2.619965104088255 0 0 0 2.122974378789621 2.228387042742021 2.228387042742023 0 0 0 0 0 0 +1 0 0 0 2.619965104088255 0 0 2.000347299268466 2.122974378789621 2.228387042742021 2.228387042742023 0 0 0 0 0 0 +0 2.857738033247042 0 0 2.619965104088255 0 0 0 2.122974378789621 2.228387042742021 2.228387042742023 0 0 0 0 0 0 +1 2.857738033247042 0 2.061393766919624 0 0 2.004684436494304 0 0 2.228387042742021 2.228387042742023 0 0 0 0 0 0 +0 2.857738033247042 2.52078447201548 0 2.619965104088255 0 2.004684436494304 2.000347299268466 0 0 0 0 0 0 0 0 0 +0 2.857738033247042 0 2.061393766919624 2.619965104088255 0 2.004684436494304 0 2.122974378789621 0 0 0 0 0 0 0 0 +1 2.857738033247042 0 0 2.619965104088255 0 0 0 2.122974378789621 2.228387042742021 2.228387042742023 0 0 0 0 0 0 +0 2.857738033247042 0 2.061393766919624 0 0 2.004684436494304 2.000347299268466 0 0 0 0 2.055002875864414 0 0 0 0 +0 2.857738033247042 0 0 2.619965104088255 0 2.004684436494304 2.000347299268466 2.122974378789621 0 0 0 0 0 0 0 0 +1 0 0 2.061393766919624 2.619965104088255 0 2.004684436494304 2.000347299268466 0 2.228387042742021 2.228387042742023 0 0 0 0 0 0 +0 2.857738033247042 0 2.061393766919624 2.619965104088255 0 2.004684436494304 0 2.122974378789621 2.228387042742021 2.228387042742023 0 0 0 0 0 0 +0 0 2.52078447201548 2.061393766919624 2.619965104088255 0 2.004684436494304 2.000347299268466 2.122974378789621 0 0 0 0 0 0 0 0 +1 2.857738033247042 0 0 0 0 0 2.000347299268466 0 2.228387042742021 2.228387042742023 0 2.055002875864414 0 0 0 0 +0 2.857738033247042 0 0 2.619965104088255 0 2.004684436494304 2.000347299268466 0 2.228387042742021 2.228387042742023 0 0 0 0 0 0 +1 2.857738033247042 0 0 2.619965104088255 0 2.004684436494304 2.000347299268466 0 0 0 0 2.055002875864414 0 0 0 0 +0 2.857738033247042 0 2.061393766919624 2.619965104088255 0 2.004684436494304 2.000347299268466 0 0 0 0 0 0 0 0 0 +1 0 0 0 2.619965104088255 0 0 0 2.122974378789621 2.228387042742021 2.228387042742023 6.857275130999357 0 0 0 0 0 +0 2.857738033247042 2.52078447201548 0 2.619965104088255 0 0 0 2.122974378789621 0 0 0 2.055002875864414 0 0 0 0 +1 2.857738033247042 2.52078447201548 0 2.619965104088255 0 0 2.000347299268466 2.122974378789621 0 0 0 0 0 0 0 0 +1 2.857738033247042 0 0 2.619965104088255 0 2.004684436494304 2.000347299268466 2.122974378789621 2.228387042742021 2.228387042742023 0 2.055002875864414 0 0 0 0 +1 2.857738033247042 0 0 2.619965104088255 4.745052855503306 2.004684436494304 2.000347299268466 0 0 0 0 0 0 0 0 0 +1 2.857738033247042 0 0 2.619965104088255 0 0 2.000347299268466 0 2.228387042742021 2.228387042742023 0 0 0 0 0 0 +1 0 2.52078447201548 2.061393766919624 2.619965104088255 0 2.004684436494304 2.000347299268466 0 0 0 0 0 0 0 0 0 +1 2.857738033247042 0 2.061393766919624 2.619965104088255 0 2.004684436494304 0 0 2.228387042742021 2.228387042742023 0 2.055002875864414 0 0 0 0 +1 2.857738033247042 0 0 2.619965104088255 0 2.004684436494304 0 2.122974378789621 2.228387042742021 2.228387042742023 0 0 0 0 0 0 +0 2.857738033247042 0 0 2.619965104088255 0 2.004684436494304 2.000347299268466 0 0 0 0 2.055002875864414 0 0 0 0 +0 2.857738033247042 0 2.061393766919624 2.619965104088255 0 2.004684436494304 0 2.122974378789621 0 0 0 0 0 0 0 0 +0 2.857738033247042 0 0 2.619965104088255 0 2.004684436494304 2.000347299268466 0 2.228387042742021 2.228387042742023 0 2.055002875864414 0 0 0 0 +1 0 0 0 2.619965104088255 0 2.004684436494304 0 2.122974378789621 2.228387042742021 2.228387042742023 0 0 0 0 0 0 +0 0 0 0 2.619965104088255 0 0 0 2.122974378789621 2.228387042742021 2.228387042742023 0 2.055002875864414 0 0 0 0 +1 2.857738033247042 0 2.061393766919624 2.619965104088255 4.745052855503306 2.004684436494304 2.000347299268466 0 0 0 0 2.055002875864414 0 0 0 0 +1 2.857738033247042 2.52078447201548 2.061393766919624 0 0 0 2.000347299268466 0 2.228387042742021 2.228387042742023 0 0 0 0 0 0 +1 2.857738033247042 0 0 2.619965104088255 0 2.004684436494304 2.000347299268466 0 2.228387042742021 2.228387042742023 0 0 0 0 0 0 +1 2.857738033247042 0 0 2.619965104088255 0 2.004684436494304 2.000347299268466 0 2.228387042742021 2.228387042742023 0 0 0 0 0 0 +1 2.857738033247042 0 0 2.619965104088255 0 0 0 0 2.228387042742021 2.228387042742023 0 2.055002875864414 0 0 0 0 +1 2.857738033247042 0 0 0 0 0 2.000347299268466 2.122974378789621 2.228387042742021 2.228387042742023 0 0 0 0 0 0 +0 2.857738033247042 0 0 2.619965104088255 0 0 0 2.122974378789621 2.228387042742021 2.228387042742023 0 0 0 0 0 0 +1 2.857738033247042 0 0 2.619965104088255 0 0 2.000347299268466 2.122974378789621 0 0 0 2.055002875864414 0 0 0 0 +0 0 2.52078447201548 2.061393766919624 2.619965104088255 0 2.004684436494304 2.000347299268466 0 0 0 0 0 0 0 0 0 +1 2.857738033247042 0 0 2.619965104088255 0 2.004684436494304 0 0 2.228387042742021 2.228387042742023 0 0 0 0 0 0 +1 2.857738033247042 0 2.061393766919624 0 0 0 0 2.122974378789621 2.228387042742021 2.228387042742023 0 0 0 0 0 0 +1 0 0 2.061393766919624 2.619965104088255 4.745052855503306 2.004684436494304 2.000347299268466 0 0 0 0 0 0 0 0 0 +1 2.857738033247042 2.52078447201548 2.061393766919624 2.619965104088255 0 0 0 0 2.228387042742021 2.228387042742023 0 0 0 0 0 0 +0 2.857738033247042 0 2.061393766919624 0 0 0 0 2.122974378789621 2.228387042742021 2.228387042742023 0 2.055002875864414 0 0 0 0 +0 2.857738033247042 0 0 2.619965104088255 0 0 0 0 2.228387042742021 2.228387042742023 0 2.055002875864414 0 0 0 0 +1 2.857738033247042 0 0 2.619965104088255 0 2.004684436494304 0 0 2.228387042742021 2.228387042742023 0 0 0 0 0 0 +0 2.857738033247042 2.52078447201548 0 2.619965104088255 0 0 0 0 2.228387042742021 2.228387042742023 0 2.055002875864414 0 0 0 0 +1 2.857738033247042 0 0 2.619965104088255 0 2.004684436494304 0 0 2.228387042742021 2.228387042742023 0 0 0 0 0 0 +0 2.857738033247042 0 0 2.619965104088255 0 0 0 2.122974378789621 2.228387042742021 2.228387042742023 0 0 0 0 0 0 +1 2.857738033247042 0 0 2.619965104088255 0 0 0 2.122974378789621 2.228387042742021 2.228387042742023 0 0 0 0 0 0 +1 2.857738033247042 0 0 2.619965104088255 0 0 0 0 2.228387042742021 2.228387042742023 0 2.055002875864414 0 0 0 0 +1 0 2.52078447201548 0 0 0 2.004684436494304 2.000347299268466 0 2.228387042742021 2.228387042742023 0 0 0 0 0 0 +1 2.857738033247042 0 0 2.619965104088255 0 0 2.000347299268466 0 2.228387042742021 2.228387042742023 0 2.055002875864414 0 0 0 0 +1 2.857738033247042 0 2.061393766919624 2.619965104088255 0 0 0 2.122974378789621 0 0 0 2.055002875864414 0 0 0 0 +1 2.857738033247042 0 0 2.619965104088255 0 2.004684436494304 2.000347299268466 0 2.228387042742021 2.228387042742023 0 0 0 0 0 0 +0 2.857738033247042 0 2.061393766919624 2.619965104088255 0 2.004684436494304 0 0 2.228387042742021 2.228387042742023 0 0 0 0 0 0 +1 2.857738033247042 2.52078447201548 0 2.619965104088255 0 2.004684436494304 0 2.122974378789621 0 0 0 0 0 0 0 0 +0 0 0 2.061393766919624 2.619965104088255 0 0 2.000347299268466 0 2.228387042742021 2.228387042742023 0 0 0 0 0 0 +0 2.857738033247042 2.52078447201548 0 2.619965104088255 0 0 2.000347299268466 0 2.228387042742021 2.228387042742023 0 0 0 0 0 0 +1 2.857738033247042 0 2.061393766919624 2.619965104088255 0 0 0 0 2.228387042742021 2.228387042742023 0 0 0 0 0 0 +0 2.857738033247042 0 2.061393766919624 0 0 2.004684436494304 2.000347299268466 0 2.228387042742021 2.228387042742023 0 0 0 0 0 0 +1 2.857738033247042 0 2.061393766919624 2.619965104088255 0 0 0 0 2.228387042742021 2.228387042742023 0 2.055002875864414 0 0 0 0 +1 2.857738033247042 0 2.061393766919624 2.619965104088255 0 0 2.000347299268466 0 0 0 0 2.055002875864414 0 0 0 0 +0 2.857738033247042 0 0 0 0 2.004684436494304 2.000347299268466 2.122974378789621 0 0 6.857275130999357 0 0 0 0 0 +1 2.857738033247042 0 0 2.619965104088255 0 2.004684436494304 2.000347299268466 0 2.228387042742021 2.228387042742023 0 0 0 0 0 0 +1 2.857738033247042 0 0 2.619965104088255 0 2.004684436494304 2.000347299268466 2.122974378789621 0 0 0 0 0 0 0 0 +0 0 2.52078447201548 2.061393766919624 0 0 0 0 2.122974378789621 2.228387042742021 2.228387042742023 0 2.055002875864414 0 0 0 0 +0 2.857738033247042 0 2.061393766919624 2.619965104088255 0 0 0 0 2.228387042742021 2.228387042742023 0 0 0 0 0 0 +1 2.857738033247042 2.52078447201548 0 2.619965104088255 0 0 0 0 2.228387042742021 2.228387042742023 0 0 0 0 0 0 +0 0 0 2.061393766919624 2.619965104088255 0 0 0 2.122974378789621 2.228387042742021 2.228387042742023 0 0 0 0 0 0 +1 2.857738033247042 0 0 2.619965104088255 0 2.004684436494304 2.000347299268466 0 2.228387042742021 2.228387042742023 0 2.055002875864414 0 0 0 0 +0 2.857738033247042 0 0 2.619965104088255 0 2.004684436494304 0 0 2.228387042742021 2.228387042742023 0 0 0 0 0 0 +1 2.857738033247042 0 0 2.619965104088255 0 0 2.000347299268466 0 2.228387042742021 2.228387042742023 0 2.055002875864414 0 0 0 0 +0 2.857738033247042 0 2.061393766919624 0 0 0 2.000347299268466 0 2.228387042742021 2.228387042742023 0 2.055002875864414 0 0 0 0 +0 2.857738033247042 2.52078447201548 0 2.619965104088255 0 0 0 0 2.228387042742021 2.228387042742023 0 0 0 0 0 0 +0 2.857738033247042 0 0 2.619965104088255 0 0 2.000347299268466 2.122974378789621 0 0 0 2.055002875864414 0 0 0 0 +1 2.857738033247042 2.52078447201548 0 2.619965104088255 0 0 2.000347299268466 0 2.228387042742021 2.228387042742023 0 0 0 0 0 0 +0 2.857738033247042 0 0 2.619965104088255 0 2.004684436494304 2.000347299268466 0 2.228387042742021 2.228387042742023 0 0 0 0 0 0 +1 2.857738033247042 2.52078447201548 0 2.619965104088255 0 2.004684436494304 2.000347299268466 0 0 0 0 0 0 0 0 0 +1 2.857738033247042 0 0 2.619965104088255 0 2.004684436494304 0 2.122974378789621 0 0 0 2.055002875864414 0 0 0 0 +1 2.857738033247042 0 2.061393766919624 2.619965104088255 0 2.004684436494304 2.000347299268466 0 0 0 0 0 0 0 0 0 +1 2.857738033247042 2.52078447201548 0 2.619965104088255 0 0 0 0 2.228387042742021 2.228387042742023 0 0 0 0 0 0 +0 2.857738033247042 2.52078447201548 0 2.619965104088255 0 2.004684436494304 2.000347299268466 0 2.228387042742021 2.228387042742023 0 0 0 0 0 0 +0 2.857738033247042 0 0 2.619965104088255 0 0 0 0 2.228387042742021 2.228387042742023 0 2.055002875864414 0 0 0 0 +1 2.857738033247042 0 0 2.619965104088255 0 0 2.000347299268466 0 2.228387042742021 2.228387042742023 0 0 0 0 0 0 +0 0 2.52078447201548 0 0 0 2.004684436494304 2.000347299268466 0 2.228387042742021 2.228387042742023 0 2.055002875864414 0 0 0 0 +1 2.857738033247042 2.52078447201548 0 2.619965104088255 0 0 0 0 2.228387042742021 2.228387042742023 0 0 0 0 0 0 +0 2.857738033247042 0 0 2.619965104088255 0 0 2.000347299268466 0 2.228387042742021 2.228387042742023 0 0 0 0 0 0 +0 2.857738033247042 0 0 2.619965104088255 0 2.004684436494304 2.000347299268466 2.122974378789621 0 0 0 0 0 0 0 0 +0 2.857738033247042 0 0 2.619965104088255 0 2.004684436494304 0 2.122974378789621 0 0 0 2.055002875864414 0 0 0 0 +1 2.857738033247042 0 0 2.619965104088255 0 0 2.000347299268466 0 2.228387042742021 2.228387042742023 0 0 0 0 0 0 +1 2.857738033247042 2.52078447201548 2.061393766919624 2.619965104088255 0 0 2.000347299268466 0 0 0 0 0 0 0 0 0 +0 2.857738033247042 0 2.061393766919624 2.619965104088255 0 2.004684436494304 0 2.122974378789621 2.228387042742021 2.228387042742023 0 2.055002875864414 0 0 0 0 +0 2.857738033247042 0 2.061393766919624 2.619965104088255 0 0 0 2.122974378789621 0 0 0 2.055002875864414 0 0 0 0 +1 2.857738033247042 0 0 2.619965104088255 0 0 2.000347299268466 2.122974378789621 2.228387042742021 2.228387042742023 0 0 0 0 0 0 +1 2.857738033247042 0 2.061393766919624 0 0 0 0 2.122974378789621 2.228387042742021 2.228387042742023 0 0 0 0 0 0 +1 2.857738033247042 2.52078447201548 2.061393766919624 2.619965104088255 0 0 2.000347299268466 0 0 0 0 0 0 0 0 0 +0 2.857738033247042 0 0 2.619965104088255 0 0 2.000347299268466 0 2.228387042742021 2.228387042742023 0 0 0 0 0 0 +0 2.857738033247042 2.52078447201548 2.061393766919624 2.619965104088255 0 0 2.000347299268466 0 0 0 0 0 0 0 0 0 +0 2.857738033247042 2.52078447201548 0 2.619965104088255 0 2.004684436494304 2.000347299268466 0 0 0 0 0 0 0 0 0 +0 2.857738033247042 0 2.061393766919624 0 0 0 2.000347299268466 2.122974378789621 2.228387042742021 2.228387042742023 0 0 0 0 0 0 +1 2.857738033247042 0 0 2.619965104088255 0 2.004684436494304 2.000347299268466 0 2.228387042742021 2.228387042742023 0 0 0 0 0 0 +0 2.857738033247042 0 2.061393766919624 0 0 0 2.000347299268466 0 2.228387042742021 2.228387042742023 0 0 0 0 0 0 +0 2.857738033247042 0 2.061393766919624 0 0 2.004684436494304 2.000347299268466 0 2.228387042742021 2.228387042742023 0 0 0 0 0 0 +0 2.857738033247042 0 2.061393766919624 0 0 0 0 2.122974378789621 2.228387042742021 2.228387042742023 0 0 0 0 0 0 +1 2.857738033247042 0 0 2.619965104088255 0 0 0 0 2.228387042742021 2.228387042742023 0 2.055002875864414 0 0 0 0 +0 2.857738033247042 2.52078447201548 0 2.619965104088255 0 0 0 0 2.228387042742021 2.228387042742023 0 0 0 0 0 0 +0 2.857738033247042 0 2.061393766919624 2.619965104088255 0 0 2.000347299268466 2.122974378789621 0 0 0 0 0 0 0 0 +1 0 0 2.061393766919624 0 0 2.004684436494304 2.000347299268466 2.122974378789621 2.228387042742021 2.228387042742023 0 0 0 0 0 0 +0 2.857738033247042 0 2.061393766919624 0 0 2.004684436494304 2.000347299268466 0 0 0 0 2.055002875864414 0 0 0 0 +0 2.857738033247042 0 2.061393766919624 0 0 0 2.000347299268466 0 2.228387042742021 2.228387042742023 0 2.055002875864414 0 0 0 0 +0 0 2.52078447201548 0 2.619965104088255 0 0 0 2.122974378789621 2.228387042742021 2.228387042742023 0 0 0 0 0 0 +0 2.857738033247042 2.52078447201548 0 2.619965104088255 0 0 0 0 2.228387042742021 2.228387042742023 0 0 0 0 0 0 +0 2.857738033247042 0 2.061393766919624 2.619965104088255 0 2.004684436494304 2.000347299268466 0 2.228387042742021 2.228387042742023 0 2.055002875864414 0 0 0 0 +0 2.857738033247042 0 0 2.619965104088255 4.745052855503306 2.004684436494304 2.000347299268466 0 0 0 0 0 0 0 0 0 +1 0 0 0 0 0 0 0 2.122974378789621 0 0 0 0 12.72816758217773 10.4087817597473 12.72816758217773 17.97228742438751 +0 2.857738033247042 0 2.061393766919624 2.619965104088255 4.745052855503306 2.004684436494304 0 2.122974378789621 2.228387042742021 2.228387042742023 0 0 0 0 0 0 +0 2.857738033247042 0 0 0 0 2.004684436494304 2.000347299268466 0 2.228387042742021 2.228387042742023 0 2.055002875864414 0 0 0 0 +1 0 2.52078447201548 2.061393766919624 0 0 2.004684436494304 2.000347299268466 0 0 0 0 2.055002875864414 0 0 0 0 +0 2.857738033247042 0 2.061393766919624 0 0 0 0 2.122974378789621 2.228387042742021 2.228387042742023 0 2.055002875864414 0 0 0 0 +0 2.857738033247042 0 0 2.619965104088255 0 2.004684436494304 2.000347299268466 0 2.228387042742021 2.228387042742023 0 0 0 0 0 0 +1 0 0 0 2.619965104088255 0 2.004684436494304 2.000347299268466 0 2.228387042742021 2.228387042742023 0 0 0 0 0 0 +1 2.857738033247042 2.52078447201548 2.061393766919624 2.619965104088255 0 2.004684436494304 0 0 2.228387042742021 2.228387042742023 0 0 0 0 0 0 +1 2.857738033247042 2.52078447201548 2.061393766919624 2.619965104088255 0 2.004684436494304 2.000347299268466 0 0 0 0 0 0 0 0 0 +1 2.857738033247042 0 2.061393766919624 2.619965104088255 0 0 2.000347299268466 0 0 0 0 2.055002875864414 0 0 0 0 +0 2.857738033247042 0 0 2.619965104088255 0 2.004684436494304 2.000347299268466 0 2.228387042742021 2.228387042742023 0 2.055002875864414 0 0 0 0 +0 0 0 2.061393766919624 2.619965104088255 0 2.004684436494304 0 0 2.228387042742021 2.228387042742023 0 0 0 0 0 0 +1 2.857738033247042 2.52078447201548 2.061393766919624 2.619965104088255 0 0 0 0 2.228387042742021 2.228387042742023 0 0 0 0 0 0 +1 0 0 0 2.619965104088255 0 2.004684436494304 2.000347299268466 0 2.228387042742021 2.228387042742023 0 0 0 0 0 0 +1 2.857738033247042 0 0 0 0 0 0 2.122974378789621 2.228387042742021 2.228387042742023 0 2.055002875864414 0 0 0 0 +1 2.857738033247042 0 2.061393766919624 2.619965104088255 0 0 2.000347299268466 0 2.228387042742021 2.228387042742023 0 2.055002875864414 0 0 0 0 +0 2.857738033247042 2.52078447201548 0 0 0 0 2.000347299268466 0 2.228387042742021 2.228387042742023 0 0 0 0 0 0 +1 2.857738033247042 0 0 2.619965104088255 0 2.004684436494304 2.000347299268466 2.122974378789621 0 0 0 0 0 0 0 0 +1 2.857738033247042 0 0 2.619965104088255 0 2.004684436494304 2.000347299268466 0 2.228387042742021 2.228387042742023 0 0 0 0 0 0 +1 2.857738033247042 0 2.061393766919624 2.619965104088255 4.745052855503306 2.004684436494304 0 0 0 0 0 0 0 0 0 0 +1 0 0 2.061393766919624 0 0 2.004684436494304 2.000347299268466 0 0 0 6.857275130999357 2.055002875864414 0 0 0 0 +0 2.857738033247042 0 0 2.619965104088255 0 2.004684436494304 0 0 2.228387042742021 2.228387042742023 0 2.055002875864414 0 0 0 0 +1 2.857738033247042 2.52078447201548 2.061393766919624 2.619965104088255 0 0 0 0 2.228387042742021 2.228387042742023 0 0 0 0 0 0 +0 2.857738033247042 0 0 2.619965104088255 0 2.004684436494304 2.000347299268466 2.122974378789621 0 0 0 2.055002875864414 0 0 0 0 +0 2.857738033247042 0 2.061393766919624 2.619965104088255 0 2.004684436494304 0 0 2.228387042742021 2.228387042742023 0 0 0 0 0 0 +1 2.857738033247042 0 0 2.619965104088255 0 0 0 0 2.228387042742021 2.228387042742023 0 2.055002875864414 0 0 0 0 +0 2.857738033247042 0 0 2.619965104088255 0 2.004684436494304 0 0 2.228387042742021 2.228387042742023 0 0 0 0 0 0 +0 2.857738033247042 0 2.061393766919624 0 4.745052855503306 0 0 2.122974378789621 2.228387042742021 2.228387042742023 0 0 0 0 0 0 +0 2.857738033247042 0 0 2.619965104088255 0 2.004684436494304 2.000347299268466 0 0 0 0 2.055002875864414 0 0 0 0 +1 2.857738033247042 0 0 2.619965104088255 0 0 0 0 2.228387042742021 2.228387042742023 6.857275130999357 0 0 0 0 0 +0 2.857738033247042 2.52078447201548 0 2.619965104088255 0 2.004684436494304 2.000347299268466 0 0 0 0 2.055002875864414 0 0 0 0 +0 2.857738033247042 0 2.061393766919624 0 0 0 2.000347299268466 0 2.228387042742021 2.228387042742023 0 2.055002875864414 0 0 0 0 +0 2.857738033247042 0 2.061393766919624 0 0 0 0 2.122974378789621 2.228387042742021 2.228387042742023 0 0 0 0 0 0 +0 2.857738033247042 0 2.061393766919624 2.619965104088255 0 0 0 2.122974378789621 2.228387042742021 2.228387042742023 0 2.055002875864414 0 0 0 0 +0 2.857738033247042 0 2.061393766919624 2.619965104088255 0 0 0 0 2.228387042742021 2.228387042742023 0 0 0 0 0 0 +1 2.857738033247042 0 2.061393766919624 2.619965104088255 0 0 0 0 2.228387042742021 2.228387042742023 0 0 0 0 0 0 +0 2.857738033247042 0 0 0 4.745052855503306 0 0 0 2.228387042742021 2.228387042742023 0 2.055002875864414 0 0 0 0 +0 2.857738033247042 2.52078447201548 0 2.619965104088255 0 0 0 2.122974378789621 0 0 0 2.055002875864414 0 0 0 0 +0 2.857738033247042 0 0 2.619965104088255 0 2.004684436494304 2.000347299268466 2.122974378789621 0 0 0 2.055002875864414 0 0 0 0 +0 2.857738033247042 0 0 2.619965104088255 0 2.004684436494304 2.000347299268466 2.122974378789621 0 0 0 0 0 0 0 0 +1 2.857738033247042 0 2.061393766919624 2.619965104088255 0 2.004684436494304 2.000347299268466 2.122974378789621 0 0 0 0 0 0 0 0 +1 2.857738033247042 0 0 2.619965104088255 0 0 0 2.122974378789621 2.228387042742021 2.228387042742023 0 0 0 0 0 0 +1 2.857738033247042 2.52078447201548 0 0 0 0 2.000347299268466 0 2.228387042742021 2.228387042742023 0 0 0 0 0 0 +0 2.857738033247042 0 2.061393766919624 2.619965104088255 4.745052855503306 2.004684436494304 2.000347299268466 0 0 0 0 2.055002875864414 0 0 0 0 +0 2.857738033247042 0 2.061393766919624 2.619965104088255 0 0 0 2.122974378789621 0 0 0 2.055002875864414 0 0 0 0 +0 0 2.52078447201548 2.061393766919624 0 0 0 0 2.122974378789621 2.228387042742021 2.228387042742023 0 0 0 0 0 0 +0 2.857738033247042 0 0 2.619965104088255 4.745052855503306 2.004684436494304 0 2.122974378789621 2.228387042742021 2.228387042742023 0 0 0 0 0 0 +1 2.857738033247042 0 0 2.619965104088255 0 2.004684436494304 0 0 2.228387042742021 2.228387042742023 0 0 0 0 0 0 +0 2.857738033247042 0 2.061393766919624 0 0 0 0 2.122974378789621 2.228387042742021 2.228387042742023 0 0 0 0 0 0 +0 2.857738033247042 0 0 2.619965104088255 0 2.004684436494304 2.000347299268466 2.122974378789621 0 0 0 0 0 0 0 0 +0 2.857738033247042 0 0 2.619965104088255 0 0 0 0 2.228387042742021 2.228387042742023 0 2.055002875864414 0 0 0 0 +1 0 2.52078447201548 2.061393766919624 2.619965104088255 0 2.004684436494304 0 0 2.228387042742021 2.228387042742023 0 0 0 0 0 0 +0 2.857738033247042 0 2.061393766919624 2.619965104088255 0 0 0 2.122974378789621 2.228387042742021 2.228387042742023 0 0 0 0 0 0 +0 2.857738033247042 0 0 2.619965104088255 0 2.004684436494304 0 0 2.228387042742021 2.228387042742023 0 0 0 0 0 0 +0 2.857738033247042 0 0 2.619965104088255 0 0 0 0 2.228387042742021 2.228387042742023 0 2.055002875864414 0 0 0 0 +1 2.857738033247042 0 0 2.619965104088255 0 0 0 0 2.228387042742021 2.228387042742023 0 2.055002875864414 0 0 0 0 +1 2.857738033247042 0 0 2.619965104088255 0 0 0 0 2.228387042742021 2.228387042742023 0 2.055002875864414 0 0 0 0 +1 2.857738033247042 0 0 2.619965104088255 0 0 0 2.122974378789621 2.228387042742021 2.228387042742023 0 2.055002875864414 0 0 0 0 +1 2.857738033247042 0 0 0 0 0 2.000347299268466 2.122974378789621 0 0 6.857275130999357 2.055002875864414 0 0 0 0 +0 2.857738033247042 0 2.061393766919624 2.619965104088255 4.745052855503306 2.004684436494304 0 0 2.228387042742021 2.228387042742023 0 0 0 0 0 0 +1 2.857738033247042 0 2.061393766919624 2.619965104088255 0 2.004684436494304 0 0 2.228387042742021 2.228387042742023 0 0 0 0 0 0 +0 2.857738033247042 2.52078447201548 0 2.619965104088255 0 0 0 0 2.228387042742021 2.228387042742023 0 2.055002875864414 0 0 0 0 +1 2.857738033247042 0 0 2.619965104088255 0 2.004684436494304 2.000347299268466 0 2.228387042742021 2.228387042742023 0 2.055002875864414 0 0 0 0 +1 2.857738033247042 0 0 2.619965104088255 0 0 2.000347299268466 0 2.228387042742021 2.228387042742023 0 0 0 0 0 0 +1 2.857738033247042 0 0 2.619965104088255 0 2.004684436494304 2.000347299268466 0 0 0 0 2.055002875864414 0 0 0 0 +0 2.857738033247042 2.52078447201548 0 2.619965104088255 0 0 2.000347299268466 2.122974378789621 0 0 0 0 0 0 0 0 +0 2.857738033247042 0 0 2.619965104088255 0 0 0 2.122974378789621 2.228387042742021 2.228387042742023 0 2.055002875864414 0 0 0 0 +0 0 0 2.061393766919624 0 0 2.004684436494304 2.000347299268466 2.122974378789621 0 0 0 2.055002875864414 0 0 0 0 +1 2.857738033247042 0 0 2.619965104088255 0 2.004684436494304 2.000347299268466 0 2.228387042742021 2.228387042742023 0 0 0 0 0 0 +1 2.857738033247042 2.52078447201548 2.061393766919624 0 0 0 0 0 2.228387042742021 2.228387042742023 0 0 0 0 0 0 +1 0 0 0 2.619965104088255 0 0 2.000347299268466 0 2.228387042742021 2.228387042742023 6.857275130999357 0 0 0 0 0 +1 2.857738033247042 0 2.061393766919624 2.619965104088255 0 0 0 0 2.228387042742021 2.228387042742023 0 2.055002875864414 0 0 0 0 +0 2.857738033247042 0 0 2.619965104088255 0 2.004684436494304 0 0 2.228387042742021 2.228387042742023 0 0 0 0 0 0 +1 2.857738033247042 0 0 2.619965104088255 0 2.004684436494304 2.000347299268466 0 0 0 0 2.055002875864414 0 0 0 0 +0 2.857738033247042 0 2.061393766919624 2.619965104088255 0 2.004684436494304 2.000347299268466 0 0 0 0 2.055002875864414 0 0 0 0 +0 2.857738033247042 2.52078447201548 2.061393766919624 2.619965104088255 0 0 2.000347299268466 0 0 0 0 0 0 0 0 0 +0 2.857738033247042 0 0 2.619965104088255 0 0 0 2.122974378789621 2.228387042742021 2.228387042742023 0 2.055002875864414 0 0 0 0 +0 2.857738033247042 0 2.061393766919624 2.619965104088255 0 2.004684436494304 0 0 0 0 0 2.055002875864414 0 0 0 0 +1 2.857738033247042 0 0 2.619965104088255 0 2.004684436494304 2.000347299268466 2.122974378789621 2.228387042742021 2.228387042742023 0 0 0 0 0 0 +0 2.857738033247042 2.52078447201548 0 0 0 0 0 2.122974378789621 2.228387042742021 2.228387042742023 0 0 0 0 0 0 +0 2.857738033247042 0 2.061393766919624 2.619965104088255 4.745052855503306 0 0 0 2.228387042742021 2.228387042742023 0 0 0 0 0 0 +1 0 0 0 2.619965104088255 0 2.004684436494304 2.000347299268466 0 2.228387042742021 2.228387042742023 0 0 0 0 0 0 +0 2.857738033247042 2.52078447201548 0 0 0 0 0 2.122974378789621 2.228387042742021 2.228387042742023 0 0 0 0 0 0 +1 2.857738033247042 2.52078447201548 0 2.619965104088255 0 2.004684436494304 0 0 2.228387042742021 2.228387042742023 0 0 0 0 0 0 +0 2.857738033247042 0 0 2.619965104088255 0 0 0 2.122974378789621 2.228387042742021 2.228387042742023 0 0 0 0 0 0 +0 2.857738033247042 0 2.061393766919624 0 0 2.004684436494304 0 2.122974378789621 0 0 0 0 0 10.4087817597473 0 0 +0 2.857738033247042 0 2.061393766919624 2.619965104088255 0 2.004684436494304 0 2.122974378789621 0 0 0 0 0 0 0 0 +1 2.857738033247042 0 0 2.619965104088255 0 2.004684436494304 2.000347299268466 0 2.228387042742021 2.228387042742023 0 0 0 0 0 0 +0 2.857738033247042 0 0 2.619965104088255 0 2.004684436494304 2.000347299268466 2.122974378789621 0 0 0 0 0 0 0 0 +1 2.857738033247042 0 0 2.619965104088255 0 0 2.000347299268466 0 2.228387042742021 2.228387042742023 0 0 0 0 0 0 +1 0 2.52078447201548 0 2.619965104088255 0 0 0 0 2.228387042742021 2.228387042742023 0 2.055002875864414 0 0 0 0 +1 2.857738033247042 0 0 2.619965104088255 0 0 0 2.122974378789621 2.228387042742021 2.228387042742023 0 2.055002875864414 0 0 0 0 diff --git a/mllib/src/main/scala/org/apache/spark/mllib/classification/SVM.scala b/mllib/src/main/scala/org/apache/spark/mllib/classification/SVM.scala index 3511e24bce..3b8f8550d0 100644 --- a/mllib/src/main/scala/org/apache/spark/mllib/classification/SVM.scala +++ b/mllib/src/main/scala/org/apache/spark/mllib/classification/SVM.scala @@ -29,7 +29,7 @@ import org.apache.spark.mllib.util.DataValidators import org.jblas.DoubleMatrix /** - * Model built using SVM. + * Model for Support Vector Machines (SVMs). * * @param weights Weights computed for every feature. * @param intercept Intercept computed for this model. @@ -48,8 +48,8 @@ class SVMModel( } /** - * Train an SVM using Stochastic Gradient Descent. - * NOTE: Labels used in SVM should be {0, 1} + * Train a Support Vector Machine (SVM) using Stochastic Gradient Descent. + * NOTE: Labels used in SVM should be {0, 1}. */ class SVMWithSGD private ( var stepSize: Double, @@ -79,7 +79,7 @@ class SVMWithSGD private ( } /** - * Top-level methods for calling SVM. NOTE: Labels used in SVM should be {0, 1} + * Top-level methods for calling SVM. NOTE: Labels used in SVM should be {0, 1}. */ object SVMWithSGD { @@ -88,14 +88,15 @@ object SVMWithSGD { * of iterations of gradient descent using the specified step size. Each iteration uses * `miniBatchFraction` fraction of the data to calculate the gradient. The weights used in * gradient descent are initialized using the initial weights provided. - * NOTE: Labels used in SVM should be {0, 1} + * + * NOTE: Labels used in SVM should be {0, 1}. * * @param input RDD of (label, array of features) pairs. * @param numIterations Number of iterations of gradient descent to run. * @param stepSize Step size to be used for each iteration of gradient descent. * @param regParam Regularization parameter. * @param miniBatchFraction Fraction of data to be used per iteration. - * @param initialWeights Initial set of weights to be used. Array should be equal in size to + * @param initialWeights Initial set of weights to be used. Array should be equal in size to * the number of features in the data. */ def train( diff --git a/mllib/src/main/scala/org/apache/spark/mllib/regression/LinearRegression.scala b/mllib/src/main/scala/org/apache/spark/mllib/regression/LinearRegression.scala index ae95ea24fc..597d55e0bb 100644 --- a/mllib/src/main/scala/org/apache/spark/mllib/regression/LinearRegression.scala +++ b/mllib/src/main/scala/org/apache/spark/mllib/regression/LinearRegression.scala @@ -43,7 +43,7 @@ class LinearRegressionModel( } /** - * Train a regression model with no regularization using Stochastic Gradient Descent. + * Train a linear regression model with no regularization using Stochastic Gradient Descent. */ class LinearRegressionWithSGD private ( var stepSize: Double, @@ -83,7 +83,7 @@ object LinearRegressionWithSGD { * @param numIterations Number of iterations of gradient descent to run. * @param stepSize Step size to be used for each iteration of gradient descent. * @param miniBatchFraction Fraction of data to be used per iteration. - * @param initialWeights Initial set of weights to be used. Array should be equal in size to + * @param initialWeights Initial set of weights to be used. Array should be equal in size to * the number of features in the data. */ def train( @@ -38,6 +38,7 @@ </licenses> <scm> <connection>scm:git:git@github.com:apache/incubator-spark.git</connection> + <developerConnection>scm:git:https://git-wip-us.apache.org/repos/asf/incubator-spark.git</developerConnection> <url>scm:git:git@github.com:apache/incubator-spark.git</url> </scm> <developers> @@ -89,6 +90,7 @@ <slf4j.version>1.7.2</slf4j.version> <log4j.version>1.2.17</log4j.version> <hadoop.version>1.0.4</hadoop.version> + <yarn.version>0.23.7</yarn.version> <hbase.version>0.94.6</hbase.version> <PermGen>64m</PermGen> @@ -295,6 +297,11 @@ <version>3.0.0</version> </dependency> <dependency> + <groupId>com.codahale.metrics</groupId> + <artifactId>metrics-ganglia</artifactId> + <version>3.0.0</version> + </dependency> + <dependency> <groupId>org.scala-lang</groupId> <artifactId>scala-compiler</artifactId> <version>2.10.0</version> @@ -376,6 +383,104 @@ </exclusion> </exclusions> </dependency> + <dependency> + <groupId>net.java.dev.jets3t</groupId> + <artifactId>jets3t</artifactId> + <version>0.7.1</version> + </dependency> + <dependency> + <groupId>org.apache.hadoop</groupId> + <artifactId>hadoop-yarn-api</artifactId> + <version>${yarn.version}</version> + <exclusions> + <exclusion> + <groupId>asm</groupId> + <artifactId>asm</artifactId> + </exclusion> + <exclusion> + <groupId>org.jboss.netty</groupId> + <artifactId>netty</artifactId> + </exclusion> + <exclusion> + <groupId>org.codehaus.jackson</groupId> + <artifactId>jackson-core-asl</artifactId> + </exclusion> + <exclusion> + <groupId>org.codehaus.jackson</groupId> + <artifactId>jackson-mapper-asl</artifactId> + </exclusion> + <exclusion> + <groupId>org.codehaus.jackson</groupId> + <artifactId>jackson-jaxrs</artifactId> + </exclusion> + <exclusion> + <groupId>org.codehaus.jackson</groupId> + <artifactId>jackson-xc</artifactId> + </exclusion> + </exclusions> + </dependency> + <dependency> + <groupId>org.apache.hadoop</groupId> + <artifactId>hadoop-yarn-common</artifactId> + <version>${yarn.version}</version> + <exclusions> + <exclusion> + <groupId>asm</groupId> + <artifactId>asm</artifactId> + </exclusion> + <exclusion> + <groupId>org.jboss.netty</groupId> + <artifactId>netty</artifactId> + </exclusion> + <exclusion> + <groupId>org.codehaus.jackson</groupId> + <artifactId>jackson-core-asl</artifactId> + </exclusion> + <exclusion> + <groupId>org.codehaus.jackson</groupId> + <artifactId>jackson-mapper-asl</artifactId> + </exclusion> + <exclusion> + <groupId>org.codehaus.jackson</groupId> + <artifactId>jackson-jaxrs</artifactId> + </exclusion> + <exclusion> + <groupId>org.codehaus.jackson</groupId> + <artifactId>jackson-xc</artifactId> + </exclusion> + </exclusions> + </dependency> + <dependency> + <groupId>org.apache.hadoop</groupId> + <artifactId>hadoop-yarn-client</artifactId> + <version>${yarn.version}</version> + <exclusions> + <exclusion> + <groupId>asm</groupId> + <artifactId>asm</artifactId> + </exclusion> + <exclusion> + <groupId>org.jboss.netty</groupId> + <artifactId>netty</artifactId> + </exclusion> + <exclusion> + <groupId>org.codehaus.jackson</groupId> + <artifactId>jackson-core-asl</artifactId> + </exclusion> + <exclusion> + <groupId>org.codehaus.jackson</groupId> + <artifactId>jackson-mapper-asl</artifactId> + </exclusion> + <exclusion> + <groupId>org.codehaus.jackson</groupId> + <artifactId>jackson-jaxrs</artifactId> + </exclusion> + <exclusion> + <groupId>org.codehaus.jackson</groupId> + <artifactId>jackson-xc</artifactId> + </exclusion> + </exclusions> + </dependency> <!-- Specify Avro version because Kafka also has it as a dependency --> <dependency> <groupId>org.apache.avro</groupId> @@ -604,8 +709,8 @@ <properties> <hadoop.major.version>2</hadoop.major.version> <!-- 0.23.* is same as 2.0.* - except hardened to run production jobs --> - <!-- <hadoop.version>0.23.7</hadoop.version> --> - <hadoop.version>2.0.5-alpha</hadoop.version> + <hadoop.version>0.23.7</hadoop.version> + <!--<hadoop.version>2.0.5-alpha</hadoop.version> --> </properties> <modules> @@ -628,131 +733,6 @@ <dependencyManagement> <dependencies> - <!-- TODO: check versions, bringover from yarn branch ! --> - <dependency> - <groupId>org.apache.hadoop</groupId> - <artifactId>hadoop-client</artifactId> - <version>${hadoop.version}</version> - <exclusions> - <exclusion> - <groupId>asm</groupId> - <artifactId>asm</artifactId> - </exclusion> - <exclusion> - <groupId>org.jboss.netty</groupId> - <artifactId>netty</artifactId> - </exclusion> - <exclusion> - <groupId>org.codehaus.jackson</groupId> - <artifactId>jackson-core-asl</artifactId> - </exclusion> - <exclusion> - <groupId>org.codehaus.jackson</groupId> - <artifactId>jackson-mapper-asl</artifactId> - </exclusion> - <exclusion> - <groupId>org.codehaus.jackson</groupId> - <artifactId>jackson-jaxrs</artifactId> - </exclusion> - <exclusion> - <groupId>org.codehaus.jackson</groupId> - <artifactId>jackson-xc</artifactId> - </exclusion> - </exclusions> - </dependency> - <dependency> - <groupId>org.apache.hadoop</groupId> - <artifactId>hadoop-yarn-api</artifactId> - <version>${hadoop.version}</version> - <exclusions> - <exclusion> - <groupId>asm</groupId> - <artifactId>asm</artifactId> - </exclusion> - <exclusion> - <groupId>org.jboss.netty</groupId> - <artifactId>netty</artifactId> - </exclusion> - <exclusion> - <groupId>org.codehaus.jackson</groupId> - <artifactId>jackson-core-asl</artifactId> - </exclusion> - <exclusion> - <groupId>org.codehaus.jackson</groupId> - <artifactId>jackson-mapper-asl</artifactId> - </exclusion> - <exclusion> - <groupId>org.codehaus.jackson</groupId> - <artifactId>jackson-jaxrs</artifactId> - </exclusion> - <exclusion> - <groupId>org.codehaus.jackson</groupId> - <artifactId>jackson-xc</artifactId> - </exclusion> - </exclusions> - </dependency> - <dependency> - <groupId>org.apache.hadoop</groupId> - <artifactId>hadoop-yarn-common</artifactId> - <version>${hadoop.version}</version> - <exclusions> - <exclusion> - <groupId>asm</groupId> - <artifactId>asm</artifactId> - </exclusion> - <exclusion> - <groupId>org.jboss.netty</groupId> - <artifactId>netty</artifactId> - </exclusion> - <exclusion> - <groupId>org.codehaus.jackson</groupId> - <artifactId>jackson-core-asl</artifactId> - </exclusion> - <exclusion> - <groupId>org.codehaus.jackson</groupId> - <artifactId>jackson-mapper-asl</artifactId> - </exclusion> - <exclusion> - <groupId>org.codehaus.jackson</groupId> - <artifactId>jackson-jaxrs</artifactId> - </exclusion> - <exclusion> - <groupId>org.codehaus.jackson</groupId> - <artifactId>jackson-xc</artifactId> - </exclusion> - </exclusions> - </dependency> - <dependency> - <groupId>org.apache.hadoop</groupId> - <artifactId>hadoop-yarn-client</artifactId> - <version>${hadoop.version}</version> - <exclusions> - <exclusion> - <groupId>asm</groupId> - <artifactId>asm</artifactId> - </exclusion> - <exclusion> - <groupId>org.jboss.netty</groupId> - <artifactId>netty</artifactId> - </exclusion> - <exclusion> - <groupId>org.codehaus.jackson</groupId> - <artifactId>jackson-core-asl</artifactId> - </exclusion> - <exclusion> - <groupId>org.codehaus.jackson</groupId> - <artifactId>jackson-mapper-asl</artifactId> - </exclusion> - <exclusion> - <groupId>org.codehaus.jackson</groupId> - <artifactId>jackson-jaxrs</artifactId> - </exclusion> - <exclusion> - <groupId>org.codehaus.jackson</groupId> - <artifactId>jackson-xc</artifactId> - </exclusion> - </exclusions> - </dependency> </dependencies> </dependencyManagement> </profile> diff --git a/project/SparkBuild.scala b/project/SparkBuild.scala index e781519be9..5e7ed81c1e 100644 --- a/project/SparkBuild.scala +++ b/project/SparkBuild.scala @@ -33,15 +33,19 @@ object SparkBuild extends Build { // HBase version; set as appropriate. val HBASE_VERSION = "0.94.6" + // Target JVM version + val SCALAC_JVM_VERSION = "jvm-1.5" + val JAVAC_JVM_VERSION = "1.5" + lazy val root = Project("root", file("."), settings = rootSettings) aggregate(allProjects: _*) lazy val core = Project("core", file("core"), settings = coreSettings) lazy val repl = Project("repl", file("repl"), settings = replSettings) - .dependsOn(core, bagel, mllib) dependsOn(maybeYarn: _*) + .dependsOn(core, bagel, mllib) lazy val examples = Project("examples", file("examples"), settings = examplesSettings) - .dependsOn(core, mllib, bagel, streaming) dependsOn(maybeYarn: _*) + .dependsOn(core, mllib, bagel, streaming) lazy val tools = Project("tools", file("tools"), settings = toolsSettings) dependsOn(core) dependsOn(streaming) @@ -77,7 +81,8 @@ object SparkBuild extends Build { organization := "org.apache.spark", version := "0.8.0-SNAPSHOT", scalaVersion := "2.10.2", - scalacOptions := Seq("-unchecked", "-optimize", "-deprecation"), + scalacOptions := Seq("-unchecked", "-optimize", "-deprecation", "-target:" + SCALAC_JVM_VERSION), + javacOptions := Seq("-target", JAVAC_JVM_VERSION, "-source", JAVAC_JVM_VERSION), unmanagedJars in Compile <<= baseDirectory map { base => (base / "lib" ** "*.jar").classpath }, retrieveManaged := true, retrievePattern := "[type]s/[artifact](-[revision])(-[classifier]).[ext]", @@ -186,7 +191,7 @@ object SparkBuild extends Build { libraryDependencies ++= Seq( "com.google.guava" % "guava" % "14.0.1", "com.google.code.findbugs" % "jsr305" % "1.3.9", - "log4j" % "log4j" % "1.2.16", + "log4j" % "log4j" % "1.2.17", "org.slf4j" % "slf4j-api" % slf4jVersion, "org.slf4j" % "slf4j-log4j12" % slf4jVersion, "com.ning" % "compress-lzf" % "0.8.4", @@ -200,7 +205,8 @@ object SparkBuild extends Build { "net.liftweb" %% "lift-json" % "2.5.1", "it.unimi.dsi" % "fastutil" % "6.4.4", "colt" % "colt" % "1.2.0", - "org.apache.mesos" % "mesos" % "0.9.0-incubating", + "org.apache.mesos" % "mesos" % "0.12.1", + "net.java.dev.jets3t" % "jets3t" % "0.7.1", "org.apache.derby" % "derby" % "10.4.2.0" % "test", "org.apache.hadoop" % "hadoop-client" % hadoopVersion excludeAll(excludeJackson, excludeNetty, excludeAsm), "org.apache.avro" % "avro" % "1.7.4", @@ -208,6 +214,7 @@ object SparkBuild extends Build { "com.codahale.metrics" % "metrics-core" % "3.0.0", "com.codahale.metrics" % "metrics-jvm" % "3.0.0", "com.codahale.metrics" % "metrics-json" % "3.0.0", + "com.codahale.metrics" % "metrics-ganglia" % "3.0.0", "com.twitter" %% "chill" % "0.3.1", "com.twitter" % "chill-java" % "0.3.1", "org.scala-lang" % "jline" % "2.10.2", @@ -296,6 +303,7 @@ object SparkBuild extends Build { mergeStrategy in assembly := { case m if m.toLowerCase.endsWith("manifest.mf") => MergeStrategy.discard case m if m.toLowerCase.matches("meta-inf.*\\.sf$") => MergeStrategy.discard + case "META-INF/services/org.apache.hadoop.fs.FileSystem" => MergeStrategy.concat case "reference.conf" => MergeStrategy.concat case _ => MergeStrategy.first } diff --git a/project/project/SparkPluginBuild.scala b/project/project/SparkPluginBuild.scala index 999611982a..6a66bd1d06 100644 --- a/project/project/SparkPluginBuild.scala +++ b/project/project/SparkPluginBuild.scala @@ -1,7 +1,24 @@ +/* + * 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. + */ + import sbt._ object SparkPluginDef extends Build { lazy val root = Project("plugins", file(".")) dependsOn(junitXmlListener) /* This is not published in a Maven repository, so we get it from GitHub directly */ lazy val junitXmlListener = uri("git://github.com/ijuma/junit_xml_listener.git#fe434773255b451a38e8d889536ebc260f4225ce") -}
\ No newline at end of file +} diff --git a/python/pyspark/__init__.py b/python/pyspark/__init__.py index fd5972d381..1f35f6f939 100644 --- a/python/pyspark/__init__.py +++ b/python/pyspark/__init__.py @@ -30,6 +30,8 @@ Public classes: An "add-only" shared variable that tasks can only add values to. - L{SparkFiles<pyspark.files.SparkFiles>} Access files shipped with jobs. + - L{StorageLevel<pyspark.storagelevel.StorageLevel>} + Finer-grained cache persistence levels. """ import sys import os @@ -39,6 +41,7 @@ sys.path.insert(0, os.path.join(os.environ["SPARK_HOME"], "python/lib/py4j0.7.eg from pyspark.context import SparkContext from pyspark.rdd import RDD from pyspark.files import SparkFiles +from pyspark.storagelevel import StorageLevel -__all__ = ["SparkContext", "RDD", "SparkFiles"] +__all__ = ["SparkContext", "RDD", "SparkFiles", "StorageLevel"] diff --git a/python/pyspark/context.py b/python/pyspark/context.py index 8fbf296509..597110321a 100644 --- a/python/pyspark/context.py +++ b/python/pyspark/context.py @@ -27,6 +27,7 @@ from pyspark.broadcast import Broadcast from pyspark.files import SparkFiles from pyspark.java_gateway import launch_gateway from pyspark.serializers import dump_pickle, write_with_length, batched +from pyspark.storagelevel import StorageLevel from pyspark.rdd import RDD from py4j.java_collections import ListConverter @@ -279,6 +280,16 @@ class SparkContext(object): """ self._jsc.sc().setCheckpointDir(dirName, useExisting) + def _getJavaStorageLevel(self, storageLevel): + """ + Returns a Java StorageLevel based on a pyspark.StorageLevel. + """ + if not isinstance(storageLevel, StorageLevel): + raise Exception("storageLevel must be of type pyspark.StorageLevel") + + newStorageLevel = self._jvm.org.apache.spark.storage.StorageLevel + return newStorageLevel(storageLevel.useDisk, storageLevel.useMemory, + storageLevel.deserialized, storageLevel.replication) def _test(): import atexit diff --git a/python/pyspark/rdd.py b/python/pyspark/rdd.py index 1831435b33..7611b13e82 100644 --- a/python/pyspark/rdd.py +++ b/python/pyspark/rdd.py @@ -70,6 +70,25 @@ class RDD(object): self._jrdd.cache() return self + def persist(self, storageLevel): + """ + Set this RDD's storage level to persist its values across operations after the first time + it is computed. This can only be used to assign a new storage level if the RDD does not + have a storage level set yet. + """ + self.is_cached = True + javaStorageLevel = self.ctx._getJavaStorageLevel(storageLevel) + self._jrdd.persist(javaStorageLevel) + return self + + def unpersist(self): + """ + Mark the RDD as non-persistent, and remove all blocks for it from memory and disk. + """ + self.is_cached = False + self._jrdd.unpersist() + return self + def checkpoint(self): """ Mark this RDD for checkpointing. It will be saved to a file inside the diff --git a/python/pyspark/shell.py b/python/pyspark/shell.py index 54823f8037..dc205b306f 100644 --- a/python/pyspark/shell.py +++ b/python/pyspark/shell.py @@ -24,6 +24,7 @@ import os import platform import pyspark from pyspark.context import SparkContext +from pyspark.storagelevel import StorageLevel # this is the equivalent of ADD_JARS add_files = os.environ.get("ADD_FILES").split(',') if os.environ.get("ADD_FILES") != None else None diff --git a/python/pyspark/storagelevel.py b/python/pyspark/storagelevel.py new file mode 100644 index 0000000000..b31f4762e6 --- /dev/null +++ b/python/pyspark/storagelevel.py @@ -0,0 +1,43 @@ +# +# 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. +# + +__all__ = ["StorageLevel"] + +class StorageLevel: + """ + Flags for controlling the storage of an RDD. Each StorageLevel records whether to use memory, + whether to drop the RDD to disk if it falls out of memory, whether to keep the data in memory + in a serialized format, and whether to replicate the RDD partitions on multiple nodes. + Also contains static constants for some commonly used storage levels, such as MEMORY_ONLY. + """ + + def __init__(self, useDisk, useMemory, deserialized, replication = 1): + self.useDisk = useDisk + self.useMemory = useMemory + self.deserialized = deserialized + self.replication = replication + +StorageLevel.DISK_ONLY = StorageLevel(True, False, False) +StorageLevel.DISK_ONLY_2 = StorageLevel(True, False, False, 2) +StorageLevel.MEMORY_ONLY = StorageLevel(False, True, True) +StorageLevel.MEMORY_ONLY_2 = StorageLevel(False, True, True, 2) +StorageLevel.MEMORY_ONLY_SER = StorageLevel(False, True, False) +StorageLevel.MEMORY_ONLY_SER_2 = StorageLevel(False, True, False, 2) +StorageLevel.MEMORY_AND_DISK = StorageLevel(True, True, True) +StorageLevel.MEMORY_AND_DISK_2 = StorageLevel(True, True, True, 2) +StorageLevel.MEMORY_AND_DISK_SER = StorageLevel(True, True, False) +StorageLevel.MEMORY_AND_DISK_SER_2 = StorageLevel(True, True, False, 2) diff --git a/repl-bin/pom.xml b/repl-bin/pom.xml index d61b36a61a..3685561501 100644 --- a/repl-bin/pom.xml +++ b/repl-bin/pom.xml @@ -106,16 +106,6 @@ <profiles> <profile> - <id>hadoop2-yarn</id> - <dependencies> - <dependency> - <groupId>org.apache.spark</groupId> - <artifactId>spark-yarn</artifactId> - <version>${project.version}</version> - </dependency> - </dependencies> - </profile> - <profile> <id>deb</id> <build> <plugins> diff --git a/repl/pom.xml b/repl/pom.xml index faabb0e1ec..b1ca5220bc 100644 --- a/repl/pom.xml +++ b/repl/pom.xml @@ -133,16 +133,4 @@ </plugin> </plugins> </build> - <profiles> - <profile> - <id>hadoop2-yarn</id> - <dependencies> - <dependency> - <groupId>org.apache.spark</groupId> - <artifactId>spark-yarn</artifactId> - <version>${project.version}</version> - </dependency> - </dependencies> - </profile> - </profiles> </project> diff --git a/run-example b/run-example index 24d83ba5cf..08ec717ca5 100755 --- a/run-example +++ b/run-example @@ -39,14 +39,14 @@ fi # to avoid the -sources and -doc packages that are built by publish-local. EXAMPLES_DIR="$FWDIR"/examples SPARK_EXAMPLES_JAR="" -if [ -e "$EXAMPLES_DIR"/target/scala-$SCALA_VERSION/*assembly*[0-9T].jar ]; then +if [ -e "$EXAMPLES_DIR"/target/scala-$SCALA_VERSION/*assembly*[0-9Tg].jar ]; then # Use the JAR from the SBT build - export SPARK_EXAMPLES_JAR=`ls "$EXAMPLES_DIR"/target/scala-$SCALA_VERSION/*assembly*[0-9T].jar` + export SPARK_EXAMPLES_JAR=`ls "$EXAMPLES_DIR"/target/scala-$SCALA_VERSION/*assembly*[0-9Tg].jar` fi -if [ -e "$EXAMPLES_DIR"/target/spark-examples*[0-9T].jar ]; then +if [ -e "$EXAMPLES_DIR"/target/spark-examples*[0-9Tg].jar ]; then # Use the JAR from the Maven build # TODO: this also needs to become an assembly! - export SPARK_EXAMPLES_JAR=`ls "$EXAMPLES_DIR"/target/spark-examples*[0-9T].jar` + export SPARK_EXAMPLES_JAR=`ls "$EXAMPLES_DIR"/target/spark-examples*[0-9Tg].jar` fi if [[ -z $SPARK_EXAMPLES_JAR ]]; then echo "Failed to find Spark examples assembly in $FWDIR/examples/target" >&2 diff --git a/yarn/pom.xml b/yarn/pom.xml index 654b5bcd2d..21b650d1ea 100644 --- a/yarn/pom.xml +++ b/yarn/pom.xml @@ -30,6 +30,39 @@ <name>Spark Project YARN Support</name> <url>http://spark.incubator.apache.org/</url> + <dependencies> + <dependency> + <groupId>org.apache.spark</groupId> + <artifactId>spark-core</artifactId> + <version>${project.version}</version> + </dependency> + <dependency> + <groupId>org.apache.hadoop</groupId> + <artifactId>hadoop-yarn-api</artifactId> + </dependency> + <dependency> + <groupId>org.apache.hadoop</groupId> + <artifactId>hadoop-yarn-common</artifactId> + </dependency> + <dependency> + <groupId>org.apache.hadoop</groupId> + <artifactId>hadoop-yarn-client</artifactId> + </dependency> + <dependency> + <groupId>org.apache.hadoop</groupId> + <artifactId>hadoop-client</artifactId> + <version>${yarn.version}</version> + </dependency> + <dependency> + <groupId>org.apache.avro</groupId> + <artifactId>avro</artifactId> + </dependency> + <dependency> + <groupId>org.apache.avro</groupId> + <artifactId>avro-ipc</artifactId> + </dependency> + </dependencies> + <build> <outputDirectory>target/scala-${scala.version}/classes</outputDirectory> <testOutputDirectory>target/scala-${scala.version}/test-classes</testOutputDirectory> @@ -75,37 +108,4 @@ </plugin> </plugins> </build> - - <profiles> - <profile> - <id>hadoop2-yarn</id> - <dependencies> - <dependency> - <groupId>org.apache.spark</groupId> - <artifactId>spark-core</artifactId> - <version>${project.version}</version> - </dependency> - <dependency> - <groupId>org.apache.hadoop</groupId> - <artifactId>hadoop-yarn-api</artifactId> - </dependency> - <dependency> - <groupId>org.apache.hadoop</groupId> - <artifactId>hadoop-yarn-common</artifactId> - </dependency> - <dependency> - <groupId>org.apache.hadoop</groupId> - <artifactId>hadoop-yarn-client</artifactId> - </dependency> - <dependency> - <groupId>org.apache.avro</groupId> - <artifactId>avro</artifactId> - </dependency> - <dependency> - <groupId>org.apache.avro</groupId> - <artifactId>avro-ipc</artifactId> - </dependency> - </dependencies> - </profile> - </profiles> </project> |
