I am trying to write results from Spark Streaming job to Druid datasource. Spark successfully completes its jobs and hands to Druid. Druid starts indexing but does not write anything.
My code and logs are as follows:
import org.apache.spark._
import org.apache.spark._
import org.apache.spark.streaming._
import org.apache.spark.streaming.StreamingContext
import org.apache.kafka.clients.consumer.ConsumerRecord
import org.apache.kafka.common.serialization.StringDeserializer
import org.apache.spark.streaming.kafka010._
impor org.apache.spark.streaming.kafka010.LocationStrategies.PreferConsistent
import org.apache.spark.streaming.kafka010.ConsumerStrategies.Subscribe
import scala.util.parsing.json._
import com.metamx.tranquility.spark.BeamRDD._
import org.joda.time.{DateTime, DateTimeZone}
object MyDirectStreamDriver {
def main(args:Array[String]) {
val sc = new SparkContext()
val ssc = new StreamingContext(sc, Minutes(5))
val kafkaParams = Map[String, Object](
"bootstrap.servers" -> "[$hadoopURL]:6667",
"key.deserializer" -> classOf[StringDeserializer],
"value.deserializer" -> classOf[StringDeserializer],
"group.id" -> "use_a_separate_group_id_for_each_stream",
"auto.offset.reset" -> "latest",
"enable.auto.commit" -> (false: java.lang.Boolean)
)
val eventStream = KafkaUtils.createDirectStream[String, String](
ssc,
PreferConsistent,
Subscribe[String, String](Array("events_test"), kafkaParams))
val t = eventStream.map(record => record.value).flatMap(_.split("(?<=\\}),(?=\\{)")).
map(JSON.parseRaw(_).getOrElse(new JSONObject(Map(""-> ""))).asInstanceOf[JSONObject]).
map( new DateTime(), x => (x.obj.getOrElse("OID", "").asInstanceOf[String], x.obj.getOrElse("STATUS", "").asInstanceOf[Double].toInt)).
map(x => MyEvent(x._1, x._2, x._3))
t.saveAsTextFiles("/user/username/result", "txt")
t.foreachRDD(rdd => rdd.propagate(new MyEventBeamFactory))
ssc.start
ssc.awaitTermination
}
}
case class MyEvent (time: DateTime,oid: String, status: Int)
{
#JsonValue
def toMap: Map[String, Any] = Map(
"timestamp" -> (time.getMillis / 1000),
"oid" -> oid,
"status" -> status
)
}
object MyEvent {
implicit val MyEventTimestamper = new Timestamper[MyEvent] {
def timestamp(a: MyEvent) = a.time
}
val Columns = Seq("time", "oid", "status")
def fromMap(d: Dict): MyEvent = {
MyEvent(
new DateTime(long(d("timestamp")) * 1000),
str(d("oid")),
int(d("status"))
)
}
}
import org.apache.curator.framework.CuratorFrameworkFactory
import org.apache.curator.retry.BoundedExponentialBackoffRetry
import io.druid.granularity._
import io.druid.query.aggregation.LongSumAggregatorFactory
import com.metamx.common.Granularity
import org.joda.time.Period
class MyEventBeamFactory extends BeamFactory[MyEvent]
{
// Return a singleton, so the same connection is shared across all tasks in the same JVM.
def makeBeam: Beam[MyEvent] = MyEventBeamFactory.BeamInstance
object MyEventBeamFactory {
val BeamInstance: Beam[MyEvent] = {
// Tranquility uses ZooKeeper (through Curator framework) for coordination.
val curator = CuratorFrameworkFactory.newClient(
"{IP_2}:2181",
new BoundedExponentialBackoffRetry(100, 3000, 5)
)
curator.start()
val indexService = DruidEnvironment("druid/overlord") // Your overlord's druid.service, with slashes replaced by colons.
val discoveryPath = "/druid/discovery" // Your overlord's druid.discovery.curator.path
val dataSource = "events_druid"
val dimensions = IndexedSeq("oid")
val aggregators = Seq(new LongSumAggregatorFactory("status", "status"))
// Expects simpleEvent.timestamp to return a Joda DateTime object.
DruidBeams
.builder((event: MyEvent) => event.time)
.curator(curator)
.discoveryPath(discoveryPath)
.location(DruidLocation(indexService, dataSource))
.rollup(DruidRollup(SpecificDruidDimensions(dimensions), aggregators, QueryGranularities.MINUTE))
.tuning(
ClusteredBeamTuning(
segmentGranularity = Granularity.HOUR,
windowPeriod = new Period("PT10M"),
partitions = 1,
replicants = 1
)
)
.buildBeam()
}
}
}
This is the druid indexing task log: (index_realtime_events_druid_2017-12-28T13:00:00.000Z_0_0)
2017-12-28T13:05:19,299 INFO [main] io.druid.indexing.worker.executor.ExecutorLifecycle - Running with task: {
"type" : "index_realtime",
"id" : "index_realtime_events_druid_2017-12-28T13:00:00.000Z_0_0",
"resource" : {
"availabilityGroup" : "events_druid-2017-12-28T13:00:00.000Z-0000",
"requiredCapacity" : 1
},
"spec" : {
"dataSchema" : {
"dataSource" : "events_druid",
"parser" : {
"type" : "map",
"parseSpec" : {
"format" : "json",
"timestampSpec" : {
"column" : "timestamp",
"format" : "iso",
"missingValue" : null
},
"dimensionsSpec" : {
"dimensions" : [ "oid" ],
"spatialDimensions" : [ ]
}
}
},
"metricsSpec" : [ {
"type" : "longSum",
"name" : "status",
"fieldName" : "status",
"expression" : null
} ],
"granularitySpec" : {
"type" : "uniform",
"segmentGranularity" : "HOUR",
"queryGranularity" : {
"type" : "duration",
"duration" : 60000,
"origin" : "1970-01-01T00:00:00.000Z"
},
"rollup" : true,
"intervals" : null
}
},
"ioConfig" : {
"type" : "realtime",
"firehose" : {
"type" : "clipped",
"delegate" : {
"type" : "timed",
"delegate" : {
"type" : "receiver",
"serviceName" : "firehose:druid:overlord:events_druid-013-0000-0000",
"bufferSize" : 100000
},
"shutoffTime" : "2017-12-28T14:15:00.000Z"
},
"interval" : "2017-12-28T13:00:00.000Z/2017-12-28T14:00:00.000Z"
},
"firehoseV2" : null
},
"tuningConfig" : {
"type" : "realtime",
"maxRowsInMemory" : 75000,
"intermediatePersistPeriod" : "PT10M",
"windowPeriod" : "PT10M",
"basePersistDirectory" : "/tmp/1514466313873-0",
"versioningPolicy" : {
"type" : "intervalStart"
},
"rejectionPolicy" : {
"type" : "none"
},
"maxPendingPersists" : 0,
"shardSpec" : {
"type" : "linear",
"partitionNum" : 0
},
"indexSpec" : {
"bitmap" : {
"type" : "concise"
},
"dimensionCompression" : "lz4",
"metricCompression" : "lz4",
"longEncoding" : "longs"
},
"buildV9Directly" : true,
"persistThreadPriority" : 0,
"mergeThreadPriority" : 0,
"reportParseExceptions" : false,
"handoffConditionTimeout" : 0,
"alertTimeout" : 0
}
},
"context" : null,
"groupId" : "index_realtime_events_druid",
"dataSource" : "events_druid"
}
2017-12-28T13:05:19,312 INFO [main] io.druid.indexing.worker.executor.ExecutorLifecycle - Attempting to lock file[/apps/druid/tasks/index_realtime_events_druid_2017-12-28T13:00:00.000Z_0_0/lock].
2017-12-28T13:05:19,313 INFO [main] io.druid.indexing.worker.executor.ExecutorLifecycle - Acquired lock file[/apps/druid/tasks/index_realtime_events_druid_2017-12-28T13:00:00.000Z_0_0/lock] in 1ms.
2017-12-28T13:05:19,317 INFO [task-runner-0-priority-0] io.druid.indexing.overlord.ThreadPoolTaskRunner - Running task: index_realtime_events_druid_2017-12-28T13:00:00.000Z_0_0
2017-12-28T13:05:19,323 INFO [task-runner-0-priority-0] io.druid.indexing.overlord.TaskRunnerUtils - Task [index_realtime_events_druid_2017-12-28T13:00:00.000Z_0_0] location changed to [TaskLocation{host='hadooptest9.{host}', port=8100}].
2017-12-28T13:05:19,323 INFO [task-runner-0-priority-0] io.druid.indexing.overlord.TaskRunnerUtils - Task [index_realtime_events_druid_2017-12-28T13:00:00.000Z_0_0] status changed to [RUNNING].
2017-12-28T13:05:19,327 INFO [main] org.eclipse.jetty.server.Server - jetty-9.3.19.v20170502
2017-12-28T13:05:19,350 INFO [task-runner-0-priority-0] io.druid.segment.realtime.plumber.RealtimePlumber - Creating plumber using rejectionPolicy[io.druid.segment.realtime.plumber.NoopRejectionPolicyFactory$1#7925d517]
2017-12-28T13:05:19,351 INFO [task-runner-0-priority-0] io.druid.server.coordination.CuratorDataSegmentServerAnnouncer - Announcing self[DruidServerMetadata{name='hadooptest9.{host}:8100', host='hadooptest9.{host}:8100', maxSize=0, tier='_default_tier', type='realtime', priority='0'}] at [/druid/announcements/hadooptest9.{host}:8100]
2017-12-28T13:05:19,382 INFO [task-runner-0-priority-0] io.druid.segment.realtime.plumber.RealtimePlumber - Expect to run at [2017-12-28T14:10:00.000Z]
2017-12-28T13:05:19,392 INFO [task-runner-0-priority-0] io.druid.segment.realtime.plumber.RealtimePlumber - Starting merge and push.
2017-12-28T13:05:19,392 INFO [task-runner-0-priority-0] io.druid.segment.realtime.plumber.RealtimePlumber - Found [0] segments. Attempting to hand off segments that start before [1970-01-01T00:00:00.000Z].
2017-12-28T13:05:19,392 INFO [task-runner-0-priority-0] io.druid.segment.realtime.plumber.RealtimePlumber - Found [0] sinks to persist and merge
2017-12-28T13:05:19,451 INFO [task-runner-0-priority-0] io.druid.segment.realtime.firehose.EventReceiverFirehoseFactory - Connecting firehose: firehose:druid:overlord:events_druid-013-0000-0000
2017-12-28T13:05:19,453 INFO [task-runner-0-priority-0] io.druid.segment.realtime.firehose.EventReceiverFirehoseFactory - Found chathandler of class[io.druid.segment.realtime.firehose.ServiceAnnouncingChatHandlerProvider]
2017-12-28T13:05:19,453 INFO [task-runner-0-priority-0] io.druid.segment.realtime.firehose.ServiceAnnouncingChatHandlerProvider - Registering Eventhandler[firehose:druid:overlord:events_druid-013-0000-0000]
2017-12-28T13:05:19,454 INFO [task-runner-0-priority-0] io.druid.curator.discovery.CuratorServiceAnnouncer - Announcing service[DruidNode{serviceName='firehose:druid:overlord:events_druid-013-0000-0000', host='hadooptest9.{host}', port=8100}]
2017-12-28T13:05:19,502 INFO [main] com.sun.jersey.guice.spi.container.GuiceComponentProviderFactory - Registering com.fasterxml.jackson.jaxrs.json.JacksonJsonProvider as a provider class
2017-12-28T13:05:19,502 INFO [main] com.sun.jersey.guice.spi.container.GuiceComponentProviderFactory - Registering com.fasterxml.jackson.jaxrs.smile.JacksonSmileProvider as a provider class
2017-12-28T13:05:19,502 INFO [main] com.sun.jersey.guice.spi.container.GuiceComponentProviderFactory - Registering io.druid.server.initialization.jetty.CustomExceptionMapper as a provider class
2017-12-28T13:05:19,502 INFO [main] com.sun.jersey.guice.spi.container.GuiceComponentProviderFactory - Registering io.druid.server.StatusResource as a root resource class
2017-12-28T13:05:19,505 INFO [main] com.sun.jersey.server.impl.application.WebApplicationImpl - Initiating Jersey application, version 'Jersey: 1.19.3 10/24/2016 03:43 PM'
2017-12-28T13:05:19,515 INFO [task-runner-0-priority-0] io.druid.segment.realtime.firehose.ServiceAnnouncingChatHandlerProvider - Registering Eventhandler[events_druid-013-0000-0000]
2017-12-28T13:05:19,515 INFO [task-runner-0-priority-0] io.druid.curator.discovery.CuratorServiceAnnouncer - Announcing service[DruidNode{serviceName='events_druid-013-0000-0000', host='hadooptest9.{host}', port=8100}]
2017-12-28T13:05:19,529 WARN [task-runner-0-priority-0] org.apache.curator.utils.ZKPaths - The version of ZooKeeper being used doesn't support Container nodes. CreateMode.PERSISTENT will be used instead.
2017-12-28T13:05:19,535 INFO [task-runner-0-priority-0] io.druid.server.metrics.EventReceiverFirehoseRegister - Registering EventReceiverFirehoseMetric for service [firehose:druid:overlord:events_druid-013-0000-0000]
2017-12-28T13:05:19,536 INFO [task-runner-0-priority-0] io.druid.data.input.FirehoseFactory - Firehose created, will shut down at: 2017-12-28T14:15:00.000Z
2017-12-28T13:05:19,574 INFO [main] com.sun.jersey.guice.spi.container.GuiceComponentProviderFactory - Binding io.druid.server.initialization.jetty.CustomExceptionMapper to GuiceManagedComponentProvider with the scope "Singleton"
2017-12-28T13:05:19,576 INFO [main] com.sun.jersey.guice.spi.container.GuiceComponentProviderFactory - Binding com.fasterxml.jackson.jaxrs.json.JacksonJsonProvider to GuiceManagedComponentProvider with the scope "Singleton"
2017-12-28T13:05:19,583 INFO [main] com.sun.jersey.guice.spi.container.GuiceComponentProviderFactory - Binding com.fasterxml.jackson.jaxrs.smile.JacksonSmileProvider to GuiceManagedComponentProvider with the scope "Singleton"
2017-12-28T13:05:19,845 INFO [main] com.sun.jersey.guice.spi.container.GuiceComponentProviderFactory - Binding io.druid.server.http.security.StateResourceFilter to GuiceInstantiatedComponentProvider
2017-12-28T13:05:19,863 INFO [main] com.sun.jersey.guice.spi.container.GuiceComponentProviderFactory - Binding io.druid.server.http.SegmentListerResource to GuiceInstantiatedComponentProvider
2017-12-28T13:05:19,874 INFO [main] com.sun.jersey.guice.spi.container.GuiceComponentProviderFactory - Binding io.druid.server.QueryResource to GuiceInstantiatedComponentProvider
2017-12-28T13:05:19,876 INFO [main] com.sun.jersey.guice.spi.container.GuiceComponentProviderFactory - Binding io.druid.segment.realtime.firehose.ChatHandlerResource to GuiceInstantiatedComponentProvider
2017-12-28T13:05:19,880 INFO [main] com.sun.jersey.guice.spi.container.GuiceComponentProviderFactory - Binding io.druid.query.lookup.LookupListeningResource to GuiceInstantiatedComponentProvider
2017-12-28T13:05:19,882 INFO [main] com.sun.jersey.guice.spi.container.GuiceComponentProviderFactory - Binding io.druid.query.lookup.LookupIntrospectionResource to GuiceInstantiatedComponentProvider
2017-12-28T13:05:19,883 INFO [main] com.sun.jersey.guice.spi.container.GuiceComponentProviderFactory - Binding io.druid.server.StatusResource to GuiceManagedComponentProvider with the scope "Undefined"
2017-12-28T13:05:19,896 WARN [main] com.sun.jersey.spi.inject.Errors - The following warnings have been detected with resource and/or provider classes:
WARNING: A HTTP GET method, public void io.druid.server.http.SegmentListerResource.getSegments(long,long,long,javax.servlet.http.HttpServletRequest) throws java.io.IOException, MUST return a non-void type.
2017-12-28T13:05:19,905 INFO [main] org.eclipse.jetty.server.handler.ContextHandler - Started o.e.j.s.ServletContextHandler#2fba0dac{/,null,AVAILABLE}
2017-12-28T13:05:19,914 INFO [main] org.eclipse.jetty.server.AbstractConnector - Started ServerConnector#25218a4d{HTTP/1.1,[http/1.1]}{0.0.0.0:8100}
2017-12-28T13:05:19,914 INFO [main] org.eclipse.jetty.server.Server - Started #6014ms
2017-12-28T13:05:19,915 INFO [main] io.druid.java.util.common.lifecycle.Lifecycle$AnnotationBasedHandler - Invoking start method[public void io.druid.server.listener.announcer.ListenerResourceAnnouncer.start()] on object[io.druid.query.lookup.LookupResourceListenerAnnouncer#426710f0].
2017-12-28T13:05:19,919 INFO [main] io.druid.server.listener.announcer.ListenerResourceAnnouncer - Announcing start time on [/druid/listeners/lookups/__default/hadooptest9.{host}:8100]
2017-12-28T13:05:20,517 WARN [task-runner-0-priority-0] io.druid.segment.realtime.firehose.PredicateFirehose - [0] InputRow(s) ignored as they do not satisfy the predicate
This is index_realtime_events_druid_2017-12-28T13:00:00.000Z_0_0 payload:
{
"task":"index_realtime_events_druid_2017-12-28T13:00:00.000Z_0_0","payload":{
"id":"index_realtime_events_druid_2017-12-28T13:00:00.000Z_0_0","resource":{
"availabilityGroup":"events_druid-2017-12-28T13:00:00.000Z-0000","requiredCapacity":1},"spec":{
"dataSchema":{
"dataSource":"events_druid","parser":{
"type":"map","parseSpec":{
"format":"json","timestampSpec":{
"column":"timestamp","format":"iso","missingValue":null},"dimensionsSpec":{
"dimensions":["oid"],"spatialDimensions":[]}}},"metricsSpec":[{
"type":"longSum","name":"status","fieldName":"status","expression":null}],"granularitySpec":{
"type":"uniform","segmentGranularity":"HOUR","queryGranularity":{
"type":"duration","duration":60000,"origin":"1970-01-01T00:00:00.000Z"},"rollup":true,"intervals":null}},"ioConfig":{
"type":"realtime","firehose":{
"type":"clipped","delegate":{
"type":"timed","delegate":{
"type":"receiver","serviceName":"firehose:druid:overlord:events_druid-013-0000-0000","bufferSize":100000},"shutoffTime":"2017-12-28T14:15:00.000Z"},"interval":"2017-12-28T13:00:00.000Z/2017-12-28T14:00:00.000Z"},"firehoseV2":null},"tuningConfig":{
"type":"realtime","maxRowsInMemory":75000,"intermediatePersistPeriod":"PT10M","windowPeriod":"PT10M","basePersistDirectory":"/tmp/1514466313873-0","versioningPolicy":{
"type":"intervalStart"},"rejectionPolicy":{
"type":"none"},"maxPendingPersists":0,"shardSpec":{
"type":"linear","partitionNum":0},"indexSpec":{
"bitmap":{
"type":"concise"},"dimensionCompression":"lz4","metricCompression":"lz4","longEncoding":"longs"},"buildV9Directly":true,"persistThreadPriority":0,"mergeThreadPriority":0,"reportParseExceptions":false,"handoffConditionTimeout":0,"alertTimeout":0}},"context":null,"groupId":"index_realtime_events_druid","dataSource":"events_druid"}}
This is end of spark job stderr
50:09 INFO ZooKeeper: Client environment:os.version=3.10.0-514.10.2.el7.x86_64
17/12/28 14:50:09 INFO ZooKeeper: Client environment:user.name=yarn
17/12/28 14:50:09 INFO ZooKeeper: Client environment:user.home=/home/yarn
17/12/28 14:50:09 INFO ZooKeeper: Client environment:user.dir=/data1/hadoop/yarn/local/usercache/hdfs/appcache/application_1512485869804_6924/container_e58_1512485869804_6924_01_000002
17/12/28 14:50:09 INFO ZooKeeper: Initiating client connection, connectString={IP2}:2181 sessionTimeout=60000 watcher=org.apache.curator.ConnectionState#5967905
17/12/28 14:50:09 INFO ClientCnxn: Opening socket connection to server {IP2}/{IP2}:2181. Will not attempt to authenticate using SASL (unknown error)
17/12/28 14:50:09 INFO ClientCnxn: Socket connection established, initiating session, client: /{IP6}:42704, server: {IP2}/{IP2}:2181
17/12/28 14:50:09 INFO ClientCnxn: Session establishment complete on server {IP2}/{IP2}:2181, sessionid = 0x25fa4ea15980119, negotiated timeout = 40000
17/12/28 14:50:10 INFO ConnectionStateManager: State change: CONNECTED
17/12/28 14:50:10 INFO Version: HV000001: Hibernate Validator 5.1.3.Final
17/12/28 14:50:10 INFO JsonConfigurator: Loaded class[class io.druid.guice.ExtensionsConfig] from props[druid.extensions.] as [ExtensionsConfig{searchCurrentClassloader=true, directory='extensions', hadoopDependenciesDir='hadoop-dependencies', hadoopContainerDruidClasspath='null', loadList=null}]
17/12/28 14:50:10 INFO LoggingEmitter: Start: started [true]
17/12/28 14:50:11 INFO FinagleRegistry: Adding resolver for scheme[disco].
17/12/28 14:50:11 INFO CachedKafkaConsumer: Initial fetch for spark-executor-use_a_separate_group_id_for_each_stream events_test 0 6658
17/12/28 14:50:12 INFO ClusteredBeam: Global latestCloseTime[2017-12-28T12:00:00.000Z] for identifier[druid:overlord/events_druid] has moved past timestamp[2017-12-28T12:00:00.000Z], not creating merged beam
17/12/28 14:50:12 INFO ClusteredBeam: Turns out we decided not to actually make beams for identifier[druid:overlord/events_druid] timestamp[2017-12-28T12:00:00.000Z]. Returning None.
17/12/28 14:50:12 WARN MapPartitioner: Cannot partition object of class[class MyEvent] by time and dimensions. Consider implementing a Partitioner.
17/12/28 14:50:12 INFO ClusteredBeam: Global latestCloseTime[2017-12-28T12:00:00.000Z] for identifier[druid:overlord/events_druid] has moved past timestamp[2017-12-28T12:00:00.000Z], not creating merged beam
17/12/28 14:50:12 INFO ClusteredBeam: Turns out we decided not to actually make beams for identifier[druid:overlord/events_druid] timestamp[2017-12-28T12:00:00.000Z]. Returning None.
17/12/28 14:50:12 INFO ClusteredBeam: Global latestCloseTime[2017-12-28T12:00:00.000Z] for identifier[druid:overlord/events_druid] has moved past timestamp[2017-12-28T12:00:00.000Z], not creating merged beam
17/12/28 14:50:12 INFO ClusteredBeam: Turns out we decided not to actually make beams for identifier[druid:overlord/events_druid] timestamp[2017-12-28T12:00:00.000Z]. Returning None.
17/12/28 14:50:12 INFO ClusteredBeam: Global latestCloseTime[2017-12-28T12:00:00.000Z] for identifier[druid:overlord/events_druid] has moved past timestamp[2017-12-28T12:00:00.000Z], not creating merged beam
17/12/28 14:50:12 INFO ClusteredBeam: Turns out we decided not to actually make beams for identifier[druid:overlord/events_druid] timestamp[2017-12-28T12:00:00.000Z]. Returning None.
17/12/28 14:50:12 INFO ClusteredBeam: Global latestCloseTime[2017-12-28T12:00:00.000Z] for identifier[druid:overlord/events_druid] has moved past timestamp[2017-12-28T12:00:00.000Z], not creating merged beam
17/12/28 14:50:12 INFO ClusteredBeam: Turns out we decided not to actually make beams for identifier[druid:overlord/events_druid] timestamp[2017-12-28T12:00:00.000Z]. Returning None.
17/12/28 14:50:16 INFO Executor: Finished task 0.0 in stage 1.0 (TID 1). 1541 bytes result sent to driver
I have also written result to a text file to make sure data is coming and formatted. Here are a few lines of text file:
MyEvent(2017-12-28T16:10:00.387+03:00,0010,1)
MyEvent(2017-12-28T16:10:00.406+03:00,0030,1)
MyEvent(2017-12-28T16:10:00.417+03:00,0010,1)
MyEvent(2017-12-28T16:10:00.431+03:00,0010,1)
MyEvent(2017-12-28T16:10:00.448+03:00,0010,1)
MyEvent(2017-12-28T16:10:00.464+03:00,0030,1)
Help is much appreciated. Thanks.
This problem was solved by adding timestampSpec to DruidBeams as such:
DruidBeams
.builder((event: MyEvent) => event.time)
.curator(curator)
.discoveryPath(discoveryPath)
.location(DruidLocation(indexService, dataSource))
.rollup(DruidRollup(SpecificDruidDimensions(dimensions), aggregators, QueryGranularities.MINUTE))
.tuning(
ClusteredBeamTuning(
segmentGranularity = Granularity.HOUR,
windowPeriod = new Period("PT10M"),
partitions = 1,
replicants = 1
)
)
.timestampSpec(new TimestampSpec("timestamp", "posix", null))
.buildBeam()
On every slave node through Marathon we run Mesos External Shuffle Service . When we submit spark job via dcos CLI in coarse grained mode without dynamic allocation everything working as expected. But when we submit the same job with dynamic allocation it fails.
16/12/08 19:20:42 ERROR OneForOneBlockFetcher: Failed while starting block fetches
java.lang.RuntimeException: java.lang.RuntimeException: Failed to open file:/tmp/blockmgr-d4df5df4-24c9-41a3-9f26-4c1aba096814/30/shuffle_0_0_0.index
at org.apache.spark.network.shuffle.ExternalShuffleBlockResolver.getSortBasedShuffleBlockData(ExternalShuffleBlockResolver.java:234)
...
at io.netty.channel.nio.NioEventLoop.run(NioEventLoop.java:354)
...
Caused by: java.io.FileNotFoundException: /tmp/blockmgr-d4df5df4-24c9-41a3-9f26-4c1aba096814/30/shuffle_0_0_0.index (No such file or directory)
Full description:
We installed Mesos (DCOS) with Marathon using Azure Portal.
Via Universe Packages we installed: Cassandra, Spark and Marathon-lb
We generated test data in Cassandra.
On laptop I installed dcos CLI
When I submit job as below everything is working as expected:
./dcos spark run --submit-args="--properties-file coarse-grained.conf --class portal.spark.cassandra.app.ProductModelPerNrOfAlerts http://marathon-lb-default.marathon.mesos:10018/jars/spark-cassandra-assembly-1.0.jar"
Run job succeeded. Submission id: driver-20161208185927-0043
cqlsh:sp> select count(*) from product_model_per_alerts_by_date ;
count
-------
476
coarse-grained.conf:
spark.cassandra.connection.host 10.32.0.17
spark.serializer org.apache.spark.serializer.KryoSerializer
spark.executor.cores 1
spark.executor.memory 1g
spark.executor.instances 2
spark.submit.deployMode cluster
spark.cores.max 4
portal.spark.cassandra.app.ProductModelPerNrOfAlerts:
package portal.spark.cassandra.app
import org.apache.spark.sql.{SQLContext, SaveMode}
import org.apache.spark.{SparkConf, SparkContext}
object ProductModelPerNrOfAlerts {
def main(args: Array[String]): Unit = {
val conf = new SparkConf(true)
.setAppName("cassandraSpark-ProductModelPerNrOfAlerts")
val sc = new SparkContext(conf)
val sqlContext = new SQLContext(sc)
import sqlContext.implicits._
val df = sqlContext
.read
.format("org.apache.spark.sql.cassandra")
.options(Map("table" -> "asset_history", "keyspace" -> "sp"))
.load()
.select("datestamp","product_model","nr_of_alerts")
val dr = df
.groupBy("datestamp","product_model")
.avg("nr_of_alerts")
.toDF("datestamp","product_model","nr_of_alerts")
dr.write
.mode(SaveMode.Overwrite)
.format("org.apache.spark.sql.cassandra")
.options(Map("table" -> "product_model_per_alerts_by_date", "keyspace" -> "sp"))
.save()
sc.stop()
}
}
Dynamic Allocation
Through Marathon we run Mesos External Shuffle Service:
{
"id": "spark-mesos-external-shuffle-service-tt",
"container": {
"type": "DOCKER",
"docker": {
"image": "jpavt/mesos-spark-hadoop:mesos-external-shuffle-service-1.0.4-2.0.1",
"network": "BRIDGE",
"portMappings": [
{ "hostPort": 7337, "containerPort": 7337, "servicePort": 7337 }
],
"forcePullImage":true,
"volumes": [
{
"containerPath": "/tmp",
"hostPath": "/tmp",
"mode": "RW"
}
]
}
},
"instances": 9,
"cpus": 0.2,
"mem": 512,
"constraints": [["hostname", "UNIQUE"]]
}
Dockerfile for jpavt/mesos-spark-hadoop:mesos-external-shuffle-service-1.0.4-2.0.1:
FROM mesosphere/spark:1.0.4-2.0.1
WORKDIR /opt/spark/dist
ENTRYPOINT ["./bin/spark-class", "org.apache.spark.deploy.mesos.MesosExternalShuffleService"]
Now when I submit job with dynamic allocation it fails:
./dcos spark run --submit-args="--properties-file dynamic-allocation.conf --class portal.spark.cassandra.app.ProductModelPerNrOfAlerts http://marathon-lb-default.marathon.mesos:10018/jars/spark-cassandra-assembly-1.0.jar"
Run job succeeded. Submission id: driver-20161208191958-0047
select count(*) from product_model_per_alerts_by_date ;
count
-------
5
dynamic-allocation.conf:
spark.cassandra.connection.host 10.32.0.17
spark.serializer org.apache.spark.serializer.KryoSerializer
spark.executor.cores 1
spark.executor.memory 1g
spark.submit.deployMode cluster
spark.cores.max 4
spark.shuffle.service.enabled true
spark.dynamicAllocation.enabled true
spark.dynamicAllocation.minExecutors 2
spark.dynamicAllocation.maxExecutors 5
spark.dynamicAllocation.cachedExecutorIdleTimeout 120s
spark.dynamicAllocation.schedulerBacklogTimeout 10s
spark.dynamicAllocation.sustainedSchedulerBacklogTimeout 20s
spark.mesos.executor.docker.volumes /tmp:/tmp:rw
spark.local.dir /tmp
logs from mesos:
16/12/08 19:20:42 INFO MemoryStore: Block broadcast_7_piece0 stored as bytes in memory (estimated size 18.0 KB, free 366.0 MB)
16/12/08 19:20:42 INFO TorrentBroadcast: Reading broadcast variable 7 took 21 ms
16/12/08 19:20:42 INFO MemoryStore: Block broadcast_7 stored as values in memory (estimated size 38.6 KB, free 366.0 MB)
16/12/08 19:20:42 INFO MapOutputTrackerWorker: Don't have map outputs for shuffle 0, fetching them
16/12/08 19:20:42 INFO MapOutputTrackerWorker: Doing the fetch; tracker endpoint = NettyRpcEndpointRef(spark://MapOutputTracker#10.32.0.4:45422)
16/12/08 19:20:42 INFO MapOutputTrackerWorker: Got the output locations
16/12/08 19:20:42 INFO ShuffleBlockFetcherIterator: Getting 4 non-empty blocks out of 58 blocks
16/12/08 19:20:42 INFO TransportClientFactory: Successfully created connection to /10.32.0.11:7337 after 2 ms (0 ms spent in bootstraps)
16/12/08 19:20:42 INFO ShuffleBlockFetcherIterator: Started 1 remote fetches in 13 ms
16/12/08 19:20:42 ERROR OneForOneBlockFetcher: Failed while starting block fetches java.lang.RuntimeException: java.lang.RuntimeException: Failed to open file: /tmp/blockmgr-d4df5df4-24c9-41a3-9f26-4c1aba096814/30/shuffle_0_0_0.index
at org.apache.spark.network.shuffle.ExternalShuffleBlockResolver.getSortBasedShuffleBlockData(ExternalShuffleBlockResolver.java:234)
...
at io.netty.channel.nio.NioEventLoop.run(NioEventLoop.java:354)
...
Caused by: java.io.FileNotFoundException: /tmp/blockmgr-d4df5df4-24c9-41a3-9f26-4c1aba096814/30/shuffle_0_0_0.index (No such file or directory)
logs from marathon spark-mesos-external-shuffle-service-tt:
...
16/12/08 19:20:29 INFO MesosExternalShuffleBlockHandler: Received registration request from app 704aec43-1aa3-4971-bb98-e892beeb2c45-0008-driver-20161208191958-0047 (remote address /10.32.0.4:49710, heartbeat timeout 120000 ms).
16/12/08 19:20:31 INFO ExternalShuffleBlockResolver: Registered executor AppExecId{appId=704aec43-1aa3-4971-bb98-e892beeb2c45-0008-driver-20161208191958-0047, execId=2} with ExecutorShuffleInfo{localDirs=[/tmp/blockmgr-14525ef0-22e9-49fb-8e81-dc84e5fba8b2], subDirsPerLocalDir=64, shuffleManager=org.apache.spark.shuffle.sort.SortShuffleManager}
16/12/08 19:20:38 ERROR TransportRequestHandler: Error while invoking RpcHandler#receive() on RPC id 8157825166903585542
java.lang.RuntimeException: Failed to open file: /tmp/blockmgr-14525ef0-22e9-49fb-8e81-dc84e5fba8b2/16/shuffle_0_55_0.index
at org.apache.spark.network.shuffle.ExternalShuffleBlockResolver.getSortBasedShuffleBlockData(ExternalShuffleBlockResolver.java:234)
...
at io.netty.channel.nio.NioEventLoop.run(NioEventLoop.java:354)
Caused by: java.io.FileNotFoundException: /tmp/blockmgr-14525ef0-22e9-49fb-8e81-dc84e5fba8b2/16/shuffle_0_55_0.index (No such file or directory)
...
but file exists on given slave box:
$ ls -l /tmp/blockmgr-14525ef0-22e9-49fb-8e81-dc84e5fba8b2/16/shuffle_0_55_0.index
-rw-r--r-- 1 root root 1608 Dec 8 19:20 /tmp/blockmgr-14525ef0-22e9-49fb-8e81-dc84e5fba8b2/16/shuffle_0_55_0.index
stat shuffle_0_55_0.index
File: 'shuffle_0_55_0.index'
Size: 1608 Blocks: 8 IO Block: 4096 regular file
Device: 801h/2049d Inode: 1805493 Links: 1
Access: (0644/-rw-r--r--) Uid: ( 0/ root) Gid: ( 0/ root)
Access: 2016-12-08 19:20:38.163188836 +0000
Modify: 2016-12-08 19:20:38.163188836 +0000
Change: 2016-12-08 19:20:38.163188836 +0000
Birth: -
I am not familiar with DCOS, Marathon and Azure though, I use dynamic resource allocation(Mesos external shuffle service) on Mesos and Aurora with Docker.
Each Mesos agent node has its own external shuffle service (that is, one external shuffle service for one mesos agent) ?
spark.local.dir setting is exactly same string and pointing same directory ? Your spark.local.dir for shuffle service is /tmp though, I don't know DCOS setting.
spark.local.dir directory can be readable/writable for both ? If both mesos agent and external shuffle service are launched by docker, spark.local.dir on host MUST be mounted to both containers.
EDIT
If SPARK_LOCAL_DIRS (mesos or standalone) environment variable is set, spark.local.dir will be overridden.
There was error in marathon external shuffle service config instead of path container.docker.volumes we should use container.volumes path.
Correct configuration:
{
"id": "mesos-external-shuffle-service-simple",
"container": {
"type": "DOCKER",
"docker": {
"image": "jpavt/mesos-spark-hadoop:mesos-external-shuffle-service-1.0.4-2.0.1",
"network": "BRIDGE",
"portMappings": [
{ "hostPort": 7337, "containerPort": 7337, "servicePort": 7337 }
],
"forcePullImage":true
},
"volumes": [
{
"containerPath": "/tmp",
"hostPath": "/tmp",
"mode": "RW"
}
]
},
"instances": 9,
"cpus": 0.2,
"mem": 512,
"constraints": [["hostname", "UNIQUE"]]
}
Right now I'm using spark-submit to launch an application in cluster mode. The response from the master server gives a json object with a submissionId which I use to identify the application and kill it if necessary. However, I haven't found a simple way to retrieve the worker rest url from the master server response or the driver id (probably could web scrape the master web ui but that would be ugly). Instead, I have to wait until the application finishes, then look up the application statistics from the history server.
Is there any way to use the driver-id to identify the worker url from an application deployed in cluster mode (usually at worker-node:4040)?
16/08/12 11:39:47 INFO RestSubmissionClient: Submitting a request to launch an application in spark://192.yyy:6066.
16/08/12 11:39:47 INFO RestSubmissionClient: Submission successfully created as driver-20160812114003-0001. Polling submission state...
16/08/12 11:39:47 INFO RestSubmissionClient: Submitting a request for the status of submission driver-20160812114003-0001 in spark://192.yyy:6066.
16/08/12 11:39:47 INFO RestSubmissionClient: State of driver driver-20160812114003-0001 is now RUNNING.
16/08/12 11:39:47 INFO RestSubmissionClient: Driver is running on worker worker-20160812113715-192.xxx-46215 at 192.xxx:46215.
16/08/12 11:39:47 INFO RestSubmissionClient: Server responded with CreateSubmissionResponse:
{
"action" : "CreateSubmissionResponse",
"message" : "Driver successfully submitted as driver-20160812114003-0001",
"serverSparkVersion" : "1.6.1",
"submissionId" : "driver-20160812114003-0001",
"success" : true
}
EDIT: Here's what a typical output looks like with log4j console output at DEBUG
Spark-submit command:
./apps/spark-2.0.0-bin-hadoop2.7/bin/spark-submit --master mesos://masterurl:7077
--verbose --class MainClass --deploy-mode cluster
~/path/myjar.jar args
Spark-submit output:
Using properties file: null
Parsed arguments:
master mesos://masterurl:7077
deployMode cluster
executorMemory null
executorCores null
totalExecutorCores null
propertiesFile null
driverMemory null
driverCores null
driverExtraClassPath null
driverExtraLibraryPath null
driverExtraJavaOptions null
supervise false
queue null
numExecutors null
files null
pyFiles null
archives null
mainClass MyApp
primaryResource file:/path/myjar.jar
name MyApp
childArgs [args]
jars null
packages null
packagesExclusions null
repositories null
verbose true
Spark properties used, including those specified through
--conf and those from the properties file null:
Main class:
org.apache.spark.deploy.rest.RestSubmissionClient
Arguments:
file:/path/myjar.jar
MyApp
args
System properties:
SPARK_SUBMIT -> true
spark.driver.supervise -> false
spark.app.name -> MyApp
spark.jars -> file:/path/myjar.jar
spark.submit.deployMode -> cluster
spark.master -> mesos://masterurl:7077
Classpath elements:
16/08/17 13:26:49 INFO RestSubmissionClient: Submitting a request to launch an application in mesos://masterurl:7077.
16/08/17 13:26:49 DEBUG RestSubmissionClient: Sending POST request to server at http://masterurl:7077/v1/submissions/create:
{
"action" : "CreateSubmissionRequest",
"appArgs" : [ args ],
"appResource" : "file:/path/myjar.jar",
"clientSparkVersion" : "2.0.0",
"environmentVariables" : {
"SPARK_SCALA_VERSION" : "2.10"
},
"mainClass" : "SimpleSort",
"sparkProperties" : {
"spark.jars" : "file:/path/myjar.jar",
"spark.driver.supervise" : "false",
"spark.app.name" : "MyApp",
"spark.submit.deployMode" : "cluster",
"spark.master" : "mesos://masterurl:7077"
}
}
16/08/17 13:26:49 DEBUG RestSubmissionClient: Response from the server:
{
"action" : "CreateSubmissionResponse",
"serverSparkVersion" : "2.0.0",
"submissionId" : "driver-20160817132658-0004",
"success" : true
}
16/08/17 13:26:49 INFO RestSubmissionClient: Submission successfully created as driver-20160817132658-0004. Polling submission state...
16/08/17 13:26:49 INFO RestSubmissionClient: Submitting a request for the status of submission driver-20160817132658-0004 in mesos://masterurl:7077.
16/08/17 13:26:49 DEBUG RestSubmissionClient: Sending GET request to server at http://masterurl:7077/v1/submissions/status/driver-20160817132658-0004.
16/08/17 13:26:49 DEBUG RestSubmissionClient: Response from the server:
{
"action" : "SubmissionStatusResponse",
"driverState" : "RUNNING",
"serverSparkVersion" : "2.0.0",
"submissionId" : "driver-20160817132658-0004",
"success" : true
}
16/08/17 13:26:49 INFO RestSubmissionClient: State of driver driver-20160817132658-0004 is now RUNNING.
16/08/17 13:26:49 INFO RestSubmissionClient: Server responded with CreateSubmissionResponse:
{
"action" : "CreateSubmissionResponse",
"serverSparkVersion" : "2.0.0",
"submissionId" : "driver-20160817132658-0004",
"success" : true
}
Does the master server's response not provide application-id?
I believe all you need is the master-URL and application-id of your application for this problem. Once you have the application-id, use the port 4040 at master-URL and append your intended endpoint to it.
For example, if your application id is application_1468141556944_1055
To get the list of all jobs
http://<master>:4040/api/v1/applications/application_1468141556944_1055/jobs
To get the list of stored RDDs
http://<master>:4040/api/v1/applications/application_1468141556944_1055/storage/rdd
However if you don't have application-id, I would probably start with following:
Set verbose mode (--verbose) while launching spark job to get application id on console. You can then parse for application-id in log output. The log output usually looks like:
16/08/12 08:50:53 INFO Client: Application report for application_1468141556944_3791 (state: RUNNING)
thus, application-id is application_1468141556944_3791
You can also find master-url and application-id through tracking URL in the log output, which looks like
client token: N/A
diagnostics: N/A
ApplicationMaster host: 10.50.0.33
ApplicationMaster RPC port: 0
queue: ns_debug
start time: 1470992969127
final status: UNDEFINED
tracking URL: http://<master>:8088/proxy/application_1468141556944_3799/
These messages are at INFO log level so make sure you set log4j.rootCategory=INFO, console in log4j.properties file so that you can see them.
Had to scrape the spark master web ui for an application id that's close (within the same minute & same suffix e.g. 20161010025XXX-0005 with X as wildcard), then look for the worker url in the link tag after it. Not pretty, reliable, or secure, but for now it'll work. Leaving open for a bit in case someone has another approach.