Have been extensively trying to integrate spark rdd's with ignite. We have
spark version 1.6.1 with apache-ignite-1.6.0-src. Tried out the example in
"https://apacheignite-fs.readme.io/docs/testing-integration-with-spark-shell";
and it is working fine. However, all efforts w.r.t connecting to spark
dataframes/rdd's have been fruitless. Have listed the steps below, Any inputs
on what is missing will be of great help. We have a 10 node spark-hadoop
cluster. Please suggest if there are any other better approach than converting
df's to rdd's and using ignite saveValues ?
1. val df2 = sqlContext.read.jdbc(url, "SAMPLE_DATA", props) // Dataframe
that reads Oracle SAMPLE_DATA table.
df2.show() returns all the values in table. We are good from spark perspective
at this point.
2.
import org.apache.spark.rdd.RDD
import org.apache.spark.sql.Row
val rows: RDD[Row] = df2.rdd // Converting dataframe to rdd's
Setting up ignite properties:
1. scala> import org.apache.ignite.spark._
2. scala> import org.apache.ignite.configuration._
3. val igniteContext = new
IgniteContext[org.apache.spark.sql.Row,org.apache.spark.sql.Row](sc, () => new
IgniteConfiguration())
4. val sharedRDD = igniteContext.fromCache("partitioned")
5. sharedRDD.saveValues(rows: RDD[Row])
After this, hitting the below error..
scala> sharedRDD.saveValues(rows: RDD[Row])
16/11/23 13:23:57 WARN TaskSetManager: Lost task 0.0 in stage 0.0 (TID 0,
xxx006.xxx.com): java.lang.IllegalStateException: Did not find registered
driver with class oracle.jdbc.OracleDriver
at
org.apache.spark.sql.execution.datasources.jdbc.JdbcUtils$$anonfun$createConnectionFactory$2$$anonfun$3.apply(JdbcUtils.scala:58)
at
org.apache.spark.sql.execution.datasources.jdbc.JdbcUtils$$anonfun$createConnectionFactory$2$$anonfun$3.apply(JdbcUtils.scala:58)
at scala.Option.getOrElse(Option.scala:120)
at
org.apache.spark.sql.execution.datasources.jdbc.JdbcUtils$$anonfun$createConnectionFactory$2.apply(JdbcUtils.scala:57)
at
org.apache.spark.sql.execution.datasources.jdbc.JdbcUtils$$anonfun$createConnectionFactory$2.apply(JdbcUtils.scala:52)
at
org.apache.spark.sql.execution.datasources.jdbc.JDBCRDD$$anon$1.<init>(JDBCRDD.scala:347)
at
org.apache.spark.sql.execution.datasources.jdbc.JDBCRDD.compute(JDBCRDD.scala:339)
at org.apache.spark.rdd.RDD.computeOrReadCheckpoint(RDD.scala:306)
at org.apache.spark.rdd.RDD.iterator(RDD.scala:270)
at org.apache.spark.rdd.MapPartitionsRDD.compute(MapPartitionsRDD.scala:38)
at org.apache.spark.rdd.RDD.computeOrReadCheckpoint(RDD.scala:306)
at org.apache.spark.rdd.RDD.iterator(RDD.scala:270)
at org.apache.spark.scheduler.ResultTask.runTask(ResultTask.scala:66)
at org.apache.spark.scheduler.Task.run(Task.scala:89)
at org.apache.spark.executor.Executor$TaskRunner.run(Executor.scala:214)
at
java.util.concurrent.ThreadPoolExecutor.runWorker(ThreadPoolExecutor.java:1145)
at
java.util.concurrent.ThreadPoolExecutor$Worker.run(ThreadPoolExecutor.java:615)
at java.lang.Thread.run(Thread.java:745)
[13:24:00] Topology snapshot [ver=28, servers=3, clients=1, CPUs=16, heap=4.0GB]
16/11/23 13:24:01 WARN TaskSetManager: Lost task 0.1 in stage 0.0 (TID 1,
xxx001): java.lang.NoSuchMethodError:
scala.Predef$.$conforms()Lscala/Predef$$less$colon$less;
at
org.apache.ignite.spark.IgniteRDD$$anonfun$saveValues$1$$anonfun$apply$1.apply(IgniteRDD.scala:151)
at
org.apache.ignite.spark.IgniteRDD$$anonfun$saveValues$1$$anonfun$apply$1.apply(IgniteRDD.scala:150)
at scala.collection.Iterator$class.foreach(Iterator.scala:727)
at scala.collection.AbstractIterator.foreach(Iterator.scala:1157)
at
org.apache.ignite.spark.IgniteRDD$$anonfun$saveValues$1.apply(IgniteRDD.scala:150)
at
org.apache.ignite.spark.IgniteRDD$$anonfun$saveValues$1.apply(IgniteRDD.scala:138)
at
org.apache.spark.rdd.RDD$$anonfun$foreachPartition$1$$anonfun$apply$33.apply(RDD.scala:920)
at
org.apache.spark.rdd.RDD$$anonfun$foreachPartition$1$$anonfun$apply$33.apply(RDD.scala:920)
at
org.apache.spark.SparkContext$$anonfun$runJob$5.apply(SparkContext.scala:1858)
at
org.apache.spark.SparkContext$$anonfun$runJob$5.apply(SparkContext.scala:1858)
at org.apache.spark.scheduler.ResultTask.runTask(ResultTask.scala:66)
at org.apache.spark.scheduler.Task.run(Task.scala:89)
at org.apache.spark.executor.Executor$TaskRunner.run(Executor.scala:214)
at
java.util.concurrent.ThreadPoolExecutor.runWorker(ThreadPoolExecutor.java:1145)
at
java.util.concurrent.ThreadPoolExecutor$Worker.run(ThreadPoolExecutor.java:615)
at java.lang.Thread.run(Thread.java:745)
[13:24:01] Topology snapshot [ver=29, servers=2, clients=1, CPUs=16, heap=3.0GB]
16/11/23 13:24:02 ERROR TaskSchedulerImpl: Lost executor 3 on xxx001: Remote
RPC client disassociated. Likely due to containers exceeding thresholds, or
network issues. Check driver logs for WARN messages.
16/11/23 13:24:05 ERROR TaskSetManager: Task 0 in stage 0.0 failed 4 times;
aborting job
org.apache.spark.SparkException: Job aborted due to stage failure: Task 0 in
stage 0.0 failed 4 times, most recent failure: Lost task 0.3 in stage 0.0 (TID
3, xxx008.xxx.com): java.lang.IllegalStateException: Did not find registered
driver with class oracle.jdbc.OracleDriver
at
org.apache.spark.sql.execution.datasources.jdbc.JdbcUtils$$anonfun$createConnectionFactory$2$$anonfun$3.apply(JdbcUtils.scala:58)
at
org.apache.spark.sql.execution.datasources.jdbc.JdbcUtils$$anonfun$createConnectionFactory$2$$anonfun$3.apply(JdbcUtils.scala:58)
at scala.Option.getOrElse(Option.scala:120)
at
org.apache.spark.sql.execution.datasources.jdbc.JdbcUtils$$anonfun$createConnectionFactory$2.apply(JdbcUtils.scala:57)
at
org.apache.spark.sql.execution.datasources.jdbc.JdbcUtils$$anonfun$createConnectionFactory$2.apply(JdbcUtils.scala:52)
at
org.apache.spark.sql.execution.datasources.jdbc.JDBCRDD$$anon$1.<init>(JDBCRDD.scala:347)
at
org.apache.spark.sql.execution.datasources.jdbc.JDBCRDD.compute(JDBCRDD.scala:339)
at org.apache.spark.rdd.RDD.computeOrReadCheckpoint(RDD.scala:306)
at org.apache.spark.rdd.RDD.iterator(RDD.scala:270)
at org.apache.spark.rdd.MapPartitionsRDD.compute(MapPartitionsRDD.scala:38)
at org.apache.spark.rdd.RDD.computeOrReadCheckpoint(RDD.scala:306)
at org.apache.spark.rdd.RDD.iterator(RDD.scala:270)
at org.apache.spark.scheduler.ResultTask.runTask(ResultTask.scala:66)
at org.apache.spark.scheduler.Task.run(Task.scala:89)
at org.apache.spark.executor.Executor$TaskRunner.run(Executor.scala:214)
at
java.util.concurrent.ThreadPoolExecutor.runWorker(ThreadPoolExecutor.java:1145)
at
java.util.concurrent.ThreadPoolExecutor$Worker.run(ThreadPoolExecutor.java:615)
at java.lang.Thread.run(Thread.java:745)
Driver stacktrace:
at
org.apache.spark.scheduler.DAGScheduler.org$apache$spark$scheduler$DAGScheduler$$failJobAndIndependentStages(DAGScheduler.scala:1431)
at
org.apache.spark.scheduler.DAGScheduler$$anonfun$abortStage$1.apply(DAGScheduler.scala:1419)
at
org.apache.spark.scheduler.DAGScheduler$$anonfun$abortStage$1.apply(DAGScheduler.scala:1418)
at
scala.collection.mutable.ResizableArray$class.foreach(ResizableArray.scala:59)
at scala.collection.mutable.ArrayBuffer.foreach(ArrayBuffer.scala:47)
at org.apache.spark.scheduler.DAGScheduler.abortStage(DAGScheduler.scala:1418)
at
org.apache.spark.scheduler.DAGScheduler$$anonfun$handleTaskSetFailed$1.apply(DAGScheduler.scala:799)
at
org.apache.spark.scheduler.DAGScheduler$$anonfun$handleTaskSetFailed$1.apply(DAGScheduler.scala:799)
at scala.Option.foreach(Option.scala:236)
at
org.apache.spark.scheduler.DAGScheduler.handleTaskSetFailed(DAGScheduler.scala:799)
at
org.apache.spark.scheduler.DAGSchedulerEventProcessLoop.doOnReceive(DAGScheduler.scala:1640)
at
org.apache.spark.scheduler.DAGSchedulerEventProcessLoop.onReceive(DAGScheduler.scala:1599)
at
org.apache.spark.scheduler.DAGSchedulerEventProcessLoop.onReceive(DAGScheduler.scala:1588)
at org.apache.spark.util.EventLoop$$anon$1.run(EventLoop.scala:48)
at org.apache.spark.scheduler.DAGScheduler.runJob(DAGScheduler.scala:620)
at org.apache.spark.SparkContext.runJob(SparkContext.scala:1832)
at org.apache.spark.SparkContext.runJob(SparkContext.scala:1845)
at org.apache.spark.SparkContext.runJob(SparkContext.scala:1858)
at org.apache.spark.SparkContext.runJob(SparkContext.scala:1929)
at org.apache.spark.rdd.RDD$$anonfun$foreachPartition$1.apply(RDD.scala:920)
at org.apache.spark.rdd.RDD$$anonfun$foreachPartition$1.apply(RDD.scala:918)
at
org.apache.spark.rdd.RDDOperationScope$.withScope(RDDOperationScope.scala:150)
at
org.apache.spark.rdd.RDDOperationScope$.withScope(RDDOperationScope.scala:111)
at org.apache.spark.rdd.RDD.withScope(RDD.scala:316)
at org.apache.spark.rdd.RDD.foreachPartition(RDD.scala:918)
at org.apache.ignite.spark.IgniteRDD.saveValues(IgniteRDD.scala:138)
at
$iwC$$iwC$$iwC$$iwC$$iwC$$iwC$$iwC$$iwC$$iwC$$iwC$$iwC$$iwC.<init>(<console>:48)
at $iwC$$iwC$$iwC$$iwC$$iwC$$iwC$$iwC$$iwC$$iwC$$iwC$$iwC.<init>(<console>:53)
at $iwC$$iwC$$iwC$$iwC$$iwC$$iwC$$iwC$$iwC$$iwC$$iwC.<init>(<console>:55)
at $iwC$$iwC$$iwC$$iwC$$iwC$$iwC$$iwC$$iwC$$iwC.<init>(<console>:57)
at $iwC$$iwC$$iwC$$iwC$$iwC$$iwC$$iwC$$iwC.<init>(<console>:59)
at $iwC$$iwC$$iwC$$iwC$$iwC$$iwC$$iwC.<init>(<console>:61)
at $iwC$$iwC$$iwC$$iwC$$iwC$$iwC.<init>(<console>:63)
at $iwC$$iwC$$iwC$$iwC$$iwC.<init>(<console>:65)
at $iwC$$iwC$$iwC$$iwC.<init>(<console>:67)
at $iwC$$iwC$$iwC.<init>(<console>:69)
at $iwC$$iwC.<init>(<console>:71)
at $iwC.<init>(<console>:73)
at <init>(<console>:75)
at .<init>(<console>:79)
at .<clinit>(<console>)
at .<init>(<console>:7)
at .<clinit>(<console>)
at $print(<console>)
at sun.reflect.NativeMethodAccessorImpl.invoke0(Native Method)
at sun.reflect.NativeMethodAccessorImpl.invoke(NativeMethodAccessorImpl.java:57)
at
sun.reflect.DelegatingMethodAccessorImpl.invoke(DelegatingMethodAccessorImpl.java:43)
at java.lang.reflect.Method.invoke(Method.java:606)
at org.apache.spark.repl.SparkIMain$ReadEvalPrint.call(SparkIMain.scala:1065)
at org.apache.spark.repl.SparkIMain$Request.loadAndRun(SparkIMain.scala:1346)
at org.apache.spark.repl.SparkIMain.loadAndRunReq$1(SparkIMain.scala:840)
at org.apache.spark.repl.SparkIMain.interpret(SparkIMain.scala:871)
at org.apache.spark.repl.SparkIMain.interpret(SparkIMain.scala:819)
at org.apache.spark.repl.SparkILoop.reallyInterpret$1(SparkILoop.scala:857)
at org.apache.spark.repl.SparkILoop.interpretStartingWith(SparkILoop.scala:902)
at org.apache.spark.repl.SparkILoop.command(SparkILoop.scala:814)
at org.apache.spark.repl.SparkILoop.processLine$1(SparkILoop.scala:657)
at org.apache.spark.repl.SparkILoop.innerLoop$1(SparkILoop.scala:665)
at
org.apache.spark.repl.SparkILoop.org$apache$spark$repl$SparkILoop$$loop(SparkILoop.scala:670)
at
org.apache.spark.repl.SparkILoop$$anonfun$org$apache$spark$repl$SparkILoop$$process$1.apply$mcZ$sp(SparkILoop.scala:997)
at
org.apache.spark.repl.SparkILoop$$anonfun$org$apache$spark$repl$SparkILoop$$process$1.apply(SparkILoop.scala:945)
at
org.apache.spark.repl.SparkILoop$$anonfun$org$apache$spark$repl$SparkILoop$$process$1.apply(SparkILoop.scala:945)
at
scala.tools.nsc.util.ScalaClassLoader$.savingContextLoader(ScalaClassLoader.scala:135)
at
org.apache.spark.repl.SparkILoop.org$apache$spark$repl$SparkILoop$$process(SparkILoop.scala:945)
at org.apache.spark.repl.SparkILoop.process(SparkILoop.scala:1059)
at org.apache.spark.repl.Main$.main(Main.scala:31)
at org.apache.spark.repl.Main.main(Main.scala)
at sun.reflect.NativeMethodAccessorImpl.invoke0(Native Method)
at sun.reflect.NativeMethodAccessorImpl.invoke(NativeMethodAccessorImpl.java:57)
at
sun.reflect.DelegatingMethodAccessorImpl.invoke(DelegatingMethodAccessorImpl.java:43)
at java.lang.reflect.Method.invoke(Method.java:606)
at
org.apache.spark.deploy.SparkSubmit$.org$apache$spark$deploy$SparkSubmit$$runMain(SparkSubmit.scala:731)
at org.apache.spark.deploy.SparkSubmit$.doRunMain$1(SparkSubmit.scala:181)
at org.apache.spark.deploy.SparkSubmit$.submit(SparkSubmit.scala:206)
at org.apache.spark.deploy.SparkSubmit$.main(SparkSubmit.scala:121)
at org.apache.spark.deploy.SparkSubmit.main(SparkSubmit.scala)
Caused by: java.lang.IllegalStateException: Did not find registered driver with
class oracle.jdbc.OracleDriver
at
org.apache.spark.sql.execution.datasources.jdbc.JdbcUtils$$anonfun$createConnectionFactory$2$$anonfun$3.apply(JdbcUtils.scala:58)
at
org.apache.spark.sql.execution.datasources.jdbc.JdbcUtils$$anonfun$createConnectionFactory$2$$anonfun$3.apply(JdbcUtils.scala:58)
at scala.Option.getOrElse(Option.scala:120)
at
org.apache.spark.sql.execution.datasources.jdbc.JdbcUtils$$anonfun$createConnectionFactory$2.apply(JdbcUtils.scala:57)
at
org.apache.spark.sql.execution.datasources.jdbc.JdbcUtils$$anonfun$createConnectionFactory$2.apply(JdbcUtils.scala:52)
at
org.apache.spark.sql.execution.datasources.jdbc.JDBCRDD$$anon$1.<init>(JDBCRDD.scala:347)
at
org.apache.spark.sql.execution.datasources.jdbc.JDBCRDD.compute(JDBCRDD.scala:339)
at org.apache.spark.rdd.RDD.computeOrReadCheckpoint(RDD.scala:306)
at org.apache.spark.rdd.RDD.iterator(RDD.scala:270)
at org.apache.spark.rdd.MapPartitionsRDD.compute(MapPartitionsRDD.scala:38)
at org.apache.spark.rdd.RDD.computeOrReadCheckpoint(RDD.scala:306)
at org.apache.spark.rdd.RDD.iterator(RDD.scala:270)
at org.apache.spark.scheduler.ResultTask.runTask(ResultTask.scala:66)
at org.apache.spark.scheduler.Task.run(Task.scala:89)
at org.apache.spark.executor.Executor$TaskRunner.run(Executor.scala:214)
at
java.util.concurrent.ThreadPoolExecutor.runWorker(ThreadPoolExecutor.java:1145)
at
java.util.concurrent.ThreadPoolExecutor$Worker.run(ThreadPoolExecutor.java:615)
at java.lang.Thread.run(Thread.java:745)
Thanks
Vidhya
