Hi
I use the ElasticSearch package for Spark and very often it times out reading
data from ES into an RDD.
How can I keep the connection alive (why doesn't it? Bug?)
Here's the exception I get:
org.elasticsearch.hadoop.serialization.EsHadoopSerializationException:
java.net.SocketTimeoutException: Read timed out
at
org.elasticsearch.hadoop.serialization.json.JacksonJsonParser.nextToken(JacksonJsonParser.java:86)
~[elasticsearch-hadoop-2.1.0.Beta3.jar:2.1.0.Beta3]
at
org.elasticsearch.hadoop.serialization.ParsingUtils.doSeekToken(ParsingUtils.java:70)
~[elasticsearch-hadoop-2.1.0.Beta3.jar:2.1.0.Beta3]
at
org.elasticsearch.hadoop.serialization.ParsingUtils.seek(ParsingUtils.java:58)
~[elasticsearch-hadoop-2.1.0.Beta3.jar:2.1.0.Beta3]
at
org.elasticsearch.hadoop.serialization.ScrollReader.readHit(ScrollReader.java:149)
~[elasticsearch-hadoop-2.1.0.Beta3.jar:2.1.0.Beta3]
at
org.elasticsearch.hadoop.serialization.ScrollReader.read(ScrollReader.java:102)
~[elasticsearch-hadoop-2.1.0.Beta3.jar:2.1.0.Beta3]
at
org.elasticsearch.hadoop.serialization.ScrollReader.read(ScrollReader.java:81)
~[elasticsearch-hadoop-2.1.0.Beta3.jar:2.1.0.Beta3]
at
org.elasticsearch.hadoop.rest.RestRepository.scroll(RestRepository.java:314)
~[elasticsearch-hadoop-2.1.0.Beta3.jar:2.1.0.Beta3]
at
org.elasticsearch.hadoop.rest.ScrollQuery.hasNext(ScrollQuery.java:76)
~[elasticsearch-hadoop-2.1.0.Beta3.jar:2.1.0.Beta3]
at
org.elasticsearch.spark.rdd.AbstractEsRDDIterator.hasNext(AbstractEsRDDIterator.scala:46)
~[elasticsearch-hadoop-2.1.0.Beta3.jar:2.1.0.Beta3]
at
scala.collection.Iterator$$anon$11.hasNext(Iterator.scala:327)
~[scala-library.jar:na]
at
scala.collection.Iterator$$anon$13.hasNext(Iterator.scala:371)
~[scala-library.jar:na]
at
scala.collection.Iterator$$anon$14.hasNext(Iterator.scala:388)
~[scala-library.jar:na]
at
scala.collection.Iterator$$anon$11.hasNext(Iterator.scala:327)
~[scala-library.jar:na]
at scala.collection.Iterator$class.foreach(Iterator.scala:727)
~[scala-library.jar:na]
at
scala.collection.AbstractIterator.foreach(Iterator.scala:1157)
~[scala-library.jar:na]
at
org.apache.spark.shuffle.hash.HashShuffleWriter.write(HashShuffleWriter.scala:65)
~[spark-core_2.10-1.1.0.jar:1.1.0]
at
org.apache.spark.scheduler.ShuffleMapTask.runTask(ShuffleMapTask.scala:68)
~[spark-core_2.10-1.1.0.jar:1.1.0]
at
org.apache.spark.scheduler.ShuffleMapTask.runTask(ShuffleMapTask.scala:41)
~[spark-core_2.10-1.1.0.jar:1.1.0]
at org.apache.spark.scheduler.Task.run(Task.scala:54)
~[spark-core_2.10-1.1.0.jar:1.1.0]
at
org.apache.spark.executor.Executor$TaskRunner.run(Executor.scala:177)
~[spark-core_2.10-1.1.0.jar:1.1.0]
at
java.util.concurrent.ThreadPoolExecutor.runWorker(ThreadPoolExecutor.java:1145)
[na:1.7.0_75]
at
java.util.concurrent.ThreadPoolExecutor$Worker.run(ThreadPoolExecutor.java:615)
[na:1.7.0_75]
at java.lang.Thread.run(Thread.java:745) [na:1.7.0_75]
Caused by: java.net.SocketTimeoutException: Read timed out
at java.net.SocketInputStream.socketRead0(Native Method)
~[na:1.7.0_75]
at java.net.SocketInputStream.read(SocketInputStream.java:152)
~[na:1.7.0_75]
at java.net.SocketInputStream.read(SocketInputStream.java:122)
~[na:1.7.0_75]
at
java.io.BufferedInputStream.read1(BufferedInputStream.java:273) ~[na:1.7.0_75]
at
java.io.BufferedInputStream.read(BufferedInputStream.java:334) ~[na:1.7.0_75]
at
org.apache.commons.httpclient.WireLogInputStream.read(WireLogInputStream.java:69)
~[commons-httpclient-3.1.jar:na]
at
org.apache.commons.httpclient.ContentLengthInputStream.read(ContentLengthInputStream.java:170)
~[commons-httpclient-3.1.jar:na]
at java.io.FilterInputStream.read(FilterInputStream.java:133)
~[na:1.7.0_75]
at
org.apache.commons.httpclient.AutoCloseInputStream.read(AutoCloseInputStream.java:108)
~[commons-httpclient-3.1.jar:na]
at
org.elasticsearch.hadoop.rest.DelegatingInputStream.read(DelegatingInputStream.java:57)
~[elasticsearch-hadoop-2.1.0.Beta3.jar:2.1.0.Beta3]
at
org.codehaus.jackson.impl.Utf8StreamParser.loadMore(Utf8StreamParser.java:172)
~[jackson-core-asl-1.9.11.jar:1.9.11]
at
org.codehaus.jackson.impl.Utf8StreamParser.parseEscapedFieldName(Utf8StreamParser.java:1502)
~[jackson-core-asl-1.9.11.jar:1.9.11]
at
org.codehaus.jackson.impl.Utf8StreamParser.slowParseFieldName(Utf8StreamParser.java:1404)
~[jackson-core-asl-1.9.11.jar:1.9.11]
at
org.codehaus.jackson.impl.Utf8StreamParser._parseFieldName(Utf8StreamParser.java:1231)
~[jackson-core-asl-1.9.11.jar:1.9.11]
at
org.codehaus.jackson.impl.Utf8StreamParser.nextToken(Utf8StreamParser.java:495)
~[jackson-core-asl-1.9.11.jar:1.9.11]
at
org.elasticsearch.hadoop.serialization.json.JacksonJsonParser.nextToken(JacksonJsonParser.java:84)
~[elasticsearch-hadoop-2.1.0.Beta3.jar:2.1.0.Beta3]
... 22 common frames omitted
