Я работаю в локальном режиме просто отлично. Когда я бегу в режиме ПРЯЖИ я получаю следующее сообщение об ошибке:Spark Runs in Local, но не в YARN
Я получаю эту ошибку:
File "/hdfs15/yarn/nm/usercache/jvy234/filecache/11/spark-assembly-1.1.0-cdh5.2.1-hadoop2.5.0-cdh5.2.1.jar/pyspark/worker.py", line 79, in main
serializer.dump_stream(func(split_index, iterator), outfile)
File "/hdfs15/yarn/nm/usercache/jvy234/filecache/11/spark-assembly-1.1.0-cdh5.2.1-hadoop2.5.0-cdh5.2.1.jar/pyspark/serializers.py", line 196, in dump_stream
self.serializer.dump_stream(self._batched(iterator), stream)
File "/hdfs15/yarn/nm/usercache/jvy234/filecache/11/spark-assembly-1.1.0-cdh5.2.1-hadoop2.5.0-cdh5.2.1.jar/pyspark/serializers.py", line 127, in dump_stream
for obj in iterator:
File "/hdfs15/yarn/nm/usercache/jvy234/filecache/11/spark-assembly-1.1.0-cdh5.2.1-hadoop2.5.0-cdh5.2.1.jar/pyspark/serializers.py", line 185, in _batched
for item in iterator:
File "/home/jvy234/globalHawk.py", line 84, in <lambda>
TypeError: 'bool' object is not callable
org.apache.spark.api.python.PythonRDD$$anon$1.read(PythonRDD.scala:124)
org.apache.spark.api.python.PythonRDD$$anon$1.<init>(PythonRDD.scala:154)
org.apache.spark.api.python.PythonRDD.compute(PythonRDD.scala:87)
org.apache.spark.rdd.RDD.computeOrReadCheckpoint(RDD.scala:262)
org.apache.spark.CacheManager.getOrCompute(CacheManager.scala:61)
org.apache.spark.rdd.RDD.iterator(RDD.scala:227)
org.apache.spark.api.python.PythonRDD$WriterThread$$anonfun$run$1.apply$mcV$sp(PythonRDD.scala:209)
org.apache.spark.api.python.PythonRDD$WriterThread$$anonfun$run$1.apply(PythonRDD.scala:184)
org.apache.spark.api.python.PythonRDD$WriterThread$$anonfun$run$1.apply(PythonRDD.scala:184)
org.apache.spark.util.Utils$.logUncaughtExceptions(Utils.scala:1319)
org.apache.spark.api.python.PythonRDD$WriterThread.run(PythonRDD.scala:183)
Line 84 в моих сценариях:
dataSplit = dataFile.map(lambda line: line.split(deli))
запускать локально:
spark-submit --master local globalHawk.py -i 20140817_011500_offer_init.dat -s kh_offers_schema4.txt4 -o txt.txt -d "|"
To Run Yarn-Client:
spark-submit --master yarn-client globalHawk.py -i 20140817_011500_offer_init.dat -s kh_offers_schema4.txt4 -o txt.txt -d "|"
Update работает с некоторыми людьми: https: // вопросами. apache.org/jira/browse/SPARK-6216 – theMadKing