Are you sure it's memory related? What is the disk utilization and IO performance on the workers? The error you posted looks to be related to shuffle trying to obtain block data from another worker node and failing to do so in reasonable amount of time. It may still be memory related, but I'm not sure that other resources are ruled out yet. 

On Tue, Jun 2, 2015 at 5:10 AM, octavian.ganea <> wrote:
I was tried using reduceByKey, without success.

I also tried this: rdd.persist(MEMORY_AND_DISK).flatMap(...).reduceByKey .
However, I got the same error as before, namely the error described here:

My task is to count the frequencies of pairs of words that occur in a set of
documents at least 5 times. I know that this final output is sparse and
should comfortably fit in memory. However, the intermediate pairs that are
spilled by flatMap might need to be stored on the disk, but I don't
understand why the persist option does not work and my job fails.

My code:

     .flatMap(x => outputPairsOfWords(x)) // outputs pairs of type
((word1,word2) , 1)
    .reduceByKey((a,b) => (a + b).toShort)
    .filter({case((x,y),count) => count >= 5})

My cluster has 8 nodes, each with 129 GB of RAM and 16 cores per node. One
node I keep for the master, 7 nodes for the workers.

my conf:

    conf.set("spark.cores.max", "128")
    conf.set("spark.akka.frameSize", "1024")
    conf.set("spark.executor.memory", "115g")
    conf.set("spark.shuffle.file.buffer.kb", "1000")

 ulimit -n 200000
 SPARK_JAVA_OPTS="-Xss1g -Xmx129g -d64 -XX:-UseGCOverheadLimit

spark version: 1.1.1

Thank you a lot for your help!

View this message in context:
Sent from the Apache Spark User List mailing list archive at

To unsubscribe, e-mail:
For additional commands, e-mail: