[
  {
    "Name": "flowlogs-aggregate",
    "Type": "STREAMING",
    "ActionOnFailure": "CANCEL_AND_WAIT",
    "Args": [
      "-files", "s3://aws-big-data-blog/vpc-toptalkers/flowlogs-counter.py",
      "-mapper", "flowlogs-counter.py",
      "-reducer", "aggregate",
      "-input", "s3://<bucket>/flowlogs",
      "-output","s3://<bucket>/aggregate"
    ]
  },
  {
    "Name" : "flowlogs-sort",
    "Type": "STREAMING",
    "ActionOnFailure": "CONTINUE",
    "Args" : [
      "-D", "mapreduce.job.reduces=1",
      "-D", "mapreduce.output.fileoutputformat.compress=true",
      "-D", "mapreduce.output.fileoutputformat.compress.codec=org.apache.hadoop.io.compress.GzipCodec",
      "-D", "mapreduce.job.output.key.comparator.class=org.apache.hadoop.mapreduce.lib.partition.KeyFieldBasedComparator",
      "-D", "stream.num.map.output.key.fields=2",
      "-D", "mapreduce.partition.keycomparator.options=-k2,2nr",
      "-files", "s3://aws-big-data-blog/vpc-toptalkers/portfilter.awk",
      "-mapper", "portfilter.awk",
      "-reducer", "cat",
      "-input", "s3://<bucket>/aggregate",
      "-output", "s3://<bucket>/toptalker"
    ]
  }
]