Details

    • Type: Improvement Improvement
    • Status: Resolved
    • Priority: Major Major
    • Resolution: Fixed
    • Affects Version/s: None
    • Fix Version/s: 3.0.0
    • Component/s: task
    • Labels:
      None
    • Environment:

      x86-64 Linux/Unix

    • Hadoop Flags:
      Reviewed
    • Release Note:
      Hide
      Adds a native implementation of the map output collector. The native library will build automatically with -Pnative. Users may choose the new collector on a job-by-job basis by setting mapreduce.job.map.output.collector.class=org.apache.hadoop.mapred.
      nativetask.NativeMapOutputCollectorDelegator in their job configuration. For shuffle-intensive jobs this may provide speed-ups of 30% or more.
      Show
      Adds a native implementation of the map output collector. The native library will build automatically with -Pnative. Users may choose the new collector on a job-by-job basis by setting mapreduce.job.map.output.collector.class=org.apache.hadoop.mapred. nativetask.NativeMapOutputCollectorDelegator in their job configuration. For shuffle-intensive jobs this may provide speed-ups of 30% or more.
    • Tags:
      optimization task

      Description

      I'm recently working on native optimization for MapTask based on JNI.

      The basic idea is that, add a NativeMapOutputCollector to handle k/v pairs emitted by mapper, therefore sort, spill, IFile serialization can all be done in native code, preliminary test(on Xeon E5410, jdk6u24) showed promising results:

      1. Sort is about 3x-10x as fast as java(only binary string compare is supported)

      2. IFile serialization speed is about 3x of java, about 500MB/s, if hardware CRC32C is used, things can get much faster(1G/

      3. Merge code is not completed yet, so the test use enough io.sort.mb to prevent mid-spill

      This leads to a total speed up of 2x~3x for the whole MapTask, if IdentityMapper(mapper does nothing) is used

      There are limitations of course, currently only Text and BytesWritable is supported, and I have not think through many things right now, such as how to support map side combine. I had some discussion with somebody familiar with hive, it seems that these limitations won't be much problem for Hive to benefit from those optimizations, at least. Advices or discussions about improving compatibility are most welcome

      Currently NativeMapOutputCollector has a static method called canEnable(), which checks if key/value type, comparator type, combiner are all compatible, then MapTask can choose to enable NativeMapOutputCollector.

      This is only a preliminary test, more work need to be done. I expect better final results, and I believe similar optimization can be adopt to reduce task and shuffle too.

      1. mr-2841-merge-4.patch
        2.68 MB
        Sean Zhong
      2. mr-2841-merge-3.patch
        2.73 MB
        Sean Zhong
      3. mr-2841-merge-2.txt
        2.70 MB
        Sean Zhong
      4. mr-2841-merge.txt
        2.72 MB
        Todd Lipcon
      5. MR-2841benchmarks.pdf
        213 kB
        Todd Lipcon
      6. micro-benchmark.txt
        13 kB
        Todd Lipcon
      7. MAPREDUCE-2841.v2.patch
        190 kB
        Binglin Chang
      8. MAPREDUCE-2841.v1.patch
        180 kB
        Binglin Chang
      9. hadoop-3.0-mapreduce-2841-2014-7-17.patch
        3.50 MB
        Sean Zhong
      10. fb-shuffle.patch
        76 kB
        Todd Lipcon
      11. dualpivotv20-0.patch
        4 kB
        Chris Douglas
      12. dualpivot-0.patch
        5 kB
        Chris Douglas
      13. DESIGN.html
        42 kB
        Binglin Chang

        Issue Links

          Activity

          No work has yet been logged on this issue.

            People

            • Assignee:
              Sean Zhong
              Reporter:
              Binglin Chang
            • Votes:
              4 Vote for this issue
              Watchers:
              70 Start watching this issue

              Dates

              • Created:
                Updated:
                Resolved:

                Development