-
- Downloads
[SPARK-12388] change default compression to lz4
According the benchmark [1], LZ4-java could be 80% (or 30%) faster than Snappy. After changing the compressor to LZ4, I saw 20% improvement on end-to-end time for a TPCDS query (Q4). [1] https://github.com/ning/jvm-compressor-benchmark/wiki cc rxin Author: Davies Liu <davies@databricks.com> Closes #10342 from davies/lz4.
Showing
- .rat-excludes 1 addition, 0 deletions.rat-excludes
- core/src/main/scala/org/apache/spark/io/CompressionCodec.scala 6 additions, 6 deletions...src/main/scala/org/apache/spark/io/CompressionCodec.scala
- core/src/main/scala/org/apache/spark/io/LZ4BlockInputStream.java 263 additions, 0 deletions...c/main/scala/org/apache/spark/io/LZ4BlockInputStream.java
- core/src/test/scala/org/apache/spark/io/CompressionCodecSuite.scala 3 additions, 5 deletions...est/scala/org/apache/spark/io/CompressionCodecSuite.scala
- docs/configuration.md 1 addition, 1 deletiondocs/configuration.md
- sql/core/src/test/scala/org/apache/spark/sql/execution/ExchangeCoordinatorSuite.scala 2 additions, 2 deletions...apache/spark/sql/execution/ExchangeCoordinatorSuite.scala
Loading
Please register or sign in to comment