Uploaded image for project: 'Spark'
  1. Spark
  2. SPARK-14482

Change default compression codec for Parquet from gzip to snappy

    XMLWordPrintableJSON

Details

    • Improvement
    • Status: Resolved
    • Major
    • Resolution: Fixed
    • None
    • 2.0.0
    • SQL
    • None

    Description

      Based on our tests, gzip decompression is very slow (< 100MB/s), making queries decompression bound. Snappy can decompress at ~ 500MB/s on a single core.

      Attachments

        Activity

          People

            rxin Reynold Xin
            rxin Reynold Xin
            Votes:
            0 Vote for this issue
            Watchers:
            3 Start watching this issue

            Dates

              Created:
              Updated:
              Resolved: