Skip to content
New issue

Have a question about this project? Sign up for a free GitHub account to open an issue and contact its maintainers and the community.

Sign up for GitHub

By clicking “Sign up for GitHub”, you agree to our terms of service and privacy statement. We’ll occasionally send you account related emails.

Already on GitHub? Sign in to your account

Jump to bottom

[SPARK-3294][SQL] Eliminates boxing costs from in-memory columnar storage #2327

Closed
wants to merge 13 commits into from
Closed

[SPARK-3294][SQL] Eliminates boxing costs from in-memory columnar storage #2327

wants to merge 13 commits into from

Commits on Sep 10, 2014

  1. Made some in-memory columnar storage interfaces row-based

    @liancheng
    liancheng committed Sep 10, 2014
    Configuration menu
    Copy the full SHA
    b70d519 View commit details
    Browse the repository at this point in the history

  2. Removes boxing cost in IntDelta and LongDelta by providing specialize… 

    …d implementations
    @liancheng
    liancheng committed Sep 10, 2014
    Configuration menu
    Copy the full SHA
    8216936 View commit details
    Browse the repository at this point in the history

  3. Makes ColumnAccessor.extractSingle row based

    @liancheng
    liancheng committed Sep 10, 2014
    Configuration menu
    Copy the full SHA
    edac3cd View commit details
    Browse the repository at this point in the history

  4. Made compression decoder row based

    @liancheng
    liancheng committed Sep 10, 2014
    Configuration menu
    Copy the full SHA
    456c366 View commit details
    Browse the repository at this point in the history

  5. Added row based ColumnType.append/extract

    @liancheng
    liancheng committed Sep 10, 2014
    Configuration menu
    Copy the full SHA
    9cf30b0 View commit details
    Browse the repository at this point in the history

  6. Use SpecificMutableRow in InMemoryColumnarTableScan to avoid boxing

    @liancheng
    liancheng committed Sep 10, 2014
    Configuration menu
    Copy the full SHA
    f2a7890 View commit details
    Browse the repository at this point in the history

  7. Lowers log level of compression scheme details

    @liancheng
    liancheng committed Sep 10, 2014
    Configuration menu
    Copy the full SHA
    5b39cb9 View commit details
    Browse the repository at this point in the history

  8. Minor changes to eliminate row object creation

    @liancheng
    liancheng committed Sep 10, 2014
    Configuration menu
    Copy the full SHA
    3dc1f94 View commit details
    Browse the repository at this point in the history

  9. Optimizes hive.TableReader by by providing specific Writable unwrappe… 

    …rs a head of time
    @liancheng
    liancheng committed Sep 10, 2014
    Configuration menu
    Copy the full SHA
    97bbc4e View commit details
    Browse the repository at this point in the history

  10. Bug fix: TableReader.fillObject uses wrong ordinals

    @liancheng
    liancheng committed Sep 10, 2014
    Configuration menu
    Copy the full SHA
    489f97b View commit details
    Browse the repository at this point in the history

  11. Only checks for partition batch pruning flag once

    @liancheng
    liancheng committed Sep 10, 2014
    Configuration menu
    Copy the full SHA
    8b8552b View commit details
    Browse the repository at this point in the history

Commits on Sep 11, 2014

  1. Bug fix: should call setNullAt when field value is null to avoid NPE

    @liancheng
    liancheng committed Sep 11, 2014
    Configuration menu
    Copy the full SHA
    e5d2cf2 View commit details
    Browse the repository at this point in the history

Commits on Sep 13, 2014

  1. Addressing comments

    @liancheng
    liancheng committed Sep 13, 2014
    Configuration menu
    Copy the full SHA
    4419fe4 View commit details
    Browse the repository at this point in the history