Skip to content

Commit

Permalink
Added docs for scaling task writers
Browse files Browse the repository at this point in the history
  • Loading branch information
gaurav8297 authored and sopel39 committed Aug 30, 2022
1 parent b37fdc8 commit 75ca607
Show file tree
Hide file tree
Showing 2 changed files with 42 additions and 2 deletions.
10 changes: 10 additions & 0 deletions docs/src/main/sphinx/admin/properties-task.rst
Original file line number Diff line number Diff line change
Expand Up @@ -111,6 +111,16 @@ resource utilization, but uses additional memory.
The minimum number of drivers guaranteed to run concurrently for a single task given
the task has remaining splits to process.

``task.scale-writers.enabled``
^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^

* **Description:** :ref:`prop-task-scale-writers`

``task.scale-writers.max-writer-count``
^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^

* **Description:** :ref:`prop-task-scale-writers-max-writer-count`

``task.writer-count``
^^^^^^^^^^^^^^^^^^^^^

Expand Down
34 changes: 32 additions & 2 deletions docs/src/main/sphinx/admin/properties-writer-scaling.rst
Original file line number Diff line number Diff line change
Expand Up @@ -19,8 +19,38 @@ the needs of the query.
* **Type:** :ref:`prop-type-boolean`
* **Default value:** ``true``

Enable writer scaling. This can be specified on a per-query basis
using the ``scale_writers`` session property.
Enable writer scaling by dynamically increasing the number of writer tasks on
the cluster. This can be specified on a per-query basis using the ``scale_writers``
session property.

.. _prop-task-scale-writers:

``task.scale-writers.enabled``
^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^

* **Type:** :ref:`prop-type-boolean`
* **Default value:** ``true``

Enable scaling the number of concurrent writers within a task. The maximum writer
count per task for scaling is ``task.scale-writers.max-writer-count``. Additional
writers are added only when the average amount of physical data written per writer
is above the minimum threshold of ``writer-min-size`` and query is bottlenecked on
writing. This can be specified on a per-query basis using the ``task_scale_writers``
session property.

.. _prop-task-scale-writers-max-writer-count:

``task.scale-writers.max-writer-count``
^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^

* **Type:** :ref:`prop-type-integer`
* **Restrictions:** Must be a power of two
* **Default value:** ``8``

Maximum number of concurrent writers per task upto which the task can be scaled when
``task.scale-writers.enabled`` is set. Increasing this value may improve the
performance of writes when the query is bottlenecked on writing. Setting this too high
may cause the cluster to become overloaded due to excessive resource utilization.

``writer-min-size``
^^^^^^^^^^^^^^^^^^^
Expand Down

0 comments on commit 75ca607

Please sign in to comment.