Document parallelism and thread scheduling in the architecture guide #8986
Conversation
This file contains bidirectional Unicode text that may be interpreted or compiled differently than what appears below. To review, open the file in an editor that reveals hidden Unicode characters.
Learn more about bidirectional Unicode characters
github-actions
bot
added
core
tustvold
approved these changes
Jan 25, 2024
| @@ -364,8 +368,26 @@ | |||
| //! | |||
| //! [`RepartitionExec`]: https://docs.rs/datafusion/latest/datafusion/physical_plan/repartition/struct.RepartitionExec.html | |||
| //! [Volcano style]: https://w6113.github.io/files/papers/volcanoparallelism-89.pdf | |||
| //! [Morsel-Driven Parallelism]: https://db.in.tum.de/~leis/papers/morsels.pdf | |||
| //! [DataFusion paper submitted SIGMOD]: https://github.com/apache/arrow-datafusion/files/13874720/DataFusion_Query_Engine___SIGMOD_2024.pdf | |||
There was a problem hiding this comment.
Suggested change
| //! [DataFusion paper submitted SIGMOD]: https://github.com/apache/arrow-datafusion/files/13874720/DataFusion_Query_Engine___SIGMOD_2024.pdf | |
| //! [DataFusion paper submitted to SIGMOD]: https://github.com/apache/arrow-datafusion/files/13874720/DataFusion_Query_Engine___SIGMOD_2024.pdf |
Co-authored-by: Raphael Taylor-Davies <[email protected]>
alamb
commented
Jan 25, 2024
| //! DataFusion incrementally computes output from a [`SendableRecordBatchStream`] | ||
| //! with `target_partitions` threads. Parallelism is implementing using multiple | ||
| //! [Tokio] [`task`]s, which are executed by threads managed by a tokio Runtime. | ||
| //! While tokio is most commonly used |
There was a problem hiding this comment.
I should probably also point out that this phrasing came from the SIGMOD paper and I think at least @yjshen and @ozankabak had a part in authoring it
alamb
changed the title
Sign up for free
to join this conversation on GitHub.
Already have an account?
Sign in to comment
Add this suggestion to a batch that can be applied as a single commit.
This suggestion is invalid because no changes were made to the code.
Suggestions cannot be applied while the pull request is closed.
Suggestions cannot be applied while viewing a subset of changes.
Only one suggestion per line can be applied in a batch.
Add this suggestion to a batch that can be applied as a single commit.
Applying suggestions on deleted lines is not supported.
You must change the existing code in this line in order to create a valid suggestion.
Outdated suggestions cannot be applied.
This suggestion has been applied or marked resolved.
Suggestions cannot be applied from pending reviews.
Suggestions cannot be applied on multi-line comments.
Suggestions cannot be applied while the pull request is queued to merge.
Suggestion cannot be applied right now. Please check back later.
Which issue does this PR close?
Part of #7013
Rationale for this change
The topic of thread scheduling and why not use Rayon or morsel driven parallelism has come up several times, most recently in the Discord channel: https://discord.com/channels/885562378132000778/1166447479609376850/1198721509842235402
I would like to document what is going on so that we can refer people to the documentation when these questions inevitably arise in the future
What changes are included in this PR?
Are these changes tested?
Existing CI checks
Are there any user-facing changes?
More docs