496f6ac860
### What changes were proposed in this pull request? This is another PR for stage level scheduling. In particular this adds changes to the dynamic allocation manager and the scheduler backend to be able to track what executors are needed per ResourceProfile. Note the api is still private to Spark until the entire feature gets in, so this functionality will be there but only usable by tests for profiles other then the DefaultProfile. The main changes here are simply tracking things on a ResourceProfile basis as well as sending the executor requests to the scheduler backend for all ResourceProfiles. I introduce a ResourceProfileManager in this PR that will track all the actual ResourceProfile objects so that we can keep them all in a single place and just pass around and use in datastructures the resource profile id. The resource profile id can be used with the ResourceProfileManager to get the actual ResourceProfile contents. There are various places in the code that use executor "slots" for things. The ResourceProfile adds functionality to keep that calculation in it. This logic is more complex then it should due to standalone mode and mesos coarse grained not setting the executor cores config. They default to all cores on the worker, so calculating slots is harder there. This PR keeps the functionality to make the cores the limiting resource because the scheduler still uses that for "slots" for a few things. This PR does also add the resource profile id to the Stage and stage info classes to be able to test things easier. That full set of changes will come with the scheduler PR that will be after this one. The PR stops at the scheduler backend pieces for the cluster manager and the real YARN support hasn't been added in this PR, that again will be in a separate PR, so this has a few of the API changes up to the cluster manager and then just uses the default profile requests to continue. The code for the entire feature is here for reference: https://github.com/apache/spark/pull/27053/files although it needs to be upmerged again as well. ### Why are the changes needed? Needed for stage level scheduling feature. ### Does this PR introduce any user-facing change? No user facing api changes added here. ### How was this patch tested? Lots of unit tests and manually testing. I tested on yarn, k8s, standalone, local modes. Ran both failure and success cases. Closes #27313 from tgravescs/SPARK-29148. Authored-by: Thomas Graves <tgraves@nvidia.com> Signed-off-by: Thomas Graves <tgraves@apache.org> |
||
|---|---|---|
| .. | ||
| docs | ||
| lib | ||
| pyspark | ||
| test_coverage | ||
| test_support | ||
| .coveragerc | ||
| .gitignore | ||
| MANIFEST.in | ||
| pylintrc | ||
| README.md | ||
| run-tests | ||
| run-tests-with-coverage | ||
| run-tests.py | ||
| setup.cfg | ||
| setup.py | ||
Apache Spark
Spark is a unified analytics engine for large-scale data processing. It provides high-level APIs in Scala, Java, Python, and R, and an optimized engine that supports general computation graphs for data analysis. It also supports a rich set of higher-level tools including Spark SQL for SQL and DataFrames, MLlib for machine learning, GraphX for graph processing, and Structured Streaming for stream processing.
Online Documentation
You can find the latest Spark documentation, including a programming guide, on the project web page
Python Packaging
This README file only contains basic information related to pip installed PySpark. This packaging is currently experimental and may change in future versions (although we will do our best to keep compatibility). Using PySpark requires the Spark JARs, and if you are building this from source please see the builder instructions at "Building Spark".
The Python packaging for Spark is not intended to replace all of the other use cases. This Python packaged version of Spark is suitable for interacting with an existing cluster (be it Spark standalone, YARN, or Mesos) - but does not contain the tools required to set up your own standalone Spark cluster. You can download the full version of Spark from the Apache Spark downloads page.
NOTE: If you are using this with a Spark standalone cluster you must ensure that the version (including minor version) matches or you may experience odd errors.
Python Requirements
At its core PySpark depends on Py4J (currently version 0.10.8.1), but some additional sub-packages have their own extra requirements for some features (including numpy, pandas, and pyarrow).