Add Spark-based data generation for K8s (replaces MapReduce)#248
Open
wjxiz1992 wants to merge 7 commits intoNVIDIA:devfrom
Open
Add Spark-based data generation for K8s (replaces MapReduce)#248wjxiz1992 wants to merge 7 commits intoNVIDIA:devfrom
wjxiz1992 wants to merge 7 commits intoNVIDIA:devfrom
Conversation
Signed-off-by: Allen Xu <allxu@nvidia.com>
Greptile SummaryThis PR adds K8s-native TPC-DS data generation support via a new PySpark-based approach ( Key additions:
Review findings: Confidence Score: 4/5
Important Files Changed
Sequence DiagramsequenceDiagram
participant User
participant Driver as Spark Driver<br/>(K8s Pod)
participant Executor as Spark Executor<br/>(K8s Pod)
participant FS as Filesystem<br/>(HDFS/S3/etc)
User->>Driver: spark-submit with --archives dsdgen.tar.gz#dsdgen
Driver->>Driver: Parse args (scale, parallel, range)
Driver->>Driver: Create RDD with child indices
Driver->>Executor: Distribute archive + tasks
Executor->>Executor: Extract dsdgen.tar.gz to SparkFiles
Executor->>Executor: run_dsdgen_and_read(child_index)
Executor->>Executor: subprocess.run(dsdgen -child N)
Executor->>Executor: Stream .dat files line-by-line
Executor->>FS: Write partitioned data (table_name=xxx/)
Executor-->>Driver: Task complete
Driver->>Driver: All tasks finished
Driver->>FS: rename_partition_dirs()
Driver->>FS: Rename table_name=xxx to xxx/
FS-->>Driver: Rename complete
Driver->>User: Data generation complete
Last reviewed commit: 3160717 |
![greptile-apps[bot]](https://avatars.githubusercontent.com/in/867647?s=60&v=4){kind=small}
Contributor
There was a problem hiding this comment.
Pull request overview
This PR introduces a new Spark-based approach for TPC-DS data generation that works with Kubernetes and other Spark cluster managers, complementing the existing Hadoop MapReduce-based approach. The implementation distributes the dsdgen binary via Spark's --archives mechanism and generates data in parallel across Spark executors.
Changes:
- Added
nds_gen_data_spark.py: PySpark application that replaces MapReduce approach for data generation, supporting K8s, YARN, Standalone, and local modes - Updated README with documentation and examples for the new Spark-based data generation workflow
Reviewed changes
Copilot reviewed 2 out of 2 changed files in this pull request and generated 6 comments.
| File | Description |
|---|---|
| nds/nds_gen_data_spark.py | New PySpark script implementing distributed TPC-DS data generation via Spark executors with support for incremental generation and multiple filesystem backends |
| nds/README.md | Added comprehensive documentation section explaining Spark-based data generation with usage examples for K8s and other cluster managers |
💡 Add Copilot custom instructions for smarter, more guided reviews. Learn how to get started.
Signed-off-by: Allen Xu <allxu@nvidia.com>
Signed-off-by: Allen Xu <allxu@nvidia.com>
- Use dsdgen.tar.gz instead of dsdgen.jar for archive format consistency - Add return value checks in rename_partition_dirs to prevent silent failures - Use shutil.rmtree for robust temp directory cleanup - Add encoding="utf-8" to file open calls - Fix Partitions print alignment Made-with: Cursor
| if len(parts) != 2: | ||
| print("ERROR: --range must be 'start,end'", file=sys.stderr) | ||
| sys.exit(1) | ||
| range_start, range_end = int(parts[0]), int(parts[1]) |
There was a problem hiding this comment.
Missing exception handling for int() conversion - passing non-numeric values like --range abc,def will crash with unclear ValueError
Suggested change
| range_start, range_end = int(parts[0]), int(parts[1]) | |
| try: | |
| range_start, range_end = int(parts[0]), int(parts[1]) | |
| except ValueError as e: | |
| print(f"ERROR: --range values must be integers: {e}", file=sys.stderr) | |
| sys.exit(1) |
- Add tpcds-gen/Dockerfile.dsdgen for cross-compiling dsdgen on Linux - Add Dockerfile.k8s-test for building Spark K8s image with datagen - Remove k8s_datagen_smoketest.sh script - Update README with cross-compilation, image build, and minikube testing instructions Made-with: Cursor
| # Set up Spark directory structure | ||
| ENV SPARK_HOME=/opt/spark | ||
| ENV PATH="${SPARK_HOME}/bin:${PATH}" | ||
| ENV PYTHONPATH="${SPARK_HOME}/python:${SPARK_HOME}/python/lib/py4j-0.10.9.7-src.zip:${PYTHONPATH}" |
There was a problem hiding this comment.
Hardcoded py4j-0.10.9.7-src.zip version assumes Spark 3.5.x - will break with other Spark versions that bundle different py4j versions
- Add try/except for --range int() parsing with clear error message - Remove hardcoded py4j version in Dockerfile.spark-k8s using symlink - Add base image build instructions and ARG to Dockerfile.k8s-test - Add kubectl wait for PVC binding in README minikube guide Made-with: Cursor
- Add guard in Dockerfile.spark-k8s to fail build if no py4j zip found - Add usage instructions and build context note to Dockerfile.spark-k8s - Document both Dockerfile options (k8s-test vs spark-k8s) in README with comparison table and step-by-step instructions Made-with: Cursor
wjxiz1992
changed the title
wjxiz1992
changed the title
Collaborator
Author
|
@copilot code review[agent] review |
This file contains hidden or 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
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.
Summary
This PR adds Kubernetes-native support for TPC-DS data generation by introducing a new PySpark-based approach (
nds_gen_data_spark.py) that replaces the Hadoop MapReduce method. The dsdgen binary is distributed to Spark executors via--archives, enabling parallel data generation on any Spark cluster manager (K8s, YARN, Standalone, local) without requiring YARN or MapReduce.Changes
Core
nds/nds_gen_data_spark.py— New PySpark application that:dsdgenbinary across Spark executors via--archivestable_name=xxxdirectories to plainxxxfor NDS pipeline compatibility--rangefor incremental generation,--overwrite, and--updatefor maintenance datasetsDockerfiles
nds/tpcds-gen/Dockerfile.dsdgen— Multi-stage build for cross-compilingdsdgenon Linux (handles GCC 10+-fcommonissue)nds/Dockerfile.k8s-test— Layers datagen scripts onto the official Spark Python image (recommended, usesARG BASE_IMAGE)nds/Dockerfile.spark-k8s— Standalone full Spark + PySpark image from a Spark distribution (build context =$SPARK_HOME)Configuration
nds/datagen_submit.template— spark-submit template for use withspark-submit-templateutilityDocumentation
nds/README.md— Comprehensive new sections:Dockerfile.dsdgenTesting
Verified on local minikube (Docker driver, ARM64):
Dockerfile.dsdgenDockerfile.k8s-testnds_gen_data_spark.pywithlocal[2]mode inside a K8s pod (scale=1, parallel=2)Migration Notes
nds_gen_data.py(MapReduce-based) is unchanged — this PR adds a parallel path, not a replacementnds_gen_data_spark.py