-
Notifications
You must be signed in to change notification settings - Fork 234
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.
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
Generate CSV data per Spark version for tools [databricks] #10440
Merged
Merged
Changes from all commits
Commits
Show all changes
2 commits
Select commit
Hold shift + click to select a range
File filter
Filter by extension
Conversations
Failed to load comments.
Loading
Jump to
Jump to file
Failed to load files.
Loading
Diff view
Diff view
There are no files selected for viewing
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
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
Large diffs are not rendered by default.
Oops, something went wrong.
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
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
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
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
| Original file line number | Diff line number | Diff line change |
|---|---|---|
| @@ -0,0 +1,152 @@ | ||
| <?xml version="1.0" encoding="UTF-8"?> | ||
| <!-- | ||
| Copyright (c) 2024, NVIDIA CORPORATION. | ||
|
|
||
| Licensed under the Apache License, Version 2.0 (the "License"); | ||
| you may not use this file except in compliance with the License. | ||
| You may obtain a copy of the License at | ||
|
|
||
| http://www.apache.org/licenses/LICENSE-2.0 | ||
|
|
||
| Unless required by applicable law or agreed to in writing, software | ||
| distributed under the License is distributed on an "AS IS" BASIS, | ||
| WITHOUT WARRANTIES OR CONDITIONS OF ANY KIND, either express or implied. | ||
| See the License for the specific language governing permissions and | ||
| limitations under the License. | ||
| --> | ||
| <project xmlns="http://maven.apache.org/POM/4.0.0" | ||
| xmlns:xsi="http://www.w3.org/2001/XMLSchema-instance" | ||
| xsi:schemaLocation="http://maven.apache.org/POM/4.0.0 http://maven.apache.org/xsd/maven-4.0.0.xsd"> | ||
| <modelVersion>4.0.0</modelVersion> | ||
|
|
||
| <parent> | ||
| <groupId>com.nvidia</groupId> | ||
| <artifactId>rapids-4-spark-jdk-profiles_2.13</artifactId> | ||
| <version>24.04.0-SNAPSHOT</version> | ||
| <relativePath>../jdk-profiles/pom.xml</relativePath> | ||
| </parent> | ||
| <artifactId>rapids-4-spark-tools-support</artifactId> | ||
| <packaging>pom</packaging> | ||
| <name>RAPIDS Accelerator for Apache Spark Tools Support</name> | ||
| <description>Supporting code for RAPIDS Accelerator tools</description> | ||
| <version>24.04.0-SNAPSHOT</version> | ||
| <dependencies> | ||
| <dependency> | ||
| <groupId>com.nvidia</groupId> | ||
| <artifactId>rapids-4-spark-aggregator_${scala.binary.version}</artifactId> | ||
| <version>${project.version}</version> | ||
| <classifier>${spark.version.classifier}</classifier> | ||
| <scope>compile</scope> | ||
| </dependency> | ||
| </dependencies> | ||
| <properties> | ||
| <!-- #if scala-2.12 --><!-- | ||
| <tools.datagen.dir>${project.basedir}/generated_files/${buildver}</tools.datagen.dir> | ||
| --><!-- #endif scala-2.12 --> | ||
| <!-- #if scala-2.13 --> | ||
| <tools.datagen.dir>${project.basedir}/../../tools/generated_files/${buildver}</tools.datagen.dir> | ||
| <!-- #endif scala-2.13 --> | ||
| <rapids.default.jar.phase>none</rapids.default.jar.phase> | ||
| </properties> | ||
| <profiles> | ||
| <profile> | ||
| <id>pre-merge</id> | ||
| <properties> | ||
| <included_buildvers>${buildver}</included_buildvers> | ||
| </properties> | ||
| <build> | ||
| <plugins> | ||
| <plugin> | ||
| <groupId>org.codehaus.mojo</groupId> | ||
| <artifactId>exec-maven-plugin</artifactId> | ||
| <executions> | ||
| <execution> | ||
| <id>if_modified_files</id> | ||
| <phase>verify</phase> | ||
| <goals> | ||
| <goal>exec</goal> | ||
| </goals> | ||
| <configuration> | ||
| <executable>bash</executable> | ||
| <commandlineArgs>-c 'export MODIFIED=$(git status --porcelain | grep "^ M"); [[ -z $MODIFIED ]] && exit 0 || { echo -e "found modified files during mvn verify:\n$MODIFIED"; exit 1;}'</commandlineArgs> | ||
| </configuration> | ||
| </execution> | ||
| </executions> | ||
| </plugin> | ||
| </plugins> | ||
| </build> | ||
| </profile> | ||
| </profiles> | ||
| <build> | ||
| <plugins> | ||
| <plugin> | ||
| <groupId>org.apache.maven.plugins</groupId> | ||
| <artifactId>maven-antrun-plugin</artifactId> | ||
| <executions> | ||
| <execution> | ||
| <id>generate_tools_data</id> | ||
| <phase>package</phase> | ||
| <goals> | ||
| <goal>run</goal> | ||
| </goals> | ||
| <configuration> | ||
| <target> | ||
| <taskdef resource="net/sf/antcontrib/antcontrib.properties"/> | ||
| <ac:if xmlns:ac="antlib:net.sf.antcontrib"> | ||
| <not> | ||
| <matches pattern="db$" string="${buildver}"/> | ||
| </not> | ||
| <then> | ||
| <mkdir dir="${tools.datagen.dir}"/> | ||
| <java classname="com.nvidia.spark.rapids.SupportedOpsForTools" failonerror="true"> | ||
| <arg value="${tools.datagen.dir}/supportedDataSource.csv"/> | ||
| </java> | ||
| <java classname="com.nvidia.spark.rapids.SupportedOpsForTools" failonerror="true"> | ||
| <arg value="${tools.datagen.dir}/operatorsScore.csv"/> | ||
| <arg value="operatorScore"/> | ||
| </java> | ||
| <java classname="com.nvidia.spark.rapids.SupportedOpsForTools" failonerror="true"> | ||
| <arg value="${tools.datagen.dir}/supportedExecs.csv"/> | ||
| <arg value="execs"/> | ||
| </java> | ||
| <java classname="com.nvidia.spark.rapids.SupportedOpsForTools" failonerror="true"> | ||
| <arg value="${tools.datagen.dir}/supportedExprs.csv"/> | ||
| <arg value="exprs"/> | ||
| </java> | ||
| </then> | ||
| <else> | ||
| <echo message="Skipping tools build on Databricks"/> | ||
| </else> | ||
| </ac:if> | ||
| </target> | ||
| </configuration> | ||
| </execution> | ||
| </executions> | ||
| <dependencies> | ||
| <dependency> | ||
| <groupId>com.nvidia</groupId> | ||
| <artifactId>rapids-4-spark-aggregator_${scala.binary.version}</artifactId> | ||
| <version>${project.version}</version> | ||
| <classifier>${spark.version.classifier}</classifier> | ||
| </dependency> | ||
| <dependency> | ||
| <groupId>org.apache.spark</groupId> | ||
| <artifactId>spark-hive_${scala.binary.version}</artifactId> | ||
| <version>${spark.version}</version> | ||
| <exclusions> | ||
| <exclusion> | ||
| <groupId>org.apache.curator</groupId> | ||
| <artifactId>curator-recipes</artifactId> | ||
| </exclusion> | ||
| </exclusions> | ||
| </dependency> | ||
| <dependency> | ||
| <groupId>org.apache.spark</groupId> | ||
| <artifactId>spark-avro_${scala.binary.version}</artifactId> | ||
| <version>${spark.version}</version> | ||
| </dependency> | ||
| </dependencies> | ||
| </plugin> | ||
| </plugins> | ||
| </build> | ||
| </project> |
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
Oops, something went wrong.
Oops, something went wrong.
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.
There was a problem hiding this comment.
Choose a reason for hiding this comment
The reason will be displayed to describe this comment to others. Learn more.
Previously the idea was to build the minimum set of artifacts for dist ? Should buildall have a separate option for including tools?
There was a problem hiding this comment.
Choose a reason for hiding this comment
The reason will be displayed to describe this comment to others. Learn more.
Should there be an argument to not build tools? I would expect buildall to be used by developers as an easy way to build all the Spark versions, and more often than not they want to build the tools CSV data to know whether or not they need to checkin updated files as part of their PR. The build of these files is quick, so we're saving much by making the default to not build the tools data, and I think building the tools data is a better default. Thoughts?
There was a problem hiding this comment.
Choose a reason for hiding this comment
The reason will be displayed to describe this comment to others. Learn more.
It adds less than 4 seconds to the parallel part of the build, so
(totalShimsInProfile / numParallelShims) * 4 secis acceptable. Agree, no pressing need to add a skip option now