perf: Optimize contains expression with SIMD-based scalar pattern sea… #2991
Conversation
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
Codecov Report✅ All modified and coverable lines are covered by tests. Additional details and impacted files@@ Coverage Diff @@
## main #2991 +/- ##
============================================
+ Coverage 56.12% 59.55% +3.42%
- Complexity 976 1379 +403
============================================
Files 119 167 +48
Lines 11743 15495 +3752
Branches 2251 2568 +317
============================================
+ Hits 6591 9228 +2637
- Misses 4012 4971 +959
- Partials 1140 1296 +156 ☔ View full report in Codecov by Sentry. 🚀 New features to boost your workflow:
|
Member
|
I tested locally and see good performance now: |
andygrove
reviewed
Dec 27, 2025
native/spark-expr/Cargo.toml
Outdated
|
|
||
| [dependencies] | ||
| arrow = { workspace = true } | ||
| arrow-string = "57.0.0" |
Member
There was a problem hiding this comment.
We already depend on arrow. Is contains not re-exported in the arrow crate?
Member
|
Thanks @Shekharrajak this is a really nice speedup! Could you fix the clippy errors (you can probably just run |
Shekharrajak
force-pushed
the
fix/issue-2972-contains-performance
branch
from
54dc054 to
27929a3
Compare
andygrove
reviewed
Dec 27, 2025
Co-authored-by: Andy Grove <agrove@apache.org>
Shekharrajak
commented
Dec 29, 2025
| * Override waitForTasksToFinish to ensure SparkContext is active before checking tasks. This | ||
| * fixes the issue where waitForTasksToFinish returns -1 when SparkContext is not active. | ||
| */ | ||
| override protected def waitForTasksToFinish(): Unit = { |
Contributor
Author
There was a problem hiding this comment.
this fixes the PR check error :
Shekharrajak
commented
Dec 30, 2025
| //! scalar path in arrow-rs. | ||
| use arrow::array::{Array, ArrayRef, AsArray, BooleanArray}; | ||
| use arrow::datatypes::DataType; |
Contributor
Author
There was a problem hiding this comment.
fmt check error fix
Shekharrajak
commented
Dec 30, 2025
| op.cmd match { | ||
| case cmd: InsertIntoHadoopFsRelationCommand => | ||
| // Skip INSERT OVERWRITE DIRECTORY operations (catalogTable is None for directory writes) | ||
| if (cmd.catalogTable.isEmpty) { |
Contributor
Author
There was a problem hiding this comment.
fix for error :
RROR org.apache.spark.sql.execution.command.InsertIntoDataSourceDirCommand: Failed to write to directory Some(file:/__w/datafusion-comet/datafusion-comet/apache-spark/target/tmp/spark-76b62d31-5bd6-4d4b-9770-262cb08e84f3)
org.apache.spark.sql.AnalysisException: [COLUMN_ALREADY_EXISTS] The column `id` already exists. Choose another name or rename the existing column. SQLSTATE: 42711
at org.apache.spark.sql.errors.QueryCompilationErrors$.columnAlreadyExistsError(QueryCompilationErrors.scala:2700)
at org.apache.spark.sql.util.SchemaUtils$.checkColumnNameDuplication(SchemaUtils.scala:151)
at org.apache.spark.sql.execution.datasources.InsertIntoHadoopFsRelationCommand.run(InsertIntoHadoopFsRelationCommand.scala:86)
at org.apache.spark.sql.execution.command.DataWritingCommandExec.sideEffectResult$lzycompute(commands.scala:117)
at org.apache.spark.sql.execution.command.DataWritingCommandExec.sideEffectResult(commands.scala:115)
at org.apache.spark.sql.execution.command.DataWritingCommandExec.executeCollect(commands.scala:129)
at org.apache.spark.sql.execution.QueryExecution.$anonfun$eagerlyExecuteCommands$2(QueryExecution.scala:155)
[info] - SPARK-25389 INSERT OVERWRITE LOCAL DIRECTORY ... STORED AS with duplicated names(caseSensitivity=true, format=orc) (22 milliseconds)
18:44:25.173 ERROR org.apache.spark.sql.execution.command.InsertIntoDataSourceDirCommand: Failed to write to directory Some(file:/__w/datafusion-comet/datafusion-comet/apache-spark/target/tmp/spark-76ef391d-5d5f-4997-afb4-97ac714c1697)
Sign up for free
to join this conversation on GitHub.
Already have an account?
Sign in to comment
3 participants
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?
Closes #2972.
Rationale for this change
The contains expression shows poor performance in Comet (0.2X vs Spark) because DataFusion's make_scalar_function wrapper expands scalar patterns to arrays, bypassing arrow-rs's optimized scalar path.
What changes are included in this PR?
How are these changes tested?