This is an automated email from the ASF dual-hosted git repository.
agrove pushed a commit to branch branch-0.13
in repository https://gitbox.apache.org/repos/asf/datafusion-comet.git
The following commit(s) were added to refs/heads/branch-0.13 by this push:
new fefdc26ce chore: [branch-0.13] Prepare 0.13.0 release (#3285)
fefdc26ce is described below
commit fefdc26ced0c854f92d80d939f3427c790dcaddc
Author: Andy Grove <[email protected]>
AuthorDate: Mon Jan 26 09:28:06 2026 -0700
chore: [branch-0.13] Prepare 0.13.0 release (#3285)
---
common/pom.xml | 2 +-
dev/diffs/3.4.3.diff | 2 +-
dev/diffs/3.5.7.diff | 2 +-
dev/diffs/4.0.1.diff | 2 +-
dev/diffs/iceberg-rust/1.10.0.diff | 2 +-
dev/diffs/iceberg-rust/1.8.1.diff | 2 +-
dev/diffs/iceberg-rust/1.9.1.diff | 2 +-
dev/diffs/iceberg/1.10.0.diff | 2 +-
dev/diffs/iceberg/1.8.1.diff | 2 +-
dev/diffs/iceberg/1.9.1.diff | 2 +-
dev/generate-release-docs.sh | 8 +-
docs/source/user-guide/latest/compatibility.md | 84 +++++++
docs/source/user-guide/latest/configs.md | 297 +++++++++++++++++++++++++
fuzz-testing/pom.xml | 2 +-
native/Cargo.lock | 68 +++---
pom.xml | 2 +-
spark-integration/pom.xml | 2 +-
spark/pom.xml | 30 ++-
18 files changed, 458 insertions(+), 55 deletions(-)
diff --git a/common/pom.xml b/common/pom.xml
index c7a6147c3..37c086aa5 100644
--- a/common/pom.xml
+++ b/common/pom.xml
@@ -26,7 +26,7 @@ under the License.
<parent>
<groupId>org.apache.datafusion</groupId>
<artifactId>comet-parent-spark${spark.version.short}_${scala.binary.version}</artifactId>
- <version>0.13.0-SNAPSHOT</version>
+ <version>0.13.0</version>
<relativePath>../pom.xml</relativePath>
</parent>
diff --git a/dev/diffs/3.4.3.diff b/dev/diffs/3.4.3.diff
index fc8fd923f..7e4f72ac3 100644
--- a/dev/diffs/3.4.3.diff
+++ b/dev/diffs/3.4.3.diff
@@ -7,7 +7,7 @@ index d3544881af1..07d1ed97925 100644
<ivy.version>2.5.1</ivy.version>
<oro.version>2.0.8</oro.version>
+ <spark.version.short>3.4</spark.version.short>
-+ <comet.version>0.13.0-SNAPSHOT</comet.version>
++ <comet.version>0.13.0</comet.version>
<!--
If you changes codahale.metrics.version, you also need to change
the link to metrics.dropwizard.io in docs/monitoring.md.
diff --git a/dev/diffs/3.5.7.diff b/dev/diffs/3.5.7.diff
index 3adc8c833..7bf132d7f 100644
--- a/dev/diffs/3.5.7.diff
+++ b/dev/diffs/3.5.7.diff
@@ -7,7 +7,7 @@ index a0e25ce4d8d..29d3b93f994 100644
<ivy.version>2.5.1</ivy.version>
<oro.version>2.0.8</oro.version>
+ <spark.version.short>3.5</spark.version.short>
-+ <comet.version>0.13.0-SNAPSHOT</comet.version>
++ <comet.version>0.13.0</comet.version>
<!--
If you changes codahale.metrics.version, you also need to change
the link to metrics.dropwizard.io in docs/monitoring.md.
diff --git a/dev/diffs/4.0.1.diff b/dev/diffs/4.0.1.diff
index a9315db00..84ed43e29 100644
--- a/dev/diffs/4.0.1.diff
+++ b/dev/diffs/4.0.1.diff
@@ -7,7 +7,7 @@ index 22922143fc3..477d4ec4194 100644
<ivy.version>2.5.3</ivy.version>
<oro.version>2.0.8</oro.version>
+ <spark.version.short>4.0</spark.version.short>
-+ <comet.version>0.13.0-SNAPSHOT</comet.version>
++ <comet.version>0.13.0</comet.version>
<!--
If you change codahale.metrics.version, you also need to change
the link to metrics.dropwizard.io in docs/monitoring.md.
diff --git a/dev/diffs/iceberg-rust/1.10.0.diff
b/dev/diffs/iceberg-rust/1.10.0.diff
index da56aabfe..6e6cf150a 100644
--- a/dev/diffs/iceberg-rust/1.10.0.diff
+++ b/dev/diffs/iceberg-rust/1.10.0.diff
@@ -25,7 +25,7 @@ index eeabe54f5..867018058 100644
caffeine = "2.9.3"
calcite = "1.40.0"
-comet = "0.8.1"
-+comet = "0.13.0-SNAPSHOT"
++comet = "0.13.0"
datasketches = "6.2.0"
delta-standalone = "3.3.2"
delta-spark = "3.3.2"
diff --git a/dev/diffs/iceberg-rust/1.8.1.diff
b/dev/diffs/iceberg-rust/1.8.1.diff
index aa9774d96..838ac8983 100644
--- a/dev/diffs/iceberg-rust/1.8.1.diff
+++ b/dev/diffs/iceberg-rust/1.8.1.diff
@@ -24,7 +24,7 @@ index 04ffa8f4e..3a57af315 100644
awssdk-s3accessgrants = "2.3.0"
caffeine = "2.9.3"
calcite = "1.10.0"
-+comet = "0.13.0-SNAPSHOT"
++comet = "0.13.0"
datasketches = "6.2.0"
delta-standalone = "3.3.0"
delta-spark = "3.3.0"
diff --git a/dev/diffs/iceberg-rust/1.9.1.diff
b/dev/diffs/iceberg-rust/1.9.1.diff
index d9bcdb2e3..2cc3a25a5 100644
--- a/dev/diffs/iceberg-rust/1.9.1.diff
+++ b/dev/diffs/iceberg-rust/1.9.1.diff
@@ -24,7 +24,7 @@ index c50991c5f..3acb395a6 100644
bson-ver = "4.11.5"
caffeine = "2.9.3"
calcite = "1.39.0"
-+comet = "0.13.0-SNAPSHOT"
++comet = "0.13.0"
datasketches = "6.2.0"
delta-standalone = "3.3.1"
delta-spark = "3.3.1"
diff --git a/dev/diffs/iceberg/1.10.0.diff b/dev/diffs/iceberg/1.10.0.diff
index dbce4622e..95583599b 100644
--- a/dev/diffs/iceberg/1.10.0.diff
+++ b/dev/diffs/iceberg/1.10.0.diff
@@ -25,7 +25,7 @@ index eeabe54f5f0..867018058ee 100644
caffeine = "2.9.3"
calcite = "1.40.0"
-comet = "0.8.1"
-+comet = "0.13.0-SNAPSHOT"
++comet = "0.13.0"
datasketches = "6.2.0"
delta-standalone = "3.3.2"
delta-spark = "3.3.2"
diff --git a/dev/diffs/iceberg/1.8.1.diff b/dev/diffs/iceberg/1.8.1.diff
index 999ce63b8..3c3a548a9 100644
--- a/dev/diffs/iceberg/1.8.1.diff
+++ b/dev/diffs/iceberg/1.8.1.diff
@@ -24,7 +24,7 @@ index 04ffa8f4edc..3a57af3156a 100644
awssdk-s3accessgrants = "2.3.0"
caffeine = "2.9.3"
calcite = "1.10.0"
-+comet = "0.13.0-SNAPSHOT"
++comet = "0.13.0"
datasketches = "6.2.0"
delta-standalone = "3.3.0"
delta-spark = "3.3.0"
diff --git a/dev/diffs/iceberg/1.9.1.diff b/dev/diffs/iceberg/1.9.1.diff
index 2eee87d7d..6f04a5883 100644
--- a/dev/diffs/iceberg/1.9.1.diff
+++ b/dev/diffs/iceberg/1.9.1.diff
@@ -24,7 +24,7 @@ index c50991c5fc6..f7ad00f0b78 100644
bson-ver = "4.11.5"
caffeine = "2.9.3"
calcite = "1.39.0"
-+comet = "0.13.0-SNAPSHOT"
++comet = "0.13.0"
datasketches = "6.2.0"
delta-standalone = "3.3.1"
delta-spark = "3.3.1"
diff --git a/dev/generate-release-docs.sh b/dev/generate-release-docs.sh
index 5da77a9d6..747d1649b 100755
--- a/dev/generate-release-docs.sh
+++ b/dev/generate-release-docs.sh
@@ -42,13 +42,7 @@ PROJECT_ROOT="$(cd "${SCRIPT_DIR}/.." && pwd)"
cd "${PROJECT_ROOT}"
echo "Compiling common and spark modules..."
-./mvnw -q compile -pl common,spark -DskipTests
-
-echo "Generating documentation content..."
-./mvnw -q exec:java -pl spark \
- -Dexec.mainClass=org.apache.comet.GenerateDocs \
- -Dexec.arguments="${PROJECT_ROOT}/docs/source/user-guide/latest/" \
- -Dexec.classpathScope=compile
+./mvnw package -Pgenerate-docs -DskipTests -Dmaven.test.skip=true
echo ""
echo "Done! Generated documentation content in docs/source/user-guide/latest/"
diff --git a/docs/source/user-guide/latest/compatibility.md
b/docs/source/user-guide/latest/compatibility.md
index c09f6a61e..6f5e42bdb 100644
--- a/docs/source/user-guide/latest/compatibility.md
+++ b/docs/source/user-guide/latest/compatibility.md
@@ -111,16 +111,100 @@ Cast operations in Comet fall into three levels of
support:
### Legacy Mode
<!--BEGIN:CAST_LEGACY_TABLE-->
+<!-- prettier-ignore-start -->
+| | binary | boolean | byte | date | decimal | double | float | integer | long
| short | string | timestamp |
+|---|---|---|---|---|---|---|---|---|---|---|---|---|
+| binary | - | N/A | N/A | N/A | N/A | N/A | N/A | N/A | N/A | N/A | C | N/A |
+| boolean | N/A | - | C | N/A | U | C | C | C | C | C | C | U |
+| byte | U | C | - | N/A | C | C | C | C | C | C | C | U |
+| date | N/A | U | U | - | U | U | U | U | U | U | C | U |
+| decimal | N/A | C | C | N/A | - | C | C | C | C | C | C | U |
+| double | N/A | C | C | N/A | I | - | C | C | C | C | C | U |
+| float | N/A | C | C | N/A | I | C | - | C | C | C | C | U |
+| integer | U | C | C | N/A | C | C | C | - | C | C | C | U |
+| long | U | C | C | N/A | C | C | C | C | - | C | C | U |
+| short | U | C | C | N/A | C | C | C | C | C | - | C | U |
+| string | C | C | C | C | I | C | C | C | C | C | - | I |
+| timestamp | N/A | U | U | C | U | U | U | U | C | U | C | - |
+<!-- prettier-ignore-end -->
+
+**Notes:**
+
+- **decimal -> string**: There can be formatting differences in some case due
to Spark using scientific notation where Comet does not
+- **double -> decimal**: There can be rounding differences
+- **double -> string**: There can be differences in precision. For example,
the input "1.4E-45" will produce 1.0E-45 instead of 1.4E-45
+- **float -> decimal**: There can be rounding differences
+- **float -> string**: There can be differences in precision. For example, the
input "1.4E-45" will produce 1.0E-45 instead of 1.4E-45
+- **string -> date**: Only supports years between 262143 BC and 262142 AD
+- **string -> decimal**: Does not support fullwidth unicode digits (e.g
\\uFF10)
+ or strings containing null bytes (e.g \\u0000)
+- **string -> timestamp**: Not all valid formats are supported
<!--END:CAST_LEGACY_TABLE-->
### Try Mode
<!--BEGIN:CAST_TRY_TABLE-->
+<!-- prettier-ignore-start -->
+| | binary | boolean | byte | date | decimal | double | float | integer | long
| short | string | timestamp |
+|---|---|---|---|---|---|---|---|---|---|---|---|---|
+| binary | - | N/A | N/A | N/A | N/A | N/A | N/A | N/A | N/A | N/A | C | N/A |
+| boolean | N/A | - | C | N/A | U | C | C | C | C | C | C | U |
+| byte | U | C | - | N/A | C | C | C | C | C | C | C | U |
+| date | N/A | U | U | - | U | U | U | U | U | U | C | U |
+| decimal | N/A | C | C | N/A | - | C | C | C | C | C | C | U |
+| double | N/A | C | C | N/A | I | - | C | C | C | C | C | U |
+| float | N/A | C | C | N/A | I | C | - | C | C | C | C | U |
+| integer | U | C | C | N/A | C | C | C | - | C | C | C | U |
+| long | U | C | C | N/A | C | C | C | C | - | C | C | U |
+| short | U | C | C | N/A | C | C | C | C | C | - | C | U |
+| string | C | C | C | C | I | C | C | C | C | C | - | I |
+| timestamp | N/A | U | U | C | U | U | U | U | C | U | C | - |
+<!-- prettier-ignore-end -->
+
+**Notes:**
+
+- **decimal -> string**: There can be formatting differences in some case due
to Spark using scientific notation where Comet does not
+- **double -> decimal**: There can be rounding differences
+- **double -> string**: There can be differences in precision. For example,
the input "1.4E-45" will produce 1.0E-45 instead of 1.4E-45
+- **float -> decimal**: There can be rounding differences
+- **float -> string**: There can be differences in precision. For example, the
input "1.4E-45" will produce 1.0E-45 instead of 1.4E-45
+- **string -> date**: Only supports years between 262143 BC and 262142 AD
+- **string -> decimal**: Does not support fullwidth unicode digits (e.g
\\uFF10)
+ or strings containing null bytes (e.g \\u0000)
+- **string -> timestamp**: Not all valid formats are supported
<!--END:CAST_TRY_TABLE-->
### ANSI Mode
<!--BEGIN:CAST_ANSI_TABLE-->
+<!-- prettier-ignore-start -->
+| | binary | boolean | byte | date | decimal | double | float | integer | long
| short | string | timestamp |
+|---|---|---|---|---|---|---|---|---|---|---|---|---|
+| binary | - | N/A | N/A | N/A | N/A | N/A | N/A | N/A | N/A | N/A | C | N/A |
+| boolean | N/A | - | C | N/A | U | C | C | C | C | C | C | U |
+| byte | U | C | - | N/A | C | C | C | C | C | C | C | U |
+| date | N/A | U | U | - | U | U | U | U | U | U | C | U |
+| decimal | N/A | C | C | N/A | - | C | C | C | C | C | C | U |
+| double | N/A | C | C | N/A | I | - | C | C | C | C | C | U |
+| float | N/A | C | C | N/A | I | C | - | C | C | C | C | U |
+| integer | U | C | C | N/A | C | C | C | - | C | C | C | U |
+| long | U | C | C | N/A | C | C | C | C | - | C | C | U |
+| short | U | C | C | N/A | C | C | C | C | C | - | C | U |
+| string | C | C | C | C | I | C | C | C | C | C | - | I |
+| timestamp | N/A | U | U | C | U | U | U | U | C | U | C | - |
+<!-- prettier-ignore-end -->
+
+**Notes:**
+
+- **decimal -> string**: There can be formatting differences in some case due
to Spark using scientific notation where Comet does not
+- **double -> decimal**: There can be rounding differences
+- **double -> string**: There can be differences in precision. For example,
the input "1.4E-45" will produce 1.0E-45 instead of 1.4E-45
+- **float -> decimal**: There can be rounding differences
+- **float -> string**: There can be differences in precision. For example, the
input "1.4E-45" will produce 1.0E-45 instead of 1.4E-45
+- **string -> date**: Only supports years between 262143 BC and 262142 AD
+- **string -> decimal**: Does not support fullwidth unicode digits (e.g
\\uFF10)
+ or strings containing null bytes (e.g \\u0000)
+- **string -> timestamp**: ANSI mode not supported
<!--END:CAST_ANSI_TABLE-->
See the [tracking
issue](https://github.com/apache/datafusion-comet/issues/286) for more details.
diff --git a/docs/source/user-guide/latest/configs.md
b/docs/source/user-guide/latest/configs.md
index a268691a3..9828b8b7f 100644
--- a/docs/source/user-guide/latest/configs.md
+++ b/docs/source/user-guide/latest/configs.md
@@ -24,16 +24,54 @@ Comet provides the following configuration settings.
## Scan Configuration Settings
<!--BEGIN:CONFIG_TABLE[scan]-->
+<!-- prettier-ignore-start -->
+| Config | Description | Default Value |
+|--------|-------------|---------------|
+| `spark.comet.scan.enabled` | Whether to enable native scans. When this is
turned on, Spark will use Comet to read supported data sources (currently only
Parquet is supported natively). Note that to enable native vectorized
execution, both this config and `spark.comet.exec.enabled` need to be enabled.
| true |
+| `spark.comet.scan.icebergNative.enabled` | Whether to enable native Iceberg
table scan using iceberg-rust. When enabled, Iceberg tables are read directly
through native execution, bypassing Spark's DataSource V2 API for better
performance. | false |
+| `spark.comet.scan.preFetch.enabled` | Whether to enable pre-fetching feature
of CometScan. | false |
+| `spark.comet.scan.preFetch.threadNum` | The number of threads running
pre-fetching for CometScan. Effective if spark.comet.scan.preFetch.enabled is
enabled. Note that more pre-fetching threads means more memory requirement to
store pre-fetched row groups. | 2 |
+| `spark.comet.scan.unsignedSmallIntSafetyCheck` | Parquet files may contain
unsigned 8-bit integers (UINT_8) which Spark maps to ShortType. When this
config is true (default), Comet falls back to Spark for ShortType columns
because we cannot distinguish signed INT16 (safe) from unsigned UINT_8 (may
produce different results). Set to false to allow native execution of ShortType
columns if you know your data does not contain unsigned UINT_8 columns from
improperly encoded Parquet files. F [...]
+| `spark.hadoop.fs.comet.libhdfs.schemes` | Defines filesystem schemes (e.g.,
hdfs, webhdfs) that the native side accesses via libhdfs, separated by commas.
Valid only when built with hdfs feature enabled. | |
+<!-- prettier-ignore-end -->
<!--END:CONFIG_TABLE-->
## Parquet Reader Configuration Settings
<!--BEGIN:CONFIG_TABLE[parquet]-->
+<!-- prettier-ignore-start -->
+| Config | Description | Default Value |
+|--------|-------------|---------------|
+| `spark.comet.parquet.enable.directBuffer` | Whether to use Java direct byte
buffer when reading Parquet. | false |
+| `spark.comet.parquet.read.io.adjust.readRange.skew` | In the parallel
reader, if the read ranges submitted are skewed in sizes, this option will
cause the reader to break up larger read ranges into smaller ranges to reduce
the skew. This will result in a slightly larger number of connections opened to
the file system but may give improved performance. | false |
+| `spark.comet.parquet.read.io.mergeRanges` | When enabled the parallel reader
will try to merge ranges of data that are separated by less than
`comet.parquet.read.io.mergeRanges.delta` bytes. Longer continuous reads are
faster on cloud storage. | true |
+| `spark.comet.parquet.read.io.mergeRanges.delta` | The delta in bytes between
consecutive read ranges below which the parallel reader will try to merge the
ranges. The default is 8MB. | 8388608 |
+| `spark.comet.parquet.read.parallel.io.enabled` | Whether to enable Comet's
parallel reader for Parquet files. The parallel reader reads ranges of
consecutive data in a file in parallel. It is faster for large files and row
groups but uses more resources. | true |
+| `spark.comet.parquet.read.parallel.io.thread-pool.size` | The maximum number
of parallel threads the parallel reader will use in a single executor. For
executors configured with a smaller number of cores, use a smaller number. | 16
|
+| `spark.comet.parquet.respectFilterPushdown` | Whether to respect Spark's
PARQUET_FILTER_PUSHDOWN_ENABLED config. This needs to be respected when running
the Spark SQL test suite but the default setting results in poor performance in
Comet when using the new native scans, disabled by default | false |
+<!-- prettier-ignore-end -->
<!--END:CONFIG_TABLE-->
## Query Execution Settings
<!--BEGIN:CONFIG_TABLE[exec]-->
+<!-- prettier-ignore-start -->
+| Config | Description | Default Value |
+|--------|-------------|---------------|
+| `spark.comet.caseConversion.enabled` | Java uses locale-specific rules when
converting strings to upper or lower case and Rust does not, so we disable
upper and lower by default. | false |
+| `spark.comet.debug.enabled` | Whether to enable debug mode for Comet. When
enabled, Comet will do additional checks for debugging purpose. For example,
validating array when importing arrays from JVM at native side. Note that these
checks may be expensive in performance and should only be enabled for debugging
purpose. | false |
+| `spark.comet.dppFallback.enabled` | Whether to fall back to Spark for
queries that use DPP. | true |
+| `spark.comet.enabled` | Whether to enable Comet extension for Spark. When
this is turned on, Spark will use Comet to read Parquet data source. Note that
to enable native vectorized execution, both this config and
`spark.comet.exec.enabled` need to be enabled. It can be overridden by the
environment variable `ENABLE_COMET`. | true |
+| `spark.comet.exceptionOnDatetimeRebase` | Whether to throw exception when
seeing dates/timestamps from the legacy hybrid (Julian + Gregorian) calendar.
Since Spark 3, dates/timestamps were written according to the Proleptic
Gregorian calendar. When this is true, Comet will throw exceptions when seeing
these dates/timestamps that were written by Spark version before 3.0. If this
is false, these dates/timestamps will be read as if they were written to the
Proleptic Gregorian calendar and [...]
+| `spark.comet.exec.columnarToRow.native.enabled` | Whether to enable native
columnar to row conversion. When enabled, Comet will use native Rust code to
convert Arrow columnar data to Spark UnsafeRow format instead of the JVM
implementation. This can improve performance for queries that need to convert
between columnar and row formats. This is an experimental feature. | false |
+| `spark.comet.exec.enabled` | Whether to enable Comet native vectorized
execution for Spark. This controls whether Spark should convert operators into
their Comet counterparts and execute them in native space. Note: each operator
is associated with a separate config in the format of
`spark.comet.exec.<operator_name>.enabled` at the moment, and both the config
and this need to be turned on, in order for the operator to be executed in
native. | true |
+| `spark.comet.exec.replaceSortMergeJoin` | Experimental feature to force
Spark to replace SortMergeJoin with ShuffledHashJoin for improved performance.
This feature is not stable yet. For more information, refer to the [Comet
Tuning Guide](https://datafusion.apache.org/comet/user-guide/tuning.html). |
false |
+| `spark.comet.exec.strictFloatingPoint` | When enabled, fall back to Spark
for floating-point operations that may differ from Spark, such as when
comparing or sorting -0.0 and 0.0. For more information, refer to the [Comet
Compatibility
Guide](https://datafusion.apache.org/comet/user-guide/compatibility.html). |
false |
+| `spark.comet.maxTempDirectorySize` | The maximum amount of data (in bytes)
stored inside the temporary directories. | 107374182400b |
+| `spark.comet.metrics.updateInterval` | The interval in milliseconds to
update metrics. If interval is negative, metrics will be updated upon task
completion. | 3000 |
+| `spark.comet.nativeLoadRequired` | Whether to require Comet native library
to load successfully when Comet is enabled. If not, Comet will silently
fallback to Spark when it fails to load the native lib. Otherwise, an error
will be thrown and the Spark job will be aborted. | false |
+| `spark.comet.regexp.allowIncompatible` | Comet is not currently fully
compatible with Spark for all regular expressions. Set this config to true to
allow them anyway. For more information, refer to the [Comet Compatibility
Guide](https://datafusion.apache.org/comet/user-guide/compatibility.html). |
false |
+<!-- prettier-ignore-end -->
<!--END:CONFIG_TABLE-->
## Viewing Explain Plan & Fallback Reasons
@@ -41,34 +79,293 @@ Comet provides the following configuration settings.
These settings can be used to determine which parts of the plan are
accelerated by Comet and to see why some parts of the plan could not be
supported by Comet.
<!--BEGIN:CONFIG_TABLE[exec_explain]-->
+<!-- prettier-ignore-start -->
+| Config | Description | Default Value |
+|--------|-------------|---------------|
+| `spark.comet.explain.format` | Choose extended explain output. The default
format of 'verbose' will provide the full query plan annotated with fallback
reasons as well as a summary of how much of the plan was accelerated by Comet.
The format 'fallback' provides a list of fallback reasons instead. | verbose |
+| `spark.comet.explain.native.enabled` | When this setting is enabled, Comet
will provide a tree representation of the native query plan before execution
and again after execution, with metrics. | false |
+| `spark.comet.explain.rules` | When this setting is enabled, Comet will log
all plan transformations performed in physical optimizer rules. Default: false
| false |
+| `spark.comet.explainFallback.enabled` | When this setting is enabled, Comet
will provide logging explaining the reason(s) why a query stage cannot be
executed natively. Set this to false to reduce the amount of logging. | false |
+| `spark.comet.logFallbackReasons.enabled` | When this setting is enabled,
Comet will log warnings for all fallback reasons. It can be overridden by the
environment variable `ENABLE_COMET_LOG_FALLBACK_REASONS`. | false |
+<!-- prettier-ignore-end -->
<!--END:CONFIG_TABLE-->
## Shuffle Configuration Settings
<!--BEGIN:CONFIG_TABLE[shuffle]-->
+<!-- prettier-ignore-start -->
+| Config | Description | Default Value |
+|--------|-------------|---------------|
+| `spark.comet.columnar.shuffle.async.enabled` | Whether to enable
asynchronous shuffle for Arrow-based shuffle. | false |
+| `spark.comet.columnar.shuffle.async.max.thread.num` | Maximum number of
threads on an executor used for Comet async columnar shuffle. This is the upper
bound of total number of shuffle threads per executor. In other words, if the
number of cores * the number of shuffle threads per task
`spark.comet.columnar.shuffle.async.thread.num` is larger than this config.
Comet will use this config as the number of shuffle threads per executor
instead. | 100 |
+| `spark.comet.columnar.shuffle.async.thread.num` | Number of threads used for
Comet async columnar shuffle per shuffle task. Note that more threads means
more memory requirement to buffer shuffle data before flushing to disk. Also,
more threads may not always improve performance, and should be set based on the
number of cores available. | 3 |
+| `spark.comet.columnar.shuffle.batch.size` | Batch size when writing out
sorted spill files on the native side. Note that this should not be larger than
batch size (i.e., `spark.comet.batchSize`). Otherwise it will produce larger
batches than expected in the native operator after shuffle. | 8192 |
+| `spark.comet.exec.shuffle.compression.codec` | The codec of Comet native
shuffle used to compress shuffle data. lz4, zstd, and snappy are supported.
Compression can be disabled by setting spark.shuffle.compress=false. | lz4 |
+| `spark.comet.exec.shuffle.compression.zstd.level` | The compression level to
use when compressing shuffle files with zstd. | 1 |
+| `spark.comet.exec.shuffle.enabled` | Whether to enable Comet native shuffle.
Note that this requires setting `spark.shuffle.manager` to
`org.apache.spark.sql.comet.execution.shuffle.CometShuffleManager`.
`spark.shuffle.manager` must be set before starting the Spark application and
cannot be changed during the application. | true |
+| `spark.comet.exec.shuffle.writeBufferSize` | Size of the write buffer in
bytes used by the native shuffle writer when writing shuffle data to disk.
Larger values may improve write performance by reducing the number of system
calls, but will use more memory. The default is 1MB which provides a good
balance between performance and memory usage. | 1048576b |
+| `spark.comet.native.shuffle.partitioning.hash.enabled` | Whether to enable
hash partitioning for Comet native shuffle. | true |
+| `spark.comet.native.shuffle.partitioning.range.enabled` | Whether to enable
range partitioning for Comet native shuffle. | true |
+| `spark.comet.native.shuffle.partitioning.roundrobin.enabled` | Whether to
enable round robin partitioning for Comet native shuffle. This is disabled by
default because Comet's round-robin produces different partition assignments
than Spark. Spark sorts rows by their binary UnsafeRow representation before
assigning partitions, but Comet uses Arrow format which has a different binary
layout. Instead, Comet implements round-robin as hash partitioning on all
columns, which achieves the sam [...]
+| `spark.comet.native.shuffle.partitioning.roundrobin.maxHashColumns` | The
maximum number of columns to hash for round robin partitioning. When set to 0
(the default), all columns are hashed. When set to a positive value, only the
first N columns are used for hashing, which can improve performance for wide
tables while still providing reasonable distribution. | 0 |
+| `spark.comet.shuffle.preferDictionary.ratio` | The ratio of total values to
distinct values in a string column to decide whether to prefer dictionary
encoding when shuffling the column. If the ratio is higher than this config,
dictionary encoding will be used on shuffling string column. This config is
effective if it is higher than 1.0. Note that this config is only used when
`spark.comet.exec.shuffle.mode` is `jvm`. | 10.0 |
+| `spark.comet.shuffle.sizeInBytesMultiplier` | Comet reports smaller sizes
for shuffle due to using Arrow's columnar memory format and this can result in
Spark choosing a different join strategy due to the estimated size of the
exchange being smaller. Comet will multiple sizeInBytes by this amount to avoid
regressions in join strategy. | 1.0 |
+<!-- prettier-ignore-end -->
<!--END:CONFIG_TABLE-->
## Memory & Tuning Configuration Settings
<!--BEGIN:CONFIG_TABLE[tuning]-->
+<!-- prettier-ignore-start -->
+| Config | Description | Default Value |
+|--------|-------------|---------------|
+| `spark.comet.batchSize` | The columnar batch size, i.e., the maximum number
of rows that a batch can contain. | 8192 |
+| `spark.comet.exec.memoryPool` | The type of memory pool to be used for Comet
native execution when running Spark in off-heap mode. Available pool types are
`greedy_unified` and `fair_unified`. For more information, refer to the [Comet
Tuning Guide](https://datafusion.apache.org/comet/user-guide/tuning.html). |
fair_unified |
+| `spark.comet.exec.memoryPool.fraction` | Fraction of off-heap memory pool
that is available to Comet. Only applies to off-heap mode. For more
information, refer to the [Comet Tuning
Guide](https://datafusion.apache.org/comet/user-guide/tuning.html). | 1.0 |
+| `spark.comet.tracing.enabled` | Enable fine-grained tracing of events and
memory usage. For more information, refer to the [Comet Tracing
Guide](https://datafusion.apache.org/comet/contributor-guide/tracing.html). |
false |
+<!-- prettier-ignore-end -->
<!--END:CONFIG_TABLE-->
## Development & Testing Settings
<!--BEGIN:CONFIG_TABLE[testing]-->
+<!-- prettier-ignore-start -->
+| Config | Description | Default Value |
+|--------|-------------|---------------|
+| `spark.comet.columnar.shuffle.memory.factor` | Fraction of Comet memory to
be allocated per executor process for columnar shuffle when running in on-heap
mode. For more information, refer to the [Comet Tuning
Guide](https://datafusion.apache.org/comet/user-guide/tuning.html). | 1.0 |
+| `spark.comet.convert.csv.enabled` | When enabled, data from Spark
(non-native) CSV v1 and v2 scans will be converted to Arrow format. This is an
experimental feature and has known issues with non-UTC timezones. | false |
+| `spark.comet.convert.json.enabled` | When enabled, data from Spark
(non-native) JSON v1 and v2 scans will be converted to Arrow format. This is an
experimental feature and has known issues with non-UTC timezones. | false |
+| `spark.comet.convert.parquet.enabled` | When enabled, data from Spark
(non-native) Parquet v1 and v2 scans will be converted to Arrow format. This
is an experimental feature and has known issues with non-UTC timezones. | false
|
+| `spark.comet.exec.onHeap.enabled` | Whether to allow Comet to run in on-heap
mode. Required for running Spark SQL tests. It can be overridden by the
environment variable `ENABLE_COMET_ONHEAP`. | false |
+| `spark.comet.exec.onHeap.memoryPool` | The type of memory pool to be used
for Comet native execution when running Spark in on-heap mode. Available pool
types are `greedy`, `fair_spill`, `greedy_task_shared`,
`fair_spill_task_shared`, `greedy_global`, `fair_spill_global`, and
`unbounded`. | greedy_task_shared |
+| `spark.comet.memoryOverhead` | The amount of additional memory to be
allocated per executor process for Comet, in MiB, when running Spark in on-heap
mode. | 1024 MiB |
+| `spark.comet.parquet.write.enabled` | Whether to enable native Parquet write
through Comet. When enabled, Comet will intercept Parquet write operations and
execute them natively. This feature is highly experimental and only partially
implemented. It should not be used in production. | false |
+| `spark.comet.scan.csv.v2.enabled` | Whether to use the native Comet V2 CSV
reader for improved performance. Default: false (uses standard Spark CSV
reader) Experimental: Performance benefits are workload-dependent. | false |
+| `spark.comet.sparkToColumnar.enabled` | Whether to enable Spark to Arrow
columnar conversion. When this is turned on, Comet will convert operators in
`spark.comet.sparkToColumnar.supportedOperatorList` into Arrow columnar format
before processing. This is an experimental feature and has known issues with
non-UTC timezones. | false |
+| `spark.comet.sparkToColumnar.supportedOperatorList` | A comma-separated list
of operators that will be converted to Arrow columnar format when
`spark.comet.sparkToColumnar.enabled` is true. |
Range,InMemoryTableScan,RDDScan |
+| `spark.comet.testing.strict` | Experimental option to enable strict testing,
which will fail tests that could be more comprehensive, such as checking for a
specific fallback reason. It can be overridden by the environment variable
`ENABLE_COMET_STRICT_TESTING`. | false |
+<!-- prettier-ignore-end -->
<!--END:CONFIG_TABLE-->
## Enabling or Disabling Individual Operators
<!--BEGIN:CONFIG_TABLE[enable_exec]-->
+<!-- prettier-ignore-start -->
+| Config | Description | Default Value |
+|--------|-------------|---------------|
+| `spark.comet.exec.aggregate.enabled` | Whether to enable aggregate by
default. | true |
+| `spark.comet.exec.broadcastExchange.enabled` | Whether to enable
broadcastExchange by default. | true |
+| `spark.comet.exec.broadcastHashJoin.enabled` | Whether to enable
broadcastHashJoin by default. | true |
+| `spark.comet.exec.coalesce.enabled` | Whether to enable coalesce by default.
| true |
+| `spark.comet.exec.collectLimit.enabled` | Whether to enable collectLimit by
default. | true |
+| `spark.comet.exec.expand.enabled` | Whether to enable expand by default. |
true |
+| `spark.comet.exec.explode.enabled` | Whether to enable explode by default. |
true |
+| `spark.comet.exec.filter.enabled` | Whether to enable filter by default. |
true |
+| `spark.comet.exec.globalLimit.enabled` | Whether to enable globalLimit by
default. | true |
+| `spark.comet.exec.hashJoin.enabled` | Whether to enable hashJoin by default.
| true |
+| `spark.comet.exec.localLimit.enabled` | Whether to enable localLimit by
default. | true |
+| `spark.comet.exec.localTableScan.enabled` | Whether to enable localTableScan
by default. | false |
+| `spark.comet.exec.project.enabled` | Whether to enable project by default. |
true |
+| `spark.comet.exec.sort.enabled` | Whether to enable sort by default. | true |
+| `spark.comet.exec.sortMergeJoin.enabled` | Whether to enable sortMergeJoin
by default. | true |
+| `spark.comet.exec.sortMergeJoinWithJoinFilter.enabled` | Experimental
support for Sort Merge Join with filter | false |
+| `spark.comet.exec.takeOrderedAndProject.enabled` | Whether to enable
takeOrderedAndProject by default. | true |
+| `spark.comet.exec.union.enabled` | Whether to enable union by default. |
true |
+| `spark.comet.exec.window.enabled` | Whether to enable window by default. |
true |
+<!-- prettier-ignore-end -->
<!--END:CONFIG_TABLE-->
## Enabling or Disabling Individual Scalar Expressions
<!--BEGIN:CONFIG_TABLE[enable_expr]-->
+<!-- prettier-ignore-start -->
+| Config | Description | Default Value |
+|--------|-------------|---------------|
+| `spark.comet.expression.Abs.enabled` | Enable Comet acceleration for `Abs` |
true |
+| `spark.comet.expression.Acos.enabled` | Enable Comet acceleration for `Acos`
| true |
+| `spark.comet.expression.Add.enabled` | Enable Comet acceleration for `Add` |
true |
+| `spark.comet.expression.Alias.enabled` | Enable Comet acceleration for
`Alias` | true |
+| `spark.comet.expression.And.enabled` | Enable Comet acceleration for `And` |
true |
+| `spark.comet.expression.ArrayAppend.enabled` | Enable Comet acceleration for
`ArrayAppend` | true |
+| `spark.comet.expression.ArrayCompact.enabled` | Enable Comet acceleration
for `ArrayCompact` | true |
+| `spark.comet.expression.ArrayContains.enabled` | Enable Comet acceleration
for `ArrayContains` | true |
+| `spark.comet.expression.ArrayDistinct.enabled` | Enable Comet acceleration
for `ArrayDistinct` | true |
+| `spark.comet.expression.ArrayExcept.enabled` | Enable Comet acceleration for
`ArrayExcept` | true |
+| `spark.comet.expression.ArrayFilter.enabled` | Enable Comet acceleration for
`ArrayFilter` | true |
+| `spark.comet.expression.ArrayInsert.enabled` | Enable Comet acceleration for
`ArrayInsert` | true |
+| `spark.comet.expression.ArrayIntersect.enabled` | Enable Comet acceleration
for `ArrayIntersect` | true |
+| `spark.comet.expression.ArrayJoin.enabled` | Enable Comet acceleration for
`ArrayJoin` | true |
+| `spark.comet.expression.ArrayMax.enabled` | Enable Comet acceleration for
`ArrayMax` | true |
+| `spark.comet.expression.ArrayMin.enabled` | Enable Comet acceleration for
`ArrayMin` | true |
+| `spark.comet.expression.ArrayRemove.enabled` | Enable Comet acceleration for
`ArrayRemove` | true |
+| `spark.comet.expression.ArrayRepeat.enabled` | Enable Comet acceleration for
`ArrayRepeat` | true |
+| `spark.comet.expression.ArrayUnion.enabled` | Enable Comet acceleration for
`ArrayUnion` | true |
+| `spark.comet.expression.ArraysOverlap.enabled` | Enable Comet acceleration
for `ArraysOverlap` | true |
+| `spark.comet.expression.Ascii.enabled` | Enable Comet acceleration for
`Ascii` | true |
+| `spark.comet.expression.Asin.enabled` | Enable Comet acceleration for `Asin`
| true |
+| `spark.comet.expression.Atan.enabled` | Enable Comet acceleration for `Atan`
| true |
+| `spark.comet.expression.Atan2.enabled` | Enable Comet acceleration for
`Atan2` | true |
+| `spark.comet.expression.AttributeReference.enabled` | Enable Comet
acceleration for `AttributeReference` | true |
+| `spark.comet.expression.BitLength.enabled` | Enable Comet acceleration for
`BitLength` | true |
+| `spark.comet.expression.BitwiseAnd.enabled` | Enable Comet acceleration for
`BitwiseAnd` | true |
+| `spark.comet.expression.BitwiseCount.enabled` | Enable Comet acceleration
for `BitwiseCount` | true |
+| `spark.comet.expression.BitwiseGet.enabled` | Enable Comet acceleration for
`BitwiseGet` | true |
+| `spark.comet.expression.BitwiseNot.enabled` | Enable Comet acceleration for
`BitwiseNot` | true |
+| `spark.comet.expression.BitwiseOr.enabled` | Enable Comet acceleration for
`BitwiseOr` | true |
+| `spark.comet.expression.BitwiseXor.enabled` | Enable Comet acceleration for
`BitwiseXor` | true |
+| `spark.comet.expression.BloomFilterMightContain.enabled` | Enable Comet
acceleration for `BloomFilterMightContain` | true |
+| `spark.comet.expression.CaseWhen.enabled` | Enable Comet acceleration for
`CaseWhen` | true |
+| `spark.comet.expression.Cast.enabled` | Enable Comet acceleration for `Cast`
| true |
+| `spark.comet.expression.Ceil.enabled` | Enable Comet acceleration for `Ceil`
| true |
+| `spark.comet.expression.CheckOverflow.enabled` | Enable Comet acceleration
for `CheckOverflow` | true |
+| `spark.comet.expression.Chr.enabled` | Enable Comet acceleration for `Chr` |
true |
+| `spark.comet.expression.Coalesce.enabled` | Enable Comet acceleration for
`Coalesce` | true |
+| `spark.comet.expression.Concat.enabled` | Enable Comet acceleration for
`Concat` | true |
+| `spark.comet.expression.ConcatWs.enabled` | Enable Comet acceleration for
`ConcatWs` | true |
+| `spark.comet.expression.Contains.enabled` | Enable Comet acceleration for
`Contains` | true |
+| `spark.comet.expression.Cos.enabled` | Enable Comet acceleration for `Cos` |
true |
+| `spark.comet.expression.Cosh.enabled` | Enable Comet acceleration for `Cosh`
| true |
+| `spark.comet.expression.Cot.enabled` | Enable Comet acceleration for `Cot` |
true |
+| `spark.comet.expression.CreateArray.enabled` | Enable Comet acceleration for
`CreateArray` | true |
+| `spark.comet.expression.CreateNamedStruct.enabled` | Enable Comet
acceleration for `CreateNamedStruct` | true |
+| `spark.comet.expression.DateAdd.enabled` | Enable Comet acceleration for
`DateAdd` | true |
+| `spark.comet.expression.DateDiff.enabled` | Enable Comet acceleration for
`DateDiff` | true |
+| `spark.comet.expression.DateFormatClass.enabled` | Enable Comet acceleration
for `DateFormatClass` | true |
+| `spark.comet.expression.DateSub.enabled` | Enable Comet acceleration for
`DateSub` | true |
+| `spark.comet.expression.DayOfMonth.enabled` | Enable Comet acceleration for
`DayOfMonth` | true |
+| `spark.comet.expression.DayOfWeek.enabled` | Enable Comet acceleration for
`DayOfWeek` | true |
+| `spark.comet.expression.DayOfYear.enabled` | Enable Comet acceleration for
`DayOfYear` | true |
+| `spark.comet.expression.Divide.enabled` | Enable Comet acceleration for
`Divide` | true |
+| `spark.comet.expression.ElementAt.enabled` | Enable Comet acceleration for
`ElementAt` | true |
+| `spark.comet.expression.EndsWith.enabled` | Enable Comet acceleration for
`EndsWith` | true |
+| `spark.comet.expression.EqualNullSafe.enabled` | Enable Comet acceleration
for `EqualNullSafe` | true |
+| `spark.comet.expression.EqualTo.enabled` | Enable Comet acceleration for
`EqualTo` | true |
+| `spark.comet.expression.Exp.enabled` | Enable Comet acceleration for `Exp` |
true |
+| `spark.comet.expression.Expm1.enabled` | Enable Comet acceleration for
`Expm1` | true |
+| `spark.comet.expression.Flatten.enabled` | Enable Comet acceleration for
`Flatten` | true |
+| `spark.comet.expression.Floor.enabled` | Enable Comet acceleration for
`Floor` | true |
+| `spark.comet.expression.FromUnixTime.enabled` | Enable Comet acceleration
for `FromUnixTime` | true |
+| `spark.comet.expression.GetArrayItem.enabled` | Enable Comet acceleration
for `GetArrayItem` | true |
+| `spark.comet.expression.GetArrayStructFields.enabled` | Enable Comet
acceleration for `GetArrayStructFields` | true |
+| `spark.comet.expression.GetMapValue.enabled` | Enable Comet acceleration for
`GetMapValue` | true |
+| `spark.comet.expression.GetStructField.enabled` | Enable Comet acceleration
for `GetStructField` | true |
+| `spark.comet.expression.GreaterThan.enabled` | Enable Comet acceleration for
`GreaterThan` | true |
+| `spark.comet.expression.GreaterThanOrEqual.enabled` | Enable Comet
acceleration for `GreaterThanOrEqual` | true |
+| `spark.comet.expression.Hex.enabled` | Enable Comet acceleration for `Hex` |
true |
+| `spark.comet.expression.Hour.enabled` | Enable Comet acceleration for `Hour`
| true |
+| `spark.comet.expression.If.enabled` | Enable Comet acceleration for `If` |
true |
+| `spark.comet.expression.In.enabled` | Enable Comet acceleration for `In` |
true |
+| `spark.comet.expression.InSet.enabled` | Enable Comet acceleration for
`InSet` | true |
+| `spark.comet.expression.InitCap.enabled` | Enable Comet acceleration for
`InitCap` | true |
+| `spark.comet.expression.IntegralDivide.enabled` | Enable Comet acceleration
for `IntegralDivide` | true |
+| `spark.comet.expression.IsNaN.enabled` | Enable Comet acceleration for
`IsNaN` | true |
+| `spark.comet.expression.IsNotNull.enabled` | Enable Comet acceleration for
`IsNotNull` | true |
+| `spark.comet.expression.IsNull.enabled` | Enable Comet acceleration for
`IsNull` | true |
+| `spark.comet.expression.JsonToStructs.enabled` | Enable Comet acceleration
for `JsonToStructs` | true |
+| `spark.comet.expression.KnownFloatingPointNormalized.enabled` | Enable Comet
acceleration for `KnownFloatingPointNormalized` | true |
+| `spark.comet.expression.LastDay.enabled` | Enable Comet acceleration for
`LastDay` | true |
+| `spark.comet.expression.Left.enabled` | Enable Comet acceleration for `Left`
| true |
+| `spark.comet.expression.Length.enabled` | Enable Comet acceleration for
`Length` | true |
+| `spark.comet.expression.LessThan.enabled` | Enable Comet acceleration for
`LessThan` | true |
+| `spark.comet.expression.LessThanOrEqual.enabled` | Enable Comet acceleration
for `LessThanOrEqual` | true |
+| `spark.comet.expression.Like.enabled` | Enable Comet acceleration for `Like`
| true |
+| `spark.comet.expression.Literal.enabled` | Enable Comet acceleration for
`Literal` | true |
+| `spark.comet.expression.Log.enabled` | Enable Comet acceleration for `Log` |
true |
+| `spark.comet.expression.Log10.enabled` | Enable Comet acceleration for
`Log10` | true |
+| `spark.comet.expression.Log2.enabled` | Enable Comet acceleration for `Log2`
| true |
+| `spark.comet.expression.Lower.enabled` | Enable Comet acceleration for
`Lower` | true |
+| `spark.comet.expression.MakeDecimal.enabled` | Enable Comet acceleration for
`MakeDecimal` | true |
+| `spark.comet.expression.MapEntries.enabled` | Enable Comet acceleration for
`MapEntries` | true |
+| `spark.comet.expression.MapFromArrays.enabled` | Enable Comet acceleration
for `MapFromArrays` | true |
+| `spark.comet.expression.MapKeys.enabled` | Enable Comet acceleration for
`MapKeys` | true |
+| `spark.comet.expression.MapValues.enabled` | Enable Comet acceleration for
`MapValues` | true |
+| `spark.comet.expression.Md5.enabled` | Enable Comet acceleration for `Md5` |
true |
+| `spark.comet.expression.Minute.enabled` | Enable Comet acceleration for
`Minute` | true |
+| `spark.comet.expression.MonotonicallyIncreasingID.enabled` | Enable Comet
acceleration for `MonotonicallyIncreasingID` | true |
+| `spark.comet.expression.Month.enabled` | Enable Comet acceleration for
`Month` | true |
+| `spark.comet.expression.Multiply.enabled` | Enable Comet acceleration for
`Multiply` | true |
+| `spark.comet.expression.Murmur3Hash.enabled` | Enable Comet acceleration for
`Murmur3Hash` | true |
+| `spark.comet.expression.Not.enabled` | Enable Comet acceleration for `Not` |
true |
+| `spark.comet.expression.OctetLength.enabled` | Enable Comet acceleration for
`OctetLength` | true |
+| `spark.comet.expression.Or.enabled` | Enable Comet acceleration for `Or` |
true |
+| `spark.comet.expression.Pow.enabled` | Enable Comet acceleration for `Pow` |
true |
+| `spark.comet.expression.Quarter.enabled` | Enable Comet acceleration for
`Quarter` | true |
+| `spark.comet.expression.RLike.enabled` | Enable Comet acceleration for
`RLike` | true |
+| `spark.comet.expression.Rand.enabled` | Enable Comet acceleration for `Rand`
| true |
+| `spark.comet.expression.Randn.enabled` | Enable Comet acceleration for
`Randn` | true |
+| `spark.comet.expression.RegExpReplace.enabled` | Enable Comet acceleration
for `RegExpReplace` | true |
+| `spark.comet.expression.Remainder.enabled` | Enable Comet acceleration for
`Remainder` | true |
+| `spark.comet.expression.Reverse.enabled` | Enable Comet acceleration for
`Reverse` | true |
+| `spark.comet.expression.Round.enabled` | Enable Comet acceleration for
`Round` | true |
+| `spark.comet.expression.ScalarSubquery.enabled` | Enable Comet acceleration
for `ScalarSubquery` | true |
+| `spark.comet.expression.Second.enabled` | Enable Comet acceleration for
`Second` | true |
+| `spark.comet.expression.Sha1.enabled` | Enable Comet acceleration for `Sha1`
| true |
+| `spark.comet.expression.Sha2.enabled` | Enable Comet acceleration for `Sha2`
| true |
+| `spark.comet.expression.ShiftLeft.enabled` | Enable Comet acceleration for
`ShiftLeft` | true |
+| `spark.comet.expression.ShiftRight.enabled` | Enable Comet acceleration for
`ShiftRight` | true |
+| `spark.comet.expression.Signum.enabled` | Enable Comet acceleration for
`Signum` | true |
+| `spark.comet.expression.Sin.enabled` | Enable Comet acceleration for `Sin` |
true |
+| `spark.comet.expression.Sinh.enabled` | Enable Comet acceleration for `Sinh`
| true |
+| `spark.comet.expression.Size.enabled` | Enable Comet acceleration for `Size`
| true |
+| `spark.comet.expression.SortOrder.enabled` | Enable Comet acceleration for
`SortOrder` | true |
+| `spark.comet.expression.SparkPartitionID.enabled` | Enable Comet
acceleration for `SparkPartitionID` | true |
+| `spark.comet.expression.Sqrt.enabled` | Enable Comet acceleration for `Sqrt`
| true |
+| `spark.comet.expression.StartsWith.enabled` | Enable Comet acceleration for
`StartsWith` | true |
+| `spark.comet.expression.StaticInvoke.enabled` | Enable Comet acceleration
for `StaticInvoke` | true |
+| `spark.comet.expression.StringInstr.enabled` | Enable Comet acceleration for
`StringInstr` | true |
+| `spark.comet.expression.StringLPad.enabled` | Enable Comet acceleration for
`StringLPad` | true |
+| `spark.comet.expression.StringRPad.enabled` | Enable Comet acceleration for
`StringRPad` | true |
+| `spark.comet.expression.StringRepeat.enabled` | Enable Comet acceleration
for `StringRepeat` | true |
+| `spark.comet.expression.StringReplace.enabled` | Enable Comet acceleration
for `StringReplace` | true |
+| `spark.comet.expression.StringSpace.enabled` | Enable Comet acceleration for
`StringSpace` | true |
+| `spark.comet.expression.StringTranslate.enabled` | Enable Comet acceleration
for `StringTranslate` | true |
+| `spark.comet.expression.StringTrim.enabled` | Enable Comet acceleration for
`StringTrim` | true |
+| `spark.comet.expression.StringTrimBoth.enabled` | Enable Comet acceleration
for `StringTrimBoth` | true |
+| `spark.comet.expression.StringTrimLeft.enabled` | Enable Comet acceleration
for `StringTrimLeft` | true |
+| `spark.comet.expression.StringTrimRight.enabled` | Enable Comet acceleration
for `StringTrimRight` | true |
+| `spark.comet.expression.StructsToJson.enabled` | Enable Comet acceleration
for `StructsToJson` | true |
+| `spark.comet.expression.Substring.enabled` | Enable Comet acceleration for
`Substring` | true |
+| `spark.comet.expression.Subtract.enabled` | Enable Comet acceleration for
`Subtract` | true |
+| `spark.comet.expression.Tan.enabled` | Enable Comet acceleration for `Tan` |
true |
+| `spark.comet.expression.Tanh.enabled` | Enable Comet acceleration for `Tanh`
| true |
+| `spark.comet.expression.TruncDate.enabled` | Enable Comet acceleration for
`TruncDate` | true |
+| `spark.comet.expression.TruncTimestamp.enabled` | Enable Comet acceleration
for `TruncTimestamp` | true |
+| `spark.comet.expression.UnaryMinus.enabled` | Enable Comet acceleration for
`UnaryMinus` | true |
+| `spark.comet.expression.Unhex.enabled` | Enable Comet acceleration for
`Unhex` | true |
+| `spark.comet.expression.UnixDate.enabled` | Enable Comet acceleration for
`UnixDate` | true |
+| `spark.comet.expression.UnixTimestamp.enabled` | Enable Comet acceleration
for `UnixTimestamp` | true |
+| `spark.comet.expression.UnscaledValue.enabled` | Enable Comet acceleration
for `UnscaledValue` | true |
+| `spark.comet.expression.Upper.enabled` | Enable Comet acceleration for
`Upper` | true |
+| `spark.comet.expression.WeekDay.enabled` | Enable Comet acceleration for
`WeekDay` | true |
+| `spark.comet.expression.WeekOfYear.enabled` | Enable Comet acceleration for
`WeekOfYear` | true |
+| `spark.comet.expression.XxHash64.enabled` | Enable Comet acceleration for
`XxHash64` | true |
+| `spark.comet.expression.Year.enabled` | Enable Comet acceleration for `Year`
| true |
+<!-- prettier-ignore-end -->
<!--END:CONFIG_TABLE-->
## Enabling or Disabling Individual Aggregate Expressions
<!--BEGIN:CONFIG_TABLE[enable_agg_expr]-->
+<!-- prettier-ignore-start -->
+| Config | Description | Default Value |
+|--------|-------------|---------------|
+| `spark.comet.expression.Average.enabled` | Enable Comet acceleration for
`Average` | true |
+| `spark.comet.expression.BitAndAgg.enabled` | Enable Comet acceleration for
`BitAndAgg` | true |
+| `spark.comet.expression.BitOrAgg.enabled` | Enable Comet acceleration for
`BitOrAgg` | true |
+| `spark.comet.expression.BitXorAgg.enabled` | Enable Comet acceleration for
`BitXorAgg` | true |
+| `spark.comet.expression.BloomFilterAggregate.enabled` | Enable Comet
acceleration for `BloomFilterAggregate` | true |
+| `spark.comet.expression.Corr.enabled` | Enable Comet acceleration for `Corr`
| true |
+| `spark.comet.expression.Count.enabled` | Enable Comet acceleration for
`Count` | true |
+| `spark.comet.expression.CovPopulation.enabled` | Enable Comet acceleration
for `CovPopulation` | true |
+| `spark.comet.expression.CovSample.enabled` | Enable Comet acceleration for
`CovSample` | true |
+| `spark.comet.expression.First.enabled` | Enable Comet acceleration for
`First` | true |
+| `spark.comet.expression.Last.enabled` | Enable Comet acceleration for `Last`
| true |
+| `spark.comet.expression.Max.enabled` | Enable Comet acceleration for `Max` |
true |
+| `spark.comet.expression.Min.enabled` | Enable Comet acceleration for `Min` |
true |
+| `spark.comet.expression.StddevPop.enabled` | Enable Comet acceleration for
`StddevPop` | true |
+| `spark.comet.expression.StddevSamp.enabled` | Enable Comet acceleration for
`StddevSamp` | true |
+| `spark.comet.expression.Sum.enabled` | Enable Comet acceleration for `Sum` |
true |
+| `spark.comet.expression.VariancePop.enabled` | Enable Comet acceleration for
`VariancePop` | true |
+| `spark.comet.expression.VarianceSamp.enabled` | Enable Comet acceleration
for `VarianceSamp` | true |
+<!-- prettier-ignore-end -->
<!--END:CONFIG_TABLE-->
diff --git a/fuzz-testing/pom.xml b/fuzz-testing/pom.xml
index 35beddd2a..ba6d32278 100644
--- a/fuzz-testing/pom.xml
+++ b/fuzz-testing/pom.xml
@@ -25,7 +25,7 @@ under the License.
<parent>
<groupId>org.apache.datafusion</groupId>
<artifactId>comet-parent-spark${spark.version.short}_${scala.binary.version}</artifactId>
- <version>0.13.0-SNAPSHOT</version>
+ <version>0.13.0</version>
<relativePath>../pom.xml</relativePath>
</parent>
diff --git a/native/Cargo.lock b/native/Cargo.lock
index 2e53b3c27..c7fd984a3 100644
--- a/native/Cargo.lock
+++ b/native/Cargo.lock
@@ -601,9 +601,9 @@ dependencies = [
[[package]]
name = "aws-lc-rs"
-version = "1.15.3"
+version = "1.15.4"
source = "registry+https://github.com/rust-lang/crates.io-index";
-checksum = "e84ce723ab67259cfeb9877c6a639ee9eb7a27b28123abd71db7f0d5d0cc9d86"
+checksum = "7b7b6141e96a8c160799cc2d5adecd5cbbe5054cb8c7c4af53da0f83bb7ad256"
dependencies = [
"aws-lc-sys",
"zeroize",
@@ -611,9 +611,9 @@ dependencies = [
[[package]]
name = "aws-lc-sys"
-version = "0.36.0"
+version = "0.37.0"
source = "registry+https://github.com/rust-lang/crates.io-index";
-checksum = "43a442ece363113bd4bd4c8b18977a7798dd4d3c3383f34fb61936960e8f4ad8"
+checksum = "5c34dda4df7017c8db52132f0f8a2e0f8161649d15723ed63fc00c82d0f2081a"
dependencies = [
"cc",
"cmake",
@@ -1242,9 +1242,9 @@ checksum =
"37b2a672a2cb129a2e41c10b1224bb368f9f37a2b16b612598138befd7b37eb5"
[[package]]
name = "cc"
-version = "1.2.53"
+version = "1.2.54"
source = "registry+https://github.com/rust-lang/crates.io-index";
-checksum = "755d2fce177175ffca841e9a06afdb2c4ab0f593d53b4dee48147dfaade85932"
+checksum = "6354c81bbfd62d9cfa9cb3c773c2b7b2a3a482d569de977fd0e961f6e7c00583"
dependencies = [
"find-msvc-tools",
"jobserver",
@@ -3711,9 +3711,9 @@ dependencies = [
[[package]]
name = "libm"
-version = "0.2.15"
+version = "0.2.16"
source = "registry+https://github.com/rust-lang/crates.io-index";
-checksum = "f9fbbcab51052fe104eb5e5d351cf728d30a5be1fe14d9be8a3b097481fb97de"
+checksum = "b6d2cec3eae94f9f509c767b45932f1ada8350c4bdb85af2fcab4a3c14807981"
[[package]]
name = "libmimalloc-sys"
@@ -3892,9 +3892,9 @@ checksum =
"dce6dd36094cac388f119d2e9dc82dc730ef91c32a6222170d630e5414b956e6"
[[package]]
name = "moka"
-version = "0.12.12"
+version = "0.12.13"
source = "registry+https://github.com/rust-lang/crates.io-index";
-checksum = "a3dec6bd31b08944e08b58fd99373893a6c17054d6f3ea5006cc894f4f4eee2a"
+checksum = "b4ac832c50ced444ef6be0767a008b02c106a909ba79d1d830501e94b96f6b7e"
dependencies = [
"async-lock",
"crossbeam-channel",
@@ -3979,9 +3979,9 @@ dependencies = [
[[package]]
name = "num-conv"
-version = "0.1.0"
+version = "0.2.0"
source = "registry+https://github.com/rust-lang/crates.io-index";
-checksum = "51d515d32fb182ee37cda2ccdcb92950d6a3c2893aa280e540671c2cd0f3b1d9"
+checksum = "cf97ec579c3c42f953ef76dbf8d55ac91fb219dde70e49aa4a6b7d74e9919050"
[[package]]
name = "num-format"
@@ -4141,9 +4141,9 @@ dependencies = [
[[package]]
name = "openssl-probe"
-version = "0.2.0"
+version = "0.2.1"
source = "registry+https://github.com/rust-lang/crates.io-index";
-checksum = "9f50d9b3dabb09ecd771ad0aa242ca6894994c130308ca3d7684634df8037391"
+checksum = "7c87def4c32ab89d880effc9e097653c8da5d6ef28e6b539d313baaacfbafcbe"
[[package]]
name = "ordered-float"
@@ -4514,9 +4514,9 @@ dependencies = [
[[package]]
name = "proc-macro2"
-version = "1.0.105"
+version = "1.0.106"
source = "registry+https://github.com/rust-lang/crates.io-index";
-checksum = "535d180e0ecab6268a3e718bb9fd44db66bbbc256257165fc699dadf70d16fe7"
+checksum = "8fd00f0bb2e90d81d1044c2b32617f68fcb9fa3bb7640c23e9c748e53fb30934"
dependencies = [
"unicode-ident",
]
@@ -4708,9 +4708,9 @@ dependencies = [
[[package]]
name = "quote"
-version = "1.0.43"
+version = "1.0.44"
source = "registry+https://github.com/rust-lang/crates.io-index";
-checksum = "dc74d9a594b72ae6656596548f56f667211f8a97b3d4c3d467150794690dc40a"
+checksum = "21b2ebcf727b7760c461f091f9f0f539b77b8e87f2fd88131e7f1b433b3cece4"
dependencies = [
"proc-macro2",
]
@@ -5492,9 +5492,9 @@ checksum =
"1b6b67fb9a61334225b5b790716f609cd58395f895b3fe8b328786812a40bc3b"
[[package]]
name = "socket2"
-version = "0.6.1"
+version = "0.6.2"
source = "registry+https://github.com/rust-lang/crates.io-index";
-checksum = "17129e116933cf371d018bb80ae557e889637989d8638274fb25622827b03881"
+checksum = "86f4aa3ad99f2088c990dfa82d367e19cb29268ed67c574d10d0a4bfe71f07e0"
dependencies = [
"libc",
"windows-sys 0.60.2",
@@ -5759,9 +5759,9 @@ dependencies = [
[[package]]
name = "time"
-version = "0.3.45"
+version = "0.3.46"
source = "registry+https://github.com/rust-lang/crates.io-index";
-checksum = "f9e442fc33d7fdb45aa9bfeb312c095964abdf596f7567261062b2a7107aaabd"
+checksum = "9da98b7d9b7dad93488a84b8248efc35352b0b2657397d4167e7ad67e5d535e5"
dependencies = [
"deranged",
"itoa",
@@ -5774,15 +5774,15 @@ dependencies = [
[[package]]
name = "time-core"
-version = "0.1.7"
+version = "0.1.8"
source = "registry+https://github.com/rust-lang/crates.io-index";
-checksum = "8b36ee98fd31ec7426d599183e8fe26932a8dc1fb76ddb6214d05493377d34ca"
+checksum = "7694e1cfe791f8d31026952abf09c69ca6f6fa4e1a1229e18988f06a04a12dca"
[[package]]
name = "time-macros"
-version = "0.2.25"
+version = "0.2.26"
source = "registry+https://github.com/rust-lang/crates.io-index";
-checksum = "71e552d1249bf61ac2a52db88179fd0673def1e1ad8243a00d9ec9ed71fee3dd"
+checksum = "78cc610bac2dcee56805c99642447d4c5dbde4d01f752ffea0199aee1f601dc4"
dependencies = [
"num-conv",
"time-core",
@@ -6110,9 +6110,9 @@ checksum =
"b6c140620e7ffbb22c2dee59cafe6084a59b5ffc27a8859a5f0d494b5d52b6be"
[[package]]
name = "uuid"
-version = "1.19.0"
+version = "1.20.0"
source = "registry+https://github.com/rust-lang/crates.io-index";
-checksum = "e2e054861b4bd027cd373e18e8d8d8e6548085000e41290d95ce0c373a654b4a"
+checksum = "ee48d38b119b0cd71fe4141b30f5ba9c7c5d9f4e7a3a8b4a674e4b6ef789976f"
dependencies = [
"getrandom 0.3.4",
"js-sys",
@@ -6676,18 +6676,18 @@ dependencies = [
[[package]]
name = "zerocopy"
-version = "0.8.33"
+version = "0.8.34"
source = "registry+https://github.com/rust-lang/crates.io-index";
-checksum = "668f5168d10b9ee831de31933dc111a459c97ec93225beb307aed970d1372dfd"
+checksum = "71ddd76bcebeed25db614f82bf31a9f4222d3fbba300e6fb6c00afa26cbd4d9d"
dependencies = [
"zerocopy-derive",
]
[[package]]
name = "zerocopy-derive"
-version = "0.8.33"
+version = "0.8.34"
source = "registry+https://github.com/rust-lang/crates.io-index";
-checksum = "2c7962b26b0a8685668b671ee4b54d007a67d4eaf05fda79ac0ecf41e32270f1"
+checksum = "d8187381b52e32220d50b255276aa16a084ec0a9017a0ca2152a1f55c539758d"
dependencies = [
"proc-macro2",
"quote",
@@ -6762,9 +6762,9 @@ checksum =
"40990edd51aae2c2b6907af74ffb635029d5788228222c4bb811e9351c0caad3"
[[package]]
name = "zmij"
-version = "1.0.16"
+version = "1.0.17"
source = "registry+https://github.com/rust-lang/crates.io-index";
-checksum = "dfcd145825aace48cff44a8844de64bf75feec3080e0aa5cdbde72961ae51a65"
+checksum = "02aae0f83f69aafc94776e879363e9771d7ecbffe2c7fbb6c14c5e00dfe88439"
[[package]]
name = "zstd"
diff --git a/pom.xml b/pom.xml
index ab42aa773..2d9df9852 100644
--- a/pom.xml
+++ b/pom.xml
@@ -30,7 +30,7 @@ under the License.
</parent>
<groupId>org.apache.datafusion</groupId>
<artifactId>comet-parent-spark${spark.version.short}_${scala.binary.version}</artifactId>
- <version>0.13.0-SNAPSHOT</version>
+ <version>0.13.0</version>
<packaging>pom</packaging>
<name>Comet Project Parent POM</name>
diff --git a/spark-integration/pom.xml b/spark-integration/pom.xml
index c1da41721..946387edf 100644
--- a/spark-integration/pom.xml
+++ b/spark-integration/pom.xml
@@ -26,7 +26,7 @@ under the License.
<parent>
<groupId>org.apache.datafusion</groupId>
<artifactId>comet-parent-spark${spark.version.short}_${scala.binary.version}</artifactId>
- <version>0.13.0-SNAPSHOT</version>
+ <version>0.13.0</version>
<relativePath>../pom.xml</relativePath>
</parent>
diff --git a/spark/pom.xml b/spark/pom.xml
index a113e145f..27373042a 100644
--- a/spark/pom.xml
+++ b/spark/pom.xml
@@ -26,7 +26,7 @@ under the License.
<parent>
<groupId>org.apache.datafusion</groupId>
<artifactId>comet-parent-spark${spark.version.short}_${scala.binary.version}</artifactId>
- <version>0.13.0-SNAPSHOT</version>
+ <version>0.13.0</version>
<relativePath>../pom.xml</relativePath>
</parent>
@@ -256,6 +256,34 @@ under the License.
</dependency>
</dependencies>
</profile>
+ <profile>
+ <id>generate-docs</id>
+ <build>
+ <plugins>
+ <plugin>
+ <groupId>org.codehaus.mojo</groupId>
+ <artifactId>exec-maven-plugin</artifactId>
+ <version>${exec-maven-plugin.version}</version>
+ <executions>
+ <execution>
+ <id>generate-user-guide-reference-docs</id>
+ <phase>package</phase>
+ <goals>
+ <goal>java</goal>
+ </goals>
+ <configuration>
+ <mainClass>org.apache.comet.GenerateDocs</mainClass>
+ <arguments>
+
<argument>${project.parent.basedir}/docs/source/user-guide/latest/</argument>
+ </arguments>
+ <classpathScope>compile</classpathScope>
+ </configuration>
+ </execution>
+ </executions>
+ </plugin>
+ </plugins>
+ </build>
+ </profile>
</profiles>
<build>
---------------------------------------------------------------------
To unsubscribe, e-mail: [email protected]
For additional commands, e-mail: [email protected]
