This is an automated email from the ASF dual-hosted git repository.
agrove pushed a commit to branch main
in repository https://gitbox.apache.org/repos/asf/datafusion-comet.git
The following commit(s) were added to refs/heads/main by this push:
new 3d1dbb03 feat: Add config option to enable converting CSV to columnar
(#871)
3d1dbb03 is described below
commit 3d1dbb03eff2ead2f863371b6d93c9073f3619b4
Author: Andy Grove <[email protected]>
AuthorDate: Tue Aug 27 08:38:29 2024 -0600
feat: Add config option to enable converting CSV to columnar (#871)
* CSV
* save progress
* test passes
* Revert additional json test
* fix path
* revert a change
* update docs
* scalastyle
---
common/src/main/scala/org/apache/comet/CometConf.scala | 9 +++++++++
docs/source/user-guide/configs.md | 1 +
docs/source/user-guide/datasources.md | 5 +++++
.../org/apache/comet/CometSparkSessionExtensions.scala | 4 ++++
spark/src/test/resources/test-data/csv-test-1.csv | 3 +++
.../scala/org/apache/comet/exec/CometExecSuite.scala | 16 ++++++++++++++++
6 files changed, 38 insertions(+)
diff --git a/common/src/main/scala/org/apache/comet/CometConf.scala
b/common/src/main/scala/org/apache/comet/CometConf.scala
index ee429b80..b02f526e 100644
--- a/common/src/main/scala/org/apache/comet/CometConf.scala
+++ b/common/src/main/scala/org/apache/comet/CometConf.scala
@@ -92,6 +92,15 @@ object CometConf extends ShimCometConf {
.booleanConf
.createWithDefault(false)
+ val COMET_CONVERT_FROM_CSV_ENABLED: ConfigEntry[Boolean] =
+ conf("spark.comet.convert.csv.enabled")
+ .doc(
+ "When enabled, data from Spark (non-native) CSV v1 and v2 scans will
be converted to " +
+ "Arrow format. Note that to enable native vectorized execution, both
this config and " +
+ "'spark.comet.exec.enabled' need to be enabled.")
+ .booleanConf
+ .createWithDefault(false)
+
val COMET_EXEC_ENABLED: ConfigEntry[Boolean] =
conf(s"$COMET_EXEC_CONFIG_PREFIX.enabled")
.doc(
"Whether to enable Comet native vectorized execution for Spark. This
controls whether " +
diff --git a/docs/source/user-guide/configs.md
b/docs/source/user-guide/configs.md
index d23e4c71..0679bacb 100644
--- a/docs/source/user-guide/configs.md
+++ b/docs/source/user-guide/configs.md
@@ -30,6 +30,7 @@ Comet provides the following configuration settings.
| spark.comet.columnar.shuffle.async.max.thread.num | Maximum number of
threads on an executor used for Comet async columnar shuffle. By default, this
config is 100. 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. By default, this config is 3.
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.memory.factor | Fraction of Comet memory to be
allocated per executor process for Comet shuffle. Comet memory size is
specified by `spark.comet.memoryOverhead` or calculated by
`spark.comet.memory.overhead.factor` * `spark.executor.memory`. By default,
this config is 1.0. | 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. Note that to enable
native vectorized execution, both this config and 'spark.comet.exec.enabled'
need to be enabled. | false |
| spark.comet.convert.json.enabled | When enabled, data from Spark
(non-native) JSON v1 and v2 scans will be converted to Arrow format. Note that
to enable native vectorized execution, both this config and
'spark.comet.exec.enabled' need to be enabled. | false |
| spark.comet.convert.parquet.enabled | When enabled, data from Spark
(non-native) Parquet v1 and v2 scans will be converted to Arrow format. Note
that to enable native vectorized execution, both this config and
'spark.comet.exec.enabled' need to be enabled. | false |
| spark.comet.debug.enabled | Whether to enable debug mode for Comet. By
default, this config is false. 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 |
diff --git a/docs/source/user-guide/datasources.md
b/docs/source/user-guide/datasources.md
index 92c13f67..9607ba60 100644
--- a/docs/source/user-guide/datasources.md
+++ b/docs/source/user-guide/datasources.md
@@ -26,6 +26,11 @@ in the schema are supported. When this option is not
enabled, the scan will fall
enabling `spark.comet.convert.parquet.enabled` will immediately convert the
data into Arrow format, allowing native
execution to happen after that, but the process may not be efficient.
+## CSV
+
+Comet does not provide native CSV scan, but when
`spark.comet.convert.csv.enabled` is enabled, data is immediately
+converted into Arrow format, allowing native execution to happen after that.
+
## JSON
Comet does not provide native JSON scan, but when
`spark.comet.convert.json.enabled` is enabled, data is immediately
diff --git
a/spark/src/main/scala/org/apache/comet/CometSparkSessionExtensions.scala
b/spark/src/main/scala/org/apache/comet/CometSparkSessionExtensions.scala
index 2b2c0ebe..268264a5 100644
--- a/spark/src/main/scala/org/apache/comet/CometSparkSessionExtensions.scala
+++ b/spark/src/main/scala/org/apache/comet/CometSparkSessionExtensions.scala
@@ -35,9 +35,11 @@ import org.apache.spark.sql.execution._
import org.apache.spark.sql.execution.adaptive.{AQEShuffleReadExec,
BroadcastQueryStageExec, ShuffleQueryStageExec}
import org.apache.spark.sql.execution.aggregate.{BaseAggregateExec,
HashAggregateExec, ObjectHashAggregateExec}
import org.apache.spark.sql.execution.datasources._
+import org.apache.spark.sql.execution.datasources.csv.CSVFileFormat
import org.apache.spark.sql.execution.datasources.json.JsonFileFormat
import org.apache.spark.sql.execution.datasources.parquet.ParquetFileFormat
import org.apache.spark.sql.execution.datasources.v2.BatchScanExec
+import org.apache.spark.sql.execution.datasources.v2.csv.CSVScan
import org.apache.spark.sql.execution.datasources.v2.json.JsonScan
import org.apache.spark.sql.execution.datasources.v2.parquet.ParquetScan
import org.apache.spark.sql.execution.exchange.{BroadcastExchangeExec,
ReusedExchangeExec, ShuffleExchangeExec}
@@ -1111,6 +1113,7 @@ object CometSparkSessionExtensions extends Logging {
// Convert Spark DS v1 scan to Arrow format
case scan: FileSourceScanExec =>
scan.relation.fileFormat match {
+ case _: CSVFileFormat =>
CometConf.COMET_CONVERT_FROM_CSV_ENABLED.get(conf)
case _: JsonFileFormat =>
CometConf.COMET_CONVERT_FROM_JSON_ENABLED.get(conf)
case _: ParquetFileFormat =>
CometConf.COMET_CONVERT_FROM_PARQUET_ENABLED.get(conf)
case _ => isSparkToArrowEnabled(conf, op)
@@ -1118,6 +1121,7 @@ object CometSparkSessionExtensions extends Logging {
// Convert Spark DS v2 scan to Arrow format
case scan: BatchScanExec =>
scan.scan match {
+ case _: CSVScan =>
CometConf.COMET_CONVERT_FROM_CSV_ENABLED.get(conf)
case _: JsonScan =>
CometConf.COMET_CONVERT_FROM_JSON_ENABLED.get(conf)
case _: ParquetScan =>
CometConf.COMET_CONVERT_FROM_PARQUET_ENABLED.get(conf)
case _ => isSparkToArrowEnabled(conf, op)
diff --git a/spark/src/test/resources/test-data/csv-test-1.csv
b/spark/src/test/resources/test-data/csv-test-1.csv
new file mode 100644
index 00000000..c919cbd5
--- /dev/null
+++ b/spark/src/test/resources/test-data/csv-test-1.csv
@@ -0,0 +1,3 @@
+1,2,3
+4,5,6
+7,0,8
\ No newline at end of file
diff --git a/spark/src/test/scala/org/apache/comet/exec/CometExecSuite.scala
b/spark/src/test/scala/org/apache/comet/exec/CometExecSuite.scala
index b7839abd..bfddd74d 100644
--- a/spark/src/test/scala/org/apache/comet/exec/CometExecSuite.scala
+++ b/spark/src/test/scala/org/apache/comet/exec/CometExecSuite.scala
@@ -1658,6 +1658,22 @@ class CometExecSuite extends CometTestBase {
})
}
+ test("read CSV file") {
+ Seq("", "csv").foreach { v1List =>
+ withSQLConf(
+ SQLConf.USE_V1_SOURCE_LIST.key -> v1List,
+ CometConf.COMET_EXPLAIN_FALLBACK_ENABLED.key -> "true",
+ CometConf.COMET_CONVERT_FROM_CSV_ENABLED.key -> "true") {
+ spark.read
+ .csv("src/test/resources/test-data/csv-test-1.csv")
+ .createOrReplaceTempView("tbl")
+ // use a projection with an expression otherwise we end up with
+ // just the file scan
+ checkSparkAnswerAndOperator("SELECT cast(_c0 as int), _c1, _c2 FROM
tbl")
+ }
+ }
+ }
+
test("read JSON file") {
Seq("", "json").foreach { v1List =>
withSQLConf(
---------------------------------------------------------------------
To unsubscribe, e-mail: [email protected]
For additional commands, e-mail: [email protected]
