Skip to content
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.

Sign up for GitHub

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

Jump to bottom

Use BasicColumnarWriteTaskStats instead of BasicWriteTaskStats #1009

Closed
wants to merge 1 commit into from
Closed

Use BasicColumnarWriteTaskStats instead of BasicWriteTaskStats #1009

Changes from all commits
Commits
Show all changes
1 commit
Select commit
File filter

Filter by extension

Filter by extension
Conversations
Failed to load comments.
Loading
Jump to
Jump to file
Failed to load files.
Loading
Diff view
Diff view
20 changes: 16 additions & 4 deletions sql-plugin/src/main/scala/org/apache/spark/sql/rapids/BasicColumnarWriteStatsTracker.scala
View file
Open in desktop
Original file line number Diff line number Diff line change
Expand Up @@ -24,11 +24,23 @@ import org.apache.hadoop.fs.Path
import org.apache.spark.{SparkContext, TaskContext}
import org.apache.spark.internal.Logging
import org.apache.spark.sql.execution.SQLExecution
import org.apache.spark.sql.execution.datasources.{BasicWriteTaskStats, WriteTaskStats}
import org.apache.spark.sql.execution.datasources.WriteTaskStats
import org.apache.spark.sql.execution.metric.{SQLMetric, SQLMetrics}
import org.apache.spark.sql.vectorized.ColumnarBatch
import org.apache.spark.util.SerializableConfiguration

/**
* Simple metrics collected during an instance of [[GpuFileFormatDataWriter]].
* These were first introduced in https://github.com/apache/spark/pull/18159 (SPARK-20703).
*/
case class BasicColumnarWriteTaskStats(
numPartitions: Int,
numFiles: Int,
numBytes: Long,
numRows: Long)
extends WriteTaskStats


/**
* Simple metrics collected during an instance of [[GpuFileFormatDataWriter]].
* This is the columnar version of
Expand Down Expand Up @@ -104,15 +116,15 @@ class BasicColumnarWriteTaskStatsTracker(hadoopConf: Configuration)
"This could be due to the output format not writing empty files, " +
"or files being not immediately visible in the filesystem.")
}
BasicWriteTaskStats(numPartitions, numFiles, numBytes, numRows)
BasicColumnarWriteTaskStats(numPartitions, numFiles, numBytes, numRows)
}
}


/**
* Simple [[ColumnarWriteJobStatsTracker]] implementation that's serializable,
* capable ofinstantiating [[BasicColumnarWriteTaskStatsTracker]] on executors and processing the
* `BasicWriteTaskStats` they produce by aggregating the metrics and posting them
* `BasicColumnarWriteTaskStats` they produce by aggregating the metrics and posting them
* as DriverMetricUpdates.
*/
class BasicColumnarWriteJobStatsTracker(
Expand All @@ -131,7 +143,7 @@ class BasicColumnarWriteJobStatsTracker(
var totalNumBytes: Long = 0L
var totalNumOutput: Long = 0L

val basicStats = stats.map(_.asInstanceOf[BasicWriteTaskStats])
val basicStats = stats.map(_.asInstanceOf[BasicColumnarWriteTaskStats])

basicStats.foreach { summary =>
numPartitions += summary.numPartitions
Expand Down