AngersZhuuuu commented on a change in pull request #31522:
URL: https://github.com/apache/spark/pull/31522#discussion_r673036140
##########
File path:
sql/core/src/main/scala/org/apache/spark/sql/execution/datasources/FileFormatDataWriter.scala
##########
@@ -91,11 +91,14 @@ abstract class FileFormatDataWriter(
* driver too and used to e.g. update the metrics in UI.
*/
override def commit(): WriteTaskResult = {
- releaseResources()
+ val (taskCommitMessage, taskCommitTime) = Utils.timeTakenMs {
+ releaseResources()
Review comment:
yea, fixed
##########
File path:
sql/core/src/main/scala/org/apache/spark/sql/execution/datasources/BasicWriteStatsTracker.scala
##########
@@ -221,16 +226,26 @@ object BasicWriteJobStatsTracker {
private val NUM_OUTPUT_BYTES_KEY = "numOutputBytes"
private val NUM_OUTPUT_ROWS_KEY = "numOutputRows"
private val NUM_PARTS_KEY = "numParts"
+ val TASK_COMMIT_DURATION = "taskCommitDuration"
+ private val JOB_COMMIT_DURATION = "jobCommitDuration"
/** XAttr key of the data length header added in HADOOP-17414. */
val FILE_LENGTH_XATTR = "header.x-hadoop-s3a-magic-data-length"
- def metrics: Map[String, SQLMetric] = {
+ def driverSideMetrics: Map[String, SQLMetric] = {
val sparkContext = SparkContext.getActive.get
Map(
NUM_FILES_KEY -> SQLMetrics.createMetric(sparkContext, "number of
written files"),
NUM_OUTPUT_BYTES_KEY -> SQLMetrics.createSizeMetric(sparkContext,
"written output"),
NUM_OUTPUT_ROWS_KEY -> SQLMetrics.createMetric(sparkContext, "number of
output rows"),
- NUM_PARTS_KEY -> SQLMetrics.createMetric(sparkContext, "number of
dynamic part")
+ NUM_PARTS_KEY -> SQLMetrics.createMetric(sparkContext, "number of
dynamic part"),
+ JOB_COMMIT_DURATION ->
+ SQLMetrics.createTimingMetric(sparkContext, "duration of job commit")
)
}
+
+ def taskCommitTimeMetric: Map[String, SQLMetric] = {
Review comment:
Done
--
This is an automated message from the Apache Git Service.
To respond to the message, please log on to GitHub and use the
URL above to go to the specific comment.
To unsubscribe, e-mail: [email protected]
For queries about this service, please contact Infrastructure at:
[email protected]
---------------------------------------------------------------------
To unsubscribe, e-mail: [email protected]
For additional commands, e-mail: [email protected]
