Github user HeartSaVioR commented on a diff in the pull request: https://github.com/apache/spark/pull/21622#discussion_r200554917 --- Diff: sql/core/src/main/scala/org/apache/spark/sql/execution/streaming/MetricsReporter.scala --- @@ -39,6 +42,23 @@ class MetricsReporter( registerGauge("processingRate-total", _.processedRowsPerSecond, 0.0) registerGauge("latency", _.durationMs.get("triggerExecution").longValue(), 0L) + private val timestampFormat = new SimpleDateFormat("yyyy-MM-dd'T'HH:mm:ss.SSS'Z'") // ISO8601 + timestampFormat.setTimeZone(DateTimeUtils.getTimeZone("UTC")) + + registerGauge("eventTime-watermark", + progress => convertStringDateToMillis(progress.eventTime.get("watermark")), 0L) + + registerGauge("states-rowsTotal", _.stateOperators.map(_.numRowsTotal).sum, 0L) + registerGauge("states-usedBytes", _.stateOperators.map(_.memoryUsedBytes).sum, 0L) + --- End diff -- We can add more metrics like "providerLoadedMapSizeBytes" after adopting SPARK-24441, so that actual memory usage of state store provider could be tracked via time-series manner.
--- --------------------------------------------------------------------- To unsubscribe, e-mail: reviews-unsubscr...@spark.apache.org For additional commands, e-mail: reviews-h...@spark.apache.org