[GitHub] [carbondata] jackylk commented on a change in pull request #3798: [CARBONDATA-3875] Support show segments include stage
jackylk commented on a change in pull request #3798:
URL: https://github.com/apache/carbondata/pull/3798#discussion_r446609866
##
File path:
integration/spark/src/main/scala/org/apache/spark/sql/execution/command/management/CarbonShowSegmentsCommand.scala
##
@@ -17,34 +17,40 @@
package org.apache.spark.sql.execution.command.management
+import scala.collection.JavaConverters._
+
+import org.apache.hadoop.conf.Configuration
import org.apache.spark.sql.{CarbonEnv, Row, SparkSession}
import org.apache.spark.sql.catalyst.expressions.{Attribute,
AttributeReference}
import org.apache.spark.sql.execution.command.{Checker, DataCommand}
import org.apache.spark.sql.types.StringType
-import org.apache.carbondata.api.CarbonStore.{getDataAndIndexSize,
getLoadStartTime, getLoadTimeTaken, getPartitions, readSegments}
+import org.apache.carbondata.api.CarbonStore.{getDataAndIndexSize,
getLoadStartTime, getLoadTimeTaken, getPartitions, readSegments, readStages}
import org.apache.carbondata.common.Strings
import
org.apache.carbondata.common.exceptions.sql.MalformedCarbonCommandException
-import org.apache.carbondata.core.statusmanager.LoadMetadataDetails
+import org.apache.carbondata.core.statusmanager.{LoadMetadataDetails,
StageInput}
+import org.apache.carbondata.core.util.path.CarbonTablePath
+
case class CarbonShowSegmentsCommand(
databaseNameOp: Option[String],
tableName: String,
-limit: Option[String],
+limit: Option[Int],
+includeStage: Boolean = false,
Review comment:
add as last param
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.
For queries about this service, please contact Infrastructure at:
us...@infra.apache.org
[GitHub] [carbondata] jackylk commented on a change in pull request #3798: [CARBONDATA-3875] Support show segments include stage
jackylk commented on a change in pull request #3798:
URL: https://github.com/apache/carbondata/pull/3798#discussion_r446609807
##
File path:
integration/spark/src/main/scala/org/apache/carbondata/api/CarbonStore.scala
##
@@ -63,13 +68,101 @@ object CarbonStore {
}
if (limit.isDefined) {
- val lim = Integer.parseInt(limit.get)
- segmentsMetadataDetails.slice(0, lim)
+ segmentsMetadataDetails.slice(0, limit.get)
} else {
segmentsMetadataDetails
}
}
+ /**
+ * Read stage files and return input files
+ */
+ def readStages(
+ tablePath: String,
+ configuration: Configuration): Seq[StageInput] = {
+val stageFiles = listStageFiles(
+ CarbonTablePath.getStageDir(tablePath), configuration)
+var output = Collections.synchronizedList(new util.ArrayList[StageInput]())
+output.addAll(readStageInput(stageFiles._1,
+ StageInput.StageStatus.Unload).asJavaCollection)
+output.addAll(readStageInput(stageFiles._2,
+ StageInput.StageStatus.Loading).asJavaCollection)
+Collections.sort(output, new Comparator[StageInput]() {
+ def compare(stageInput1: StageInput, stageInput2: StageInput): Int = {
+(stageInput2.getCreateTime - stageInput1.getCreateTime).intValue()
+ }
+})
+output.asScala
+ }
+
+ /**
+ * Read stage files and return input files
+ */
+ def readStageInput(
+ stageFiles: Seq[CarbonFile],
+ status: StageInput.StageStatus): Seq[StageInput] = {
+val gson = new Gson()
+val output = Collections.synchronizedList(new util.ArrayList[StageInput]())
+stageFiles.map { stage =>
+ val filePath = stage.getAbsolutePath
+ val stream = FileFactory.getDataInputStream(filePath)
+ try {
+val stageInput = gson.fromJson(new InputStreamReader(stream),
classOf[StageInput])
+stageInput.setCreateTime(stage.getLastModifiedTime)
+stageInput.setStatus(status)
+output.add(stageInput)
+ } finally {
+stream.close()
+ }
+}
+output.asScala
+ }
+
+ /*
+ * Collect all stage files and matched success files.
+ * A stage file without success file will not be collected
+ */
+ def listStageFiles(
+loadDetailsDir: String,
+hadoopConf: Configuration): (Array[CarbonFile], Array[CarbonFile]) = {
+val dir = FileFactory.getCarbonFile(loadDetailsDir, hadoopConf)
+if (dir.exists()) {
+ var allFiles = dir.listFiles()
+ val successFiles = allFiles.filter { file =>
+file.getName.endsWith(CarbonTablePath.SUCCESS_FILE_SUBFIX)
+ }.map { file =>
+(file.getName.substring(0, file.getName.indexOf(".")), file)
+ }.toMap
+ val loadingFiles = allFiles.filter { file =>
+file.getName.endsWith(CarbonTablePath.LOADING_FILE_SUBFIX)
+ }.map { file =>
+(file.getName.substring(0, file.getName.indexOf(".")), file)
+ }.toMap
+
+ allFiles = allFiles.filter { file =>
+!file.getName.endsWith(CarbonTablePath.SUCCESS_FILE_SUBFIX)
+ }.filter { file =>
+!file.getName.endsWith(CarbonTablePath.LOADING_FILE_SUBFIX)
+ }
+
+ val unloadedFiles = allFiles.filter { file =>
+successFiles.contains(file.getName)
Review comment:
maybe you can first construct the last part of the file by "file.getName
+ CarbonTablePath.LOADING_FILE_SUBFIX", then can still use endsWith. I think it
can be a little faster
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.
For queries about this service, please contact Infrastructure at:
us...@infra.apache.org
[GitHub] [carbondata] jackylk commented on a change in pull request #3798: [CARBONDATA-3875] Support show segments include stage
jackylk commented on a change in pull request #3798:
URL: https://github.com/apache/carbondata/pull/3798#discussion_r446609417
##
File path:
integration/spark/src/main/scala/org/apache/carbondata/api/CarbonStore.scala
##
@@ -63,13 +68,101 @@ object CarbonStore {
}
if (limit.isDefined) {
- val lim = Integer.parseInt(limit.get)
- segmentsMetadataDetails.slice(0, lim)
+ segmentsMetadataDetails.slice(0, limit.get)
} else {
segmentsMetadataDetails
}
}
+ /**
+ * Read stage files and return input files
+ */
+ def readStages(
+ tablePath: String,
+ configuration: Configuration): Seq[StageInput] = {
+val stageFiles = listStageFiles(
+ CarbonTablePath.getStageDir(tablePath), configuration)
+var output = Collections.synchronizedList(new util.ArrayList[StageInput]())
+output.addAll(readStageInput(stageFiles._1,
+ StageInput.StageStatus.Unload).asJavaCollection)
+output.addAll(readStageInput(stageFiles._2,
+ StageInput.StageStatus.Loading).asJavaCollection)
+Collections.sort(output, new Comparator[StageInput]() {
+ def compare(stageInput1: StageInput, stageInput2: StageInput): Int = {
+(stageInput2.getCreateTime - stageInput1.getCreateTime).intValue()
+ }
+})
+output.asScala
+ }
+
+ /**
+ * Read stage files and return input files
+ */
+ def readStageInput(
+ stageFiles: Seq[CarbonFile],
+ status: StageInput.StageStatus): Seq[StageInput] = {
+val gson = new Gson()
+val output = Collections.synchronizedList(new util.ArrayList[StageInput]())
+stageFiles.map { stage =>
+ val filePath = stage.getAbsolutePath
+ val stream = FileFactory.getDataInputStream(filePath)
+ try {
+val stageInput = gson.fromJson(new InputStreamReader(stream),
classOf[StageInput])
+stageInput.setCreateTime(stage.getLastModifiedTime)
+stageInput.setStatus(status)
+output.add(stageInput)
+ } finally {
+stream.close()
+ }
+}
+output.asScala
+ }
+
+ /*
+ * Collect all stage files and matched success files.
+ * A stage file without success file will not be collected
+ */
+ def listStageFiles(
+loadDetailsDir: String,
+hadoopConf: Configuration): (Array[CarbonFile], Array[CarbonFile]) = {
+val dir = FileFactory.getCarbonFile(loadDetailsDir, hadoopConf)
+if (dir.exists()) {
+ var allFiles = dir.listFiles()
+ val successFiles = allFiles.filter { file =>
+file.getName.endsWith(CarbonTablePath.SUCCESS_FILE_SUBFIX)
+ }.map { file =>
+(file.getName.substring(0, file.getName.indexOf(".")), file)
+ }.toMap
+ val loadingFiles = allFiles.filter { file =>
+file.getName.endsWith(CarbonTablePath.LOADING_FILE_SUBFIX)
+ }.map { file =>
+(file.getName.substring(0, file.getName.indexOf(".")), file)
+ }.toMap
+
+ allFiles = allFiles.filter { file =>
Review comment:
create another variable for this
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.
For queries about this service, please contact Infrastructure at:
us...@infra.apache.org
[GitHub] [carbondata] jackylk commented on a change in pull request #3798: [CARBONDATA-3875] Support show segments include stage
jackylk commented on a change in pull request #3798:
URL: https://github.com/apache/carbondata/pull/3798#discussion_r446609223
##
File path:
integration/spark/src/main/scala/org/apache/carbondata/api/CarbonStore.scala
##
@@ -63,13 +68,101 @@ object CarbonStore {
}
if (limit.isDefined) {
- val lim = Integer.parseInt(limit.get)
- segmentsMetadataDetails.slice(0, lim)
+ segmentsMetadataDetails.slice(0, limit.get)
} else {
segmentsMetadataDetails
}
}
+ /**
+ * Read stage files and return input files
+ */
+ def readStages(
+ tablePath: String,
+ configuration: Configuration): Seq[StageInput] = {
+val stageFiles = listStageFiles(
+ CarbonTablePath.getStageDir(tablePath), configuration)
+var output = Collections.synchronizedList(new util.ArrayList[StageInput]())
+output.addAll(readStageInput(stageFiles._1,
+ StageInput.StageStatus.Unload).asJavaCollection)
+output.addAll(readStageInput(stageFiles._2,
+ StageInput.StageStatus.Loading).asJavaCollection)
+Collections.sort(output, new Comparator[StageInput]() {
+ def compare(stageInput1: StageInput, stageInput2: StageInput): Int = {
+(stageInput2.getCreateTime - stageInput1.getCreateTime).intValue()
+ }
+})
+output.asScala
+ }
+
+ /**
+ * Read stage files and return input files
+ */
+ def readStageInput(
+ stageFiles: Seq[CarbonFile],
+ status: StageInput.StageStatus): Seq[StageInput] = {
+val gson = new Gson()
+val output = Collections.synchronizedList(new util.ArrayList[StageInput]())
+stageFiles.map { stage =>
+ val filePath = stage.getAbsolutePath
+ val stream = FileFactory.getDataInputStream(filePath)
+ try {
+val stageInput = gson.fromJson(new InputStreamReader(stream),
classOf[StageInput])
+stageInput.setCreateTime(stage.getLastModifiedTime)
+stageInput.setStatus(status)
+output.add(stageInput)
+ } finally {
+stream.close()
+ }
+}
+output.asScala
+ }
+
+ /*
+ * Collect all stage files and matched success files.
+ * A stage file without success file will not be collected
+ */
+ def listStageFiles(
Review comment:
It seems this it is only for test, can you add it to test folder instead
of adding new API?
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.
For queries about this service, please contact Infrastructure at:
us...@infra.apache.org
[GitHub] [carbondata] jackylk commented on a change in pull request #3798: [CARBONDATA-3875] Support show segments include stage
jackylk commented on a change in pull request #3798: URL: https://github.com/apache/carbondata/pull/3798#discussion_r446608882 ## File path: docs/segment-management-on-carbondata.md ## @@ -32,7 +32,7 @@ concept which helps to maintain consistency of data and easy transaction managem ``` SHOW [HISTORY] SEGMENTS - [FOR TABLE | ON] [db_name.]table_name [LIMIT number_of_segments] + [FOR TABLE | ON] [db_name.]table_name [INCLUDE STAGE] [LIMIT number_of_segments] Review comment: can user use "with stage" and segment query together? 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. For queries about this service, please contact Infrastructure at: us...@infra.apache.org
[GitHub] [carbondata] jackylk commented on a change in pull request #3798: [CARBONDATA-3875] Support show segments include stage
jackylk commented on a change in pull request #3798: URL: https://github.com/apache/carbondata/pull/3798#discussion_r446608764 ## File path: docs/segment-management-on-carbondata.md ## @@ -32,7 +32,7 @@ concept which helps to maintain consistency of data and easy transaction managem ``` SHOW [HISTORY] SEGMENTS - [FOR TABLE | ON] [db_name.]table_name [LIMIT number_of_segments] + [FOR TABLE | ON] [db_name.]table_name [INCLUDE STAGE] [LIMIT number_of_segments] Review comment: suggest to use "WITH STAGE" 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. For queries about this service, please contact Infrastructure at: us...@infra.apache.org
[GitHub] [carbondata] jackylk commented on a change in pull request #3798: [CARBONDATA-3875] Support show segments include stage
jackylk commented on a change in pull request #3798: URL: https://github.com/apache/carbondata/pull/3798#discussion_r446607939 ## File path: integration/spark/src/main/scala/org/apache/spark/sql/execution/command/management/CarbonShowSegmentsAsSelectCommand.scala ## @@ -35,7 +36,8 @@ case class CarbonShowSegmentsAsSelectCommand( databaseNameOp: Option[String], tableName: String, query: String, -limit: Option[String], +limit: Option[Int], +includeStage: Boolean = false, Review comment: add new parameter at the last 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. For queries about this service, please contact Infrastructure at: us...@infra.apache.org
