[SPARK-25865][CORE] Add GC information to ExecutorMetrics #22874
There are no files selected for viewing
This file contains hidden or bidirectional Unicode text that may be interpreted or compiled differently than what appears below. To review, open the file in an editor that reveals hidden Unicode characters.
Learn more about bidirectional Unicode characters
This file contains hidden or bidirectional Unicode text that may be interpreted or compiled differently than what appears below. To review, open the file in an editor that reveals hidden Unicode characters.
Learn more about bidirectional Unicode characters
| Original file line number | Diff line number | Diff line change |
|---|---|---|
|
|
@@ -19,9 +19,12 @@ package org.apache.spark.metrics | |
| import java.lang.management.{BufferPoolMXBean, ManagementFactory} | ||
| import javax.management.ObjectName | ||
|
|
||
| import scala.collection.JavaConverters._ | ||
| import scala.collection.mutable | ||
|
|
||
| import org.apache.spark.SparkEnv | ||
| import org.apache.spark.executor.ProcfsMetricsGetter | ||
| import org.apache.spark.internal.{config, Logging} | ||
| import org.apache.spark.memory.MemoryManager | ||
|
|
||
| /** | ||
|
|
@@ -99,6 +102,56 @@ case object ProcessTreeMetrics extends ExecutorMetricType { | |
| } | ||
| } | ||
|
|
||
| case object GarbageCollectionMetrics extends ExecutorMetricType with Logging { | ||
| override val names = Seq( | ||
| "MinorGCCount", | ||
| "MinorGCTime", | ||
| "MajorGCCount", | ||
| "MajorGCTime" | ||
| ) | ||
|
|
||
| /* We builtin some common GC collectors which categorized as young generation and old */ | ||
| private[spark] val YOUNG_GENERATION_BUILTIN_GARBAGE_COLLECTORS = Seq( | ||
| "Copy", | ||
| "PS Scavenge", | ||
| "ParNew", | ||
| "G1 Young Generation" | ||
| ) | ||
|
|
||
| private[spark] val OLD_GENERATION_BUILTIN_GARBAGE_COLLECTORS = Seq( | ||
| "MarkSweepCompact", | ||
| "PS MarkSweep", | ||
| "ConcurrentMarkSweep", | ||
| "G1 Old Generation" | ||
| ) | ||
|
|
||
| private lazy val youngGenerationGarbageCollector: Seq[String] = { | ||
| SparkEnv.get.conf.get(config.EVENT_LOG_GC_METRICS_YOUNG_GENERATION_GARBAGE_COLLECTORS) | ||
| } | ||
|
|
||
| private lazy val oldGenerationGarbageCollector: Seq[String] = { | ||
| SparkEnv.get.conf.get(config.EVENT_LOG_GC_METRICS_OLD_GENERATION_GARBAGE_COLLECTORS) | ||
| } | ||
|
|
||
| override private[spark] def getMetricValues(memoryManager: MemoryManager): Array[Long] = { | ||
| val gcMetrics = new Array[Long](names.length) // minorCount, minorTime, majorCount, majorTime | ||
| ManagementFactory.getGarbageCollectorMXBeans.asScala.foreach { mxBean => | ||
| if (youngGenerationGarbageCollector.contains(mxBean.getName)) { | ||
| gcMetrics(0) = mxBean.getCollectionCount | ||
|
||
| gcMetrics(1) = mxBean.getCollectionTime | ||
| } else if (oldGenerationGarbageCollector.contains(mxBean.getName)) { | ||
| gcMetrics(2) = mxBean.getCollectionCount | ||
| gcMetrics(3) = mxBean.getCollectionTime | ||
| } else { | ||
| logDebug(s"${mxBean.getName} is an unsupported garbage collector." + | ||
|
||
| s"Add it to ${config.EVENT_LOG_GC_METRICS_YOUNG_GENERATION_GARBAGE_COLLECTORS.key} " + | ||
| s"or ${config.EVENT_LOG_GC_METRICS_OLD_GENERATION_GARBAGE_COLLECTORS.key} to enable.") | ||
| } | ||
| } | ||
| gcMetrics | ||
| } | ||
| } | ||
|
|
||
| case object OnHeapExecutionMemory extends MemoryManagerExecutorMetricType( | ||
| _.onHeapExecutionMemoryUsed) | ||
|
|
||
|
|
@@ -137,7 +190,8 @@ private[spark] object ExecutorMetricType { | |
| OffHeapUnifiedMemory, | ||
| DirectPoolMemory, | ||
| MappedPoolMemory, | ||
| ProcessTreeMetrics, | ||
| GarbageCollectionMetrics | ||
| ) | ||
|
|
||
|
|
||
|
|
||
This file contains hidden or bidirectional Unicode text that may be interpreted or compiled differently than what appears below. To review, open the file in an editor that reveals hidden Unicode characters.
Learn more about bidirectional Unicode characters
This file contains hidden or bidirectional Unicode text that may be interpreted or compiled differently than what appears below. To review, open the file in an editor that reveals hidden Unicode characters.
Learn more about bidirectional Unicode characters
This file contains hidden or bidirectional Unicode text that may be interpreted or compiled differently than what appears below. To review, open the file in an editor that reveals hidden Unicode characters.
Learn more about bidirectional Unicode characters
| Original file line number | Diff line number | Diff line change |
|---|---|---|
| @@ -0,0 +1,122 @@ | ||
| [ { | ||
| "id" : "driver", | ||
| "hostPort" : "047.company.com:42509", | ||
| "isActive" : true, | ||
| "rddBlocks" : 0, | ||
| "memoryUsed" : 0, | ||
| "diskUsed" : 0, | ||
| "totalCores" : 0, | ||
| "maxTasks" : 0, | ||
| "activeTasks" : 0, | ||
| "failedTasks" : 0, | ||
| "completedTasks" : 0, | ||
| "totalTasks" : 0, | ||
| "totalDuration" : 0, | ||
| "totalGCTime" : 0, | ||
| "totalInputBytes" : 0, | ||
| "totalShuffleRead" : 0, | ||
| "totalShuffleWrite" : 0, | ||
| "isBlacklisted" : false, | ||
| "maxMemory" : 100977868, | ||
| "addTime" : "2019-01-08T04:33:44.502GMT", | ||
| "executorLogs" : { | ||
| "stdout" : "https://047.company.com:50060/node/containerlogs/container_e136_1536831636016_59384_01_000001/lajin/stdout?start=-4096", | ||
| "stderr" : "https://047.company.com:50060/node/containerlogs/container_e136_1536831636016_59384_01_000001/lajin/stderr?start=-4096" | ||
| }, | ||
| "memoryMetrics" : { | ||
| "usedOnHeapStorageMemory" : 0, | ||
| "usedOffHeapStorageMemory" : 0, | ||
| "totalOnHeapStorageMemory" : 100977868, | ||
| "totalOffHeapStorageMemory" : 0 | ||
| }, | ||
| "blacklistedInStages" : [ ], | ||
| "peakMemoryMetrics" : { | ||
| "JVMHeapMemory" : 211171816, | ||
| "JVMOffHeapMemory" : 90237256, | ||
| "OnHeapExecutionMemory" : 0, | ||
| "OffHeapExecutionMemory" : 0, | ||
| "OnHeapStorageMemory" : 4876, | ||
| "OffHeapStorageMemory" : 0, | ||
| "OnHeapUnifiedMemory" : 4876, | ||
| "OffHeapUnifiedMemory" : 0, | ||
| "DirectPoolMemory" : 806275, | ||
| "MappedPoolMemory" : 0, | ||
| "ProcessTreeJVMVMemory" : 2646888448, | ||
| "ProcessTreeJVMRSSMemory" : 520900608, | ||
| "ProcessTreePythonVMemory" : 0, | ||
| "ProcessTreePythonRSSMemory" : 0, | ||
| "ProcessTreeOtherVMemory" : 0, | ||
| "ProcessTreeOtherRSSMemory" : 0, | ||
| "MinorGCCount" : 8, | ||
| "MinorGCTime" : 374, | ||
| "MajorGCCount" : 3, | ||
| "MajorGCTime" : 170 | ||
| }, | ||
| "attributes" : { } | ||
| }, { | ||
| "id" : "2", | ||
| "hostPort" : "028.company.com:46325", | ||
| "isActive" : true, | ||
| "rddBlocks" : 0, | ||
| "memoryUsed" : 0, | ||
| "diskUsed" : 0, | ||
| "totalCores" : 4, | ||
| "maxTasks" : 4, | ||
| "activeTasks" : 0, | ||
| "failedTasks" : 0, | ||
| "completedTasks" : 52, | ||
| "totalTasks" : 52, | ||
| "totalDuration" : 8879, | ||
| "totalGCTime" : 420, | ||
| "totalInputBytes" : 0, | ||
| "totalShuffleRead" : 0, | ||
| "totalShuffleWrite" : 0, | ||
| "isBlacklisted" : false, | ||
| "maxMemory" : 97832140, | ||
| "addTime" : "2019-01-08T04:33:54.270GMT", | ||
| "executorLogs" : { | ||
| "stdout" : "https://028.company.com:50060/node/containerlogs/container_e136_1536831636016_59384_01_000003/lajin/stdout?start=-4096", | ||
| "stderr" : "https://028.company.com:50060/node/containerlogs/container_e136_1536831636016_59384_01_000003/lajin/stderr?start=-4096" | ||
| }, | ||
| "memoryMetrics" : { | ||
| "usedOnHeapStorageMemory" : 0, | ||
| "usedOffHeapStorageMemory" : 0, | ||
| "totalOnHeapStorageMemory" : 97832140, | ||
| "totalOffHeapStorageMemory" : 0 | ||
| }, | ||
| "blacklistedInStages" : [ ], | ||
| "attributes" : { } | ||
| }, { | ||
| "id" : "1", | ||
| "hostPort" : "036.company.com:35126", | ||
| "isActive" : true, | ||
| "rddBlocks" : 0, | ||
| "memoryUsed" : 0, | ||
| "diskUsed" : 0, | ||
| "totalCores" : 4, | ||
| "maxTasks" : 4, | ||
| "activeTasks" : 0, | ||
| "failedTasks" : 0, | ||
| "completedTasks" : 48, | ||
| "totalTasks" : 48, | ||
| "totalDuration" : 8837, | ||
| "totalGCTime" : 1192, | ||
| "totalInputBytes" : 0, | ||
| "totalShuffleRead" : 0, | ||
| "totalShuffleWrite" : 0, | ||
| "isBlacklisted" : false, | ||
| "maxMemory" : 97832140, | ||
| "addTime" : "2019-01-08T04:33:55.929GMT", | ||
| "executorLogs" : { | ||
| "stdout" : "https://036.company.com:50060/node/containerlogs/container_e136_1536831636016_59384_01_000002/lajin/stdout?start=-4096", | ||
| "stderr" : "https://036.company.com:50060/node/containerlogs/container_e136_1536831636016_59384_01_000002/lajin/stderr?start=-4096" | ||
| }, | ||
| "memoryMetrics" : { | ||
| "usedOnHeapStorageMemory" : 0, | ||
| "usedOffHeapStorageMemory" : 0, | ||
| "totalOnHeapStorageMemory" : 97832140, | ||
| "totalOffHeapStorageMemory" : 0 | ||
| }, | ||
| "blacklistedInStages" : [ ], | ||
| "attributes" : { } | ||
| } ] |
This file contains hidden or bidirectional Unicode text that may be interpreted or compiled differently than what appears below. To review, open the file in an editor that reveals hidden Unicode characters.
Learn more about bidirectional Unicode characters
This file contains hidden or bidirectional Unicode text that may be interpreted or compiled differently than what appears below. To review, open the file in an editor that reveals hidden Unicode characters.
Learn more about bidirectional Unicode characters
Oops, something went wrong.
Add this suggestion to a batch that can be applied as a single commit.
This suggestion is invalid because no changes were made to the code.
Suggestions cannot be applied while the pull request is closed.
Suggestions cannot be applied while viewing a subset of changes.
Only one suggestion per line can be applied in a batch.
Add this suggestion to a batch that can be applied as a single commit.
Applying suggestions on deleted lines is not supported.
You must change the existing code in this line in order to create a valid suggestion.
Outdated suggestions cannot be applied.
This suggestion has been applied or marked resolved.
Suggestions cannot be applied from pending reviews.
Suggestions cannot be applied on multi-line comments.
Suggestions cannot be applied while the pull request is queued to merge.
Suggestion cannot be applied right now. Please check back later.
Uh oh!
There was an error while loading. Please reload this page.