数据采集 采集源配置 Hadoop-HDFS 监控指标采集
Hadoop-HDFS 监控指标采集
简介
采集 hadoop-hdfs 指标上报到 dataflux 中
前置条件
- 已安装 DataKit(DataKit 安装文档)
- 已配置 Jolokia 指标采集
配置
进入 DataKit 安装目录下的 conf.d/hadoop_hdfs
目录,复制 hadoop_hdfs.conf.sample
并命名为 hadoop_hdfs.conf。示例如下:
[[inputs.jolokia2_agent]]
urls = ["http://localhost:8778/jolokia"]
name_prefix = "hadoop.hdfs.namenode."
[[inputs.jolokia2_agent.metric]]
name = "FSNamesystem"
mbean = "Hadoop:name=FSNamesystem,service=NameNode"
paths = ["CapacityTotal", "CapacityRemaining", "CapacityUsedNonDFS", "NumLiveDataNodes", "NumDeadDataNodes", "NumInMaintenanceDeadDataNodes", "NumDecomDeadDataNodes"]
[[inputs.jolokia2_agent.metric]]
name = "FSNamesystemState"
mbean = "Hadoop:name=FSNamesystemState,service=NameNode"
paths = ["VolumeFailuresTotal", "UnderReplicatedBlocks", "BlocksTotal"]
[[inputs.jolokia2_agent.metric]]
name = "OperatingSystem"
mbean = "java.lang:type=OperatingSystem"
paths = ["ProcessCpuLoad", "SystemLoadAverage", "SystemCpuLoad"]
[[inputs.jolokia2_agent.metric]]
name = "jvm_runtime"
mbean = "java.lang:type=Runtime"
paths = ["Uptime"]
[[inputs.jolokia2_agent.metric]]
name = "jvm_memory"
mbean = "java.lang:type=Memory"
paths = ["HeapMemoryUsage", "NonHeapMemoryUsage", "ObjectPendingFinalizationCount"]
[[inputs.jolokia2_agent.metric]]
name = "jvm_garbage_collector"
mbean = "java.lang:name=*,type=GarbageCollector"
paths = ["CollectionTime", "CollectionCount"]
tag_keys = ["name"]
[[inputs.jolokia2_agent.metric]]
name = "jvm_memory_pool"
mbean = "java.lang:name=*,type=MemoryPool"
paths = ["Usage", "PeakUsage", "CollectionUsage"]
tag_keys = ["name"]
tag_prefix = "pool_"
################
# DATANODE #
################
[[inputs.jolokia2_agent]]
urls = ["http://localhost:7778/jolokia"]
name_prefix = "hadoop.hdfs.datanode."
[[inputs.jolokia2_agent.metric]]
name = "FSDatasetState"
mbean = "Hadoop:name=FSDatasetState,service=DataNode"
paths = ["Capacity", "DfsUsed", "Remaining", "NumBlocksFailedToUnCache", "NumBlocksFailedToCache", "NumBlocksCached"]
[[inputs.jolokia2_agent.metric]]
name = "OperatingSystem"
mbean = "java.lang:type=OperatingSystem"
paths = ["ProcessCpuLoad", "SystemLoadAverage", "SystemCpuLoad"]
[[inputs.jolokia2_agent.metric]]
name = "jvm_runtime"
mbean = "java.lang:type=Runtime"
paths = ["Uptime"]
[[inputs.jolokia2_agent.metric]]
name = "jvm_memory"
mbean = "java.lang:type=Memory"
paths = ["HeapMemoryUsage", "NonHeapMemoryUsage", "ObjectPendingFinalizationCount"]
[[inputs.jolokia2_agent.metric]]
name = "jvm_garbage_collector"
mbean = "java.lang:name=*,type=GarbageCollector"
paths = ["CollectionTime", "CollectionCount"]
tag_keys = ["name"]
[[inputs.jolokia2_agent.metric]]
name = "jvm_memory_pool"
mbean = "java.lang:name=*,type=MemoryPool"
paths = ["Usage", "PeakUsage", "CollectionUsage"]
tag_keys = ["name"]
tag_prefix = "pool_"
配置好后,重启 DataKit 即可生效