Yarn metrics参数说明

获取Yarn jmx信息:
curl -i http://xxx:8088/jmx

Hadoop:service=ResourceManager,name=FSOpDurations
Hadoop:service=ResourceManager,name=JvmMetrics
Hadoop:service=ResourceManager,name=ClusterMetrics
Hadoop:service=ResourceManager,name=RpcActivityForPort8033
Hadoop:service=ResourceManager,name=MetricsSystem,sub=Stats
Hadoop:service=ResourceManager,name=QueueMetrics,q0=root,q1=user02
Hadoop:service=ResourceManager,name=QueueMetrics,q0=root,q1=A,q2=C
Hadoop:service=ResourceManager,name=QueueMetrics,q0=root
Hadoop:service=ResourceManager,name=QueueMetrics,q0=root,q1=A
Hadoop:service=ResourceManager,name=QueueMetrics,q0=root,q1=A,q2=B
Hadoop:service=ResourceManager,name=QueueMetrics,q0=root,q1=default
Hadoop:service=ResourceManager,name=QueueMetrics,q0=root,q1=user01

#QueueMetrics
running_0
running_60
running_300
running_1440
FairShareMB Fair share of memory in MB
FairShareVCores Fair share of CPU in vcores
SteadyFairShareMB Steady fair share of memory in MB
SteadyFairShareVCores Steady fair share of CPU in vcores
MinShareMB Minimum share of memory in MB
MinShareVCores Minimum share of CPU in vcores
MaxShareMB Maximum share of memory in MB
MaxShareVCores Maximum share of CPU in vcores
AppsSubmitted application提交个数
AppsRunning 正在运行的application个数
AppsPending 挂起的application个数
AppsCompleted 完成的application个数
AppsKilled 被杀死的application个数
AppsFailed 失败的application个数
AllocatedMB 已分配的内存量
AllocatedVCores 分配给正在运行的应用的虚拟core
AllocatedContainers 已分配容器数
AggregateContainersAllocated Aggregate # of allocated containers
AggregateContainersReleased Aggregate # of released containers
AvailableMB 可用内存量
AvailableVCores 可用虚拟Core数
PendingMB Pending memory allocation in MB
PendingVCores Pending CPU allocation in virtual cores
PendingContainers # of pending containers
ReservedMB 预留内存量
ReservedVCores 预留虚拟Core数
ReservedContainers 预留容器数
ActiveUsers 激活用户数
ActiveApplications 激活的应用数
AppAttemptFirstContainerAllocationDelayNumOps 为应用分配容器延迟数
AppAttemptFirstContainerAllocationDelayAvgTime 为应用分配容器延迟时间
#FSOpDurations
ContinuousSchedulingRunNumOps Duration for a continuous scheduling run
ContinuousSchedulingRunAvgTime
ContinuousSchedulingRunStdevTime
ContinuousSchedulingRunIMinTime
ContinuousSchedulingRunIMaxTime
ContinuousSchedulingRunMinTime
ContinuousSchedulingRunMaxTime
NodeUpdateCallNumOps Duration to handle a node update
NodeUpdateCallAvgTime
NodeUpdateCallStdevTime
NodeUpdateCallIMinTime
NodeUpdateCallIMaxTime
NodeUpdateCallMinTime
NodeUpdateCallMaxTime
UpdateThreadRunNumOps Duration for a update thread run
UpdateThreadRunAvgTime
UpdateThreadRunStdevTime
UpdateThreadRunIMinTime
UpdateThreadRunIMaxTime
UpdateThreadRunMinTime
UpdateThreadRunMaxTime
UpdateCallNumOps Duration for an update call
UpdateCallAvgTime
UpdateCallStdevTime
UpdateCallIMinTime
UpdateCallIMaxTime
UpdateCallMinTime
UpdateCallMaxTime
PreemptCallNumOps Duration for a preempt call
PreemptCallAvgTime
PreemptCallStdevTime
PreemptCallIMinTime
PreemptCallIMaxTime
PreemptCallMinTime
PreemptCallMaxTime
#ClusterMetrics
NumActiveNMs active NMs
NumDecommissionedNMs decommissioned NMs
NumLostNMs lost NMs
NumUnhealthyNMs unhealthy NMs
NumRebootedNMs Rebooted NMs
AMLaunchDelayNumOps AM container launch delay
AMLaunchDelayAvgTime
AMRegisterDelayNumOps AM register delay
AMRegisterDelayAvgTime
#RpcActivityForPort8033
ReceivedBytes Total number of received bytes
SentBytes Total number of sent bytes
RpcQueueTimeNumOps Total number of RPC calls
RpcQueueTimeAvgTime Average queue time in milliseconds
RpcProcessingTimeNumOps Total number of RPC calls (same to RpcQueueTimeNumOps)
RpcProcessingTimeAvgTime Average Processing time in milliseconds
RpcAuthenticationFailures Total number of authentication failures
RpcAuthenticationSuccesses Total number of authentication successes
RpcAuthorizationFailures Total number of authorization failures
RpcAuthorizationSuccesses Total number of authorization successes
RpcClientBackoff
NumOpenConnections NumOpenConnections
CallQueueLength Current length of the call queue

jmx hadoop部分参数

curl http://10.116.100.2:50070/jmx?qry=Hadoop:service=NameNode,name=RpcActivityForPort8020

NameNode

NameNode:50070

Hadoop:service=NameNode,name=JvmMetrics

  • MemHeapMaxM
  • MemMaxM

Hadoop:service=NameNode,name=FSNamesystem

  • CapacityTotal
  • CapacityTotalGB
  • CapacityRemaining
  • CapacityRemainingGB
  • TotalLoad
  • FilesTotal

Hadoop:service=NameNode,name=FSNamesystemState

  • NumLiveDataNodes

Hadoop:service=NameNode,name=NameNodeInfo

  • LiveNodes

java.lang:type=Runtime

  • StartTime

Hadoop:service=NameNode,name=FSNamesystemState

  • TopUserOpCounts:timestamp

DataNode

DataNode:50075

Hadoop:service=DataNode,name=DataNodeActivity-slave-50010

  • BytesWritten
  • BytesRead
  • BlocksWritten
  • BlocksRead
  • ReadsFromLocalClient
  • ReadsFromRemoteClient
  • WritesFromLocalClient
  • WritesFromRemoteClient
  • BlocksGetLocalPathInfo

HDFS

NameNode:50070

Hadoop:service=NameNode,name=NameNodeActivity

  • CreateFileOps
  • FilesCreated
  • FilesAppended
  • FilesRenamed
  • GetListingOps
  • DeleteFileOps
  • FilesDeleted

Hadoop:service=NameNode,name=FSNamesystem

  • CapacityTotal
  • CapacityTotalGB
  • CapacityUsed
  • CapacityUsedGB
  • CapacityRemaining
  • CapacityRemainingGB
  • CapacityUsedNonDFS

Yarn

ResourceManager:8088

Hadoop:service=ResourceManager,name=ClusterMetrics

  • NumActiveNMs
  • NumDecommissionedNMs

Hadoop:service=ResourceManager,name=JvmMetrics

  • MemHeapUsedM

Hadoop记录-JMX参数的更多相关文章

  1. Hadoop记录-Hadoop NameNode 高可用 (High Availability) 实现解析

    Hadoop NameNode 高可用 (High Availability) 实现解析   NameNode 高可用整体架构概述 在 Hadoop 1.0 时代,Hadoop 的两大核心组件 HDF ...

  2. git log 查看提交记录,参数:

    git log 查看提交记录,参数:-n (n是一个正整数),查看最近n次的提交信息 $ git log -2 查看最近2次的提交历史记录 -- fileName fileName为任意文件名,查看指 ...

  3. Hadoop集群参数和常用端口

    一.Hadoop集群参数配置 在hadoop集群中,需要配置的文件主要包括四个,分别是core-site.xml.hdfs-site.xml.mapred-site.xml和yarn-site.xml ...

  4. hadoop记录-Hadoop参数汇总

    Hadoop参数汇总 linux参数 以下参数最好优化一下: 文件描述符ulimit -n 用户最大进程 nproc (hbase需要 hbse book) 关闭swap分区 设置合理的预读取缓冲区 ...

  5. Hadoop记录-metastore jmx配置

    参考:http://www.lixiuliang.cn/categories/%E5%A4%A7%E6%95%B0%E6%8D%AE/ 1.修改bin/hive文件 添加jvm启动参数: if [ $ ...

  6. Hadoop记录-Hadoop jmx

    https://cwiki.apache.org/confluence/display/EAG/Hadoop+JMX+Monitoring+and+Alerting curl http://10.11 ...

  7. Hadoop记录-hadoop jmx配置

    1.hadoop-env.sh添加export HADOOP_JMX_OPTS="-Dcom.sun.management.jmxremote.authenticate=false -Dco ...

  8. Hadoop记录-hdfs转载

    Hadoop 存档 每个文件均按块存储,每个块的元数据存储在namenode的内存中,因此hadoop存储小文件会非常低效.因为大量的小文件会耗尽namenode中的大部分内存.但注意,存储小文件所需 ...

  9. Hadoop yarn配置参数

    参照site:http://hadoop.apache.org/docs/r2.6.0/hadoop-yarn/hadoop-yarn-common/yarn-default.xml 我们在配置yar ...

随机推荐

  1. JavaScript Uncaught TypeError: Cannot read property 'value' of null

    用 JavaScript 操作 DOM 时出现如下错误: Uncaught TypeError: Cannot set property 'value' of null Uncaught TypeEr ...

  2. 英语口语练习系列-C01-好棒

    古诗 来自百度 It's cool. It is neat. It's righteous! It's righteous! 酷毙了! righteous是 cool 的高级了 如果一件事让你无法用 ...

  3. 【English】20190415

    approximately大约 [əˈprɑ:ksɪmətli] This install will take + minutes and requires the download of appro ...

  4. 理解IO、NIO、 AIO

    转载:https://baijiahao.baidu.com/s?id=1586112410163034993&wfr=spider&for=pc nio 同步: 自己亲自出马持银行卡 ...

  5. web框架开发-Django简介

    MVC与MTV模型 MVC Web服务器开发领域里著名的MVC模式,所谓MVC就是把Web应用分为模型(M),控制器(C)和视图(V)三层,他们之间以一种插件式的.松耦合的方式连接在一起,模型负责业务 ...

  6. 转://Oracle数据库升级后保障SQL性能退化浅谈

    一.数据库升级后保障手段 为了保障从10.2.0.4版本升级到11.2.0.4版本更加平稳,我们事先采用了oracle性能分析器(SQL Performance Analyzer)来预测数据库的关键S ...

  7. vue.js 跳转同一页面,传不同值,组件监听路由

    watch: { '$route' () { this.type = this.$route.params.type this.loadData() } },

  8. [详细实例]MicroPython拼插编程实战:DIY一台会思考的壁障车

    (转载请注明文章来源,更多教程可自助参考www.tpyboard.com,QQ技术交流群:157816561,公众号:MicroPython玩家汇) 在日常生活中,大家会经常见到各种各样的遥控车,它需 ...

  9. 使用.net core efcore根据数据库结构自动生成实体类

    源码 github,已更新最新代码 https://github.com/leoparddne/GenEntities/ 使用的DB是mysql,所有先nuget一下mysql.data 创建t4模板 ...

  10. centos7下root密码丢失解决方案

    1 root密码忘记 A.[rd.break方式更改root密码!] 1.重启 CentOS 7.X,在系统引导倒计时的时候快速按键盘上的[ ↑ ]或[ ↓ ]键,使其停留在GRUB菜单界面,并按照下 ...