- 浏览: 548042 次
- 性别:
- 来自: 北京
文章分类
- 全部博客 (740)
- css (4)
- jquery (8)
- javascript (23)
- html (0)
- uml (0)
- 设计模式 (1)
- 开发工具 (14)
- json (4)
- struts 1.x (3)
- spring (3)
- hibernate (6)
- struts 2.x (17)
- JFreechart (0)
- j2se (48)
- jsp (9)
- flex (22)
- 找工作 (1)
- 技术杂谈 (18)
- 网络编程 (5)
- io流 (1)
- ORACLE (15)
- 报表 (3)
- extjs (11)
- jpbm (2)
- swing (5)
- jspereports (3)
- sql (1)
- linux (15)
- ps (1)
- storm (4)
- hbase (8)
- li (0)
- python (1)
- hive (3)
- 机器学习 (1)
- hdfs (1)
- elasticsearch (1)
- hadoop 2.2 (5)
- hadoop (1)
最新评论
-
Tristan_S:
这个有点意思
ASM -
starryskydog:
程序修改detail band部分的样式 如内容字体大小 ...
使用jasperReport实现动态表头 -
samwong:
Good, so usefule
使用YUI Compressor压缩CSS/JS -
gc715409742:
能够告诉我怎么在web项目中使用YUI Compressor? ...
使用YUI Compressor压缩CSS/JS -
JsonTeye:
您好! 我看你的代码,我现在也在做动态报表,实现功能由用户自己 ...
使用jasperreport动态生成pdf,excel,html
ganglia监控Hadoop各指标说明
default.shuffleInput<wbr></wbr><wbr></wbr>
dfs.datanode<wbr></wbr><wbr></wbr>
jvm<wbr></wbr><wbr></wbr>
mapred.shuffleOutput<wbr></wbr><wbr></wbr>
rpc<wbr></wbr><wbr></wbr>
metricssystem<wbr></wbr><wbr></wbr>
dfs.datanode.blockChecksumOp_avg_time块校验平均时间<wbr></wbr><wbr></wbr>
dfs.datanode.blockChecksumOp_num_ops块检验次数<wbr></wbr><wbr></wbr>
dfs.datanode.blockReports_avg_time块报告平均时间<wbr></wbr><wbr></wbr>
dfs.datanode.blockReports_num_ops块报告次数<wbr></wbr><wbr></wbr>
dfs.datanode.block_verification_failures块验证失败次数<wbr></wbr><wbr></wbr>
dfs.datanode.blocks_read从硬盘读块总次数<wbr></wbr><wbr></wbr>
dfs.datanode.blocks_removed删除块数目<wbr></wbr><wbr></wbr>
dfs.datanode.blocks_replicated块复制总次数<wbr></wbr><wbr></wbr>
dfs.datanode.blocks_verified块验证总次数<wbr></wbr><wbr></wbr>
dfs.datanode.blocks_written向硬盘写块总次数<wbr></wbr><wbr></wbr>
dfs.datanode.bytes_read读出总字节包含crc验证文件字节数<wbr></wbr><wbr></wbr>
dfs.datanode.bytes_written写入总字节数(在写入每个packet时计数)<wbr></wbr><wbr></wbr>
dfs.datanode.copyBlockOp_avg_time 复制块平均时间(单位ms)<wbr></wbr><wbr></wbr>
dfs.datanode.copyBlockOp_num_ops复制块次数<wbr></wbr><wbr></wbr>
dfs.datanode.heartBeats_avg_time向namenode汇报平均时间<wbr></wbr><wbr></wbr>
dfs.datanode.heartBeats_num_ops向namenode汇报总次数<wbr></wbr><wbr></wbr>
dfs.datanode.readBlockOp_avg_time读块平均时间(单位ms)<wbr></wbr><wbr></wbr>
dfs.datanode.readBlockOp_num_ops 读块总次数 一般和dfs.datanode.blocks_read一致,先从硬盘读入输入流,增加dfs.datanode.blocks_read计数,然后再增加该计数<wbr></wbr><wbr></wbr>
dfs.datanode.reads_from_local_client从本地读入块次数<wbr></wbr><wbr></wbr>
dfs.datanode.reads_from_remote_client从远程读入块次数<wbr></wbr><wbr></wbr>
dfs.datanode.replaceBlockOp_avg_time替换块平均时间(负载均衡策略)<wbr></wbr><wbr></wbr>
dfs.datanode.replaceBlockOp_num_ops替换块次数(负载均衡策略)<wbr></wbr><wbr></wbr>
dfs.datanode.volumeFailures notfound 和block拥有的volume失败有关<wbr></wbr><wbr></wbr>
dfs.datanode.writeBlockOp_avg_time写块平均时间<wbr></wbr><wbr></wbr>
dfs.datanode.writeBlockOp_num_ops写块总次数一般和dfs.datanode.blocks_written一致,先从硬盘,增加dfs.datanode.blocks_read计数,然后再增加该计数<wbr></wbr><wbr></wbr>
dfs.datanode.writes_from_local_client写本地次数<wbr></wbr><wbr></wbr>
dfs.datanode.writes_from_remote_client写远程次数<wbr></wbr><wbr></wbr>
jvm.metrics.gcCount gc总次数<wbr></wbr><wbr></wbr>
jvm.metrics.gcTimeMillisgc总耗时(ms)<wbr></wbr><wbr></wbr>
jvm.metrics.logError jvm error次数<wbr></wbr><wbr></wbr>
jvm.metrics.logFataljvm出现fatal次数<wbr></wbr><wbr></wbr>
jvm.metrics.logInfo jvminfo出现次数<wbr></wbr><wbr></wbr>
jvm.metrics.logWarn jvmwarn出现次数<wbr></wbr><wbr></wbr>
jvm.metrics.maxMemoryMjvm试图使用最大内存(M),如果没有限制返回Long.MAX_VALUE<wbr></wbr><wbr></wbr>
jvm.metrics.memHeapCommittedMjvm提交堆内存大小<wbr></wbr><wbr></wbr>
jvm.metrics.memHeapUsedMjvm使用堆内存大小<wbr></wbr><wbr></wbr>
jvm.metrics.memNonHeapCommittedMjvm非堆内存已提交大小<wbr></wbr><wbr></wbr>
jvm.metrics.memNonHeapUsedMjvm非堆内存已使用大小<wbr></wbr><wbr></wbr>
jvm.metrics.threadsBlocked正在阻塞等待监视器锁的线程数目<wbr></wbr><wbr></wbr>
jvm.metrics.threadsNew尚未启动的线程数目<wbr></wbr><wbr></wbr>
jvm.metrics.threadsRunnable正在执行状态的线程数目<wbr></wbr><wbr></wbr>
jvm.metrics.threadsTerminated已退出线程数目<wbr></wbr><wbr></wbr>
jvm.metrics.threadsTimedWaiting等待另一个线程执行取决于指定等待时间的操作的线程数目<wbr></wbr><wbr></wbr>
jvm.metrics.threadsWaiting无限期地等待另一个线程来执行某一特定操作的线程数目<wbr></wbr><wbr></wbr>
rpc.metrics.NumOpenConnections<wbr><wbr><wbr><wbr><wbr><wbr><wbr><wbr><wbr><wbr><wbr><wbr><wbr><wbr><wbr><wbr><wbr><wbr><wbr><wbr>number of open connectionsrpc连接打开的数目<wbr></wbr></wbr></wbr></wbr></wbr></wbr></wbr></wbr></wbr></wbr></wbr></wbr></wbr></wbr></wbr></wbr></wbr></wbr></wbr></wbr></wbr><wbr></wbr>
rpc.metrics.ReceivedBytes<wbr><wbr><wbr><wbr><wbr><wbr><wbr><wbr><wbr><wbr><wbr><wbr><wbr><wbr><wbr><wbr><wbr><wbr><wbr><wbr><wbr><wbr><wbr><wbr><wbr>number of bytes receivedrpc收到的字节数<wbr></wbr></wbr></wbr></wbr></wbr></wbr></wbr></wbr></wbr></wbr></wbr></wbr></wbr></wbr></wbr></wbr></wbr></wbr></wbr></wbr></wbr></wbr></wbr></wbr></wbr></wbr><wbr></wbr>
rpc.metrics.RpcProcessingTime_avg_time<wbr><wbr><wbr><wbr><wbr><wbr><wbr><wbr><wbr><wbr><wbr><wbr>Average time for RPC Operations in last intervalrpc在最近的交互中平均操作时间<wbr><wbr><wbr><wbr><wbr><wbr><wbr><wbr><wbr><wbr><wbr><wbr><wbr><wbr><wbr><wbr><wbr><wbr><wbr></wbr></wbr></wbr></wbr></wbr></wbr></wbr></wbr></wbr></wbr></wbr></wbr></wbr></wbr></wbr></wbr></wbr></wbr></wbr></wbr></wbr></wbr></wbr></wbr></wbr></wbr></wbr></wbr></wbr></wbr></wbr><wbr></wbr>
rpc.metrics.RpcProcessingTime_num_ops<wbr><wbr><wbr><wbr><wbr><wbr><wbr><wbr><wbr><wbr><wbr><wbr><wbr>rpc在最近的交互中连接数目<wbr></wbr></wbr></wbr></wbr></wbr></wbr></wbr></wbr></wbr></wbr></wbr></wbr></wbr></wbr><wbr></wbr>
rpc.metrics.RpcQueueTime_avg_time<wbr><wbr><wbr><wbr><wbr><wbr><wbr><wbr><wbr><wbr><wbr><wbr><wbr><wbr><wbr><wbr><wbr>rpc在交互中平均等待时间<wbr></wbr></wbr></wbr></wbr></wbr></wbr></wbr></wbr></wbr></wbr></wbr></wbr></wbr></wbr></wbr></wbr></wbr></wbr><wbr></wbr>
rpc.metrics.RpcQueueTime_num_ops<wbr><wbr><wbr><wbr><wbr><wbr><wbr><wbr><wbr><wbr><wbr><wbr><wbr><wbr><wbr><wbr>rpc queue中完成的rpc操作数目<wbr></wbr></wbr></wbr></wbr></wbr></wbr></wbr></wbr></wbr></wbr></wbr></wbr></wbr></wbr></wbr></wbr></wbr><wbr></wbr>
rpc.metrics.SentBytes<wbr><wbr><wbr><wbr><wbr><wbr><wbr><wbr><wbr><wbr><wbr><wbr><wbr><wbr><wbr><wbr><wbr><wbr><wbr><wbr><wbr><wbr><wbr><wbr><wbr><wbr><wbr><wbr><wbr>number of bytes sent<wbr>rpc发送的数据字节<wbr></wbr></wbr></wbr></wbr></wbr></wbr></wbr></wbr></wbr></wbr></wbr></wbr></wbr></wbr></wbr></wbr></wbr></wbr></wbr></wbr></wbr></wbr></wbr></wbr></wbr></wbr></wbr></wbr></wbr></wbr></wbr><wbr></wbr>
rpc.metrics.callQueueLen<wbr><wbr><wbr><wbr><wbr><wbr><wbr><wbr><wbr><wbr><wbr><wbr><wbr><wbr><wbr><wbr><wbr><wbr><wbr><wbr><wbr><wbr><wbr><wbr><wbr><wbr>length of the rpc queue<wbr> rpc队列长度<wbr></wbr></wbr></wbr></wbr></wbr></wbr></wbr></wbr></wbr></wbr></wbr></wbr></wbr></wbr></wbr></wbr></wbr></wbr></wbr></wbr></wbr></wbr></wbr></wbr></wbr></wbr></wbr></wbr><wbr></wbr>
rpc.metrics.rpcAuthenticationFailure<wbr>s<wbr><wbr><wbr><wbr><wbr><wbr><wbr><wbr><wbr><wbr><wbr><wbr><wbr>number of failed authentications<wbr> rpc验证失败次数<wbr></wbr></wbr></wbr></wbr></wbr></wbr></wbr></wbr></wbr></wbr></wbr></wbr></wbr></wbr></wbr></wbr><wbr></wbr>
rpc.metrics.rpcAuthenticationSuccess<wbr>es<wbr><wbr><wbr><wbr><wbr><wbr><wbr><wbr><wbr><wbr><wbr><wbr>number of successfulauthentications<wbr><wbr>验证成功数<wbr></wbr></wbr></wbr></wbr></wbr></wbr></wbr></wbr></wbr></wbr></wbr></wbr></wbr></wbr></wbr></wbr><wbr></wbr>
rpc.metrics.rpcAuthorizationFailures<wbr><wbr><wbr><wbr><wbr><wbr><wbr><wbr><wbr><wbr><wbr><wbr><wbr><wbr><wbr>number of failed authorizations<wbr><wbr>授权失败次数<wbr></wbr></wbr></wbr></wbr></wbr></wbr></wbr></wbr></wbr></wbr></wbr></wbr></wbr></wbr></wbr></wbr></wbr></wbr><wbr></wbr>
rpc.metrics.rpcAuthorizationSuccesse<wbr>s<wbr><wbr><wbr><wbr><wbr><wbr><wbr><wbr><wbr><wbr><wbr><wbr><wbr>number of successful authorizations<wbr>成功次数<wbr></wbr></wbr></wbr></wbr></wbr></wbr></wbr></wbr></wbr></wbr></wbr></wbr></wbr></wbr></wbr></wbr><wbr></wbr>
mapred.shuffleInput.shuffle_failed_fetches<wbr><wbr><wbr><wbr>从map输出中取数据过程中获取失败次数<wbr><wbr><wbr><wbr><wbr></wbr></wbr></wbr></wbr></wbr></wbr></wbr></wbr></wbr><wbr></wbr>
mapred.shuffleInput.shuffle_fetchers_busy_percent<wbr><wbr>在获取map输出过程中并行获取线程忙碌占总并行获取线程百分比<wbr></wbr></wbr></wbr><wbr></wbr>
mapred.shuffleInput.shuffle_input_bytes<wbr><wbr><wbr><wbr><wbr><wbr><wbr><wbr><wbr><wbr><wbr><wbr><wbr>shuffle过程中读入数据字节<wbr></wbr></wbr></wbr></wbr></wbr></wbr></wbr></wbr></wbr></wbr></wbr></wbr></wbr></wbr><wbr></wbr>
mapred.shuffleInput.shuffle_success_fetches<wbr><wbr><wbr>从map输出中取数据过程中获取成功次数<wbr><wbr></wbr></wbr></wbr></wbr></wbr><wbr></wbr>
mapred.shuffleOutput.shuffle_failed_outputs<wbr><wbr><wbr>向reduce发送map输出失败次数<wbr></wbr></wbr></wbr></wbr><wbr></wbr>
mapred.shuffleOutput.shuffle_handler_busy_percent<wbr><wbr><wbr>向reduce发送map输出中server线程忙碌占总工作线程(在tasktracker.http.threads中配置)百分比。<wbr></wbr></wbr></wbr></wbr><wbr></wbr>
mapred.shuffleOutput.shuffle_output_bytes<wbr><wbr><wbr><wbr><wbr><wbr><wbr><wbr><wbr><wbr><wbr>shuffle过程中输出数据字节<wbr></wbr></wbr></wbr></wbr></wbr></wbr></wbr></wbr></wbr></wbr></wbr></wbr><wbr></wbr>
mapred.shuffleOutput.shuffle_success_outputs<wbr><wbr><wbr><wbr><wbr><wbr><wbr><wbr>向reduce成功<wbr></wbr></wbr></wbr></wbr></wbr></wbr></wbr></wbr></wbr><wbr></wbr>
mapred.tasktracker.mapTaskSlots<wbr><wbr><wbr><wbr><wbr><wbr><wbr><wbr><wbr><wbr><wbr><wbr><wbr><wbr><wbr>设置map槽数<wbr></wbr></wbr></wbr></wbr></wbr></wbr></wbr></wbr></wbr></wbr></wbr></wbr></wbr></wbr></wbr></wbr><wbr></wbr>
mapred.tasktracker.maps_running<wbr><wbr><wbr><wbr><wbr><wbr><wbr><wbr><wbr><wbr><wbr><wbr><wbr><wbr><wbr>正在运行的map数<wbr></wbr></wbr></wbr></wbr></wbr></wbr></wbr></wbr></wbr></wbr></wbr></wbr></wbr></wbr></wbr></wbr><wbr></wbr>
mapred.tasktracker.reduceTaskSlots<wbr><wbr><wbr><wbr><wbr><wbr><wbr><wbr><wbr><wbr><wbr><wbr>设置reduce槽数<wbr></wbr></wbr></wbr></wbr></wbr></wbr></wbr></wbr></wbr></wbr></wbr></wbr></wbr><wbr></wbr>
mapred.tasktracker.reduces_running<wbr><wbr><wbr><wbr><wbr><wbr><wbr><wbr><wbr><wbr><wbr><wbr>正在运行的reduce数<wbr></wbr></wbr></wbr></wbr></wbr></wbr></wbr></wbr></wbr></wbr></wbr></wbr></wbr><wbr></wbr>
mapred.tasktracker.tasks_completed<wbr><wbr><wbr><wbr><wbr><wbr><wbr><wbr><wbr><wbr><wbr><wbr>完成任务数<wbr><wbr><wbr><wbr><wbr><wbr></wbr></wbr></wbr></wbr></wbr></wbr></wbr></wbr></wbr></wbr></wbr></wbr></wbr></wbr></wbr></wbr></wbr></wbr><wbr></wbr>
mapred.tasktracker.tasks_failed_ping<wbr><wbr><wbr><wbr><wbr><wbr><wbr><wbr><wbr><wbr>因tasktracker与task交互失败导致的失败的task数目<wbr></wbr></wbr></wbr></wbr></wbr></wbr></wbr></wbr></wbr></wbr></wbr><wbr></wbr>
mapred.tasktracker.tasks_failed_timeout<wbr><wbr><wbr><wbr><wbr><wbr><wbr>因task未在mapred.task.timeout配置的(默认10分钟)时间内汇报进度而超时kill的task数目<wbr></wbr></wbr></wbr></wbr></wbr></wbr></wbr></wbr><wbr></wbr>
rpc.detailed-metrics.canCommit_avg_time<wbr><wbr><wbr><wbr><wbr><wbr><wbr>rpc询问是否提交任务平均时间<wbr></wbr></wbr></wbr></wbr></wbr></wbr></wbr></wbr><wbr></wbr>
rpc.detailed-metrics.canCommit_num_ops<wbr><wbr><wbr><wbr><wbr><wbr><wbr><wbr>rpc询问是否提交任务次数<wbr></wbr></wbr></wbr></wbr></wbr></wbr></wbr></wbr></wbr><wbr></wbr>
rpc.detailed-metrics.commitPending_avg_time<wbr><wbr><wbr>rpc报告任务提交完成,但是该提交仍然处于pending状态的平均时间<wbr></wbr></wbr></wbr></wbr><wbr></wbr>
rpc.detailed-metrics.commitPending_num_ops<wbr><wbr><wbr><wbr>rpc报告任务提交完成,但是该提交仍然处于pending状态的次数<wbr></wbr></wbr></wbr></wbr></wbr><wbr></wbr>
rpc.detailed-metrics.done_avg_time<wbr><wbr><wbr><wbr><wbr><wbr><wbr><wbr><wbr><wbr><wbr><wbr>rpc报告任务成功完成的平均时间<wbr></wbr></wbr></wbr></wbr></wbr></wbr></wbr></wbr></wbr></wbr></wbr></wbr></wbr><wbr></wbr>
rpc.detailed-metrics.done_num_ops<wbr><wbr><wbr><wbr><wbr><wbr><wbr><wbr><wbr><wbr><wbr><wbr><wbr>rpc报告任务成功完成的次数<wbr></wbr></wbr></wbr></wbr></wbr></wbr></wbr></wbr></wbr></wbr></wbr></wbr></wbr></wbr><wbr></wbr>
rpc.detailed-metrics.fatalError_avg_time<wbr><wbr><wbr><wbr><wbr><wbr>rpc报告任务出现fatalerror的平均时间<wbr></wbr></wbr></wbr></wbr></wbr></wbr></wbr><wbr></wbr>
rpc.detailed-metrics.fatalError_num_ops<wbr><wbr><wbr><wbr><wbr><wbr><wbr>rpc报告任务出现fatalerror的次数<wbr></wbr></wbr></wbr></wbr></wbr></wbr></wbr></wbr><wbr></wbr>
rpc.detailed-metrics.getBlockInfo_avg_time<wbr><wbr><wbr><wbr>从指定datanode获取block的平均时间<wbr></wbr></wbr></wbr></wbr></wbr><wbr></wbr>
rpc.detailed-metrics.getBlockInfo_num_ops<wbr><wbr><wbr><wbr><wbr>从指定datanode获取block的次数<wbr></wbr></wbr></wbr></wbr></wbr></wbr><wbr></wbr>
rpc.detailed-metrics.getMapCompletionEvents_avg_time<wbr>reduce获取已经完成的map输出地址事件的平均时间<wbr></wbr></wbr><wbr></wbr>
rpc.detailed-metrics.getMapCompletionEvents_num_ops<wbr><wbr>reduce获取已经完成的map输出地址事件的次数<wbr></wbr></wbr></wbr><wbr></wbr>
rpc.detailed-metrics.getProtocolVersion_avg_time<wbr><wbr><wbr><wbr><wbr>获取rpc协议版本信息的平均时间<wbr></wbr></wbr></wbr></wbr></wbr></wbr><wbr></wbr>
rpc.detailed-metrics.getProtocolVersion_num_ops<wbr><wbr><wbr><wbr><wbr><wbr>获取rpc协议版本信息的次数<wbr></wbr></wbr></wbr></wbr></wbr></wbr></wbr><wbr></wbr>
rpc.detailed-metrics.getTask_avg_time<wbr><wbr><wbr><wbr><wbr><wbr><wbr><wbr><wbr><wbr><wbr><wbr><wbr><wbr><wbr><wbr>当子进程启动后,获取jvmtask的平均时间<wbr></wbr></wbr></wbr></wbr></wbr></wbr></wbr></wbr></wbr></wbr></wbr></wbr></wbr></wbr></wbr></wbr></wbr><wbr></wbr>
rpc.detailed-metrics.getTask_num_ops<wbr><wbr><wbr><wbr><wbr><wbr><wbr><wbr><wbr><wbr><wbr><wbr><wbr><wbr><wbr><wbr><wbr>当子进程启动后,获取jvmtask的次数<wbr></wbr></wbr></wbr></wbr></wbr></wbr></wbr></wbr></wbr></wbr></wbr></wbr></wbr></wbr></wbr></wbr></wbr></wbr><wbr></wbr>
rpc.detailed-metrics.ping_avg_time<wbr><wbr><wbr><wbr><wbr><wbr><wbr><wbr><wbr><wbr><wbr><wbr><wbr><wbr><wbr><wbr><wbr><wbr><wbr>子进程周期性的检测父进程是否还存活的平均时间<wbr></wbr></wbr></wbr></wbr></wbr></wbr></wbr></wbr></wbr></wbr></wbr></wbr></wbr></wbr></wbr></wbr></wbr></wbr></wbr></wbr><wbr></wbr>
rpc.detailed-metrics.ping_num_ops<wbr><wbr><wbr><wbr><wbr><wbr><wbr><wbr><wbr><wbr><wbr><wbr><wbr><wbr><wbr><wbr><wbr><wbr><wbr><wbr>子进程周期性的检测父进程是否还存活的次数<wbr></wbr></wbr></wbr></wbr></wbr></wbr></wbr></wbr></wbr></wbr></wbr></wbr></wbr></wbr></wbr></wbr></wbr></wbr></wbr></wbr></wbr><wbr></wbr>
rpc.detailed-metrics.recoverBlock_avg_time<wbr><wbr><wbr><wbr><wbr><wbr><wbr><wbr><wbr><wbr><wbr><wbr>为指定的block开始恢复标记生成的平均时间<wbr></wbr></wbr></wbr></wbr></wbr></wbr></wbr></wbr></wbr></wbr></wbr></wbr></wbr><wbr></wbr>
rpc.detailed-metrics.recoverBlock_num_ops<wbr><wbr><wbr><wbr><wbr><wbr><wbr><wbr><wbr><wbr><wbr><wbr><wbr>为指定的block开始恢复标记生成的次数<wbr></wbr></wbr></wbr></wbr></wbr></wbr></wbr></wbr></wbr></wbr></wbr></wbr></wbr></wbr><wbr></wbr>
rpc.detailed-metrics.reportDiagnosticInfo_avg_time<wbr><wbr><wbr><wbr>向父进程报告任务错误消息的平均时间,该操作应尽可能少,这些消息会在jobtracker中保存<wbr></wbr></wbr></wbr></wbr></wbr><wbr></wbr>
rpc.detailed-metrics.reportDiagnosticInfo_num_ops<wbr><wbr><wbr><wbr><wbr>向父进程报告任务错误消息的次数<wbr></wbr></wbr></wbr></wbr></wbr></wbr><wbr></wbr>
rpc.detailed-metrics.startBlockRecovery_avg_time<wbr><wbr><wbr><wbr><wbr><wbr>开始恢复block的平均时间<wbr></wbr></wbr></wbr></wbr></wbr></wbr></wbr><wbr></wbr>
rpc.detailed-metrics.startBlockRecovery_num_ops<wbr><wbr><wbr><wbr><wbr><wbr><wbr>开始恢复block的次数<wbr></wbr></wbr></wbr></wbr></wbr></wbr></wbr></wbr><wbr></wbr>
rpc.detailed-metrics.statusUpdate_avg_time<wbr><wbr><wbr><wbr><wbr><wbr><wbr><wbr><wbr><wbr><wbr><wbr>汇报子进程进度给父进程的平均时间<wbr></wbr></wbr></wbr></wbr></wbr></wbr></wbr></wbr></wbr></wbr></wbr></wbr></wbr><wbr></wbr>
rpc.detailed-metrics.statusUpdate_num_ops<wbr><wbr><wbr><wbr><wbr><wbr><wbr><wbr><wbr><wbr><wbr><wbr><wbr>汇报子进程进度给父进程的次数<wbr></wbr></wbr></wbr></wbr></wbr></wbr></wbr></wbr></wbr></wbr></wbr></wbr></wbr></wbr><wbr></wbr>
rpc.detailed-metrics.updateBlock_avg_time<wbr><wbr><wbr><wbr><wbr><wbr><wbr><wbr><wbr><wbr><wbr><wbr><wbr>更新block到新的标记及长度的平均操作时间<wbr></wbr></wbr></wbr></wbr></wbr></wbr></wbr></wbr></wbr></wbr></wbr></wbr></wbr></wbr><wbr></wbr>
rpc.detailed-metrics.updateBlock_num_ops<wbr><wbr><wbr><wbr><wbr><wbr><wbr><wbr><wbr><wbr><wbr><wbr><wbr><wbr>更新block到新的标记及长度的次数</wbr></wbr></wbr></wbr></wbr></wbr></wbr></wbr></wbr></wbr></wbr></wbr></wbr></wbr>
相关推荐
《Ganglia监控Hadoop 2.2详解》 Ganglia是一款开源的分布式监控系统,广泛用于监控大型计算集群的资源使用情况,包括CPU、内存、网络等关键指标。在Hadoop这样的大数据处理框架中,Ganglia的集成显得尤为重要,因为...
文档"ganglia安装和监控Hadoop.doc"应该包含了详细的步骤指导,如安装Ganglia组件,配置Ganglia以监控Hadoop集群,以及如何将Nagios与Ganglia集成。在实际操作中,你可能需要配置Ganglia的监控项以覆盖Hadoop的关键...
Ganglia 是一款分布式监控系统,它能够收集、聚合并可视化大量计算节点(如Hadoop集群)的性能数据。Ganglia的核心组件包括gmond(监控代理)和gmetad(数据聚合器)。gmond运行在每个监控节点上,收集诸如CPU使用率...
这个压缩包文件包含了Ganglia集群监控的组件、依赖包以及安装部署的详细说明,帮助用户在自己的环境中实现全面的监控功能。 Ganglia的核心组件主要包括以下几个部分: 1. **Gmond (Ganglia Monitoring Daemon)**:...
同时,为了监控Hadoop特定的指标,你可能需要安装Hadoop的Ganglia监控插件。 总的来说,Ganglia的安装过程涉及多个步骤,包括库的安装、编译和配置。完成以上步骤后,你将拥有一个能够监控Hadoop集群性能的Ganglia...
Ganglia监控集群或计算节点的性能指标,例如CPU、内存、网络、磁盘的使用情况,以及节点上运行的作业和服务的状态等。 Nagios是另一个功能强大的开源监控系统,它具备故障检测和恢复功能。Nagios能够监控网络服务、...
对于Hadoop集群的集成,Ganglia提供了监控Hadoop特定指标的功能。在Hadoop节点上,需要额外配置Gmond以收集Hadoop相关的度量,比如任务进度、MapReduce作业统计等。这通常涉及修改`gmond.conf`,添加Hadoop插件,如`...
#### 使用Ganglia监控Hadoop Ganglia是一个开源的集群监控系统,主要用来监控系统的性能指标,如CPU利用率、内存使用情况、磁盘I/O负载等。它采用图形化的方式展示每个节点的状态信息,这对于优化系统资源配置、...
Ganglia是一款开源的分布式监控系统,主要用于实时监控Linux和Unix集群的资源使用情况,包括CPU、内存、磁盘I/O、网络流量等关键性能指标。Ganglia-3.7.2是其在2015年发布的一个稳定版本,它提供了强大的数据收集、...
在实际应用中,Ganglia广泛应用于Hadoop、Spark等大数据处理框架的监控,以及云计算环境的资源监控。通过集成Ganglia,管理员可以及时发现性能瓶颈,优化系统资源分配,提升整体系统的效率和稳定性。 总的来说,...
该书通过实际操作的例子和详细的说明,帮助有经验的系统管理员深入了解Ganglia 3.x的各个组件是如何协同工作的,从而更好地利用Ganglia的强大功能来提升系统的监控能力。这本书是Ganglia设计者和维护者编写的一本...
1. **监控指标**:监控Hadoop集群涉及跟踪各种关键性能指标,如节点状态、磁盘利用率、内存使用率、CPU负载、网络带宽和数据传输速率等。这些指标有助于识别潜在的瓶颈和故障点。 2. **监控工具**:Zabbix、Ganglia...
收集和图形展示工具有很多种,Ganglia是一个流行的选择,因为它原生支持Hadoop指标框架。Ganglia是一个分布式监控框架,可以监控集群的状态和表现。为了配置HBase把指标信息输出到Ganglia,需要设置$HBASE_HOME/conf...
如果你的环境中还有Hadoop,Ganglia可以很好地集成Hadoop,通过修改Hadoop配置文件,比如`hadoop-metrics2.properties`,添加Ganglia作为指标报告的目标,然后重启Hadoop服务,就可以看到Hadoop集群的监控数据在...
10. **监控与故障排查**:学习监控Hadoop集群的性能指标,识别并解决问题,是保证系统稳定运行的关键。这部分可能涉及Ambari、Ganglia等监控工具的使用。 通过这些PPT的学习,你可以系统性地掌握Hadoop及其生态系统...
为了有效管理和优化Hadoop集群,监控工具如Hadoop Metrics2和Ganglia用于收集和展示系统的实时性能指标。这些工具可以帮助管理员快速识别性能瓶颈,及时调整资源分配,确保集群的稳定运行。 6. **Hadoop的扩展性**...
- **Ganglia实战应用**:具体演示了如何使用Ganglia监控Hadoop集群的状态。这包括安装配置过程、常用监控指标设置及数据分析方法等。 ### Hive+MapReduce编程实践 - **Hive+MapReduce编程**:结合使用Hive进行数据...
7. **监控和维护**:安装监控工具,如Ambari或Ganglia,以监控集群的健康状况和性能指标,及时发现并解决问题。 理解这些概念和步骤,对于成功搭建和管理一个高可用的Hadoop3集群至关重要。在实际应用中,还需要...