hadoop-yarn-issues mailing list archives

Site index · List index
Message view « Date » · « Thread »
Top « Date » · « Thread »
From "Anubhav Dhoot (JIRA)" <j...@apache.org>
Subject [jira] [Updated] (YARN-3122) Metrics for container's actual CPU usage
Date Fri, 06 Feb 2015 23:58:35 GMT

     [ https://issues.apache.org/jira/browse/YARN-3122?page=com.atlassian.jira.plugin.system.issuetabpanels:all-tabpanel
]

Anubhav Dhoot updated YARN-3122:
--------------------------------
    Attachment: YARN-3122.prelim.patch

[ ]# stress -c 3 &
[1] 1778
[ ]# stress: info: [1778] dispatching hogs: 3 cpu, 0 io, 0 vm, 0 hdd
[ ]# top -n 1  -p 1778 -p 1779 -p 1780 -p 1781  | grep stress
 1779 root      20   0  6516  192  100 R 99.8  0.0   1:35.90 stress
 1780 root      20   0  6516  192  100 R 99.8  0.0   1:36.04 stress
 1781 root      20   0  6516  192  100 R 99.8  0.0   1:35.87 stress
 1778 root      20   0  6516  556  468 S  0.0  0.0   0:00.00 stress
 
 [ ]# java   org.apache.hadoop.yarn.util.ProcfsBasedProcessTree 1779
 Number of processors 4
 Creating ProcfsBasedProcessTree for process 1779
 	|- PID PPID PGRPID SESSID CMD_NAME USER_MODE_TIME(MILLIS) SYSTEM_TIME(MILLIS) VMEM_USAGE(BYTES)
RSSMEM_USAGE(PAGES) FULL_CMD_LINE
 	|- 1779 1778 1778 595 (stress) 59492 7 6672384 48 stress -c 3

 Get cpu usage -1.0
 	|- PID PPID PGRPID SESSID CMD_NAME USER_MODE_TIME(MILLIS) SYSTEM_TIME(MILLIS) VMEM_USAGE(BYTES)
RSSMEM_USAGE(PAGES) FULL_CMD_LINE
 	|- 1779 1778 1778 595 (stress) 59553 7 6672384 48 stress -c 3

 Get cpu usage 24.091627
 [ ]# java   org.apache.hadoop.yarn.util.ProcfsBasedProcessTree 1778
 Number of processors 4
 Creating ProcfsBasedProcessTree for process 1778
 	|- PID PPID PGRPID SESSID CMD_NAME USER_MODE_TIME(MILLIS) SYSTEM_TIME(MILLIS) VMEM_USAGE(BYTES)
RSSMEM_USAGE(PAGES) FULL_CMD_LINE
 	|- 1779 1778 1778 595 (stress) 60692 8 6672384 48 stress -c 3
 	|- 1781 1778 1778 595 (stress) 60741 6 6672384 48 stress -c 3
 	|- 1780 1778 1778 595 (stress) 60729 5 6672384 48 stress -c 3
 	|- 1778 628 1778 595 (stress) 0 0 6672384 139 stress -c 3

 Get cpu usage -1.0
 	|- PID PPID PGRPID SESSID CMD_NAME USER_MODE_TIME(MILLIS) SYSTEM_TIME(MILLIS) VMEM_USAGE(BYTES)
RSSMEM_USAGE(PAGES) FULL_CMD_LINE
 	|- 1779 1778 1778 595 (stress) 60750 8 6672384 48 stress -c 3
 	|- 1781 1778 1778 595 (stress) 60801 6 6672384 48 stress -c 3
 	|- 1780 1778 1778 595 (stress) 60786 5 6672384 48 stress -c 3
 	|- 1778 628 1778 595 (stress) 0 0 6672384 139 stress -c 3

 Get cpu usage 72.553894

> Metrics for container's actual CPU usage
> ----------------------------------------
>
>                 Key: YARN-3122
>                 URL: https://issues.apache.org/jira/browse/YARN-3122
>             Project: Hadoop YARN
>          Issue Type: Sub-task
>          Components: nodemanager
>    Affects Versions: 2.6.0
>            Reporter: Anubhav Dhoot
>            Assignee: Anubhav Dhoot
>         Attachments: YARN-3122.prelim.patch, YARN-3122.prelim.patch
>
>
> It would be nice to capture resource usage per container, for a variety of reasons. This
JIRA is to track CPU usage. 
> YARN-2965 tracks the resource usage on the node, and the two implementations should reuse
code as much as possible. 



--
This message was sent by Atlassian JIRA
(v6.3.4#6332)

Mime
View raw message