美文网首页监控采集
docker.cpu Metrics from DataDog

docker.cpu Metrics from DataDog

作者: xufeibuaa | 来源:发表于2018-09-03 12:48 被阅读42次
    • docker.cpu.system
    • The percent of time the CPU is executing system calls on behalf of processes of this container, unnormalized
    • percent
    • docker.cpu.user
    • The percent of time the CPU is under direct control of processes of this container, unnormalized
    • percent
    • docker.cpu.usage
    • The percent of CPU time obtained by this container
    • percent
    • docker.cpu.throttled
    • Number of times the cgroup has been throttled
    • docker.cpu.shares
    • Shares of CPU usage allocated to the container

    计算公式

    docker.cpu.user = RATE(user)
    docker.cpu.system = RATE(system)
    docker.cpu.usage = RATE(usage / 10000000)
    docker.cpu.throttled = RATE(nr_throttled)
    docker.cpu.shares = RATE(shares)
    

    数据来源

    容器对应的cpuacct.stat and cpuacct.usage文件可能在如下三个位置:

    • /sys/fs/cgroup/cpuacct/docker/<container_id>/
    • /sys/fs/cgroup/cpuacct/kubepods/burstable/<pod_id>/<container_id>/
    • /sys/fs/cgroup/cpuacct/kubepods/besteffort/<pod_id>/<container_id>/
    • /sys/fs/cgroup/cpuacct/kubepods/<pod_id>/<container_id>/

    容器对应的cpu.stat and cpu.shares文件可能在如下三个位置:

    • /sys/fs/cgroup/cpu/docker/<container_id>/
    • /sys/fs/cgroup/cpu/kubepods/burstable/<pod_id>/<container_id>/
    • /sys/fs/cgroup/cpu/kubepods/besteffort/<pod_id>/<container_id>/
    • /sys/fs/cgroup/cpu/kubepods/<pod_id>/<container_id>/

    文件示例内容如下:

    # cat cpuacct.stat
    
    user 119045
    system 75873
    
    # cat cpuacct.usage
    
    2397517073279
    
    # cat cpu.stat
    
    nr_periods 0
    nr_throttled 0
    throttled_time 0
    
    # cat cpu.shares
    
    1024
    

    相关文章

      网友评论

        本文标题:docker.cpu Metrics from DataDog

        本文链接:https://www.haomeiwen.com/subject/zdubwftx.html