monitors:
- dimensions:
  doc: |
    This monitor reads container stats from a
    Docker API server.  It is meant as a metric-compatible replacement of our
    [docker-collectd](https://github.com/signalfx/docker-collectd-plugin)
    plugin, which scales rather poorly against a large number of containers.

    This currently does not support CPU share/quota metrics.

    For more information on block IO metrics, see [the Linux cgroup block io
    controller
    doc](https://www.kernel.org/doc/Documentation/cgroup-v1/blkio-controller.txt).

    If you are running the agent directly on a host (outside of a container
    itself) and you are using the default Docker UNIX socket URL, you will
    probably need to add the `signalfx-agent` user to the `docker` group in
    order to have permission to access the Docker API via the socket.

    Requires Docker API version 1.22+.
  groups:
    blkio:
      description: BlockIO metrics
    cpu:
      description: CPU metrics
    memory:
      description: Memory metrics
    network:
      description: Network metrics
  metrics:
    blkio.io_service_bytes_recursive.async:
      description: Volume, in bytes, of asynchronous block I/O
      default: false
      type: cumulative
      group: blkio
    blkio.io_service_bytes_recursive.read:
      description: Volume, in bytes, of reads from block devices
      default: true
      type: cumulative
      group: blkio
    blkio.io_service_bytes_recursive.sync:
      description: Volume, in bytes, of synchronous block I/O
      default: false
      type: cumulative
      group: blkio
    blkio.io_service_bytes_recursive.total:
      description: Total volume, in bytes, of all block I/O
      default: false
      type: cumulative
      group: blkio
    blkio.io_service_bytes_recursive.write:
      description: Volume, in bytes, of writes to block devices
      default: true
      type: cumulative
      group: blkio
    blkio.io_serviced_recursive.async:
      description: Number of asynchronous block I/O requests
      default: false
      type: cumulative
      group: blkio
    blkio.io_serviced_recursive.read:
      description: Number of reads requests from block devices
      default: false
      type: cumulative
      group: blkio
    blkio.io_serviced_recursive.sync:
      description: Number of synchronous block I/O requests
      default: false
      type: cumulative
      group: blkio
    blkio.io_serviced_recursive.total:
      description: Total number of block I/O requests
      default: false
      type: cumulative
      group: blkio
    blkio.io_serviced_recursive.write:
      description: Number of write requests to block devices
      default: false
      type: cumulative
      group: blkio
    blkio.io_service_time_recursive.async:
      default: false
      type: cumulative
      group: blkio
    blkio.io_service_time_recursive.sync:
      default: false
      type: cumulative
      group: blkio
    blkio.io_service_time_recursive.read:
      default: false
      type: cumulative
      group: blkio
    blkio.io_service_time_recursive.total:
      default: false
      type: cumulative
      group: blkio
    blkio.io_service_time_recursive.write:
      default: false
      type: cumulative
      group: blkio
    blkio.io_queue_recursive.async:
      default: false
      type: cumulative
      group: blkio
    blkio.io_queue_recursive.sync:
      default: false
      type: cumulative
      group: blkio
    blkio.io_queue_recursive.read:
      default: false
      type: cumulative
      group: blkio
    blkio.io_queue_recursive.total:
      default: false
      type: cumulative
      group: blkio
    blkio.io_queue_recursive.write:
      default: false
      type: cumulative
      group: blkio
    blkio.io_merged_recursive.async:
      default: false
      type: cumulative
      group: blkio
    blkio.io_merged_recursive.sync:
      default: false
      type: cumulative
      group: blkio
    blkio.io_merged_recursive.read:
      default: false
      type: cumulative
      group: blkio
    blkio.io_merged_recursive.total:
      default: false
      type: cumulative
      group: blkio
    blkio.io_merged_recursive.write:
      default: false
      type: cumulative
      group: blkio
    blkio.io_time_recursive.async:
      default: false
      type: cumulative
      group: blkio
    blkio.io_time_recursive.sync:
      default: false
      type: cumulative
      group: blkio
    blkio.io_time_recursive.read:
      default: false
      type: cumulative
      group: blkio
    blkio.io_time_recursive.total:
      default: false
      type: cumulative
      group: blkio
    blkio.io_time_recursive.write:
      default: false
      type: cumulative
      group: blkio
    blkio.io_wait_time_recursive.async:
      default: false
      type: cumulative
      group: blkio
    blkio.io_wait_time_recursive.sync:
      default: false
      type: cumulative
      group: blkio
    blkio.io_wait_time_recursive.read:
      default: false
      type: cumulative
      group: blkio
    blkio.io_wait_time_recursive.total:
      default: false
      type: cumulative
      group: blkio
    blkio.io_wait_time_recursive.write:
      default: false
      type: cumulative
      group: blkio
    cpu.percent:
      description: Percentage of host CPU resources used by the container
      default: false
      type: gauge
      group: cpu
    cpu.percpu.usage:
      description: Jiffies of CPU time spent by the container, per CPU core
      default: false
      type: cumulative
      group: cpu
    cpu.throttling_data.periods:
      description: Number of periods
      default: false
      type: cumulative
      group: cpu
    cpu.throttling_data.throttled_periods:
      description: Number of periods throttled
      default: false
      type: cumulative
      group: cpu
    cpu.throttling_data.throttled_time:
      description: Throttling time in nano seconds
      default: false
      type: cumulative
      group: cpu
    cpu.usage.kernelmode:
      description: Jiffies of CPU time spent in kernel mode by the container
      default: false
      type: cumulative
      group: cpu
    cpu.usage.system:
      description: Jiffies of CPU time used by the system
      default: true
      type: cumulative
      group: cpu
    cpu.usage.total:
      description: Jiffies of CPU time used by the container
      default: true
      type: cumulative
      group: cpu
    cpu.usage.usermode:
      description: Jiffies of CPU time spent in user mode by the container
      default: false
      type: cumulative
      group: cpu
    memory.percent:
      description: Percent of memory (0-100) used by the container relative to its
        limit (excludes page cache usage)
      default: false
      type: gauge
      group: memory
    memory.stats.active_anon:
      description: Amount of memory that has been identified as active by the kernel.
        Anonymous memory is memory that is not linked to disk pages.
      default: false
      type: gauge
      group: memory
    memory.stats.active_file:
      description: Amount of active file cache memory. Cache memory = active_file
        + inactive_file + tmpfs
      default: false
      type: gauge
      group: memory
    memory.stats.cache:
      description: The amount of memory used by the processes of this control group
        that can be associated with a block on a block device. Also accounts for memory
        used by tmpfs.
      default: false
      type: gauge
      group: memory
    memory.stats.dirty:
      description: The amount of memory waiting to get written to disk
      default: false
      type: gauge
      group: memory
    memory.stats.hierarchical_memory_limit:
      description: The memory limit in place by the hierarchy cgroup
      default: false
      type: gauge
      group: memory
    memory.stats.hierarchical_memsw_limit:
      description: The memory+swap limit in place by the hierarchy cgroup
      default: false
      type: gauge
      group: memory
    memory.stats.inactive_anon:
      description: Amount of memory that has been identified as inactive by the kernel.
        Anonymous memory is memory that is not linked to disk pages.
      default: false
      type: gauge
      group: memory
    memory.stats.inactive_file:
      description: Amount of inactive file cache memory. Cache memory = active_file
        + inactive_file + tmpfs
      default: false
      type: gauge
      group: memory
    memory.stats.mapped_file:
      description: Indicates the amount of memory mapped by the processes in the control
        group. It doesn’t give you information about how much memory is used; it rather
        tells you how it is used.
      default: false
      type: gauge
      group: memory
    memory.stats.pgfault:
      description: Number of times that a process of the cgroup triggered a page fault.
        Page faults occur when a process accesses part of its virtual memory space
        which is nonexistent or protected. See https://docs.docker.com/config/containers/runmetrics
        for more info.
      default: false
      type: cumulative
      group: memory
    memory.stats.pgmajfault:
      description: Number of times that a process of the cgroup triggered a major
        page fault. Page faults occur when a process accesses part of its virtual
        memory space which is nonexistent or protected. See https://docs.docker.com/config/containers/runmetrics
        for more info.
      default: false
      type: cumulative
      group: memory
    memory.stats.pgpgin:
      description: Number of charging events to the memory cgroup. Charging events
        happen each time a page is accounted as either mapped anon page(RSS) or cache
        page to the cgroup.
      default: false
      type: cumulative
      group: memory
    memory.stats.pgpgout:
      description: Number of uncharging events to the memory cgroup. Uncharging events
        happen each time a page is unaccounted from the cgroup.
      default: false
      type: cumulative
      group: memory
    memory.stats.rss:
      description: 'The amount of memory that doesn’t correspond to anything on disk:
        stacks, heaps, and anonymous memory maps.'
      default: false
      type: gauge
      group: memory
    memory.stats.rss_huge:
      description: Amount of memory due to anonymous transparent hugepages.
      default: false
      type: gauge
      group: memory
    memory.stats.shmem:
      description: "Amount of [Shared Memory](https://www.kernel.org/doc/gorman/html/understand/understand015.html) used by the container, in bytes."
      default: false
      type: gauge
      group: memory
    memory.stats.swap:
      description: Bytes of swap memory used by container
      default: false
      type: gauge
      group: memory
    memory.stats.total_active_anon:
      description: Total amount of memory that has been identified as active by the
        kernel. Anonymous memory is memory that is not linked to disk pages.
      default: false
      type: gauge
      group: memory
    memory.stats.total_active_file:
      description: Total amount of active file cache memory. Cache memory = active_file
        + inactive_file + tmpfs
      default: false
      type: gauge
      group: memory
    memory.stats.total_cache:
      description: Total amount of memory used by the processes of this control group
        that can be associated with a block on a block device. Also accounts for memory
        used by tmpfs.
      default: false
      type: gauge
      group: memory
    memory.stats.total_dirty:
      description: Total amount of memory waiting to get written to disk
      default: false
      type: gauge
      group: memory
    memory.stats.total_inactive_anon:
      description: Total amount of memory that has been identified as inactive by
        the kernel. Anonymous memory is memory that is not linked to disk pages.
      default: false
      type: gauge
      group: memory
    memory.stats.total_inactive_file:
      description: Total amount of inactive file cache memory. Cache memory = active_file
        + inactive_file + tmpfs
      default: false
      type: gauge
      group: memory
    memory.stats.total_mapped_file:
      description: Total amount of memory mapped by the processes in the control group.
        It doesn’t give you information about how much memory is used; it rather tells
        you how it is used.
      default: false
      type: gauge
      group: memory
    memory.stats.total_pgfault:
      description: Total number of page faults
      default: false
      type: cumulative
      group: memory
    memory.stats.total_pgmajfault:
      description: Total number of major page faults
      default: false
      type: cumulative
      group: memory
    memory.stats.total_pgpgin:
      description: Total number of charging events
      default: false
      type: cumulative
      group: memory
    memory.stats.total_pgpgout:
      description: Total number of uncharging events
      default: false
      type: cumulative
      group: memory
    memory.stats.total_rss:
      description: 'Total amount of memory that doesn’t correspond to anything on
        disk: stacks, heaps, and anonymous memory maps.'
      default: false
      type: gauge
      group: memory
    memory.stats.total_rss_huge:
      description: Total amount of memory due to anonymous transparent hugepages.
      default: false
      type: gauge
      group: memory
    memory.stats.total_shmem:
      description: "Available amount of [Shared Memory](https://www.kernel.org/doc/gorman/html/understand/understand015.html) used by the container, in bytes."
      default: false
      type: gauge
      group: memory
    memory.stats.total_swap:
      description: "Total amount of swap memory available to this container"
      default: false
      type: gauge
      group: memory
    memory.stats.total_unevictable:
      description: Total amount of memory that can not be reclaimed
      default: false
      type: gauge
      group: memory
    memory.stats.total_writeback:
      description: Total amount of memory from file/anon cache that are queued for
        syncing to the disk
      default: false
      type: gauge
      group: memory
    memory.stats.unevictable:
      description: The amount of memory that cannot be reclaimed.
      default: false
      type: gauge
      group: memory
    memory.stats.writeback:
      description: The amount of memory from file/anon cache that are queued for syncing
        to the disk
      default: false
      type: gauge
      group: memory
    memory.usage.limit:
      description: Memory usage limit of the container, in bytes
      default: true
      type: gauge
      group: memory
    memory.usage.max:
      description: Maximum measured memory usage of the container, in bytes
      default: false
      type: gauge
      group: memory
    memory.usage.total:
      description: |
        Bytes of memory used by the container. Note that this **includes the
        buffer cache** attributed to the process by the kernel from files that
        have been read by processes in the container.  If you don't want to
        count that when monitoring containers, enable the metric
        `memory.stats.total_cache` and subtract that metric from this one.
      default: true
      type: gauge
      group: memory
    network.usage.rx_bytes:
      description: Bytes received by the container via its network interface
      default: true
      type: cumulative
      group: network
    network.usage.rx_dropped:
      description: Number of inbound network packets dropped by the container
      default: false
      type: cumulative
      group: network
    network.usage.rx_errors:
      description: Errors receiving network packets
      default: false
      type: cumulative
      group: network
    network.usage.rx_packets:
      description: Network packets received by the container via its network interface
      default: false
      type: cumulative
      group: network
    network.usage.tx_bytes:
      description: Bytes sent by the container via its network interface
      default: true
      type: cumulative
      group: network
    network.usage.tx_dropped:
      description: Number of outbound network packets dropped by the container
      default: false
      type: cumulative
      group: network
    network.usage.tx_errors:
      description: Errors sending network packets
      default: false
      type: cumulative
      group: network
    network.usage.tx_packets:
      description: Network packets sent by the container via its network interface
      default: false
      type: cumulative
      group: network
  monitorType: docker-container-stats
  properties: