Netdata Menu Context WIP

ctx.yml

# MAIN GUIDELINES
# * All metrics related to system resources are put under `system` as a root, this implies a merging of System with CPU, Disk, Network, Memory, etc.
# * There wasn't (much) of a concern to keep the hierarhy/section levels to a minimum, logic was priortized against outcome
# * Netdata Overview screen with in-section filter capabilites, as well as, better and easier Custom Dashboard creation/management features are considered to allow better UX
# * POC was focused on doing some sections to proof the logic, System, Virtualization, ...
# * OpenTelemety Metric Semantic Convetions were followed to the best of our understanding (even they seem to have different approaches in different domains) - https://github.com/open-telemetry/opentelemetry-specification/blob/main/specification/metrics/semantic_conventions/README.md
#   - same metric attributes were purposefuly set as part of the context name to better present things to the user, e.g. system.cpu.core.utilization where `core` should be an attribute
#
# * Future ideas discussed outside of the scope of this work:
#  - collectors should provide the following context of a metric (likely more, the gist is to provide a context):
#    - applicable/default aggregation methods (e.g. no sense in SUM temperature|network interface duplex|any metric that represents encodes a state (0: running, 1: pending, 2: failed, etc.))
#    - applicable/default grouping methods
#    - key/main metrics, which should be shown per default and an element with (...) would allow user to expand --> user perference could override this

System:
  CPU:
    utilization:
    context:
    softnet:
    idlejitter:
    softirqs:
    interrupts:
    device:
      interrupts:
    core:
      utilization:
      frequency:
      softnet:
      cstate_residency_time:
      throttling:
      softirqs:
      device:
        interrupts:
  Memory:
    ram:
    available:
    pgfaults:
    oom_kill:
    ksm:
      deduplication:
      savings:
      effectiveness:
  Storage:
    physical_io:
    memory_paged:
    disk:
      io:
      busy_time:
      utilization:
      operations:
        completed:
        current:
        merged:
        backlog:
        size:
        io_time:
        service_time:
        await_time:
      extended_ops:
        discards:
        merged:
        operations:
        size:
        io_time:
        await_time:
    mountpoints:
      space:
        usage:
      inodes:
        usage:
    filesystem:
      zfs:
      btrfs:
      nfs:
  Network:
    physical_io:
    io:
    ipv4:
      io:
      packets:
      errors:
      tcp:
      udp:
      icmp:
        packets:
        errors:
        type:
          packets:
    ipv6:
      io:
      packets:
      errors:
      tcp:
      udp:
      icmp:
    sockets:
    interface:
      io:
      packets:
      drops:
      operstate:
      carrier:
      speed:
      duplex:
      mtu:
  Load:
    average:
    pressure:
      cpu:
      some:
        share:
        stall_time:
      full:
        share:
        stall_time:
      memory:
        some:
          share:
          stall_time:
        full:
          share:
          stall_time:
      io:
        some:
          share:
          stall_time:
        full:
          share:
          stall_time:
  IPC:
    semaphore:
      semaphores:
        usage:
      sets:
        usage:
    shared_memory:
      segments:
        usage:
      size:
        usage:
    message_queue:
      messages:
        usage:
      size:
        usage:
  Processes:
    active:
    forks:
    runnable:
    blocked:
    state:
  Entropy:
  Clock:
    sync:
      state:
      offset:
    status:
  Uptime:

Systemd:
  Services:
    cpu:
      utilization:
    memory:
      usage:
    disk:
      io:
        read:
        write:
      operations:
        read:
        write:

Processes:
  Groups:
    cpu:
    memory:
    swap:
    disk:
    network:
  UserGroups:
    cpu:
    memory:
    swap:
    disk:
    network:
  Users:
    cpu:
    memory:
    swap:
    disk:
    network:

K8S:
  kubelet:
  kubeproxy:
  kubestate:
  containers:
    cpu:
      utilization:
      usage:
      pressure:
        some:
          share:
          stall_time:
        full:
          share:
          stall_time:
      throttling:
        quota:
          utilization:
        duration:
    memory:
      utilization:
      usage:
      pressure:
        some:
          share:
          stall_time:
        full:
          share:
          stall_time:
      swap:
      pgfaults:
      writeback:
      stats:
    disk:
      io:
        pressure:
          some:
            share:
            stall_time:
          full:
            share:
            stall_time:
    network:
      interface:
        io:
        packets:
        operstate:
          mtu:

Containers:
  cpu:
    utilization:
    usage:
    pressure:
      some:
        share:
        stall_time:
      full:
        share:
        stall_time:
    throttling:
      quota:
        utilization:
      duration:
  memory:
    utilization:
    usage:
    pressure:
      some:
        share:
        stall_time:
      full:
        share:
        stall_time:
    swap:
    pgfaults:
    writeback:
    stats:
  disk:
    io:
      pressure:
        some:
          share:
          stall_time:
        full:
          share:
          stall_time:
  network:
    interface:
      io:
      packets:
      operstate:
      mtu:

VMs:
  cpu:
    utilization:
    usage:
    pressure:
      some:
        share:
        stall_time:
      full:
        share:
        stall_time:
    throttling:
      quota:
        utilization:
      duration:
  memory:
    utilization:
    usage:
    pressure:
      some:
        share:
        stall_time:
      full:
        share:
        stall_time:
    swap:
    pgfaults:
    writeback:
    stats:
  disk:
    io:
      pressure:
        some:
          share:
          stall_time:
        full:
          share:
          stall_time:
  network:
    interface:
      io:
      packets:
      operstate:
      mtu:

Database:
  MySQL:
  Postgres:
Web:
  Apache:
  Haproxy:
  Nginx:

Checks:
  Web:
  Port:
  Files&Directories:
  Fping:
  WHOIS:
  Certificates:
  DNS:
  IOPing:

Hardware:
  GPU:
  CUPS:
  Sensors:
  UPS:

SNMP: