k8s-node.yaml

# Licensed to the Apache Software Foundation (ASF) under one or more
# contributor license agreements.  See the NOTICE file distributed with
# this work for additional information regarding copyright ownership.
# The ASF licenses this file to You under the Apache License, Version 2.0
# (the "License"); you may not use this file except in compliance with
# the License.  You may obtain a copy of the License at
#
#     http://www.apache.org/licenses/LICENSE-2.0
#
# Unless required by applicable law or agreed to in writing, software
# distributed under the License is distributed on an "AS IS" BASIS,
# WITHOUT WARRANTIES OR CONDITIONS OF ANY KIND, either express or implied.
# See the License for the specific language governing permissions and
# limitations under the License.

# This will parse a textual representation of a duration. The formats
# accepted are based on the ISO-8601 duration format {@code PnDTnHnMn.nS}
# with days considered to be exactly 24 hours.
# <p>
# Examples:
# <pre>
#    "PT20.345S" -- parses as "20.345 seconds"
#    "PT15M"     -- parses as "15 minutes" (where a minute is 60 seconds)
#    "PT10H"     -- parses as "10 hours" (where an hour is 3600 seconds)
#    "P2D"       -- parses as "2 days" (where a day is 24 hours or 86400 seconds)
#    "P2DT3H4M"  -- parses as "2 days, 3 hours and 4 minutes"
#    "P-6H3M"    -- parses as "-6 hours and +3 minutes"
#    "-P6H3M"    -- parses as "-6 hours and -3 minutes"
#    "-P-6H+3M"  -- parses as "+6 hours and -3 minutes"
# </pre>
filter: "{ tags -> tags.job_name in [ 'kubernetes-cadvisor', 'kube-state-metrics' ] }" # The OpenTelemetry job name
expSuffix: tag({tags -> tags.cluster = 'k8s-cluster::' + tags.cluster}).instance(['cluster'] , ['node'])
metricPrefix: k8s_node
metricsRules:

  - name: cpu_cores
    exp: (kube_node_status_capacity * 1000).tagEqual('resource' , 'cpu').sum(['cluster' , 'node'])
  - name: cpu_usage
    exp: (container_cpu_usage_seconds_total * 1000).tagEqual('id' , '/').sum(['cluster' , 'node']).irate()
  - name: cpu_cores_allocatable
    exp: (kube_node_status_allocatable * 1000).tagEqual('resource' , 'cpu').sum(['cluster' , 'node'])
  - name: cpu_cores_requests
    exp: (kube_pod_container_resource_requests * 1000).tagEqual('resource' , 'cpu').sum(['cluster' , 'node'])
  - name: cpu_cores_limits
    exp: (kube_pod_container_resource_limits * 1000).tagEqual('resource' , 'cpu').sum(['cluster' , 'node'])

  - name: memory_total
    exp: kube_node_status_capacity.tagEqual('resource' , 'memory').sum(['cluster' , 'node'])
  - name: memory_allocatable
    exp: kube_node_status_allocatable.tagEqual('resource' , 'memory').sum(['cluster' , 'node'])
  - name: memory_requests
    exp: kube_pod_container_resource_requests.tagEqual('resource' , 'memory').sum(['cluster' , 'node'])
  - name: memory_limits
    exp: kube_pod_container_resource_limits.tagEqual('resource' , 'memory').sum(['cluster' , 'node'])

  - name: memory_usage
    exp: container_memory_working_set_bytes.tagEqual('id' , '/').sum(['cluster' , 'node'])


  - name: storage_total
    exp: kube_node_status_capacity.tagEqual('resource' , 'ephemeral_storage').sum(['cluster' , 'node'])
  - name: storage_allocatable
    exp: kube_node_status_allocatable.tagEqual('resource' , 'ephemeral_storage').sum(['cluster' , 'node'])

  - name: node_status
    exp: kube_node_status_condition.valueEqual(1).tagMatch('status' , 'true|unknown').sum(['cluster' , 'node' ,'condition'])

  - name: pod_total
    exp: kube_pod_info.sum(['cluster' , 'node'])

  - name: network_receive
    exp: container_network_receive_bytes_total.tagEqual('id' , '/').sum(['cluster' , 'node']).irate()
  - name: network_transmit
    exp: container_network_transmit_bytes_total.tagEqual('id' , '/').sum(['cluster' , 'node']).irate()