1apiVersion: policy/v1
2kind: PodDisruptionBudget
3metadata:
4  name: zk-pdb
5spec:
6  maxUnavailable: 1
7  selector:
8    matchLabels:
9      app: zookeeper

1spec:
2  groups:
3    - name: machine_cpu_mem_usage_active
4      interval: 30s
5      rules:
6        - record: machine_memory_usage_active
7          expr: 100*(1-node_memory_MemAvailable_bytes/node_memory_MemTotal_bytes)
8    - name: machine_memory_usage_1m
9      interval: 1m
10      rules:
11        - record: machine_memory_usage_5m
12          expr: 'avg_over_time(machine_memory_usage_active[5m])'
13    - name: machine_cpu_usage_1m
14      interval: 1m
15      rules:
16        - record: machine_cpu_usage_5m
17          expr: >-
18            100 - (avg by (instance, clusterID)
19            (irate(node_cpu_seconds_total{mode="idle"}[5m])) * 100)
20    - name: container_cpu_usage_10m
21      interval: 1m
22      rules:
23        - record: container_cpu_usage_total_5m
24          expr: >-
25            sum by(namespace, pod,
26            clusterID)(rate(container_cpu_usage_seconds_total{pod!='',image=''}[5m]))
27            * 1000
28    - name: container_memory_working_set_bytes_pod
29      interval: 1m
30      rules:
31        - record: container_memory_working_set_bytes_by_pod
32          expr: 'container_memory_working_set_bytes{pod!='''',image=''''}'

1scrape_configs:
2  - job_name: "kubernetes-cadvisor"
3    # Default to scraping over https. If required, just disable this or change to
4    # `http`.
5    scheme: https
6    
7    # Starting Kubernetes 1.7.3 the cAdvisor metrics are under /metrics/cadvisor.
8    # Kubernetes CIS Benchmark recommends against enabling the insecure HTTP
9    # servers of Kubernetes, therefore the cAdvisor metrics on the secure handler
10    # are used.
11    metrics_path: /metrics/cadvisor
12    
13    # This TLS & authorization config is used to connect to the actual scrape
14    # endpoints for cluster components. This is separate to discovery auth
15    # configuration because discovery & scraping are two separate concerns in
16    # Prometheus. The discovery auth config is automatic if Prometheus runs inside
17    # the cluster. Otherwise, more config options have to be provided within the
18    # <kubernetes_sd_config>.
19    tls_config:
20      ca_file: /var/run/secrets/kubernetes.io/serviceaccount/ca.crt
21      # If your node certificates are self-signed or use a different CA to the
22      # master CA, then disable certificate verification below. Note that
23      # certificate verification is an integral part of a secure infrastructure
24      # so this should only be disabled in a controlled environment. You can
25      # disable certificate verification by uncommenting the line below.
26      #
27      insecure_skip_verify: true
28    authorization:
29      credentials_file: /var/run/secrets/kubernetes.io/serviceaccount/token
30    
31    kubernetes_sd_configs:
32      - role: node
33    
34    relabel_configs:
35      - action: labelmap
36        regex: __meta_kubernetes_node_label_(.+)
37 
38  - job_name: 'node-exporter'
39      kubernetes_sd_configs:
40        - role: pod
41      relabel_configs:
42      - source_labels: [__meta_kubernetes_pod_name]
43        regex: 'node-exporter-(.+)'
44        action: keep

1spec:
2  groups:
3    - name: machine_cpu_mem_usage_active
4      interval: 30s
5      rules:
6        - record: machine_memory_usage_active
7          expr: 100*(1-node_memory_MemAvailable_bytes/node_memory_MemTotal_bytes)
8    - name: machine_memory_usage_1m
9      interval: 1m
10      rules:
11        - record: machine_memory_usage_5m
12          expr: 'avg_over_time(machine_memory_usage_active[5m])'
13    - name: machine_cpu_usage_1m
14      interval: 1m
15      rules:
16        - record: machine_cpu_usage_5m
17          expr: >-
18            100 - (avg by (instance)
19            (irate(node_cpu_seconds_total{mode="idle"}[5m])) * 100)
20    - name: container_cpu_usage_10m
21      interval: 1m
22      rules:
23        - record: container_cpu_usage_total_5m
24          expr: >-
25            sum by(namespace, pod)(rate(container_cpu_usage_seconds_total{pod!='',image=''}[5m])) * 1000
26    - name: container_memory_working_set_bytes_pod
27      interval: 1m
28      rules:
29        - record: container_memory_working_set_bytes_by_pod
30          expr: 'container_memory_working_set_bytes{pod!='''',image=''''}'