Configure Prometheus to scrape Kubelets directly

* Use Kubelet bearer token authn/authz to scrape metrics
* Drop RBAC permission from nodes/proxy to nodes/metrics
* Stop proxying kubelet scrapes through the apiserver, since
this required higher privilege (nodes/proxy) and can add
load to the apiserver on large clusters
This commit is contained in:
Dalton Hubble
2018-05-13 23:49:45 -07:00
parent 37981f9fb1
commit c2b719dc75
7 changed files with 40 additions and 38 deletions

View File

@ -56,12 +56,7 @@ data:
target_label: job
# Scrape config for node (i.e. kubelet) /metrics (e.g. 'kubelet_'). Explore
# metrics from a node by scraping kubelet (127.0.0.1:10255/metrics).
#
# Rather than connecting directly to the node, the scrape is proxied though the
# Kubernetes apiserver. This means it will work if Prometheus is running out of
# cluster, or can't connect to nodes for some other reason (e.g. because of
# firewalling).
# metrics from a node by scraping kubelet (127.0.0.1:10250/metrics).
- job_name: 'kubelet'
kubernetes_sd_configs:
- role: node
@ -69,50 +64,34 @@ data:
scheme: https
tls_config:
ca_file: /var/run/secrets/kubernetes.io/serviceaccount/ca.crt
# Kubelet certs don't have any fixed IP SANs
insecure_skip_verify: true
bearer_token_file: /var/run/secrets/kubernetes.io/serviceaccount/token
relabel_configs:
- action: labelmap
regex: __meta_kubernetes_node_label_(.+)
- target_label: __address__
replacement: kubernetes.default.svc:443
- source_labels: [__meta_kubernetes_node_name]
regex: (.+)
target_label: __metrics_path__
replacement: /api/v1/nodes/${1}/proxy/metrics
# Scrape config for Kubelet cAdvisor. Explore metrics from a node by
# scraping kubelet (127.0.0.1:10255/metrics/cadvisor).
#
# This is required for Kubernetes 1.7.3 and later, where cAdvisor metrics
# (those whose names begin with 'container_') have been removed from the
# Kubelet metrics endpoint. This job scrapes the cAdvisor endpoint to
# retrieve those metrics.
#
# Rather than connecting directly to the node, the scrape is proxied though the
# Kubernetes apiserver. This means it will work if Prometheus is running out of
# cluster, or can't connect to nodes for some other reason (e.g. because of
# firewalling).
# scraping kubelet (127.0.0.1:10250/metrics/cadvisor).
- job_name: 'kubernetes-cadvisor'
kubernetes_sd_configs:
- role: node
scheme: https
metrics_path: /metrics/cadvisor
tls_config:
# Kubelet certs don't have any fixed IP SANs
insecure_skip_verify: true
ca_file: /var/run/secrets/kubernetes.io/serviceaccount/ca.crt
bearer_token_file: /var/run/secrets/kubernetes.io/serviceaccount/token
relabel_configs:
- action: labelmap
regex: __meta_kubernetes_node_label_(.+)
- target_label: __address__
replacement: kubernetes.default.svc:443
- source_labels: [__meta_kubernetes_node_name]
regex: (.+)
target_label: __metrics_path__
replacement: /api/v1/nodes/${1}/proxy/metrics/cadvisor
# Scrap etcd metrics from controllers
# Scrap etcd metrics from controllers via listen-metrics-urls
- job_name: 'etcd'
kubernetes_sd_configs:
- role: node

View File

@ -6,7 +6,7 @@ rules:
- apiGroups: [""]
resources:
- nodes
- nodes/proxy
- nodes/metrics
- services
- endpoints
- pods