myLimbo/casa
1
0
Fork 0
Code Issues Pull Requests Projects Releases Wiki Activity

monitoring: remove prometheus stack, add alloy

Browse Source
This commit is contained in:
Márcio Fernandes
2026-08-30 22:15:39 +00:00
parent 4913882963
commit 115a600055
6 changed files with 192 additions and 246 deletions
Download Patch File Download Diff File Expand all files Collapse all files
services/monitoring/README.md
-5
View File
@@ -1,10 +1,5 @@
# monitoring
## prometheus-stack
- <https://github.com/prometheus-community/helm-charts/tree/main/charts/kube-prometheus-stack>
- <https://github.com/prometheus-community/helm-charts/blob/main/charts/kube-prometheus-stack/values.yaml>
## alloy
**promtail Encrypt secrets:**
services/monitoring/deploy/alloy/global/secrets.yaml
+9 -9
View File
@@ -3,20 +3,20 @@ kind: Secret
metadata:
name: alloy-global
stringData:
loki_url: ENC[AES256_GCM,data:xuMvbrKhvwvJK38ES59SuD/X5CywK3qlnDfSsYmr0W3TLv0wB08wT9kCd57pctlvAqL5RNYTaTIgJ1w=,iv:YqPv1DBbfmVC8P1KgEJPiOtYzx+OcfySIxPjqMjCnhA=,tag:aw7iW8gljmVhPvkKSKh5mw==,type:str]
prometheus_url: ENC[AES256_GCM,data:MqNjAcGzi87gC2A2+G6xcn7FroYUczfkNHj0eCXZVi46AJH+dKjFU/pVwtMIrz1Aikz4BhX0ZviijrvYlw==,iv:IydlpoIOq4bipZV/xihvpmYO/sBerDX2z+8LGl3Gu6k=,tag:dJv6nUncoJGcuoR8eQFitg==,type:str]
loki_url: ENC[AES256_GCM,data:2DeZZ+7deDbojQ/+YNgT8KwDmjFFyAqMcTX8l6itlF15hilXKgYP1p/SNoyw1JGJ7x5VZqUl0VIVhVY=,iv:SlFiLvEeIqj+zQ/8Jspc9FL/ElneIlWBzGsM+6mGZLc=,tag:9tIl6fi+xfmF+TJpMXgbKg==,type:str]
prometheus_url: ENC[AES256_GCM,data:k8Z3lvZRxOmlw6Wx4aLAgV93hPcEawtoprWU2Kn6j/WIe/YDHM9iuB+pRy7ght4I6jxyNFLotN0BaHE1yg==,iv:EEnRoS287e9EV8+25NtlEO31zN0eyfRBOUe9GVBah18=,tag:2K/MnM1QlWPbceQBqCwylw==,type:str]
sops:
age:
- enc: |
-----BEGIN AGE ENCRYPTED FILE-----
YWdlLWVuY3J5cHRpb24ub3JnL3YxCi0+IFgyNTUxOSBpemRxQTNtUTQ2a1dUcnpu
VjNlN29OeGRrdDN1bm8yWC9hYllBNVNjSVJvCnR5RUU2Z1B0RWFxREFoUlVIVStM
c1AvbUlXa0dOTDF3VkhJRGdGME1oS1UKLS0tIDdncERRSDFKRnBlMW5kMkQ1VFhs
bXJYbmZyUXJ4NU1YOEhpdmhTT2I3S2MK+Zx6ntTO08AxawYo+jKOPTfpMVXdsvlC
5hNPs6bqxei+Fa6q87LZrFENwdxjeti6QuKoi45acoOQ6zI2TM9yNw==
YWdlLWVuY3J5cHRpb24ub3JnL3YxCi0+IFgyNTUxOSBJYmx1dGJTSGZvbVdpV1di
Z3dKNUJPVGNkK1hBSnVoRXZrb0R4TmxnUjM4CmpyUXpGN2lneDViN3VPNC9Fa3d6
RURxZTFuV0o1SzF5ZEhzSVZyYkY5alkKLS0tIEF1T0tINnRUa0tDOGlaSVRJajF5
bTFTd0c4Z3p1aUNWWTZ0ZFVXQVdrMjAKku2YU048qf4E9vEPO19HNfAg78E3fSFQ
WBiUgiqtqG/T4cI5cf4CUWoUogtABawBG4z5G5+ud7sfVMzfqW+W1g==
-----END AGE ENCRYPTED FILE-----
recipient: age1f9e4pvp5y8gzuk8mz2s5xm85dd7znxhk56tcpuxqwn78qfjwja0qekwlju
encrypted_regex: ^(data|stringData)$
lastmodified: "2026-08-30T10:21:08Z"
mac: ENC[AES256_GCM,data:FZkuO1JP6Ds3XUAWUa0tpb2gVcnFC9Ki3owd+f7On+Nu0EvVRqVBzrSLBXxPVOQ69jj9HDiQVFmYq2fsRd5aAItCA+Jry/2M7m6j6BfyzPMmEChemTYSJQKvQy7l9r4FYwXqvBJ8TmPQv3wc+VPrhiYegWusF/YzcZzFvvUwVOE=,iv:gQUZEbK5l/3Gc6Xcm3RAF5kMaV14dYH/Og+SKrdhUtw=,tag:YVE3seBOcDl31huyDog+FA==,type:str]
lastmodified: "2026-08-30T22:14:34Z"
mac: ENC[AES256_GCM,data:XQ2zRn6zGBONfBiyaip3DpwzIfDBN1mPI65fVfH3c7tsEeY1mV/ZRPD+5iJsiwxlnBa7Rq0iJNOr2f84JE+CiuqYz8UKuQMS02gsvqXuBSgUn5vDRcX/aBV3+1GSOzv3ilmwMkJI/jxfyyXL4YsxKl0fsFEOJRsa3VCCVF0OvrM=,iv:enk8h+TfYBIOFln3SlOw30arg2T/kSU3IMwusrm68Qc=,tag:yp9eQc56Ht6g3x3QnMqMZg==,type:str]
version: 3.13.1
services/monitoring/deploy/alloy/kube-scraper/helm-values.yaml
+178 -6
View File
@@ -147,15 +147,182 @@ alloy:
}
}
// stage.labels {
// values = {
// kubernetes_cluster_events = "job",
// }
// }
}
discovery.kubernetes "k8s_nodes" {
role = "node"
}
discovery.relabel "cadvisor" {
targets = discovery.kubernetes.k8s_nodes.targets
rule {
replacement = "/metrics/cadvisor"
target_label = "__metrics_path__"
}
rule {
target_label = "instance"
replacement = env("NODE_IP") + ":10250"
}
rule {
target_label = "node"
replacement = env("HOSTNAME")
}
rule {
target_label = "service"
replacement = "kube-scrapper"
}
rule {
target_label = "cluster"
replacement = env("CLUSTER_NAME")
}
rule {
target_label = "job"
replacement = "kubelet"
}
}
prometheus.remote_write "metrics_service" {
endpoint {
url = env("PROMETHEUS_URL")
}
}
prometheus.scrape "cadvisor" {
job_name = "integrations/kubernetes/cadvisor"
targets = discovery.relabel.cadvisor.output
scheme = "https"
tls_config {
server_name = "kubernetes"
ca_file = "/var/run/secrets/kubernetes.io/serviceaccount/ca.crt"
insecure_skip_verify = true
}
bearer_token_file = "/var/run/secrets/kubernetes.io/serviceaccount/token"
forward_to = [prometheus.remote_write.metrics_service.receiver]
}
discovery.kubernetes "k8s_services" {
role = "service"
}
discovery.relabel "ksm" {
targets = discovery.kubernetes.k8s_services.targets
rule {
source_labels = ["__meta_kubernetes_service_name"]
regex = "kube-state-metrics"
action = "keep"
}
}
prometheus.scrape "kube_state_metrics" {
job_name = "integrations/kubernetes/kube-state-metrics"
targets = discovery.relabel.ksm.output
scheme = "http"
forward_to = [prometheus.remote_write.metrics_service.receiver]
}
// ============================================
// CoreDNS discovery
// ============================================
discovery.kubernetes "coredns_pod" {
role = "pod"
}
discovery.relabel "coredns" {
targets = discovery.kubernetes.pod.targets
rule {
source_labels = ["__meta_kubernetes_pod_label_k8s_app"]
regex = "kube-dns"
action = "keep"
}
rule {
target_label = "node"
replacement = env("HOSTNAME")
}
rule {
target_label = "cluster"
replacement = env("CLUSTER_NAME")
}
}
// ============================================
// CoreDNS scrape
// ============================================
prometheus.scrape "coredns" {
job_name = "integrations/kubernetes/coredns-pods"
targets = discovery.relabel.coredns.output
scheme = "http"
metrics_path = "/metrics"
forward_to = [prometheus.remote_write.metrics_service.receiver]
}
// ============================================
// API Server discovery
// ============================================
discovery.kubernetes "apiserver_services" {
role = "service"
}
discovery.relabel "apiserver" {
targets = discovery.kubernetes.apiserver_services.targets
rule {
source_labels = ["__meta_kubernetes_service_name"]
regex = "kubernetes"
action = "keep"
}
rule {
target_label = "node"
replacement = env("HOSTNAME")
}
rule {
target_label = "cluster"
replacement = env("CLUSTER_NAME")
}
}
// ============================================
// API Server scrape
// ============================================
prometheus.scrape "apiserver" {
job_name = "integrations/kubernetes/apiserver"
targets = discovery.relabel.apiserver.output
scheme = "https"
metrics_path = "/metrics"
tls_config {
server_name = "kubernetes"
ca_file = "/var/run/secrets/kubernetes.io/serviceaccount/ca.crt"
insecure_skip_verify = true
}
bearer_token_file = "/var/run/secrets/kubernetes.io/serviceaccount/token"
forward_to = [prometheus.remote_write.metrics_service.receiver]
}
extraEnv:
- name: NODE_IP
valueFrom:
fieldRef:
fieldPath: status.hostIP
- name: NODE_NAME
valueFrom:
fieldRef:
@@ -169,3 +336,8 @@ alloy:
secretKeyRef:
name: alloy-global
key: loki_url
- name: PROMETHEUS_URL
valueFrom:
secretKeyRef:
name: alloy-global
key: prometheus_url
services/monitoring/deploy/prometheus/helm-release.yaml
+4 -8
View File
@@ -1,19 +1,15 @@
apiVersion: helm.toolkit.fluxcd.io/v2
kind: HelmRelease
metadata:
name: kube-prometheus-stack
name: kube-state-metrics
spec:
releaseName: prometheus
releaseName: kube-state-metrics
interval: 1m
chart:
spec:
chart: kube-prometheus-stack
version: 86.x.x
chart: kube-state-metrics
version: 8.x.x
sourceRef:
kind: HelmRepository
name: prometheus
interval: 40h
valuesFrom:
- kind: Secret
name: prometheus-stack-helm-values
valuesKey: values.yaml
services/monitoring/deploy/prometheus/helm-values.yaml
-141
View File
@@ -1,141 +0,0 @@
defaultRules:
create: false
alertmanager:
enabled: false
grafana:
enabled: false
prometheus:
enabled: false
kubeStateMetrics:
enabled: true
nodeExporter:
enabled: false
prometheus-node-exporter:
prometheus:
monitor:
enabled: false
coreDns:
enabled: true
serviceMonitor:
relabelings:
- targetLabel: cluster
replacement: casa
kubeApiServer:
enabled: true
serviceMonitor:
relabelings:
- targetLabel: cluster
replacement: casa
kubeControllerManager:
enabled: false
kubeEtcd:
enabled: false
kubeProxy:
enabled: false
kubeScheduler:
enabled: false
kube-state-metrics:
podLabels:
role: worker-node
nodeSelector:
role: worker-node
prometheus:
monitor:
relabelings:
- targetLabel: cluster
replacement: casa
prometheusOperator:
kubeletService:
enabled: true
enabled: true
createCustomResource: true
tls:
enabled: false
admissionWebhooks:
enabled: false
cleanupCustomResource: false
serviceMonitor:
selfMonitor: false
kubelet:
enabled: true
namespace: kube-system
serviceMonitor:
interval: 60s #WARN: Error on ingesting out-of-order samples. https://github.com/prometheus-community/helm-charts/issues/5483
enabled: true
## Enable scraping /metrics from kubelet's service
kubelet: true
probesMetricRelabelings:
- targetLabel: cluster
replacement: casa
- sourceLabels: [__name__, image]
separator: ;
regex: container_([a-z_]+);
replacement: $1
action: drop
- sourceLabels: [__name__]
separator: ;
regex: container_(network_tcp_usage_total|network_udp_usage_total|tasks_state|cpu_load_average_10s)
replacement: $1
action: drop
# # RelabelConfigs to apply to samples before scraping
# # ref: https://github.com/prometheus-operator/prometheus-operator/blob/main/Documentation/api-reference/api.md#relabelconfig
# #
# # metrics_path is required to match upstream rules and charts
cAdvisorRelabelings:
- targetLabel: cluster
replacement: casa
- action: replace
sourceLabels: [__metrics_path__]
targetLabel: metrics_path
- sourceLabels: [__meta_kubernetes_pod_node_name]
separator: ;
regex: ^(.*)$
targetLabel: nodename
replacement: $1
action: replace
# # RelabelConfigs to apply to samples before scraping
# # ref: https://github.com/prometheus-operator/prometheus-operator/blob/main/Documentation/api-reference/api.md#relabelconfig
# #
probesRelabelings:
- targetLabel: cluster
replacement: casa
- action: replace
sourceLabels: [__metrics_path__]
targetLabel: metrics_path
- sourceLabels: [__meta_kubernetes_pod_node_name]
separator: ;
regex: ^(.*)$
targetLabel: nodename
replacement: $1
action: replace
resourceRelabelings:
- targetLabel: cluster
replacement: casa
- action: replace
sourceLabels: [__metrics_path__]
targetLabel: metrics_path
services/monitoring/deploy/prometheus/prometheus-agent.yaml
-76
View File
@@ -1,76 +0,0 @@
apiVersion: monitoring.coreos.com/v1alpha1
kind: PrometheusAgent
metadata:
name: prometheus-agent
spec:
podMonitorNamespaceSelector:
matchLabels:
prometheus-monitoring: enabled
podMonitorSelector:
matchLabels:
release: prometheus
serviceMonitorNamespaceSelector:
matchLabels:
prometheus-monitoring: enabled
serviceMonitorSelector:
matchLabels:
release: prometheus
replicas: 1
remoteWrite:
- url: https://prometheus.monitoring.limbosolutions.com/api/v1/write
scrapeInterval: 60s
resources:
requests:
cpu: 100m
memory: 128Mi
limits:
cpu: 200m
memory: 512Mi # minimum stable
serviceAccountName: prometheus-agent
nodeSelector:
role: worker-node
---
apiVersion: rbac.authorization.k8s.io/v1
kind: ClusterRole
metadata:
name: prometheus-agent
rules:
- apiGroups: [""]
resources: ["nodes", "nodes/metrics", "nodes/proxy", "services", "endpoints", "pods"]
verbs: ["get", "list", "watch"]
- apiGroups: ["monitoring.coreos.com"]
resources: ["servicemonitors", "podmonitors"]
verbs: ["get", "list", "watch"]
- nonResourceURLs:
- /metrics
- /metrics/cadvisor
- /metrics/probes
verbs: ["get"]
---
apiVersion: rbac.authorization.k8s.io/v1
kind: ClusterRoleBinding
metadata:
name: prometheus-agent-monitoring
roleRef:
kind: ClusterRole
name: prometheus-agent
apiGroup: rbac.authorization.k8s.io
subjects:
- kind: ServiceAccount
name: prometheus-agent
namespace: monitoring
---
apiVersion: v1
kind: ServiceAccount
metadata:
name: prometheus-agent
namespace: monitoring