infra/modules/kubernetes/monitoring/alloy.yaml
Viktor Barzin 3d4cdf3203
[ci skip] Fix Alloy OOMKill and iDRAC priority class conflict
- Alloy: bump memory limits from 64Mi/128Mi to 256Mi/768Mi — pods were
  OOMKilled at 128Mi, steady-state usage is ~400-450Mi per node
- iDRAC Redfish Exporter: add explicit priority_class_name to resolve
  conflict between Kyverno priority injection and default priority: 0
2026-02-16 20:09:53 +00:00

112 lines
4 KiB
YAML

alloy:
configMap:
content: |-
// Write your Alloy config here:
logging {
level = "info"
format = "logfmt"
}
loki.write "default" {
endpoint {
url = "http://loki.monitoring.svc.cluster.local:3100/loki/api/v1/push"
}
}
// discovery.kubernetes allows you to find scrape targets from Kubernetes resources.
// It watches cluster state and ensures targets are continually synced with what is currently running in your cluster.
discovery.kubernetes "pod" {
role = "pod"
}
// discovery.relabel rewrites the label set of the input targets by applying one or more relabeling rules.
// If no rules are defined, then the input targets are exported as-is.
discovery.relabel "pod_logs" {
targets = discovery.kubernetes.pod.targets
// Label creation - "namespace" field from "__meta_kubernetes_namespace"
rule {
source_labels = ["__meta_kubernetes_namespace"]
action = "replace"
target_label = "namespace"
}
// Label creation - "pod" field from "__meta_kubernetes_pod_name"
rule {
source_labels = ["__meta_kubernetes_pod_name"]
action = "replace"
target_label = "pod"
}
// Label creation - "container" field from "__meta_kubernetes_pod_container_name"
rule {
source_labels = ["__meta_kubernetes_pod_container_name"]
action = "replace"
target_label = "container"
}
// Label creation - "app" field from "__meta_kubernetes_pod_label_app_kubernetes_io_name"
rule {
source_labels = ["__meta_kubernetes_pod_label_app_kubernetes_io_name"]
action = "replace"
target_label = "app"
}
// Label creation - "job" field from "__meta_kubernetes_namespace" and "__meta_kubernetes_pod_container_name"
// Concatenate values __meta_kubernetes_namespace/__meta_kubernetes_pod_container_name
rule {
source_labels = ["__meta_kubernetes_namespace", "__meta_kubernetes_pod_container_name"]
action = "replace"
target_label = "job"
separator = "/"
replacement = "$1"
}
// Label creation - "container" field from "__meta_kubernetes_pod_uid" and "__meta_kubernetes_pod_container_name"
// Concatenate values __meta_kubernetes_pod_uid/__meta_kubernetes_pod_container_name.log
rule {
source_labels = ["__meta_kubernetes_pod_uid", "__meta_kubernetes_pod_container_name"]
action = "replace"
target_label = "__path__"
separator = "/"
replacement = "/var/log/pods/*$1/*.log"
}
// Label creation - "container_runtime" field from "__meta_kubernetes_pod_container_id"
rule {
source_labels = ["__meta_kubernetes_pod_container_id"]
action = "replace"
target_label = "container_runtime"
regex = "^(\\S+):\\/\\/.+$"
replacement = "$1"
}
}
// loki.source.kubernetes tails logs from Kubernetes containers using the Kubernetes API.
loki.source.kubernetes "pod_logs" {
targets = discovery.relabel.pod_logs.output
forward_to = [loki.process.pod_logs.receiver]
}
// loki.process receives log entries from other Loki components, applies one or more processing stages,
// and forwards the results to the list of receivers in the component's arguments.
loki.process "pod_logs" {
stage.static_labels {
values = {
cluster = "default",
}
}
forward_to = [loki.write.default.receiver]
}
# Resource limits for DaemonSet pods
# Alloy tails logs from all containers on the node via K8s API and batches
# them to Loki. Memory scales with number of active log streams (~30-50 per node).
# 128Mi was OOMKilled; steady-state usage is ~400-450Mi per pod.
resources:
requests:
cpu: 50m
memory: 256Mi
limits:
cpu: 200m
memory: 768Mi