Files
platform-core/services/observability/node-exporter
DongHyeonka bed20b456b fix(observability): stop throttling node-exporter
node-exporter averages about 2m CPU, but each scrape runs its
collectors in parallel. With a 250m limit (25ms per 100ms CFS period)
26% of its CFS periods were throttled over 30 minutes on 2026-11-11
(container_cpu_cfs_throttled_periods_total / cfs_periods_total), which
delays scrapes and can make them time out.

Raise the CPU limit to one core. The request stays 100m, so
scheduling does not change, and a runaway collector is still capped.
Removing the limit was rejected because every other workload in this
repository sets one.

Risk: none beyond one core of headroom on a 12-core node. The live
DaemonSet changes only when the observability core is applied again.

Verification: the throttling ratio and usage came from live
Prometheus queries. helm template of prometheus-node-exporter 4.56.1
with these values renders limits.cpu "1". The effect after rollout is
not measured yet.
2026-11-12 07:28:03 +09:00
..

node-exporter

The standalone node-exporter runs in observability-agent with the embedded kube-prometheus-stack copy and kube-rbac-proxy disabled. It mounts only /proc, /sys, and / from the node, all read-only, and exposes an internal ClusterIP metrics Service on port 9100.

Host network, PID, and IPC namespaces remain disabled by the platform security contract. Consequently, network-namespace metrics are treated as a known single-node visibility limitation rather than authoritative host-network data.