From 508cc3a216af3020510eccd7d6695071299be039 Mon Sep 17 00:00:00 2001
From: Rodrigo Queiro <rodrigoq@google.com>
Date: Mon, 14 Oct 2024 12:34:05 +0200
Subject: [PATCH] Add smartctl-exporter (#456)

This exports metrics for both SATA and NVMe drives (even if it
annoyingly generates a completely different set of metrics in the two
cases). The container is relatively light at 30MB (!).

This will let us see historic drive temperatures and error rates if we
start to notice drive-related problems in future.

I considered putting this behind a Helm value, but I expect we want
these metrics everywhere, and if they break something we can just roll
back the CRC change.

Tested with kubectl apply on the YAML file.
---
 .../prometheus/robot/smartctl-exporter.yaml   | 55 +++++++++++++++++++
 1 file changed, 55 insertions(+)
 create mode 100644 src/app_charts/prometheus/robot/smartctl-exporter.yaml

diff --git a/src/app_charts/prometheus/robot/smartctl-exporter.yaml b/src/app_charts/prometheus/robot/smartctl-exporter.yaml
new file mode 100644
index 000000000..d6a5af59a
--- /dev/null
+++ b/src/app_charts/prometheus/robot/smartctl-exporter.yaml
@@ -0,0 +1,55 @@
+apiVersion: apps/v1
+kind: DaemonSet
+metadata:
+  name: smartctl-exporter
+spec:
+  selector:
+    matchLabels:
+      app: smartctl-exporter
+  template:
+    metadata:
+      labels:
+        app: smartctl-exporter
+    spec:
+      containers:
+        - name: smartctl-exporter
+          # Mirrored from quay.io/prometheuscommunity/smartctl-exporter
+          image: gcr.io/cloud-robotics-releases/smartctl-exporter:v0.12.0
+          args:
+            - --web.listen-address=:9633
+          securityContext:
+            privileged: true
+            runAsUser: 0
+      tolerations:
+        - operator: Exists
+          effect: NoSchedule
+---
+apiVersion: v1
+kind: Service
+metadata:
+  name: smartctl-exporter
+  labels:
+    app: smartctl-exporter
+spec:
+  clusterIP: None
+  ports:
+    - port: 9633
+      name: http-metrics
+  selector:
+    app: smartctl-exporter
+  type: ClusterIP
+---
+apiVersion: monitoring.coreos.com/v1
+kind: ServiceMonitor
+metadata:
+  name: smartctl-exporter
+  labels:
+    prometheus: kube-prometheus
+spec:
+  endpoints:
+    - port: http-metrics
+      path: /metrics
+      interval: 60s
+  selector:
+    matchLabels:
+      app: smartctl-exporter