nix

commit 9b14ad752f4b4ab1887e5de981b87ec3521f3b88
parent 92c02253a369e16cdf9ae76280720d7af709e880
Author: mtmn <miro@haravara.org>
Date:   Wed, 10 Jun 2026 13:31:07 +0200

monitoring: remove cadvisor exporter

Diffstat:
M
modules/mixins/monitoring/alert-rules.yaml
 | 
71
-----------------------------------------------------------------------
M
modules/services/monitoring/default.nix
 | 
5
-----
M
modules/services/monitoring/exporters.nix
 | 
8
+-------

3 files changed, 1 insertion(+), 83 deletions(-)
diff --git a/modules/mixins/monitoring/alert-rules.yaml b/modules/mixins/monitoring/alert-rules.yaml
@@ -84,74 +84,3 @@ groups:
           description: >
             The systemd unit {{ $labels.name }} has been in a failed state
             for more than 5 minutes.
-
-  # ── Container resources (cAdvisor) ─────────────────────────────────────────
-  - name: containers
-    rules:
-      - alert: ContainerHighCPU
-        expr: sum(rate(container_cpu_usage_seconds_total{name!=""}[5m])) by (name) * 100 > 80
-        for: 10m
-        labels:
-          severity: warning
-        annotations:
-          summary: "Container {{ $labels.name }} CPU usage: {{ $value | printf \"%.0f\" }}%"
-          description: "Container {{ $labels.name }} CPU usage has been above 80% for 10 minutes."
-
-      - alert: ContainerHighMemory
-        expr: >
-          (
-            container_memory_usage_bytes{name!=""}
-            / container_spec_memory_limit_bytes{name!=""}
-          ) * 100 > 80
-          unless container_spec_memory_limit_bytes{name!=""} == 0
-        for: 5m
-        labels:
-          severity: warning
-        annotations:
-          summary: "Container {{ $labels.name }} memory: {{ $value | printf \"%.0f\" }}% of limit"
-          description: "Container {{ $labels.name }} memory usage has been above 80% of its limit for 5 minutes."
-
-      - alert: ContainerOOMKilled
-        expr: increase(container_oom_events_total{name!=""}[5m]) > 0
-        for: 1m
-        labels:
-          severity: critical
-        annotations:
-          summary: "Container {{ $labels.name }} was OOM-killed"
-          description: "Container {{ $labels.name }} was killed due to out-of-memory in the last 5 minutes."
-
-  # ── SeaweedFS cluster (metrics on ports 9324–9327) ─────────────────────────
-  - name: seaweedfs
-    rules:
-      - alert: SeaweedFSDown
-        expr: up{job="seaweedfs"} == 0
-        for: 2m
-        labels:
-          severity: critical
-        annotations:
-          summary: "SeaweedFS component {{ $labels.instance }} is down"
-          description: "SeaweedFS at {{ $labels.instance }} has been unreachable for more than 2 minutes."
-
-  # ── VictoriaMetrics self-health ─────────────────────────────────────────────
-  - name: victoriametrics
-    rules:
-      - alert: HighScrapeErrorRate
-        expr: rate(vm_promscrape_scrapes_failed_total[5m]) > 0.1
-        for: 10m
-        labels:
-          severity: warning
-        annotations:
-          summary: "VictoriaMetrics scrape errors: {{ $value | printf \"%.2f\" }}/s"
-          description: "More than 10% of scrapes have been failing for the last 10 minutes."
-
-  # ── vmalert self-health ─────────────────────────────────────────────────────
-  - name: vmalert
-    rules:
-      - alert: VMAlertRuleErrors
-        expr: increase(vmalert_execution_errors_total[5m]) > 0
-        for: 10m
-        labels:
-          severity: warning
-        annotations:
-          summary: "vmalert rule evaluation errors"
-          description: "vmalert has been encountering rule evaluation errors. Check vmalert logs."
diff --git a/modules/services/monitoring/default.nix b/modules/services/monitoring/default.nix
@@ -106,11 +106,6 @@ in {
               static_configs = [{targets = ["127.0.0.1:${toString config.services.prometheus.exporters.systemd.port}"];}];
               metrics_path = "/metrics";
             }
-            {
-              job_name = "cadvisor";
-              static_configs = [{targets = ["127.0.0.1:${toString config.services.cadvisor.port}"];}];
-              metrics_path = "/metrics";
-            }
           ])
           ++ lib.optional config.services.haravara.seaweedfs.enable {
             job_name = "seaweedfs";
diff --git a/modules/services/monitoring/exporters.nix b/modules/services/monitoring/exporters.nix
@@ -6,7 +6,7 @@
   cfg = config.services.haravara.monitoring;
 in {
   options.services.haravara.monitoring.exporters = {
-    enable = lib.mkEnableOption "Prometheus node/systemd exporters and cAdvisor" // {default = true;};
+    enable = lib.mkEnableOption "Enable node and systemd Prometheus exporters" // {default = true;};
   };
 
   config = lib.mkIf (cfg.enable && cfg.exporters.enable) {
@@ -28,12 +28,6 @@ in {
       };
     };
 
-    services.cadvisor = {
-      enable = true;
-      listenAddress = "127.0.0.1";
-      port = 8182;
-    };
-
     systemd.services = {
       prometheus-node-exporter.serviceConfig = {
         RestrictNamespaces = lib.mkForce false;