prometheus: update grafana annotation urls
Use the grafana.nixos.org domain and reference the node-exporter-full dashboard instead of per-instance-metrics.
Martin Weinelt committed
Jan 6, 2025 at 01:49 UTC
ae0976cbbe0eaf801932727101a9f262c3098cfe
3 files changed
+8
-6
build/pluto/prometheus/exporters/hydra.nix
+1
-1
@@ -74,7 +74,7 @@
74
for = "30m";
75
labels.severity = "warning";
76
annotations.summary = "{{ $labels.machine }} has {{ $value }} over-age jobs.";
77
- annotations.grafana = "https://monitoring.nixos.org/grafana/d/j0hJAY1Wk/in-progress-build-duration-heatmap";
77
+ annotations.grafana = "https://grafana.nixos.org/d/j0hJAY1Wk/in-progress-build-duration-heatmap";
78
}
79
{
80
alert = "HydraQueueRunnerUp";
build/pluto/prometheus/exporters/node.nix
+6
-4
@@ -74,7 +74,7 @@
74
for = "30m";
75
labels.severity = "warning";
76
annotations.summary = "{{ $labels.device }} mounted to {{ $labels.mountpoint }} ({{ $labels.fstype }}) on {{ $labels.instance }} has {{ $value }} inodes free.";
77
- annotations.grafana = "https://monitoring.nixos.org/grafana/d/5LANB9pZk/per-instance-metrics?orgId=1&refresh=30s&var-instance={{ $labels.instance }}";
77
+ annotations.grafana = "https://grafana.nixos.org/d/rYdddlPWk/node-exporter-full?orgId=1&var-job=node&var-node={{ $labels.instance }}";
78
}
79
{
80
alert = "PartitionLowDiskSpace";
@@ -86,11 +86,13 @@
86
for = "30m";
87
labels.severity = "warning";
88
annotations.summary = "{{ $labels.device }} mounted to {{ $labels.mountpoint }} ({{ $labels.fstype }}) on {{ $labels.instance }} has {{ $value }} GB free.";
89
- annotations.grafana = "https://monitoring.nixos.org/grafana/d/5LANB9pZk/per-instance-metrics?orgId=1&refresh=30s&var-instance={{ $labels.instance }}";
89
+ annotations.grafana = "https://grafana.nixos.org/d/rYdddlPWk/node-exporter-full?orgId=1&var-job=node&var-node=caliban.nixos.org:9100{{ $labels.instance }}";
90
}
91
{
92
alert = "SystemdUnitFailed";
93
- expr = ''node_systemd_unit_state{state="failed"} == 1'';
93
+ expr = ''
94
+ node_systemd_unit_state{state="failed"} == 1
95
+ '';
96
for = "15m";
97
labels.severity = "warning";
98
annotations.summary = "systemd unit {{ $labels.name }} on {{ $labels.instance }} has been down for more than 15 minutes.";
@@ -106,7 +108,7 @@
108
for = "30m";
109
labels.severity = "warning";
110
annotations.summary = "{{ $labels.name }} on {{ $labels.instance }}";
109
- annotations.grafana = "https://monitoring.nixos.org/grafana/d/fBW4tL1Wz/scheduled-task-state-channels-website?orgId=1&refresh=10s";
111
+ annotations.grafana = "https://grafana.nixos.org/d/fBW4tL1Wz/scheduled-task-state-channels-website?orgId=1&refresh=10s";
112
}
113
];
114
}
build/pluto/prometheus/exporters/rfc39.nix
+1
-1
@@ -29,7 +29,7 @@
29
expr = ''node_systemd_unit_state{name=~"^rfc39-sync.service$", state="failed"} == 1'';
30
for = "30m";
31
labels.severity = "warning";
32
- annotations.grafana = "https://monitoring.nixos.org/grafana/d/fBW4tL1Wz/scheduled-task-state-channels-website?orgId=1&refresh=10s";
32
+ annotations.grafana = "https://grafana.nixos.org/d/fBW4tL1Wz/scheduled-task-state-channels-website?orgId=1&refresh=10s";
33
}
34
];
35
}