bstein/titan-iac
1
0
Fork 0
Code Issues Pull Requests Actions Packages Projects Releases Wiki Activity

monitoring(soteria): tune PVC backup age thresholds for nightly cadence

Browse Source
This commit is contained in:
Brad Stein 2026-04-14 02:14:43 -03:00
parent 55fa72d446
commit fb43b02b2a
3 changed files with 15 additions and 13 deletions
Show Stats Download Patch File Download Diff File Expand all files Collapse all files

12
scripts/dashboards_render_atlas.py
View File

@ -2338,17 +2338,19 @@ def build_overview():
"mode": "absolute", "mode": "absolute",
"steps": [ "steps": [
{"color": "green", "value": None}, {"color": "green", "value": None},
{"color": "yellow", "value": 6}, {"color": "yellow", "value": 20},
{"color": "orange", "value": 12}, {"color": "orange", "value": 40},
{"color": "red", "value": 24}, {"color": "red", "value": 50},
], ],
}, },
) )
) )
panels[-1]["links"] = link_to("atlas-storage") panels[-1]["links"] = link_to("atlas-storage")
panels[-1]["description"] = ( panels[-1]["description"] = (
"Backup age in hours computed from last-success timestamps for restic-managed PVCs. " "Backup age in hours computed from last-success timestamps for restic-managed PVCs "
"PVCs that have backup history but currently no successful backup (missing/no_completed/error) are pinned to 999h for visibility." "(nightly target: <=20h green, <40h yellow, <50h orange, >=50h red). "
"PVCs that have backup history but currently no successful backup (missing/no_completed/error) "
"are pinned to 999h for visibility."
) )
panels.append( panels.append(

8
services/monitoring/dashboards/atlas-overview.json
View File

@ -2539,15 +2539,15 @@
}, },
{ {
"color": "yellow", "color": "yellow",
"value": 6 "value": 20
}, },
{ {
"color": "orange", "color": "orange",
"value": 12 "value": 40
}, },
{ {
"color": "red", "color": "red",
"value": 24 "value": 50
} }
] ]
} }
@ -2583,7 +2583,7 @@
"targetBlank": true "targetBlank": true
} }
], ],
"description": "Backup age in hours computed from last-success timestamps for restic-managed PVCs. PVCs that have backup history but currently no successful backup (missing/no_completed/error) are pinned to 999h for visibility." "description": "Backup age in hours computed from last-success timestamps for restic-managed PVCs (nightly target: <=20h green, <40h yellow, <50h orange, >=50h red). PVCs that have backup history but currently no successful backup (missing/no_completed/error) are pinned to 999h for visibility."
}, },
{ {
"id": 30, "id": 30,

8
services/monitoring/grafana-dashboard-overview.yaml
View File

@ -2548,15 +2548,15 @@ data:
}, },
{ {
"color": "yellow", "color": "yellow",
"value": 6 "value": 20
}, },
{ {
"color": "orange", "color": "orange",
"value": 12 "value": 40
}, },
{ {
"color": "red", "color": "red",
"value": 24 "value": 50
} }
] ]
} }
@ -2592,7 +2592,7 @@ data:
"targetBlank": true "targetBlank": true
} }
], ],
"description": "Backup age in hours computed from last-success timestamps for restic-managed PVCs. PVCs that have backup history but currently no successful backup (missing/no_completed/error) are pinned to 999h for visibility." "description": "Backup age in hours computed from last-success timestamps for restic-managed PVCs (nightly target: <=20h green, <40h yellow, <50h orange, >=50h red). PVCs that have backup history but currently no successful backup (missing/no_completed/error) are pinned to 999h for visibility."
}, },
{ {
"id": 30, "id": 30,