feat(prometheus): Fabled Archives template v2 against the live series; a state past its deadline is overdue (#5693)
Read from what Steward stored for Archives on 2026-10-14: the nightly Restic replication job had said "running" since the first scrape two days earlier, with no good copy yet and past both its late and missing times. Archives ranks "running" above lateness, so the widget called it healthy. - states blocks take warn_past / crit_past: a deadline metric per row (a *_timestamp_seconds). Once it has passed, a healthy row reads as a warning or a problem: "FullNightly-Restic is running, 11h 53m overdue". Quiet and already-failing rows keep their own reading. - The Archives template (version 2) uses the job's late_at / missing_at deadlines and shows its last good copy beside the next run. It says why section_up, the queue and the HTTP/audit counters are left out. - tests/plugins/prometheus/archives_live.py is the series as captured live, and test_archives_template.py renders the template over them. Co-Authored-By: Claude Opus 5.5 <noreply@anthropic.com>
This commit is contained in:
@@ -104,6 +104,29 @@ def _ordered(rows: list[Row]) -> list[Row]:
|
||||
|
||||
# ── Blocks ───────────────────────────────────────────────────────────────────
|
||||
|
||||
def _same_row(index, metric: str, labels: str, name_label: str, name: str) -> list[Sample]:
|
||||
"""The series of `metric` belonging to a state set's row: the same labels,
|
||||
or else the same value of the label that names it."""
|
||||
match = [s for s in index.get(metric, []) if s.labels == labels]
|
||||
if not match and name:
|
||||
match = [s for s in index.get(metric, []) if s.pairs.get(name_label) == name]
|
||||
return match
|
||||
|
||||
|
||||
def _overdue(spec: dict, index, labels: str, name: str, now: datetime) -> tuple[str, float] | None:
|
||||
"""(tone, seconds past) when the row's crit_past or warn_past deadline has passed."""
|
||||
for level in ("crit", "warn"):
|
||||
metric = spec[f"{level}_past"]
|
||||
if not metric:
|
||||
continue
|
||||
match = _same_row(index, metric, labels, spec["name"], name)
|
||||
if len(match) == 1 and match[0].value > 0:
|
||||
past = now.timestamp() - match[0].value
|
||||
if past > 0:
|
||||
return level, past
|
||||
return None
|
||||
|
||||
|
||||
def _states(block: Block, index, now) -> BlockView:
|
||||
spec = block.spec
|
||||
view = BlockView("states", block.title, columns=[c["label"] for c in spec["columns"]])
|
||||
@@ -130,13 +153,14 @@ def _states(block: Block, index, now) -> BlockView:
|
||||
else:
|
||||
tones.append("crit")
|
||||
tone = (min(tones, key=TONE_ORDER.__getitem__) if tones else "warn")
|
||||
row = Row(name=name or f["labels"] or block.title, tone=tone, text=f["state"] or "—",
|
||||
why="" if tone in ("ok", "dim") else (f"is {f['state']}" if current else "reports no state"),
|
||||
why = "" if tone in ("ok", "dim") else (f"is {f['state']}" if current else "reports no state")
|
||||
overdue = _overdue(spec, index, f["labels"], name, now) if tone == "ok" else None
|
||||
if overdue:
|
||||
tone, why = overdue[0], f"is {f['state']}, {human_duration(overdue[1])} overdue"
|
||||
row = Row(name=name or f["labels"] or block.title, tone=tone, text=f["state"] or "—", why=why,
|
||||
resource=f["resource"], metric=spec["metric"])
|
||||
for col in spec["columns"]:
|
||||
match = [s for s in index.get(col["metric"], []) if s.labels == f["labels"]]
|
||||
if not match and name:
|
||||
match = [s for s in index.get(col["metric"], []) if s.pairs.get(spec["name"]) == name]
|
||||
match = _same_row(index, col["metric"], f["labels"], spec["name"], name)
|
||||
row.cells.append(shown(col["metric"], col["unit"], match[0].value if len(match) == 1 else None))
|
||||
view.rows.append(row)
|
||||
view.rows = _ordered(view.rows)
|
||||
|
||||
Reference in New Issue
Block a user