kami/Maven
1
0
Fork 0
Code Issues 1 Pull Requests 1 Actions Packages Projects Releases Wiki Activity

kuma: a monitor must stay down before it wakes him (V-536)

Browse Source 
Technitium read down on one poll and up on the next, sixty seconds apart, and
the sev4 arrived after the service was already back.

mavpoll writes a service_down fact only when the state changes, so the fact's
timestamp IS the moment the monitor went down and its age is how long it has
stayed there. The debounce is that age against MinDownAge, 90s — one poll
interval plus jitter. No history to keep and no counter to persist.

It bounds the alarm and not the truth: DownServices still reports a monitor the
instant it goes down, because /dash showing a fresh outage is right even when
phoning him about it is not. Existing fixtures that seeded a one-minute-old
down fact now seed five, which is what they always meant.
This commit is contained in:
claude
2026-08-05 02:27:22 +04:00
parent c4cf06d610
commit 0560684b35
8 changed files with 115 additions and 39 deletions
Download Patch File Download Diff File Expand all files Collapse all files
cmd/mavend/alarm_stop_test.go
+4 -4
View File
@@ -72,7 +72,7 @@ func TestAlarmStopsWhenTheServiceComesBackUp(t *testing.T) {
st := newTestStore(t)
ctx := context.Background()
now := refNow()
seedDown(t, st, ctx, "down", now)
seedDown(t, st, ctx, "down", now.Add(-5*time.Minute))
sink := &fakeSink{}
tl := newAlarmTickLoop(t, st, sink)
@@ -101,7 +101,7 @@ func TestAlarmStopsAtTheAgeCapWhileStillDown(t *testing.T) {
st := newTestStore(t)
ctx := context.Background()
now := refNow()
seedDown(t, st, ctx, "down", now)
seedDown(t, st, ctx, "down", now.Add(-5*time.Minute))
sink := &fakeSink{}
tl := newAlarmTickLoop(t, st, sink)
@@ -132,7 +132,7 @@ func TestAFlapRaisesAFreshAlarmRatherThanReviveTheClosedOne(t *testing.T) {
st := newTestStore(t)
ctx := context.Background()
now := refNow()
seedDown(t, st, ctx, "down", now)
seedDown(t, st, ctx, "down", now.Add(-5*time.Minute))
sink := &fakeSink{}
tl := newAlarmTickLoop(t, st, sink)
@@ -145,7 +145,7 @@ func TestAFlapRaisesAFreshAlarmRatherThanReviveTheClosedOne(t *testing.T) {
t.Fatalf("closing the run changed the row count: %d → %d", first, len(got))
}
seedDown(t, st, ctx, "down", now.Add(30*time.Minute))
seedDown(t, st, ctx, "down", now.Add(25*time.Minute))
sink.sends = nil
tl.tick(ctx, now.Add(31*time.Minute))
cmd/mavend/tick_test.go
+3 -1
View File
@@ -584,7 +584,9 @@ func TestDigestSev4BypassesQueue(t *testing.T) {
ctx := context.Background()
now := refNow()
markPresent(t, st, ctx, now)
if _, err := st.SetValue(ctx, store.KindSelf, "service_down:db", "poll:uptimekuma", "down", now); err != nil {
// Older than loop.MinDownAge, so this tests the digest bypass and not the
// flap debounce (Vikunja #536).
if _, err := st.SetValue(ctx, store.KindSelf, "service_down:db", "poll:uptimekuma", "down", now.Add(-5*time.Minute)); err != nil {
t.Fatalf("seed service_down: %v", err)
}
sink := &fakeSink{}