steve
350be3f19d
Until now the open-alert key was (host_id, kind, resolved_at IS NULL). A host with two source groups both failing collapsed onto one backup_failed row — second failure bumped last_seen_at and overwrote the message but never re-fan-out. Operators saw one alert that appeared to flap, not two distinct broken things. Schema changes (column-level ALTER, no rebuild): - 0015 jobs.source_group_id (FK → source_groups, ON DELETE SET NULL, index). Populated for backup jobs in CreateJob. - 0016 alerts.dedup_key (NOT NULL DEFAULT ''). The old alerts_open partial index gets dropped and replaced with a UNIQUE partial index on (host_id, kind, dedup_key) WHERE resolved_at IS NULL — the index is now the actual dedup primitive. Plumbing: - RaiseOrTouch / AutoResolve / Alert struct gain dedup_key. - engine.JobFinishedEvent gains SourceGroupID; handleJobFinished passes it through for backup_failed only (forget/prune/check stay repo-scoped with key=''). - ws.handler reads SourceGroupID off the freshly-loaded job row. - dispatchJobWithPayload gains a *string sourceGroupID arg; the per-group Run-now path and schedule.fire path pass &g.ID. Test coverage: TestRaiseOrTouchDedupsPerSourceGroup proves two distinct groups produce two distinct open alerts and that resolving one does not auto-resolve the other. Dev tool: cmd/_fake_alert gains -dedup-key flag.
42 lines
996 B
Go
42 lines
996 B
Go
package http
|
|
|
|
import (
|
|
"context"
|
|
"encoding/json"
|
|
stdhttp "net/http"
|
|
"testing"
|
|
"time"
|
|
|
|
"github.com/oklog/ulid/v2"
|
|
|
|
"gitea.dcglab.co.uk/steve/restic-manager/internal/store"
|
|
)
|
|
|
|
func TestAPIAlertsListsOpen(t *testing.T) {
|
|
t.Parallel()
|
|
srv, ts, st := rawTestServer(t)
|
|
hostID, _ := enrolHostForWS(t, srv, st, "host-alerts")
|
|
_, _, _ = st.RaiseOrTouch(context.Background(), hostID,
|
|
"backup_failed", "", "warning", "x", time.Now().UTC())
|
|
cookie := loginAsAdmin(t, st)
|
|
|
|
req, _ := stdhttp.NewRequest("GET", ts.URL+"/api/alerts?status=open", nil)
|
|
req.AddCookie(cookie)
|
|
res, err := stdhttp.DefaultClient.Do(req)
|
|
if err != nil {
|
|
t.Fatalf("do: %v", err)
|
|
}
|
|
defer res.Body.Close()
|
|
if res.StatusCode != 200 {
|
|
t.Fatalf("status: %d", res.StatusCode)
|
|
}
|
|
var got []store.Alert
|
|
if err := json.NewDecoder(res.Body).Decode(&got); err != nil {
|
|
t.Fatalf("decode: %v", err)
|
|
}
|
|
if len(got) != 1 || got[0].Kind != "backup_failed" {
|
|
t.Fatalf("got %+v", got)
|
|
}
|
|
_ = ulid.Make() // import keep
|
|
}
|