Files
felhom-agent/cmd/felhom-agent/restoretest_due_wiring_test.go
T
admin 4618169036
gates / gates (push) Failing after 7s
R-86: restore-test follows the backup, not the clock (v0.121.0)
The ticker survives as the EVALUATION interval only. A tier is DUE when its
newest archive that has settled for `settle` (default 24h) has not been proven:
daily tier -> proved daily on yesterday's archive, weekly tier -> weekly on its
own, newborn -> UNKNOWN.

The trap avoided: the literal reading ("newest archive is >= 24h old") is NEVER
true on a daily tier, so it silently switches restore-testing off where it
matters most. Red-proved at 0 runs over 5 simulated days.

- state records WHICH archive was proven; legacy files keep their time and yield
  no proven archive (each tier due once after the upgrade, deliberately)
- two knobs replace one: restore_test_eval_interval_seconds (6h, measured) and
  restore_test_settle_seconds (24h). The old cadence key keeps its DISABLE
  meaning verbatim and now seeds the settle lag, with a start-up WARN.
- due-check runs BEFORE the heavy-op gate (a frequent poll must not make a
  starting backup record a failure, F-A1)
- candidate picker skips implausible archives (a phantom would be due forever)
- new read-only --selftest=restore-test-due prints the verdict + its cost
2026-08-03 14:54:57 +02:00

114 lines
3.6 KiB
Go

package main
import (
"go/ast"
"go/parser"
"go/token"
"testing"
)
// R-86 Scenario I — the seam-discipline test for the due-check.
//
// A due-check is worth nothing if the daemon still wires the OLD picker: every unit test in
// internal/backup would stay green (they inject the seam directly), the scheduler would ask for the
// newest archive with no settle cutoff, and the per-archive rule would run against a candidate that
// changes every time a backup lands. That is the same shape as the v0.91.0 inert seam — built,
// tested, never called — and this repo has shipped it four times.
//
// It walks main.go's AST rather than grepping: a commented-out call still satisfies a substring
// match, and a comment is not a caller.
func TestMainWiresTheSettleAwareTierPicker(t *testing.T) {
f := parseMainForWiring(t)
var settlePicker, oldPicker, settleWired, evalInterval bool
ast.Inspect(f, func(n ast.Node) bool {
switch node := n.(type) {
case *ast.SelectorExpr:
// runner.PickSettledRestoreCandidateOn passed as a value (not called).
switch node.Sel.Name {
case "PickSettledRestoreCandidateOn":
settlePicker = true
case "PickRestoreCandidateOn":
oldPicker = true
}
case *ast.KeyValueExpr:
key, ok := node.Key.(*ast.Ident)
if !ok {
return true
}
if key.Name == "Settle" {
settleWired = true
}
case *ast.CallExpr:
if sel, ok := node.Fun.(*ast.SelectorExpr); ok && sel.Sel.Name == "RestoreTestEvalInterval" {
evalInterval = true
}
}
return true
})
if !settlePicker {
t.Error("main.go never passes runner.PickSettledRestoreCandidateOn as the scheduler's TierPick — " +
"the due-check would run without a settle cutoff, i.e. against an archive that may still be being written")
}
if oldPicker {
t.Error("main.go still wires the pre-R-86 PickRestoreCandidateOn as a tier picker — " +
"two pickers means the one under test is not the one running")
}
if !settleWired {
t.Error("main.go never sets SchedulerOptions.Settle — the settle lag would default to 0 in the daemon " +
"and every freshly-landed archive would be an immediate candidate")
}
if !evalInterval {
t.Error("main.go never calls cfg.Backup.RestoreTestEvalInterval() — the scheduler would be driven by " +
"the retired cadence knob")
}
}
// The two R-85 guarantees the due-check must not have quietly dropped: the spec is still built PER
// RUN, and the shared heavy-operation gate is still handed to the scheduler.
func TestMainStillWiresTheHeavyOperationGateAndPerRunSpec(t *testing.T) {
f := parseMainForWiring(t)
var inFlightWired, specIsAFunc bool
ast.Inspect(f, func(n ast.Node) bool {
kv, ok := n.(*ast.KeyValueExpr)
if !ok {
return true
}
key, ok := kv.Key.(*ast.Ident)
if !ok {
return true
}
switch key.Name {
case "InFlight":
inFlightWired = true
case "Spec":
// A FuncLit means it is evaluated per run; anything else is a frozen value.
if _, isFunc := kv.Value.(*ast.FuncLit); isFunc {
specIsAFunc = true
}
}
return true
})
if !inFlightWired {
t.Error("main.go no longer hands the scheduler the shared InFlight gate — a restore-test could pull a " +
"multi-GB archive over the same tunnel an offsite backup is pushing one over (Scenario F)")
}
if !specIsAFunc {
t.Error("SchedulerOptions.Spec is no longer a function literal — a frozen spec is the R-85 defect " +
"(the tier and its timeout evaluated once at daemon start, forever)")
}
}
func parseMainForWiring(t *testing.T) *ast.File {
t.Helper()
fset := token.NewFileSet()
f, err := parser.ParseFile(fset, "main.go", nil, 0)
if err != nil {
t.Fatalf("parse main.go: %v", err)
}
return f
}