test(ingestion): assert the bare token is absent from both auth log lines
PR #181 review (comment 15483): - TestBuildMuxLogsARESTAuthRejection asserted only that the "Bearer <tok>" header form was absent, which a field-logging chassis could never emit. Replaced by TestBuildMuxRejectionLogLineOmitsTheBarePresentedToken (a sentinel wrong token; neither it nor the static token may appear) and TestBuildMuxAcceptedLogLineOmitsTheBareStaticToken. A local chassis v0.7.1 copy logging rawToken as token_fp (deny, then accept) turns each red. - labelRESTPattern doc: the label bound holds for refused requests only; the authenticated-404 raw-path gap is hyperguild#185. - Remove internal/startupretry: nothing imports it since the chassis bump. Co-Authored-By: Claude Opus 5.5 <noreply@anthropic.com>
This commit is contained in:
@@ -1,75 +0,0 @@
|
||||
// Package startupretry retries a startup dependency that may not be serving
|
||||
// yet, instead of exiting on its first failure.
|
||||
//
|
||||
// It exists for the cold-boot ordering race (#83): on a cluster restart the
|
||||
// ingestion pod can reach OIDC discovery before dex is answering, gets a 502
|
||||
// from ingress, and dies — after having already connected postgres, backfilled
|
||||
// the graph and ingested session batches, all of which the restart redoes.
|
||||
// Nothing is misconfigured in that scenario; the pod simply started first.
|
||||
//
|
||||
// The budget is bounded on purpose. Retrying forever would turn a genuine
|
||||
// misconfiguration (wrong issuer URL, bad audience) into a process that looks
|
||||
// healthy and never serves, which is harder to diagnose than a crash loop.
|
||||
package startupretry
|
||||
|
||||
import (
|
||||
"context"
|
||||
"fmt"
|
||||
"time"
|
||||
)
|
||||
|
||||
// Policy bounds the retry: at most Attempts calls, with the delay doubling
|
||||
// from Base and capped at Max.
|
||||
type Policy struct {
|
||||
Attempts int // total calls, including the first; < 1 means 1
|
||||
Base time.Duration // delay before the second attempt
|
||||
Max time.Duration // ceiling for the doubling delay
|
||||
}
|
||||
|
||||
// Do calls fn until it succeeds, the attempt budget is spent, or ctx ends.
|
||||
//
|
||||
// The returned error wraps the last failure, so callers keep the diagnosis
|
||||
// they would have had without the retry.
|
||||
func Do[T any](ctx context.Context, p Policy, fn func(context.Context) (T, error)) (T, error) {
|
||||
var zero T
|
||||
|
||||
attempts := p.Attempts
|
||||
if attempts < 1 {
|
||||
attempts = 1
|
||||
}
|
||||
|
||||
delay := p.Base
|
||||
var lastErr error
|
||||
|
||||
for i := range attempts {
|
||||
if err := ctx.Err(); err != nil {
|
||||
return zero, fmt.Errorf("startupretry: %w", err)
|
||||
}
|
||||
|
||||
v, err := fn(ctx)
|
||||
if err == nil {
|
||||
return v, nil
|
||||
}
|
||||
lastErr = err
|
||||
|
||||
if i == attempts-1 {
|
||||
break
|
||||
}
|
||||
|
||||
if delay <= 0 {
|
||||
delay = time.Second
|
||||
}
|
||||
if p.Max > 0 && delay > p.Max {
|
||||
delay = p.Max
|
||||
}
|
||||
|
||||
select {
|
||||
case <-ctx.Done():
|
||||
return zero, fmt.Errorf("startupretry: %w", ctx.Err())
|
||||
case <-time.After(delay):
|
||||
}
|
||||
delay *= 2
|
||||
}
|
||||
|
||||
return zero, fmt.Errorf("startupretry: gave up after %d attempts: %w", attempts, lastErr)
|
||||
}
|
||||
@@ -1,142 +0,0 @@
|
||||
// ingestion/internal/startupretry/startupretry_test.go
|
||||
package startupretry
|
||||
|
||||
import (
|
||||
"context"
|
||||
"errors"
|
||||
"testing"
|
||||
"time"
|
||||
)
|
||||
|
||||
func fastPolicy(attempts int) Policy {
|
||||
return Policy{Attempts: attempts, Base: time.Millisecond, Max: 2 * time.Millisecond}
|
||||
}
|
||||
|
||||
func TestDo_ReturnsImmediatelyOnFirstSuccess(t *testing.T) {
|
||||
calls := 0
|
||||
got, err := Do(context.Background(), fastPolicy(5), func(context.Context) (string, error) {
|
||||
calls++
|
||||
return "ready", nil
|
||||
})
|
||||
if err != nil {
|
||||
t.Fatalf("Do: %v", err)
|
||||
}
|
||||
if got != "ready" {
|
||||
t.Errorf("got %q, want %q", got, "ready")
|
||||
}
|
||||
if calls != 1 {
|
||||
t.Errorf("calls = %d, want 1", calls)
|
||||
}
|
||||
}
|
||||
|
||||
func TestDo_SurvivesTransientFailuresThenSucceeds(t *testing.T) {
|
||||
// The observed cold-boot race: dex is not serving yet, ingress answers
|
||||
// 502 for the first few attempts, then discovery works.
|
||||
calls := 0
|
||||
got, err := Do(context.Background(), fastPolicy(5), func(context.Context) (string, error) {
|
||||
calls++
|
||||
if calls < 4 {
|
||||
return "", errors.New("oidc discovery: status 502")
|
||||
}
|
||||
return "ready", nil
|
||||
})
|
||||
if err != nil {
|
||||
t.Fatalf("Do returned %v — a transient 502 must not be fatal", err)
|
||||
}
|
||||
if got != "ready" {
|
||||
t.Errorf("got %q, want %q", got, "ready")
|
||||
}
|
||||
if calls != 4 {
|
||||
t.Errorf("calls = %d, want 4", calls)
|
||||
}
|
||||
}
|
||||
|
||||
func TestDo_GivesUpAfterTheAttemptBudgetAndReportsTheLastError(t *testing.T) {
|
||||
// A genuinely broken issuer must still fail — retrying forever would turn
|
||||
// a config error into a silent hang, which is worse than crash-looping.
|
||||
last := errors.New("oidc discovery: status 404")
|
||||
calls := 0
|
||||
|
||||
_, err := Do(context.Background(), fastPolicy(3), func(context.Context) (string, error) {
|
||||
calls++
|
||||
return "", last
|
||||
})
|
||||
|
||||
if !errors.Is(err, last) {
|
||||
t.Fatalf("err = %v, want it to wrap the last failure", err)
|
||||
}
|
||||
if calls != 3 {
|
||||
t.Errorf("calls = %d, want 3 (the attempt budget)", calls)
|
||||
}
|
||||
}
|
||||
|
||||
func TestDo_StopsPromptlyWhenTheContextIsCancelled(t *testing.T) {
|
||||
ctx, cancel := context.WithCancel(context.Background())
|
||||
calls := 0
|
||||
|
||||
done := make(chan struct{})
|
||||
var err error
|
||||
go func() {
|
||||
defer close(done)
|
||||
_, err = Do(ctx, Policy{Attempts: 100, Base: 50 * time.Millisecond, Max: time.Second},
|
||||
func(context.Context) (string, error) {
|
||||
calls++
|
||||
if calls == 1 {
|
||||
cancel()
|
||||
}
|
||||
return "", errors.New("still down")
|
||||
})
|
||||
}()
|
||||
|
||||
select {
|
||||
case <-done:
|
||||
case <-time.After(2 * time.Second):
|
||||
t.Fatal("Do did not return after context cancellation")
|
||||
}
|
||||
if !errors.Is(err, context.Canceled) {
|
||||
t.Errorf("err = %v, want context.Canceled", err)
|
||||
}
|
||||
}
|
||||
|
||||
func TestDo_BacksOffAndIsCappedByMax(t *testing.T) {
|
||||
var delays []time.Duration
|
||||
p := Policy{Attempts: 5, Base: 10 * time.Millisecond, Max: 25 * time.Millisecond}
|
||||
|
||||
last := time.Now()
|
||||
_, _ = Do(context.Background(), p, func(context.Context) (string, error) {
|
||||
now := time.Now()
|
||||
delays = append(delays, now.Sub(last))
|
||||
last = now
|
||||
return "", errors.New("down")
|
||||
})
|
||||
|
||||
// delays[0] is the first call (no wait); the rest are the sleeps.
|
||||
if len(delays) != 5 {
|
||||
t.Fatalf("attempts = %d, want 5", len(delays))
|
||||
}
|
||||
if delays[1] >= delays[2] {
|
||||
t.Errorf("backoff is not growing: %v then %v", delays[1], delays[2])
|
||||
}
|
||||
for i, d := range delays[1:] {
|
||||
if d > 2*p.Max {
|
||||
t.Errorf("delay %d = %v, exceeds the Max cap %v with slack", i+1, d, p.Max)
|
||||
}
|
||||
}
|
||||
}
|
||||
|
||||
func TestPolicy_ZeroValueStillMakesOneAttempt(t *testing.T) {
|
||||
// A caller that forgets to configure the policy must not silently get a
|
||||
// no-op that returns a nil validator and a nil error.
|
||||
calls := 0
|
||||
_, err := Do(context.Background(), Policy{}, func(context.Context) (string, error) {
|
||||
calls++
|
||||
return "", errors.New("down")
|
||||
})
|
||||
|
||||
if calls != 1 {
|
||||
t.Errorf("calls = %d, want 1", calls)
|
||||
}
|
||||
if err == nil {
|
||||
t.Error("err = nil, want the failure surfaced")
|
||||
}
|
||||
}
|
||||
Reference in New Issue
Block a user