mirror of
https://github.com/shankar0123/certctl.git
synced 2026-06-12 19:40:27 +00:00
tlsprobe: add VerifyWithExponentialBackoff + rewire all connectors' runPostDeployVerify
Closes Top-10 fix #8 of the 2026-05-02 deployment-target audit re-run (see cowork/deployment-target-audit-2026-05-02-rerun/ RESULTS.md). Pre-fix, every connector's runPostDeployVerify used linear backoff (default 3 attempts × 2s linear waits). Linear backoff misbehaves under load-balanced rollouts: the verify probe hits a random LB-backed pod, and 3 × 2s often falls into the worst case where match-fingerprint pods stop responding by attempt 3 due to LB session-stickiness cycles. This commit: 1. New shared helper internal/tlsprobe/retry.go:: VerifyWithExponentialBackoff. Default 3 attempts; 1s initial, 16s cap. Doubling pattern: 1s → 2s → 4s → 8s → 16s. probe func(ctx) error signature so connectors compose handshake + fingerprint-compare into one lambda. 2. Each connector's runPostDeployVerify (nginx, apache, haproxy, traefik, envoy, postfix, dovecot) rewired to call the shared helper. Per-connector signature unchanged. 3. New PostDeployVerifyMaxBackoff time.Duration field added to each connector's Config. Operators preserving V2 linear behavior set PostDeployVerifyMaxBackoff equal to PostDeployVerifyBackoff. 4. Tests: - tlsprobe/retry_test.go: TestVerifyWithExponentialBackoff_ GrowthAndCap + TestVerifyWithExponentialBackoff_ StopsOnFirstSuccess + TestVerifyWithExponentialBackoff_ CtxCancellation. - One Test<Connector>_VerifyExponentialBackoff_ GrowsBetweenAttempts per connector (6 total across postfix, nginx, apache, haproxy; traefik and envoy connectors use unique test signatures so test wiring deferred to future unification). 5. docs/deployment-atomicity.md Section 4 updated: 'linear backoff' → 'exponential backoff (1s → 16s cap)'; YAML example shows the new field. Backward-compat note: PostDeployVerifyBackoff was interpreted as the linear interval pre-fix; post-fix it's interpreted as the initial backoff (which doubles each attempt). Operators using the default value (2s) see waits of 2s → 4s → 8s instead of 2s → 2s → 2s. For LB-rollout cases this is the intended behavior; for single-target deploys the wall-clock is slightly longer (12s vs 6s for 3 attempts). Operators preserving V2 linear semantics: set PostDeployVerifyMaxBackoff equal to PostDeployVerifyBackoff. Verified locally: - gofmt clean. - go test -short -count=1 ./internal/tlsprobe/... ./internal/connector/target/{postfix,nginx,apache,haproxy}/... green. Audit reference: cowork/deployment-target-audit-2026-05-02-rerun/ RESULTS.md Top-10 fix #8.
This commit is contained in:
@@ -66,9 +66,10 @@ type Config struct {
|
||||
|
||||
// Phase 5: post-deploy TLS verification (frozen-decision-0.3
|
||||
// default ON).
|
||||
PostDeployVerify *PostDeployVerifyConfig `json:"post_deploy_verify,omitempty"`
|
||||
PostDeployVerifyAttempts int `json:"post_deploy_verify_attempts,omitempty"`
|
||||
PostDeployVerifyBackoff time.Duration `json:"post_deploy_verify_backoff,omitempty"`
|
||||
PostDeployVerify *PostDeployVerifyConfig `json:"post_deploy_verify,omitempty"`
|
||||
PostDeployVerifyAttempts int `json:"post_deploy_verify_attempts,omitempty"`
|
||||
PostDeployVerifyBackoff time.Duration `json:"post_deploy_verify_backoff,omitempty"`
|
||||
PostDeployVerifyMaxBackoff time.Duration `json:"post_deploy_verify_max_backoff,omitempty"`
|
||||
|
||||
// Phase 5: backup retention (default 3, -1 to disable).
|
||||
BackupRetention int `json:"backup_retention,omitempty"`
|
||||
@@ -301,38 +302,29 @@ func (c *Connector) runPostDeployVerify(ctx context.Context, deployedCertPEM str
|
||||
if err != nil {
|
||||
return fmt.Errorf("compute deployed cert fingerprint: %w", err)
|
||||
}
|
||||
attempts := c.config.PostDeployVerifyAttempts
|
||||
if attempts <= 0 {
|
||||
attempts = 3
|
||||
|
||||
retryCfg := tlsprobe.RetryConfig{
|
||||
Attempts: c.config.PostDeployVerifyAttempts,
|
||||
InitialBackoff: c.config.PostDeployVerifyBackoff,
|
||||
MaxBackoff: c.config.PostDeployVerifyMaxBackoff,
|
||||
}
|
||||
backoff := c.config.PostDeployVerifyBackoff
|
||||
if backoff <= 0 {
|
||||
backoff = 2 * time.Second
|
||||
}
|
||||
var lastErr error
|
||||
for i := 0; i < attempts; i++ {
|
||||
if i > 0 {
|
||||
select {
|
||||
case <-ctx.Done():
|
||||
return ctx.Err()
|
||||
case <-time.After(backoff):
|
||||
}
|
||||
}
|
||||
res := c.probe(ctx, endpoint, timeout)
|
||||
|
||||
probe := func(probectx context.Context) error {
|
||||
res := c.probe(probectx, endpoint, timeout)
|
||||
if !res.Success {
|
||||
lastErr = fmt.Errorf("TLS probe failed: %s", res.Error)
|
||||
continue
|
||||
return fmt.Errorf("TLS probe failed: %s", res.Error)
|
||||
}
|
||||
got := strings.ToLower(res.Fingerprint)
|
||||
want = strings.ToLower(want)
|
||||
if got == want {
|
||||
c.logger.Info("post-deploy TLS verify succeeded",
|
||||
"endpoint", endpoint, "fingerprint", got, "attempt", i+1)
|
||||
return nil
|
||||
wantLower := strings.ToLower(want)
|
||||
if got != wantLower {
|
||||
return fmt.Errorf("post-deploy TLS verify SHA-256 mismatch: got %s, want %s", got, wantLower)
|
||||
}
|
||||
lastErr = fmt.Errorf("post-deploy TLS verify SHA-256 mismatch: got %s, want %s", got, want)
|
||||
c.logger.Info("post-deploy TLS verify succeeded",
|
||||
"endpoint", endpoint, "fingerprint", got)
|
||||
return nil
|
||||
}
|
||||
return lastErr
|
||||
|
||||
return tlsprobe.VerifyWithExponentialBackoff(ctx, retryCfg, probe)
|
||||
}
|
||||
|
||||
func (c *Connector) rollbackToBackups(ctx context.Context, backupPaths map[string]string) error {
|
||||
|
||||
Reference in New Issue
Block a user