Files
selfpost/internal/postfix/retry.go
T
mixandClaude Opus 5.5 a990e7cc23
test / test (push) Canceled after 0s
delivery-log-storage: findings of the technical and security reviews
Neither review (read-only agents, Opus and Fable, over ae06d8b..815236a) has
a Critical or High finding. What they found and what was done:

- A stranger on port 25 could grow the table: every queue-id line of inbound
  mail was stored and pruned an hour or more later, his own message-id among
  them. The tailer now leaves out the lines of a queue id that
  postfix/inbound/smtpd opened, until qmgr removes the message or another
  listener opens one under the id; 4096 such ids are remembered.
- A commit, so a disk sync, per stored line on the connection the journal
  milter shares, and a backlog written line by line. Lines are now written in
  one transaction per pass over the log, 500 at most, before the read offset
  is saved (InsertSendLogLines; follow() calls the keeper's flush).
- The prune asked the send log once per line and ran hourly. It asks once per
  queue id and runs at start and with the six-hourly sweep; with port-25 mail
  left out there is little without a row to wait for.
- The 4096-byte cut could split a character; it keeps characters whole.
- security.md did not say that a backup now carries these lines, and the plan
  said the time window excludes a reused queue id where it only limits the
  chance to the row's queue lifetime. Both are corrected; the collision is
  recorded as an accepted risk with its trigger.
- Tests that did not prove their comments: the prune is now tested with the
  sweep, a rejected row next to the prune, batching and the change from
  catching up to following, port-25 mail left out and its id reused.

Left as found and written down in the plan: lines the tailer never reads
(a file rotated away while the panel was down), and a message in the queue
across the upgrade, which shows only its later lines.

On the test server, for this tree: go vet clean, go test ./... 22 packages
ok, make e2e ok.

Co-Authored-By: Claude Opus 5.5 <noreply@anthropic.com>
2026-10-12 10:41:04 +03:00

147 lines
4.7 KiB
Go

package postfix
import (
"fmt"
"log"
"os/exec"
"strings"
"time"
)
// RetryPolicy is this Postfix's deferred-mail retry timings, as postconf
// reports them. The panel loads it once at HTTP start (architecture.md) and
// never re-reads it for a request.
type RetryPolicy struct {
QueueRunDelay time.Duration
MinimalBackoff time.Duration
MaximalBackoff time.Duration
MaximalQueueLifetime time.Duration
BounceQueueLifetime time.Duration
DelayWarningTime time.Duration
// FromDefaults is true when postconf could not be read and the compiled-in
// Postfix 3.x values were substituted. The Mail queue card shows a muted
// note in that case so an operator who overrode the parameters is not
// silently shown the stock numbers.
FromDefaults bool
}
// DefaultRetryPolicy is Postfix 3.x compiled-in values for the six parameters
// build/postfix-config.sh does not set. Used when postconf is missing (unit
// tests, a binary outside the container) so the panel still starts.
func DefaultRetryPolicy() RetryPolicy {
return RetryPolicy{
QueueRunDelay: 300 * time.Second,
MinimalBackoff: 300 * time.Second,
MaximalBackoff: 4000 * time.Second,
MaximalQueueLifetime: 5 * 24 * time.Hour,
BounceQueueLifetime: 5 * 24 * time.Hour,
DelayWarningTime: 0,
FromDefaults: true,
}
}
// retryConfKeys is the fixed argv tail for `postconf -h`. Order matches the
// fields of RetryPolicy. No user input is interpolated (security.md).
var retryConfKeys = []string{
"queue_run_delay",
"minimal_backoff_time",
"maximal_backoff_time",
"maximal_queue_lifetime",
"bounce_queue_lifetime",
"delay_warning_time",
}
// readRetryConf runs `postconf -h` for the retry-policy keys. Tests replace it
// the same way logtail stubs queueIDs.
var readRetryConf = postconfRetryValues
func postconfRetryValues() ([]string, error) {
// Fixed argv, no user input — same pattern as Queue (security.md).
cmd := exec.Command("postconf", "-h",
"queue_run_delay",
"minimal_backoff_time",
"maximal_backoff_time",
"maximal_queue_lifetime",
"bounce_queue_lifetime",
"delay_warning_time",
)
out, err := cmd.CombinedOutput()
if err != nil {
return nil, fmt.Errorf("postconf -h: %w: %s", err, strings.TrimSpace(string(out)))
}
lines := strings.Split(strings.TrimSpace(string(out)), "\n")
if len(lines) != len(retryConfKeys) {
return nil, fmt.Errorf("postconf -h: got %d values, want %d", len(lines), len(retryConfKeys))
}
for i := range lines {
lines[i] = strings.TrimSpace(lines[i])
}
return lines, nil
}
// LoadRetryPolicy reads the effective Postfix retry parameters. On any failure
// it logs a warning and returns DefaultRetryPolicy; the HTTP role must not
// refuse to start because postconf is absent.
func LoadRetryPolicy() RetryPolicy {
lines, err := readRetryConf()
if err != nil {
log.Printf("postfix: retry policy: %v; using compiled-in defaults", err)
return DefaultRetryPolicy()
}
p, err := parseRetryPolicy(lines)
if err != nil {
log.Printf("postfix: retry policy: %v; using compiled-in defaults", err)
return DefaultRetryPolicy()
}
return p
}
func parseRetryPolicy(lines []string) (RetryPolicy, error) {
if len(lines) != len(retryConfKeys) {
return RetryPolicy{}, fmt.Errorf("got %d values, want %d", len(lines), len(retryConfKeys))
}
var durs [6]time.Duration
for i, line := range lines {
d, err := ParseDuration(line)
if err != nil {
return RetryPolicy{}, fmt.Errorf("%s: %w", retryConfKeys[i], err)
}
durs[i] = d
}
return RetryPolicy{
QueueRunDelay: durs[0],
MinimalBackoff: durs[1],
MaximalBackoff: durs[2],
MaximalQueueLifetime: durs[3],
BounceQueueLifetime: durs[4],
DelayWarningTime: durs[5],
}, nil
}
// FirstRetry is the human string for the first deferred retry (minimal
// backoff), shared by the Mail queue card and delivery history.
func (p RetryPolicy) FirstRetry() string {
return FormatDuration(p.MinimalBackoff)
}
// BackoffCap is the human string for maximal_backoff_time.
func (p RetryPolicy) BackoffCap() string {
return FormatDuration(p.MaximalBackoff)
}
// LongestLifetime is how long Postfix may go on working on a message: the
// larger of the queue lifetime for ordinary mail and for mail from the null
// sender, which an application may submit too. It bounds which stored log
// lines can be about a send-log row (store.SendLogLines).
func (p RetryPolicy) LongestLifetime() time.Duration {
if p.BounceQueueLifetime > p.MaximalQueueLifetime {
return p.BounceQueueLifetime
}
return p.MaximalQueueLifetime
}
// QueueLifetime is the human string for maximal_queue_lifetime.
func (p RetryPolicy) QueueLifetime() string {
return FormatDuration(p.MaximalQueueLifetime)
}