Files
selfpost/internal/logtail/refusals.go
T
mixandClaude Opus 5.5 65d916f26a
test / test (push) Canceled after 0s
logtail: a refusal the panel did not get to write is written from mail.log (stage 2b)
The sender check answers 550 5.7.1 and writes the refused row through a
buffer a moment later; a panel stopped in between (a rollout, a kill) left
an application refused and a log that did not know it. A refusal at MAIL
FROM needs nothing: the journal milter writes its row before it answers.

- logtail.refusalLines remembers each queue id's login from smtpd's
  "<id>: client=..., sasl_username=<login>" (4096 ids at most) and, on
  cleanup's "<id>: milter-reject: END-OF-MESSAGE ...: 5.7.1 From: <line> -
  <why>; from=<...> to=<...>", waits 30 s and hands it to
  store.RecoverRefusal - an INSERT ... WHERE NOT EXISTS a refused row of that
  queue id within two minutes: the row the panel wrote, or one recovered
  before, means nothing is written. It is read from the saved offset on, so
  a kill is covered as well as a clean stop - which a flush of the buffer at
  shutdown would not.
- Migration 0009 (not deployed yet) gains send_log.recovered; the row is
  written with the line's time, the login's domain id, reason "from", the
  From: line as the check printed it (to the last " - " before ";").
- The message page: a fact "Written: from mail.log after a restart: the
  panel stopped before it wrote the refusal".

Tests: store (not written when the panel wrote it; written once however
often); logtail (the login from client=, the From: line with a " - " in it,
nothing before the wait is over); view (the fact). e2e
refusal_recovered_from_the_log: a From: refusal, the panel stopped, its row
deleted and the tailer's saved place moved before the message's first line
(python3 in the container, as the panel's user - a kill cannot be timed to
that moment from outside); started again, the row is back, recovered, once.

Also fixed: handlers TestMessagePageOfARefusedMessage still expected the
old sentence; it failed on the server after e166a2e, whose run showed only
the schema failures - now it wants the new one.

schema-migrations row 9, CHANGELOG [Unreleased], audit plan line ticked,
roadmap 26/62.
Evidence on the test server for this tree but the handler-test fix: make e2e
exit 0 (the new case 37 s); go test 22/23 ok, the 23rd that test - fixed,
passes locally; the full run follows before the push.

Co-Authored-By: Claude Opus 5.5 <noreply@anthropic.com>
2026-10-14 17:09:05 +03:00

160 lines
5.6 KiB
Go

package logtail
import (
"log"
"regexp"
"strings"
"time"
"github.com/mixeme/selfpost/internal/store"
)
// Postfix's line about a message the journal milter refused at MAIL FROM - a
// level-2 limit, a client address off the application's list - is put on the
// row the milter wrote, so the message's page shows it (audit 2026-10-12,
// stage 2b). The refusal has no queue id; the line is matched to its row by
// sender, login and time. As the stand writes it:
//
// postfix/smtpd[1149]: NOQUEUE: milter-reject: MAIL from unknown[10.77.0.1]: 451 4.7.1 Service unavailable - try again later; from=<billing@sender.e2e.test> proto=ESMTP helo=<e2e-client.e2e.test>
//
// Port 25's smtpd (postfix/inbound/smtpd) is a stranger's and has no such row.
var refusalLineRe = regexp.MustCompile(`^\S+ postfix/(?:([a-z0-9-]+)/)?smtpd\[\d+\]: NOQUEUE: milter-reject: MAIL from \S+: [45]\d\d .*?; from=<([^>]*)>(?:.*? sasl_username=<?([^>\s]*)>?)?`)
// refusalLineWait is how long a line waits for its row: the milter writes the
// row when it refuses, which can be read a moment after the line.
const refusalLineWait = 30 * time.Second
// RefusalStore is where the lines go. *store.Store satisfies it.
type RefusalStore interface {
AttachRefusalLine(login, from string, at time.Time, line string) (bool, error)
RecoverRefusal(e store.SendLogEntry, at time.Time) (bool, error)
}
// fromRefusalRe is cleanup's line about a message the sender check refused
// for its From: line, as the stand writes it:
//
// postfix/cleanup[1339]: E543D3C75DA0: milter-reject: END-OF-MESSAGE from unknown[10.77.0.1]: 5.7.1 From: director@other.e2e.test - not an address this application sends as; from=<alerts@sender.e2e.test> to=<rcpt@sink.e2e.test> proto=ESMTP helo=<e2e-client.e2e.test>
//
// The From: line as the check printed it runs to the last " - " before the
// semicolon; the reason after it holds neither.
var fromRefusalRe = regexp.MustCompile(`^\S+ postfix/(?:[a-z0-9-]+/)?cleanup\[\d+\]: ([0-9A-Za-z]+): milter-reject: END-OF-MESSAGE from \S+: 5\.7\.1 From: (.*) - ([^;]*); from=<([^>]*)> to=<([^>]*)>`)
// clientLoginRe is smtpd's line naming the login a queue id was submitted
// under: "<id>: client=host[addr], sasl_method=PLAIN, sasl_username=<login>".
var clientLoginRe = regexp.MustCompile(`^\S+ postfix/(?:([a-z0-9-]+)/)?smtpd\[\d+\]: ([0-9A-Za-z]+): client=.*?, sasl_username=(\S+)`)
// refusalLogins bounds the queue ids whose login is remembered.
const refusalLogins = 4096
type pendingRefusal struct {
login, from, line string
at, until time.Time
}
// pendingRecovery is a From: refusal whose row is looked for once the panel
// has had the time to write it.
type pendingRecovery struct {
e store.SendLogEntry
at, until time.Time
}
// refusalLines puts each refusal line on its row, and keeps for a while the
// lines whose row is not there yet. It also writes, from cleanup's line, the
// row of a From: refusal the panel did not get to write.
type refusalLines struct {
st RefusalStore
pending []pendingRefusal
recover []pendingRecovery
logins map[string]string // queue id -> login, from smtpd's client= line
loginKeys []string
}
// handle looks at one mail.log line.
func (r *refusalLines) handle(line string, now time.Time) {
at, rest := lineTime(line, now)
if m := clientLoginRe.FindStringSubmatch(rest); m != nil && m[1] != "inbound" {
r.remember(m[2], m[3])
return
}
if m := fromRefusalRe.FindStringSubmatch(rest); m != nil {
r.recover = append(r.recover, pendingRecovery{
e: store.SendLogEntry{
QueueID: m[1], AppLogin: r.logins[m[1]], From: m[4], To: m[5], Domain: domainOf(m[4]),
Reason: store.ReasonFrom, HeaderFrom: m[2],
},
at: at, until: now.Add(refusalLineWait),
})
return
}
m := refusalLineRe.FindStringSubmatch(rest)
if m == nil || m[1] == "inbound" {
return
}
p := pendingRefusal{login: m[3], from: m[2], line: line, at: at, until: now.Add(refusalLineWait)}
if !r.attach(p) {
r.pending = append(r.pending, p)
}
}
// retry tries the waiting lines again and lets go of those that waited long
// enough; and writes, once their wait is over, the rows of From: refusals the
// panel did not write.
func (r *refusalLines) retry(now time.Time) {
kept := r.pending[:0]
for _, p := range r.pending {
if r.attach(p) || now.After(p.until) {
continue
}
kept = append(kept, p)
}
r.pending = kept
waiting := r.recover[:0]
for _, p := range r.recover {
if !now.After(p.until) {
waiting = append(waiting, p)
continue
}
wrote, err := r.st.RecoverRefusal(p.e, p.at)
if err != nil {
log.Printf("log-tailer: recover refusal: %v", err)
} else if wrote {
log.Printf("log-tailer: wrote the refusal of %s (%s) from mail.log: the panel had not written it", p.e.QueueID, p.e.From)
}
}
r.recover = waiting
}
// remember keeps the login a queue id was submitted under, the oldest going
// first beyond refusalLogins.
func (r *refusalLines) remember(queueID, login string) {
if r.logins == nil {
r.logins = make(map[string]string)
}
if _, ok := r.logins[queueID]; !ok {
r.loginKeys = append(r.loginKeys, queueID)
if len(r.loginKeys) > refusalLogins {
delete(r.logins, r.loginKeys[0])
r.loginKeys = r.loginKeys[1:]
}
}
r.logins[queueID] = login
}
// domainOf is the domain of an address, lower-cased; "" without one.
func domainOf(addr string) string {
if i := strings.LastIndexByte(addr, '@'); i >= 0 {
return strings.ToLower(addr[i+1:])
}
return ""
}
func (r *refusalLines) attach(p pendingRefusal) bool {
ok, err := r.st.AttachRefusalLine(p.login, p.from, p.at, p.line)
if err != nil {
log.Printf("log-tailer: refusal line: %v", err)
return true // not retried: the store said no for its own reason
}
return ok
}