mixandClaude Opus 5.5
db36aa2c0e
Seen on the e2e stand, the panel frozen with SIGSTOP once DATA was
answered: the client gets 451 4.7.1 after 30 s, and the warning that names
the socket is cleanup's, not smtpd's:
postfix/cleanup[1339]: warning: milter unix:/run/selfpost/sender.sock:
can't read SMFIC_HEADER reply packet header: Connection timed out
postfix/cleanup[1339]: 7BCAF3C75DA0: milter-reject: END-OF-MESSAGE ...
4.7.1 Service unavailable - try again later; ...
The counter read smtpd lines only, so Health's "messages deferred" missed
the one case that tells a hung panel from a stopped one. milterLineRe now
takes smtpd and cleanup; cleanup's "milter unix:<socket>:" warning counts a
message each time (one cleanup process serves message after message, and the
first warning ends the message); smtpd keeps once per connection. The
composed fixture is replaced by the seen lines, with two messages through one
cleanup process and OpenDKIM hung in cleanup (not counted).
e2e panel_hung_mid_message_is_counted: freezes the panel after DATA's 354,
wants a 4xx at the end of DATA, logs what mail.log says, and waits for
Health's today count to grow. kill through sh -c: the image has no kill(1).
CHANGELOG [Unreleased], audit plan line ticked, roadmap 13/61.
Evidence on the test server for this tree (with the next commit's docs):
go vet clean, go test ./... 23 packages ok, make e2e exit 0 -
renewed_certificate_picked_up 1.2 s, panel_hung_mid_message_is_counted
31.7 s.
Co-Authored-By: Claude Opus 5.5 <noreply@anthropic.com>
118 lines
7.2 KiB
Go
118 lines
7.2 KiB
Go
package logtail
|
|
|
|
import (
|
|
"testing"
|
|
"time"
|
|
)
|
|
|
|
type deferredStore struct {
|
|
days map[string]int64
|
|
last time.Time
|
|
}
|
|
|
|
func (d *deferredStore) SenderCheckDeferredAt() (time.Time, error) { return d.last, nil }
|
|
|
|
func (d *deferredStore) AddSenderCheckDeferred(at time.Time, n int64) error {
|
|
if d.days == nil {
|
|
d.days = make(map[string]int64)
|
|
}
|
|
d.days[at.UTC().Format("2006-01-02")] += n
|
|
if at.After(d.last) {
|
|
d.last = at
|
|
}
|
|
return nil
|
|
}
|
|
|
|
// The lines of process 1183 and of cleanup are as the e2e stand wrote them
|
|
// with the panel stopped and for a refused From: (2026-10-12), and with the
|
|
// panel frozen in the middle of a message (cleanup 1339, 2026-10-14); the
|
|
// stamps are put in ISO form. Around them are the lines of two other things
|
|
// that use the same words - a level-2 refusal of the journal milter, OpenDKIM
|
|
// not answering.
|
|
func TestDeferredCounter(t *testing.T) {
|
|
st := &deferredStore{}
|
|
c := newDeferredCounter(&SenderCheck{Store: st, Socket: "/run/selfpost/sender.sock"})
|
|
now := time.Date(2026, 10, 12, 18, 0, 0, 0, time.UTC)
|
|
for _, line := range []string{
|
|
// The journal milter's own temporary refusal: no warning, not counted.
|
|
`2026-10-12T16:22:13.100000+00:00 mail postfix/smtpd[1149]: connect from unknown[10.77.0.1]`,
|
|
`2026-10-12T16:22:13.200000+00:00 mail 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> sasl_username=<l2app>`,
|
|
|
|
// The check does not answer: one connection, counted once.
|
|
`2026-10-12T16:22:57.000000+00:00 mail postfix/smtpd[1183]: connect from unknown[10.77.0.1]`,
|
|
`2026-10-12T16:22:57.100000+00:00 mail postfix/smtpd[1183]: warning: connect to Milter service unix:/run/selfpost/sender.sock: No such file or directory`,
|
|
`2026-10-12T16:22:57.200000+00:00 mail postfix/smtpd[1183]: NOQUEUE: milter-reject: CONNECT from unknown[10.77.0.1]: 451 4.7.1 Service unavailable - try again later; proto=SMTP`,
|
|
`2026-10-12T16:22:57.300000+00:00 mail postfix/smtpd[1183]: NOQUEUE: milter-reject: EHLO from unknown[10.77.0.1]: 451 4.7.1 Service unavailable - try again later; proto=SMTP helo=<e2e-client.e2e.test>`,
|
|
`2026-10-12T16:22:57.400000+00:00 mail postfix/smtpd[1183]: disconnect from unknown[10.77.0.1] ehlo=1 auth=0/1 quit=1 commands=2/3`,
|
|
|
|
// The same process takes another client, and the check answers again:
|
|
// a level-2 refusal there is not the check's.
|
|
`2026-10-12T16:23:30.000000+00:00 mail postfix/smtpd[1183]: connect from unknown[10.77.0.1]`,
|
|
`2026-10-12T16:23:30.100000+00:00 mail postfix/smtpd[1183]: NOQUEUE: milter-reject: MAIL from unknown[10.77.0.1]: 451 4.7.1 Service unavailable - try again later; from=<a@sender.e2e.test> proto=ESMTP helo=<x>`,
|
|
|
|
// A client that writes the socket's name where Postfix will quote it
|
|
// in a warning, and then runs into a level-2 refusal: not counted.
|
|
`2026-10-12T16:23:40.000000+00:00 mail postfix/smtpd[1190]: connect from unknown[10.77.0.1]`,
|
|
`2026-10-12T16:23:40.100000+00:00 mail postfix/smtpd[1190]: warning: Illegal address syntax from unknown[10.77.0.1] in MAIL command: <warning: connect to Milter service unix:/run/selfpost/sender.sock: milter>`,
|
|
`2026-10-12T16:23:40.200000+00:00 mail postfix/smtpd[1190]: NOQUEUE: milter-reject: MAIL from unknown[10.77.0.1]: 451 4.7.1 Service unavailable - try again later; from=<a@sender.e2e.test> proto=ESMTP helo=<x>`,
|
|
|
|
// OpenDKIM does not answer: another socket, not counted.
|
|
`2026-10-12T16:24:00.000000+00:00 mail postfix/smtpd[1201]: connect from unknown[10.77.0.1]`,
|
|
`2026-10-12T16:24:00.100000+00:00 mail postfix/smtpd[1201]: warning: connect to Milter service unix:/run/opendkim/opendkim.sock: Connection refused`,
|
|
`2026-10-12T16:24:00.200000+00:00 mail postfix/smtpd[1201]: NOQUEUE: milter-reject: CONNECT from unknown[10.77.0.1]: 451 4.7.1 Service unavailable - try again later; proto=SMTP`,
|
|
|
|
// The check stops answering in the middle of a message, the next day:
|
|
// cleanup meets it. Two messages through the same cleanup process are
|
|
// two messages.
|
|
`2026-10-13T00:00:05.000000+00:00 mail postfix/smtpd[1300]: connect from unknown[10.77.0.1]`,
|
|
`2026-10-13T00:00:35.000000+00:00 mail postfix/cleanup[1339]: warning: milter unix:/run/selfpost/sender.sock: can't read SMFIC_HEADER reply packet header: Connection timed out`,
|
|
`2026-10-13T00:00:35.100000+00:00 mail postfix/cleanup[1339]: 7BCAF3C75DA0: milter-reject: END-OF-MESSAGE from unknown[10.77.0.1]: 4.7.1 Service unavailable - try again later; from=<alerts@sender.e2e.test> to=<rcpt@sink.e2e.test> proto=ESMTP helo=<e2e-client.e2e.test>`,
|
|
`2026-10-13T00:01:20.000000+00:00 mail postfix/cleanup[1339]: warning: milter unix:/run/selfpost/sender.sock: can't read SMFIC_HEADER reply packet header: Connection timed out`,
|
|
`2026-10-13T00:01:20.100000+00:00 mail postfix/cleanup[1339]: 8C1D43C75DA0: milter-reject: END-OF-MESSAGE from unknown[10.77.0.1]: 4.7.1 Service unavailable - try again later; from=<alerts@sender.e2e.test> to=<rcpt@sink.e2e.test> proto=ESMTP helo=<e2e-client.e2e.test>`,
|
|
|
|
// OpenDKIM hung in the middle of a message: another socket.
|
|
`2026-10-13T00:01:30.000000+00:00 mail postfix/cleanup[1339]: warning: milter unix:/run/opendkim/opendkim.sock: can't read SMFIC_HEADER reply packet header: Connection timed out`,
|
|
|
|
// The check's own verdict is a refusal, not a deferral, and it is
|
|
// cleanup that writes it.
|
|
`2026-10-13T00:01:00.000000+00:00 mail postfix/cleanup[1195]: B6B484831946: 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=<x>`,
|
|
} {
|
|
c.handle(line, now, false)
|
|
}
|
|
if len(st.days) != 2 || st.days["2026-10-12"] != 1 || st.days["2026-10-13"] != 2 {
|
|
t.Fatalf("deferred per day = %v, want one on the first day and two on the second", st.days)
|
|
}
|
|
}
|
|
|
|
// After an unclean stop the tailer reads again some lines it had read. What
|
|
// was counted then is not counted now; what was written while the panel was
|
|
// down - the very lines this count exists for - is.
|
|
func TestDeferredCounterDoesNotCountALogReadAgain(t *testing.T) {
|
|
st := &deferredStore{}
|
|
now := time.Date(2026, 10, 12, 18, 0, 0, 0, time.UTC)
|
|
outage := func(pid, at string) []string {
|
|
return []string{
|
|
at + `0+00:00 mail postfix/smtpd[` + pid + `]: connect from unknown[10.77.0.1]`,
|
|
at + `1+00:00 mail postfix/smtpd[` + pid + `]: warning: connect to Milter service unix:/run/selfpost/sender.sock: Connection refused`,
|
|
}
|
|
}
|
|
first := append(outage("11", "2026-10-12T16:00:00.00000"), outage("12", "2026-10-12T16:00:05.00000")...)
|
|
|
|
c := newDeferredCounter(&SenderCheck{Store: st, Socket: "/run/selfpost/sender.sock"})
|
|
for _, line := range first {
|
|
c.handle(line, now, false)
|
|
}
|
|
if st.days["2026-10-12"] != 2 {
|
|
t.Fatalf("first run counted %d, want 2", st.days["2026-10-12"])
|
|
}
|
|
|
|
// A new run: the same lines again, then what the outage added.
|
|
c = newDeferredCounter(&SenderCheck{Store: st, Socket: "/run/selfpost/sender.sock"})
|
|
for _, line := range append(first, outage("13", "2026-10-12T16:00:09.00000")...) {
|
|
c.handle(line, now, true)
|
|
}
|
|
if st.days["2026-10-12"] != 3 {
|
|
t.Fatalf("after the restart the day has %d, want 3", st.days["2026-10-12"])
|
|
}
|
|
}
|