sender check: connections and messages counted apart; downtime estimated when supervisord is silent (stage 2b)
Following the design commit df96690.
- Two columns (owner, 2026-10-14): sender_check_days.messages (migration
0009, not deployed) holds the messages deferred mid-message, from
cleanup's warning; deferred stays the connections smtpd turned away.
AddSenderCheckDeferred takes which; the counter passes cleanup's as a
message. The card has "Connections turned away" and "Messages deferred";
it warns on either within 24 hours (one mark, as before).
- Supervisord silent at start: postfixStarted asks again every 2 s for 30 s
(postfixState: started, running, known). With no answer the downtime is
the time since the alive mark - an upper bound - booked with estimated = 1
(sender_check_days.estimated, MAX over a day); the card prefixes such a
period's time with "≈ " and its note says what ≈ means. Before, such a
start counted nothing and the number the owner decides by read low.
- Help topic sender-check and the log topic word for word as the mockup
(help.go).
Tests: store (connections and messages apart, a period with an estimated
day); logtail (cleanup's warnings are messages); cmd/panel (supervisord
silent: the time since the mark, estimated); view fixture and the Health
page at four columns with ≈; e2e reads the row's two counts (panel down:
connections; panel hung: messages). Schema at 0009 with the columns.
schema-migrations row 9, CHANGELOG [Unreleased], audit plan lines ticked
(two), roadmap 28/62.
Evidence: go vet ./... clean; go test of store, view, cmd/panel ok locally,
logtail but for the Windows-only test; the server run follows before the
push.
Co-Authored-By: Claude Opus 5.5 <noreply@anthropic.com>
This commit is contained in:
@@ -13,3 +13,12 @@ ALTER TABLE send_log ADD COLUMN refusal_line TEXT NOT NULL DEFAULT '';
|
||||
-- none - is written by the log tailer from Postfix's line about it, and marked
|
||||
-- so: recovered = 1.
|
||||
ALTER TABLE send_log ADD COLUMN recovered INTEGER NOT NULL DEFAULT 0;
|
||||
|
||||
-- The Sender check card counts two things apart (the owner, 2026-10-14):
|
||||
-- deferred stays the connections Postfix turned away while the check did not
|
||||
-- answer, and messages are those deferred in the middle, when the check
|
||||
-- stopped answering after a message had begun (cleanup's warning). estimated
|
||||
-- marks a day whose downtime was taken from the alive mark alone, because
|
||||
-- supervisord could not say at start since when Postfix ran: an upper bound.
|
||||
ALTER TABLE sender_check_days ADD COLUMN messages INTEGER NOT NULL DEFAULT 0;
|
||||
ALTER TABLE sender_check_days ADD COLUMN estimated INTEGER NOT NULL DEFAULT 0;
|
||||
|
||||
@@ -59,7 +59,7 @@ func TestBaselineSchema(t *testing.T) {
|
||||
"inbound_spam_list": "id list_type entry_type value note created_at",
|
||||
"send_log_lines": "id queue_id logged_at line",
|
||||
"notify_state": "key phase count mark since sent_at",
|
||||
"sender_check_days": "day down_seconds deferred",
|
||||
"sender_check_days": "day down_seconds deferred messages estimated",
|
||||
"delivery_log_days": "day reconcile_closed reconcile_missed reconcile_contradicted tailer_blind_seconds queued_over_lifetime",
|
||||
}
|
||||
rows, err := st.db.Query("SELECT name FROM sqlite_master WHERE type = 'table' AND name NOT LIKE 'sqlite_%' ORDER BY name")
|
||||
|
||||
@@ -43,7 +43,11 @@ const dayLayout = "2006-01-02"
|
||||
// SenderCheckTotals is what the strict sender check has cost over a period.
|
||||
type SenderCheckTotals struct {
|
||||
Down time.Duration // the panel not answering while Postfix was running
|
||||
Deferred int64 // messages Postfix deferred because of it
|
||||
Deferred int64 // connections Postfix turned away because of it
|
||||
Messages int64 // messages deferred in the middle because of it
|
||||
// Estimated: a day of the period had its downtime taken from the alive
|
||||
// mark alone - at most what it was.
|
||||
Estimated bool
|
||||
}
|
||||
|
||||
// SenderCheckStats is the card of Server > Health.
|
||||
@@ -65,16 +69,18 @@ func (s *Store) StartSenderCheckStats(now time.Time) error {
|
||||
}
|
||||
|
||||
// AddSenderCheckDown adds to the day of at the time the panel did not answer
|
||||
// while Postfix was running.
|
||||
func (s *Store) AddSenderCheckDown(at time.Time, d time.Duration) error {
|
||||
// while Postfix was running; estimated marks the day when that time is an
|
||||
// upper bound (supervisord could not say since when Postfix ran).
|
||||
func (s *Store) AddSenderCheckDown(at time.Time, d time.Duration, estimated bool) error {
|
||||
secs := int64(d / time.Second)
|
||||
if secs <= 0 {
|
||||
return nil
|
||||
}
|
||||
_, err := s.db.Exec(
|
||||
`INSERT INTO sender_check_days (day, down_seconds) VALUES (?, ?)
|
||||
ON CONFLICT (day) DO UPDATE SET down_seconds = down_seconds + excluded.down_seconds`,
|
||||
at.UTC().Format(dayLayout), secs,
|
||||
`INSERT INTO sender_check_days (day, down_seconds, estimated) VALUES (?, ?, ?)
|
||||
ON CONFLICT (day) DO UPDATE SET down_seconds = down_seconds + excluded.down_seconds,
|
||||
estimated = MAX(estimated, excluded.estimated)`,
|
||||
at.UTC().Format(dayLayout), secs, estimated,
|
||||
)
|
||||
if err != nil {
|
||||
return fmt.Errorf("sender check downtime: %w", err)
|
||||
@@ -87,7 +93,10 @@ func (s *Store) AddSenderCheckDown(at time.Time, d time.Duration) error {
|
||||
// place - where in mail.log the counted line ends - in the same transaction:
|
||||
// a count without its place, or the other way round, would be counted again
|
||||
// or lost at the next start (audit 2026-10-12, stage 2b).
|
||||
func (s *Store) AddSenderCheckDeferred(at time.Time, n int64, place string) error {
|
||||
//
|
||||
// message says which of the two it is: a message deferred in the middle
|
||||
// (cleanup's warning) rather than a connection turned away (smtpd's).
|
||||
func (s *Store) AddSenderCheckDeferred(at time.Time, n int64, place string, message bool) error {
|
||||
if n <= 0 {
|
||||
return nil
|
||||
}
|
||||
@@ -96,9 +105,13 @@ func (s *Store) AddSenderCheckDeferred(at time.Time, n int64, place string) erro
|
||||
return fmt.Errorf("sender check deferred: %w", err)
|
||||
}
|
||||
defer tx.Rollback()
|
||||
if _, err := tx.Exec(
|
||||
`INSERT INTO sender_check_days (day, deferred) VALUES (?, ?)
|
||||
ON CONFLICT (day) DO UPDATE SET deferred = deferred + excluded.deferred`,
|
||||
column := "deferred"
|
||||
if message {
|
||||
column = "messages"
|
||||
}
|
||||
if _, err := tx.Exec(fmt.Sprintf(
|
||||
`INSERT INTO sender_check_days (day, %[1]s) VALUES (?, ?)
|
||||
ON CONFLICT (day) DO UPDATE SET %[1]s = %[1]s + excluded.%[1]s`, column),
|
||||
at.UTC().Format(dayLayout), n,
|
||||
); err != nil {
|
||||
return fmt.Errorf("sender check deferred: %w", err)
|
||||
@@ -149,16 +162,18 @@ func (s *Store) SenderCheckStats(now time.Time) (SenderCheckStats, error) {
|
||||
now = now.UTC()
|
||||
var out SenderCheckStats
|
||||
sum := func(days int) (SenderCheckTotals, error) {
|
||||
var secs, deferred int64
|
||||
var secs, deferred, messages, estimated int64
|
||||
err := s.db.QueryRow(
|
||||
`SELECT COALESCE(SUM(down_seconds), 0), COALESCE(SUM(deferred), 0)
|
||||
`SELECT COALESCE(SUM(down_seconds), 0), COALESCE(SUM(deferred), 0), COALESCE(SUM(messages), 0),
|
||||
COALESCE(MAX(estimated), 0)
|
||||
FROM sender_check_days WHERE day > ? AND day <= ?`,
|
||||
now.AddDate(0, 0, -days).Format(dayLayout), now.Format(dayLayout),
|
||||
).Scan(&secs, &deferred)
|
||||
).Scan(&secs, &deferred, &messages, &estimated)
|
||||
if err != nil {
|
||||
return SenderCheckTotals{}, fmt.Errorf("sender check stats: %w", err)
|
||||
}
|
||||
return SenderCheckTotals{Down: time.Duration(secs) * time.Second, Deferred: deferred}, nil
|
||||
return SenderCheckTotals{Down: time.Duration(secs) * time.Second, Deferred: deferred,
|
||||
Messages: messages, Estimated: estimated > 0}, nil
|
||||
}
|
||||
var err error
|
||||
if out.Today, err = sum(1); err != nil {
|
||||
|
||||
@@ -39,16 +39,16 @@ func TestSenderCheckStats(t *testing.T) {
|
||||
t.Fatal(err)
|
||||
}
|
||||
}
|
||||
must(st.AddSenderCheckDown(now, 3*time.Second))
|
||||
must(st.AddSenderCheckDown(now, 1500*time.Millisecond)) // whole seconds: one
|
||||
must(st.AddSenderCheckDown(now, 400*time.Millisecond)) // nothing
|
||||
must(st.AddSenderCheckDeferred(now.Add(-time.Hour), 2, ""))
|
||||
must(st.AddSenderCheckDown(day(10), 30*time.Second))
|
||||
must(st.AddSenderCheckDeferred(day(10), 1, ""))
|
||||
must(st.AddSenderCheckDown(day(29), time.Minute))
|
||||
must(st.AddSenderCheckDown(day(30), time.Hour)) // the 31st day back: the year's only
|
||||
must(st.AddSenderCheckDeferred(day(200), 5, ""))
|
||||
must(st.AddSenderCheckDown(day(365), 24*time.Hour)) // a year and a day: nobody's
|
||||
must(st.AddSenderCheckDown(now, 3*time.Second, false))
|
||||
must(st.AddSenderCheckDown(now, 1500*time.Millisecond, false)) // whole seconds: one
|
||||
must(st.AddSenderCheckDown(now, 400*time.Millisecond, false)) // nothing
|
||||
must(st.AddSenderCheckDeferred(now.Add(-time.Hour), 2, "", false))
|
||||
must(st.AddSenderCheckDown(day(10), 30*time.Second, false))
|
||||
must(st.AddSenderCheckDeferred(day(10), 1, "", false))
|
||||
must(st.AddSenderCheckDown(day(29), time.Minute, false))
|
||||
must(st.AddSenderCheckDown(day(30), time.Hour, false)) // the 31st day back: the year's only
|
||||
must(st.AddSenderCheckDeferred(day(200), 5, "", false))
|
||||
must(st.AddSenderCheckDown(day(365), 24*time.Hour, false)) // a year and a day: nobody's
|
||||
|
||||
got, err = st.SenderCheckStats(now)
|
||||
if err != nil {
|
||||
@@ -118,10 +118,10 @@ func TestRefusedRowKeepsItsReason(t *testing.T) {
|
||||
func TestSenderCheckDeferredSavesItsPlace(t *testing.T) {
|
||||
st := openTestStore(t)
|
||||
later := time.Date(2026, 10, 14, 12, 0, 1, 0, time.UTC)
|
||||
if err := st.AddSenderCheckDeferred(later, 1, "abc:1.2@100"); err != nil {
|
||||
if err := st.AddSenderCheckDeferred(later, 1, "abc:1.2@100", false); err != nil {
|
||||
t.Fatal(err)
|
||||
}
|
||||
if err := st.AddSenderCheckDeferred(later.Add(-time.Hour), 1, "abc:1.2@200"); err != nil {
|
||||
if err := st.AddSenderCheckDeferred(later.Add(-time.Hour), 1, "abc:1.2@200", false); err != nil {
|
||||
t.Fatal(err)
|
||||
}
|
||||
if p, err := st.SenderCheckCountedPlace(); err != nil || p != "abc:1.2@200" {
|
||||
@@ -131,3 +131,29 @@ func TestSenderCheckDeferredSavesItsPlace(t *testing.T) {
|
||||
t.Fatalf("last deferral = %s, %v; want %s", at, err, later)
|
||||
}
|
||||
}
|
||||
|
||||
// Connections turned away and messages deferred in the middle are counted
|
||||
// apart (the owner, 2026-10-14), and a period holding a day whose downtime is
|
||||
// an estimate says so.
|
||||
func TestSenderCheckCountsConnectionsAndMessagesApart(t *testing.T) {
|
||||
st := openTestStore(t)
|
||||
now := time.Date(2026, 10, 14, 12, 0, 0, 0, time.UTC)
|
||||
must := func(err error) {
|
||||
t.Helper()
|
||||
if err != nil {
|
||||
t.Fatal(err)
|
||||
}
|
||||
}
|
||||
must(st.AddSenderCheckDeferred(now, 3, "", false))
|
||||
must(st.AddSenderCheckDeferred(now, 1, "", true))
|
||||
must(st.AddSenderCheckDown(now.AddDate(0, 0, -3), 20*time.Second, true))
|
||||
must(st.AddSenderCheckDown(now.AddDate(0, 0, -3), 5*time.Second, false))
|
||||
got, err := st.SenderCheckStats(now)
|
||||
must(err)
|
||||
if got.Today.Deferred != 3 || got.Today.Messages != 1 || got.Today.Estimated {
|
||||
t.Errorf("today = %+v, want 3 connections, 1 message, not estimated", got.Today)
|
||||
}
|
||||
if got.Month.Down != 25*time.Second || !got.Month.Estimated {
|
||||
t.Errorf("the month = %+v, want 25 s, estimated", got.Month)
|
||||
}
|
||||
}
|
||||
|
||||
Reference in New Issue
Block a user