TODO.md

@@ -35,6 +35,12 @@ tested.
 
 # Completed Steps
 
+- 2026-11-02: like a failed WHOIS lookup, a lookup skipped because its RIR is
+  paused makes the fetcher wait longer before the next lookup. The longest wait
+  is one minute. The status page does not count a skip as a failure. A skip used
+  to leave the wait as it was. Each lookup asks IANA before it finds its RIR
+  paused. So while most stale ASes belonged to a paused RIR, the fetcher could
+  ask IANA every second (closes #222)
 - 2026-11-02: a peer's session going down no longer stops the prefix handler.
   The handler runs the table's `PeerDown` on a separate goroutine, one peer at a
   time, and goes on taking messages. `PeerDown` holds the table's lock for

internal/routewatch/asnfetcher.go

@@ -187,25 +187,33 @@ func (f *ASNFetcher) recordSuccess() {
 	f.statsMu.Unlock()
 }
 
-// recordFailure increases the interval on failed fetch using exponential backoff.
-func (f *ASNFetcher) recordFailure() {
+// lengthenInterval makes the interval 1.5 times as long, up to maxInterval.
+// A failed lookup and a skipped one both lengthen it.
+func (f *ASNFetcher) lengthenInterval() {
 	f.intervalMu.Lock()
-	f.consecutiveFails++
+	defer f.intervalMu.Unlock()
 
-	// Exponential backoff: multiply by 1.5, capped at max
 	newInterval := min(
 		f.currentInterval*backoffNumerator/backoffDenominator, maxInterval)
 
 	if newInterval != f.currentInterval {
-		f.logger.Debug("Increased fetch interval due to failure",
+		f.logger.Debug("Increased fetch interval",
 			"old_interval", f.currentInterval,
 			"new_interval", newInterval,
 			"consecutive_failures", f.consecutiveFails,
 		)
 		f.currentInterval = newInterval
 	}
+}
+
+// recordFailure counts a failed fetch and lengthens the interval.
+func (f *ASNFetcher) recordFailure() {
+	f.intervalMu.Lock()
+	f.consecutiveFails++
 	f.intervalMu.Unlock()
 
+	f.lengthenInterval()
+
 	// Record error time for stats, dropping those older than statsWindow
 	f.statsMu.Lock()
 	now := f.now()
@@ -291,9 +299,12 @@ func (f *ASNFetcher) fetchNextStale(ctx context.Context) {
 // The WHOIS client pauses an RIR's or NIC.br's server for whois.PauseTime
 // after the server refuses a query. Lookups at the other servers go on. IANA
 // is never paused, so a refusal by IANA is an ordinary failure. A lookup
-// whose RIR is paused fails with whois.ErrPaused. Such a lookup leaves the
-// AS stale, and counts as neither a success nor a failure. The lookups that
-// QueueImmediate asks for also run through fetchAndUpdate.
+// whose RIR is paused fails with whois.ErrPaused and is skipped. A skipped
+// lookup leaves the AS stale and is not counted as a failure. Like a
+// failure, a skipped lookup lengthens the interval. Each lookup asks IANA
+// before it finds its RIR paused, so with a one-second interval the fetcher
+// would ask IANA every second. The lookups that QueueImmediate asks for also
+// run through fetchAndUpdate.
 func (f *ASNFetcher) fetchAndUpdate(ctx context.Context, asn int) bool {
 	ctx, cancel := context.WithTimeout(ctx, time.Minute)
 	defer cancel()
@@ -317,6 +328,7 @@ func (f *ASNFetcher) fetchAndUpdate(ctx context.Context, asn int) bool {
 	if errors.Is(err, whois.ErrPaused) {
 		f.logger.Info("Skipped WHOIS lookup, the RIR's server is paused",
 			"asn", asn, "error", err)
+		f.lengthenInterval()
 
 		return false
 	}

internal/routewatch/asnfetcher_internal_test.go

@@ -196,6 +196,48 @@ func TestFetchAndUpdateWaitsOutAPause(t *testing.T) {
 	}
 }
 
+// TestFetchAndUpdateBacksOffDuringAPause looks up an AS at RIPE while RIPE
+// refuses the query. The refusal pauses RIPE for an hour, so every later
+// lookup in the test is skipped. The test sets the WHOIS client's clock and
+// looks the AS up again each time the interval has passed. Like a failure,
+// each skip must make the interval 1.5 times as long, up to one minute. The
+// skips must not count as failures.
+func TestFetchAndUpdateBacksOffDuringAPause(t *testing.T) {
+	t.Parallel()
+
+	f, _ := newFetcherWithWHOISAnswers(t, map[string]string{
+		ianaWHOISServer: ianaRefersToRIPE,
+		ripeWHOISServer: ripeAccessDenied,
+	})
+
+	now := time.Date(2026, 11, 2, 0, 0, 0, 0, time.UTC)
+	f.whoisClient.Now = func() time.Time { return now }
+
+	f.fetchAndUpdate(t.Context(), testASNA)
+
+	for i, want := range []time.Duration{
+		33750 * time.Millisecond,
+		50625 * time.Millisecond,
+		time.Minute,
+		time.Minute,
+	} {
+		now = now.Add(f.getInterval())
+
+		f.fetchAndUpdate(t.Context(), testASNA)
+
+		if got := f.getInterval(); got != want {
+			t.Errorf("interval after %d skipped lookups = %v, want %v",
+				i+1, got, want)
+		}
+	}
+
+	got := f.GetStats()
+	if got.ConsecutiveFails != 1 || got.ErrorsLastHour != 1 {
+		t.Errorf("%d failures in a row and %d errors, want 1 and 1",
+			got.ConsecutiveFails, got.ErrorsLastHour)
+	}
+}
+
 // TestFetchAndUpdateKeepsAskingIANA looks up an AS while IANA's server
 // refuses the connection. The test sets the WHOIS client's clock. The next
 // lookup comes a second before whois.PauseTime has passed. IANA is never