Keep a scan out of route-proxy's unrouted state: only names under a served domain, a few a minute, no visitor address (issue 774)
Review of 3e14a13b: a scanner's random Host or SNI names each became a key, bounded only by the
bucket's lifetime and size, and every failed write was retried at each change and logged each time.
A refused name is now kept by name only under the registrable domain of a name the proxy serves, and
at most five new names a minute; every other refusal is counted in memory and written once a minute
under <node>._other (last minute, since start), which route_proxy_unrouted shows. A refused write of
that state is dropped and logged once until a write succeeds; trimming memory to 4096 names moved
from the request to the writer. The visitor's address is no longer kept: the journal has it.
Quick: drop unrouted keys from strangers by a fixed allow-list. Thorough: bound by the proxy's own
domains, by rate, and by never retrying. Chose thorough: the scan is constant on a public machine.
This commit is contained in:
@@ -11,11 +11,13 @@ import (
|
||||
"encoding/json"
|
||||
"encoding/pem"
|
||||
"errors"
|
||||
"fmt"
|
||||
"math/big"
|
||||
"net"
|
||||
"net/http"
|
||||
"net/http/httptest"
|
||||
"sort"
|
||||
"strings"
|
||||
"testing"
|
||||
"time"
|
||||
|
||||
@@ -30,11 +32,17 @@ import (
|
||||
type fakeState struct {
|
||||
values map[string]json.RawMessage
|
||||
puts int
|
||||
tries int // every Put asked, refused or not
|
||||
fail error // what every Put is refused with, while set
|
||||
}
|
||||
|
||||
func newFakeState() *fakeState { return &fakeState{values: map[string]json.RawMessage{}} }
|
||||
|
||||
func (f *fakeState) Put(key string, value any) (uint64, error) {
|
||||
f.tries++
|
||||
if f.fail != nil {
|
||||
return 0, f.fail
|
||||
}
|
||||
raw, err := json.Marshal(value)
|
||||
if err != nil {
|
||||
return 0, err
|
||||
@@ -158,19 +166,22 @@ func TestTheBusIsToldWhatIsServedAndRefused(t *testing.T) {
|
||||
t.Fatalf("the same answer was written %d times in all, want 3 writes", routes.puts)
|
||||
}
|
||||
}},
|
||||
{"a name not served is written as asked, and leaves when it is served",
|
||||
{"a name under a served domain is written as asked, without who asked, and leaves when it is served",
|
||||
func(t *testing.T, held *table) {
|
||||
req := httptest.NewRequest(http.MethodGet, "http://grafana.other.example/", nil)
|
||||
req := httptest.NewRequest(http.MethodGet, "http://wiki.grafana.example/", nil)
|
||||
req.RemoteAddr = "192.0.2.7:51000"
|
||||
handler(held).ServeHTTP(httptest.NewRecorder(), req)
|
||||
held.ledger.flush()
|
||||
var a routestate.Unrouted
|
||||
raw := held.ledger.unrouted.(*fakeState).values["anchor.grafana.other.example"]
|
||||
if err := json.Unmarshal(raw, &a); err != nil || a.From != "192.0.2.7" || a.Times != 1 || a.AskedAt.IsZero() {
|
||||
raw := held.ledger.unrouted.(*fakeState).values["anchor.wiki.grafana.example"]
|
||||
if err := json.Unmarshal(raw, &a); err != nil || a.Times != 1 || a.AskedAt.IsZero() {
|
||||
t.Fatalf("the refused name is not on the bus as asked: %s", raw)
|
||||
}
|
||||
if strings.Contains(string(raw), "192.0.2.7") || strings.Contains(string(raw), `"from"`) {
|
||||
t.Fatalf("who asked is on the bus: %s", raw)
|
||||
}
|
||||
routes, public := routesOf(append(contributions, contribution{From: "grafana", Node: "anchor",
|
||||
Values: map[string]any{"name": "grafana.other.example", "port": 3000.0}}))
|
||||
Values: map[string]any{"name": "wiki.grafana.example", "port": 3000.0}}))
|
||||
held.set(routes, public)
|
||||
},
|
||||
func(t *testing.T, _, unrouted *fakeState) {
|
||||
@@ -181,16 +192,51 @@ func TestTheBusIsToldWhatIsServedAndRefused(t *testing.T) {
|
||||
{"a handshake for a name not routed is written as asked",
|
||||
func(t *testing.T, held *table) {
|
||||
pick := certificateFor(held, func(*tls.ClientHelloInfo) (*tls.Certificate, error) {
|
||||
return nil, errors.New("no public route for \"forgotten.example\" in this mesh, so no certificate is asked for")
|
||||
return nil, errors.New("no public route for \"forgotten.grafana.example\" in this mesh, so no certificate is asked for")
|
||||
}, nil)
|
||||
_, _ = pick(&tls.ClientHelloInfo{ServerName: "forgotten.example"})
|
||||
_, _ = pick(&tls.ClientHelloInfo{ServerName: "forgotten.grafana.example"})
|
||||
},
|
||||
func(t *testing.T, _, unrouted *fakeState) {
|
||||
var a routestate.Unrouted
|
||||
if err := json.Unmarshal(unrouted.values["anchor.forgotten.example"], &a); err != nil || !a.Handshake {
|
||||
if err := json.Unmarshal(unrouted.values["anchor.forgotten.grafana.example"], &a); err != nil || !a.Handshake {
|
||||
t.Fatalf("a handshake refused for its name is not on the bus: %v", unrouted.values)
|
||||
}
|
||||
}},
|
||||
{"a flood of names writes at most the limit by name, counts the rest once a minute, and never retries a refused write",
|
||||
func(t *testing.T, held *table) {
|
||||
clock := time.Date(2026, 10, 30, 21, 0, 0, 0, time.UTC)
|
||||
held.ledger.now = func() time.Time { return clock }
|
||||
full := held.ledger.unrouted.(*fakeState)
|
||||
for i := range 40 {
|
||||
held.ledger.refused(fmt.Sprintf("x%d.grafana.example", i), false, false) // under a served domain
|
||||
held.ledger.refused(fmt.Sprintf("x%d.scan.test", i), false, true) // under none
|
||||
}
|
||||
held.ledger.flush()
|
||||
if named := len(full.values); named != newPerMinute {
|
||||
t.Fatalf("a flood wrote %d names, want the limit %d: %v", named, newPerMinute, full.values)
|
||||
}
|
||||
full.fail = errors.New("nats: maximum bytes exceeded")
|
||||
clock = clock.Add(time.Minute)
|
||||
held.ledger.refused("y.grafana.example", false, false) // a new minute: one more name,
|
||||
held.ledger.refused("v.scan.test", false, false) // and the last minute's count
|
||||
held.ledger.flush()
|
||||
tries := full.tries
|
||||
held.ledger.refused("y.grafana.example", false, false)
|
||||
held.ledger.refused("z.scan.test", false, false)
|
||||
held.ledger.flush()
|
||||
if full.tries != tries {
|
||||
t.Fatalf("writes the bucket refused were tried again: %d tries, then %d", tries, full.tries)
|
||||
}
|
||||
full.fail = nil
|
||||
clock = clock.Add(time.Minute)
|
||||
held.ledger.refused("w.scan.test", false, false)
|
||||
},
|
||||
func(t *testing.T, _, unrouted *fakeState) {
|
||||
var o routestate.Other
|
||||
if err := json.Unmarshal(unrouted.values["anchor._other"], &o); err != nil || o.LastMinute != 2 || o.SinceStart != 78 {
|
||||
t.Fatalf("the refusals not kept by name are not counted on the bus: %s", unrouted.values["anchor._other"])
|
||||
}
|
||||
}},
|
||||
{"a certificate an authority issued is written with its issuer, expiry and renewal",
|
||||
func(t *testing.T, held *table) {
|
||||
cache := recordingCache{Cache: autocert.DirCache(t.TempDir()), held: held}
|
||||
|
||||
Reference in New Issue
Block a user