mirror of
https://github.com/slackhq/nebula.git
synced 2026-11-15 10:46:52 +01:00
With tun.staged.workers set, each Linux UDP listener classifies a recvmmsg
batch, hands its data packets to that many decrypt workers, and an ordered
writer commits the batch in arrival order: replay window, roaming, firewall,
control packets and tun writes go through the same helpers inline receive
uses. Six batches per routine bound memory and backpressure. Conns that cannot
hand off their buffers stay inline.
The listener's classification is speculative. Before touching replay state the
writer resolves each data packet through its own batch-local hostmap cache,
exactly where inline receive would, so data after a close in the same batch is
still delivered while data after a removal or replacement between batches is
dropped, with the same RecvError reply inline receive sends. Known replays are
marked by a precheck and skip decryption, but keep their place so that reply
stays identical when an earlier RecvError deleted their tunnel.
New API: udp.StdConn.ListenOutHandoff, and the same on TesterConn for e2e,
runs the receive loop while handing each batch's buffers to the caller in
exchange for replacements. It is found through an unexported interface in
nebula, so udp.Conn and its other implementations are unchanged.
Metrics: flow.rx.batches, and flow.stage.{rx_read,rx_decrypt,rx_write}.q<N>.busy_ns.
Tests cover both ciphers, ordering, duplicate and corrupted packets from other
addresses, window jumps, control packets mid-batch, RecvError then replay,
tunnel replacement, firewall parity, fallback, real UDP sockets, partial
batches at close, and a handshake and traffic through e2e that checks pipeline
use on Linux and the inline fallback elsewhere. No isolated receive throughput
claim is made.
148 lines
4.6 KiB
Go
148 lines
4.6 KiB
Go
package nebula
|
|
|
|
import (
|
|
"fmt"
|
|
"net/netip"
|
|
"os"
|
|
"path/filepath"
|
|
"runtime"
|
|
"testing"
|
|
"time"
|
|
|
|
"github.com/slackhq/nebula/cert"
|
|
cert_test "github.com/slackhq/nebula/cert_test"
|
|
"github.com/slackhq/nebula/config"
|
|
"github.com/slackhq/nebula/noiseutil"
|
|
"github.com/slackhq/nebula/test"
|
|
"github.com/slackhq/nebula/util"
|
|
"github.com/stretchr/testify/assert"
|
|
"github.com/stretchr/testify/require"
|
|
"go.uber.org/goleak"
|
|
)
|
|
|
|
func TestParseCpuAffinity(t *testing.T) {
|
|
l := test.NewLogger()
|
|
|
|
// newConfig returns a config.C with tun.cpu_affinity set to v. A nil v
|
|
// leaves the key unset.
|
|
newConfig := func(v any) *config.C {
|
|
c := config.NewC(l)
|
|
if v != nil {
|
|
c.Settings["tun"] = map[string]any{"cpu_affinity": v}
|
|
}
|
|
return c
|
|
}
|
|
|
|
// unset -> nil (listenIn falls back to spreading across the allowed set)
|
|
assert.Nil(t, parseCpuAffinity(newConfig(nil), l, 1))
|
|
|
|
// Pick a CPU we're actually allowed to run on so a valid list survives
|
|
// validation regardless of the host's affinity mask.
|
|
allowed, _ := util.AllowedCPUs()
|
|
validCPU := 0
|
|
if len(allowed) > 0 {
|
|
validCPU = allowed[0]
|
|
}
|
|
|
|
// valid list -> parsed through unchanged
|
|
assert.Equal(t, []int{validCPU, validCPU}, parseCpuAffinity(newConfig([]any{validCPU, validCPU}), l, 2))
|
|
|
|
// a negative entry is out of range on every platform -> disables the override
|
|
assert.Nil(t, parseCpuAffinity(newConfig([]any{validCPU, -1}), l, 2))
|
|
|
|
// a non-integer entry -> disables the override
|
|
assert.Nil(t, parseCpuAffinity(newConfig([]any{validCPU, "not-a-cpu"}), l, 2))
|
|
|
|
// a CPU id outside the allowed set -> disables the override. Only assertable
|
|
// where we can enumerate the allowed set (e.g. linux); 1<<20 is far beyond
|
|
// any representable CPU id so it can never be in the mask.
|
|
if len(allowed) > 0 {
|
|
assert.Nil(t, parseCpuAffinity(newConfig([]any{1 << 20}), l, 1))
|
|
}
|
|
}
|
|
|
|
// TestMain_ConfigTestReleasesItsGoroutines pins the rule that Main only leaves goroutines running
|
|
// when it hands back a Control to stop them with.
|
|
//
|
|
// A config test gets no Control, so anything it started had nothing to stop it: the lighthouse
|
|
// query worker, and a hostname resolver per dns named static host, ran for the life of the
|
|
// process. That matters to every embedder that validates a config in process rather than by
|
|
// exec'ing, dnclient and the apple clients included, because they do it on each config load and
|
|
// the leak accumulates.
|
|
func TestMain_ConfigTestReleasesItsGoroutines(t *testing.T) {
|
|
defer goleak.VerifyNone(t, goleak.IgnoreCurrent())
|
|
|
|
l := test.NewLogger()
|
|
dir := t.TempDir()
|
|
|
|
before := time.Now().Add(-time.Hour)
|
|
after := time.Now().Add(time.Hour)
|
|
ca, _, caKey, caPEM := cert_test.NewTestCaCert(cert.Version2, cert.Curve_CURVE25519, before, after, nil, nil, nil)
|
|
networks := []netip.Prefix{netip.MustParsePrefix("10.0.0.1/24")}
|
|
_, _, keyPEM, certPEM := cert_test.NewTestCert(
|
|
cert.Version2, cert.Curve_CURVE25519, ca, caKey, "config-test", before, after, networks, nil, nil)
|
|
|
|
caPath := filepath.Join(dir, "ca.pem")
|
|
certPath := filepath.Join(dir, "cert.pem")
|
|
keyPath := filepath.Join(dir, "key.pem")
|
|
require.NoError(t, os.WriteFile(caPath, caPEM, 0o600))
|
|
require.NoError(t, os.WriteFile(certPath, certPEM, 0o600))
|
|
require.NoError(t, os.WriteFile(keyPath, keyPEM, 0o600))
|
|
|
|
// A static host by address, not by name: the query worker is the goroutine under test and a
|
|
// hostname would drag a real dns lookup into a unit test.
|
|
configBody := fmt.Sprintf(`
|
|
pki:
|
|
ca: %s
|
|
cert: %s
|
|
key: %s
|
|
static_host_map:
|
|
"10.0.0.2": ["192.0.2.1:4242"]
|
|
lighthouse:
|
|
hosts:
|
|
- "10.0.0.2"
|
|
listen:
|
|
host: 127.0.0.1
|
|
port: 0
|
|
tun:
|
|
disabled: true
|
|
firewall:
|
|
outbound:
|
|
- port: any
|
|
proto: any
|
|
host: any
|
|
inbound:
|
|
- port: any
|
|
proto: any
|
|
host: any
|
|
`, caPath, certPath, keyPath)
|
|
require.NoError(t, os.WriteFile(filepath.Join(dir, "config.yml"), []byte(configBody), 0o600))
|
|
|
|
c := config.NewC(l)
|
|
require.NoError(t, c.Load(dir))
|
|
|
|
ctrl, err := Main(c, true, "config-test", l, nil)
|
|
require.NoError(t, err)
|
|
require.Nil(t, ctrl, "a config test hands back nothing to stop, so it must stop itself")
|
|
}
|
|
|
|
func TestParseStagedConfig(t *testing.T) {
|
|
l := test.NewLogger()
|
|
staged := func(workers any) stagedConfig {
|
|
c := config.NewC(l)
|
|
if workers != nil {
|
|
c.Settings["tun"] = map[string]any{"staged": map[string]any{"workers": workers}}
|
|
}
|
|
return parseStagedConfig(c, l)
|
|
}
|
|
for _, workers := range []any{nil, -1, 0} {
|
|
require.Equal(t, stagedConfig{}, staged(workers))
|
|
}
|
|
if runtime.GOOS != "linux" {
|
|
require.Equal(t, stagedConfig{}, staged(2))
|
|
return
|
|
}
|
|
want := stagedConfig{workers: 2, tx: !noiseutil.EncryptLockNeeded, rx: true}
|
|
require.Equal(t, want, staged(2))
|
|
}
|