mirror of
https://github.com/slackhq/nebula.git
synced 2026-11-15 07:06:52 +01:00
With staged transmit, an idle reader encrypted and sent a small read itself, while larger reads went to the workers and left from the ordered sender. Each read chose on its own, so under load a routine alternated between the two paths. Their packets left from different CPUs, and the receiver's TCP saw them out of order: on 100 GbE, summed over four hosts, dsack_dups rose from 0-1 on master to about 25k and reord_seen from 0 to 13k-19k. Each routine now holds one mode, inline on the reader or fanout to the workers and the sender. It switches only after tun.staged.gate_hold (default 64) reads in a row want the other mode, and before going inline it waits until every batch in flight is on the wire, so a switch never lets a later packet overtake an earlier one. Going to fanout nothing is in flight. flow.tx.gate_switches counts the switches. On the same hosts dsack_dups fell to 20-52 and reord_seen to 0-2, while throughput matched or beat per-read mixing (many-to-one 34.9 instead of 30.7 Gbit/s). The affinity test waited only for the previous batch's packets to be captured before the next read, but the sender returns the slot after its write, so the reader could still see it in flight and stage the small read. Switching to inline now drains, which makes the inline send deterministic there.
136 lines
4.7 KiB
Go
136 lines
4.7 KiB
Go
//go:build linux && !android && !e2e_testing
|
|
|
|
package nebula
|
|
|
|
import (
|
|
"fmt"
|
|
"testing"
|
|
"time"
|
|
|
|
"github.com/flynn/noise"
|
|
"github.com/rcrowley/go-metrics"
|
|
"github.com/slackhq/nebula/overlay/tio"
|
|
"github.com/slackhq/nebula/udp"
|
|
"github.com/stretchr/testify/require"
|
|
"go.uber.org/goleak"
|
|
)
|
|
|
|
// gated is staging with an inline threshold of 4 segments and the given gate hold.
|
|
func gated(hold int) stagedConfig {
|
|
sc := adaptive(2)
|
|
sc.inlineBelow, sc.gateHold = 4, hold
|
|
return sc
|
|
}
|
|
|
|
// gateCounters snapshots the transmit counters a gate test checks.
|
|
type gateCounters struct{ inline, batches, switches int64 }
|
|
|
|
func readGateCounters() gateCounters {
|
|
return gateCounters{
|
|
inline: metrics.GetOrRegisterCounter("flow.tx.inline", nil).Count(),
|
|
batches: metrics.GetOrRegisterCounter("flow.tx.batches", nil).Count(),
|
|
switches: metrics.GetOrRegisterCounter("flow.tx.gate_switches", nil).Count(),
|
|
}
|
|
}
|
|
|
|
func (c gateCounters) since(c0 gateCounters) gateCounters {
|
|
return gateCounters{c.inline - c0.inline, c.batches - c0.batches, c.switches - c0.switches}
|
|
}
|
|
|
|
// gateReads builds reads of small (3 segments, below the threshold) or large (2 superpackets of 9) shape, in order,
|
|
// for one flow, and the segments they carry.
|
|
func gateReads(large ...bool) ([][]tio.Packet, []decodedSeg) {
|
|
var reads [][]tio.Packet
|
|
var want []decodedSeg
|
|
seq := uint32(0)
|
|
for _, l := range large {
|
|
per, segs := 1, 3
|
|
if l {
|
|
per, segs = 2, 9
|
|
}
|
|
var b []tio.Packet
|
|
for range per {
|
|
b = append(b, flowTCPSuperpacket(0, seq, segs))
|
|
for s := range segs {
|
|
want = append(want, decodedSeg{seq: seq, idx: uint16(s)})
|
|
}
|
|
seq++
|
|
}
|
|
reads = append(reads, b)
|
|
}
|
|
return reads, want
|
|
}
|
|
|
|
func repeatBool(v bool, n int) []bool {
|
|
out := make([]bool, n)
|
|
for i := range out {
|
|
out[i] = v
|
|
}
|
|
return out
|
|
}
|
|
|
|
// TestFlowStagedTXGateSwitch forces the gate from inline to fanout and back, with a slow socket and slow
|
|
// workers so the fanout batches are still in flight when the small reads arrive: wire order is read order, counters
|
|
// are contiguous, and each switch happens on exactly the gate_hold-th read that wants it.
|
|
func TestFlowStagedTXGateSwitch(t *testing.T) {
|
|
defer goleak.VerifyNone(t, goleak.IgnoreCurrent())
|
|
const hold = 3
|
|
for _, routines := range []int{1, 2} {
|
|
t.Run(fmt.Sprintf("routines=%d", routines), func(t *testing.T) {
|
|
sender, receiver := newFlowTestPair(t, noise.CipherChaChaPoly, gated(hold))
|
|
sender.f.routines = routines
|
|
sender.f.writers = []udp.Conn{sender.conn, sender.conn}
|
|
delayCrypto(sender, func(n uint64) {
|
|
if n%7 == 0 {
|
|
time.Sleep(time.Millisecond)
|
|
}
|
|
})
|
|
sender.conn.delay = 4 * time.Millisecond
|
|
// 4 small inline, 2 large held inline, 6 large fanout from the switch on, 2 small held in fanout, then
|
|
// the switch back drains and 3 small go inline
|
|
shape := append(repeatBool(false, 4), repeatBool(true, 8)...)
|
|
shape = append(shape, repeatBool(false, 5)...)
|
|
reads, want := gateReads(shape...)
|
|
ci := sender.hostinfo.ConnectionState
|
|
start := ci.messageCounter.Load()
|
|
c0 := readGateCounters()
|
|
p := newStagedTx(sender.f, newFlowBatchQueue(nil), 0)
|
|
for i, r := range reads {
|
|
p.send(r)
|
|
if i == 13 {
|
|
require.Positive(t, p.inFlight, "fanout batches must still be in flight when the small reads start")
|
|
}
|
|
if i == 14 {
|
|
require.Zero(t, p.inFlight, "switching to inline drains the pipeline")
|
|
}
|
|
}
|
|
p.close()
|
|
require.Equal(t, want, decryptWire(t, receiver, sender.conn.captured()), "wire order must match read order")
|
|
require.Equal(t, start+uint64(len(want)), ci.messageCounter.Load(), "every reserved counter is used once")
|
|
require.Equal(t, gateCounters{inline: 4 + 2 + 3, batches: 6 + 2, switches: 2}, readGateCounters().since(c0))
|
|
require.Zero(t, ci.txBudget.state.Load())
|
|
})
|
|
}
|
|
}
|
|
|
|
// TestFlowStagedTXGateHold: the gate never switches before gate_hold consecutive reads want the other mode, and
|
|
// a read that wants the current mode restarts the count.
|
|
func TestFlowStagedTXGateHold(t *testing.T) {
|
|
defer goleak.VerifyNone(t, goleak.IgnoreCurrent())
|
|
const hold = 5
|
|
sender, receiver := newFlowTestPair(t, noise.CipherChaChaPoly, gated(hold))
|
|
shape := append(repeatBool(true, hold-1), false)
|
|
shape = append(shape, repeatBool(true, hold-1)...)
|
|
reads, want := gateReads(append(shape, true)...)
|
|
c0 := readGateCounters()
|
|
p := newStagedTx(sender.f, newFlowBatchQueue(nil), 0)
|
|
for _, r := range reads[:len(reads)-1] {
|
|
p.send(r)
|
|
}
|
|
require.Equal(t, gateCounters{inline: 2*hold - 1}, readGateCounters().since(c0), "no switch before gate_hold")
|
|
p.send(reads[len(reads)-1])
|
|
require.Equal(t, gateCounters{inline: 2*hold - 1, batches: 1, switches: 1}, readGateCounters().since(c0))
|
|
p.close()
|
|
require.Equal(t, want, decryptWire(t, receiver, sender.conn.captured()))
|
|
}
|