mirror of
https://github.com/slackhq/nebula.git
synced 2026-11-16 22:56:52 +01:00
tun: Add tun.staged.tx and tun.staged.inline_below
tx: false keeps transmit inline and stages only receive. inline_below sets the idle-reader shortcut threshold, 0 hands every batch to the workers and the ordered sender or writer.
This commit is contained in:
1 parent
82488caa32
commit
d16a52f921
4 files changed
+93
-8
No files matched your search
+6
-2
@@ -284,14 +284,18 @@ tun:
|
|||||||
# Staged reservations may use half the window, the other half absorbs inline and control traffic, relay forwarding
|
# Staged reservations may use half the window, the other half absorbs inline and control traffic, relay forwarding
|
||||||
# and network reordering; unlimited forwarding or delay can still exceed it. Waiting for credit on a busy tunnel
|
# and network reordering; unlimited forwarding or delay can still exceed it. Waiting for credit on a busy tunnel
|
||||||
# also delays the other tunnels of the same read, and readers are not guaranteed fairness.
|
# also delays the other tunnels of the same read, and readers are not guaranteed fairness.
|
||||||
# Idle batches below 256 TX segments or RX packets stay on the reader. With multiple routines, those sends still
|
# Idle batches below inline_below TX segments or RX packets stay on the reader, default 256. With multiple routines,
|
||||||
# take tunnel reservation credit.
|
# those sends still take tunnel reservation credit. 0 hands every batch to the workers and the ordered sender or
|
||||||
|
# writer; only TX reads too large for a tunnel's whole credit are still sent by the reader, after it drains.
|
||||||
|
# tx: false keeps transmit inline and stages only receive.
|
||||||
# tx_slots and rx_slots bound the batches each routine has in flight per direction, minimum 2. A TX slot holds one
|
# tx_slots and rx_slots bound the batches each routine has in flight per direction, minimum 2. A TX slot holds one
|
||||||
# tun read and its ciphertext, about 1.1 MiB; the default is 8, or workers + 2 if more. An RX slot holds one
|
# tun read and its ciphertext, about 1.1 MiB; the default is 8, or workers + 2 if more. An RX slot holds one
|
||||||
# recvmmsg batch, listen.batch * 64 KiB with udp_offloads or * 9 KiB without; the default keeps up to 384 receive
|
# recvmmsg batch, listen.batch * 64 KiB with udp_offloads or * 9 KiB without; the default keeps up to 384 receive
|
||||||
# entries in flight in 4 to 6 slots: 6 slots or 24 MiB at the default listen.batch of 64. Lower them to save memory.
|
# entries in flight in 4 to 6 slots: 6 slots or 24 MiB at the default listen.batch of 64. Lower them to save memory.
|
||||||
#staged:
|
#staged:
|
||||||
# workers: 0
|
# workers: 0
|
||||||
|
# tx: true
|
||||||
|
# inline_below: 256
|
||||||
# tx_slots: 8
|
# tx_slots: 8
|
||||||
# rx_slots: 6
|
# rx_slots: 6
|
||||||
|
|
||||||
|
|||||||
@@ -34,7 +34,7 @@ type stagedConfig struct {
|
|||||||
workers int
|
workers int
|
||||||
tx bool
|
tx bool
|
||||||
rx bool
|
rx bool
|
||||||
// inlineBelow is the TX segment or RX packet count below which an idle reader skips the worker handoff
|
// inlineBelow is the TX segment or RX packet count below which an idle reader skips the worker handoff, 0 never
|
||||||
inlineBelow int
|
inlineBelow int
|
||||||
// txSlots and rxSlots are how many batches each routine can have in flight per direction
|
// txSlots and rxSlots are how many batches each routine can have in flight per direction
|
||||||
txSlots, rxSlots int
|
txSlots, rxSlots int
|
||||||
@@ -78,17 +78,17 @@ func parseStagedConfig(c *config.C, l *slog.Logger) stagedConfig {
|
|||||||
l.Warn("tun.staged is only supported on Linux; packet processing stays inline")
|
l.Warn("tun.staged is only supported on Linux; packet processing stays inline")
|
||||||
return stagedConfig{}
|
return stagedConfig{}
|
||||||
}
|
}
|
||||||
sc.tx, sc.rx = true, true
|
sc.tx, sc.rx = c.GetBool("tun.staged.tx", true), true
|
||||||
// 256 is the measured crossover
|
// 256 is the measured crossover, 0 hands every batch to the workers
|
||||||
sc.inlineBelow = 256
|
sc.inlineBelow = max(c.GetInt("tun.staged.inline_below", 256), 0)
|
||||||
if noiseutil.EncryptLockNeeded {
|
if sc.tx && noiseutil.EncryptLockNeeded {
|
||||||
l.Warn("tun.staged cannot encrypt in parallel with boringcrypto or fips140; transmit stays inline")
|
l.Warn("tun.staged cannot encrypt in parallel with boringcrypto or fips140; transmit stays inline")
|
||||||
sc.tx = false
|
sc.tx = false
|
||||||
}
|
}
|
||||||
sc.txSlots, sc.rxSlots = stagedSlots(sc.workers, c.GetInt("listen.batch", 64),
|
sc.txSlots, sc.rxSlots = stagedSlots(sc.workers, c.GetInt("listen.batch", 64),
|
||||||
c.GetInt("tun.staged.tx_slots", 0), c.GetInt("tun.staged.rx_slots", 0))
|
c.GetInt("tun.staged.tx_slots", 0), c.GetInt("tun.staged.rx_slots", 0))
|
||||||
l.Info("Staged packet processing enabled", "workers", sc.workers, "tx", sc.tx, "rx", sc.rx,
|
l.Info("Staged packet processing enabled", "workers", sc.workers, "tx", sc.tx, "rx", sc.rx,
|
||||||
"txSlots", sc.txSlots, "rxSlots", sc.rxSlots)
|
"inlineBelow", sc.inlineBelow, "txSlots", sc.txSlots, "rxSlots", sc.rxSlots)
|
||||||
return sc
|
return sc
|
||||||
}
|
}
|
||||||
|
|
||||||
|
|||||||
@@ -14,12 +14,14 @@ import (
|
|||||||
|
|
||||||
"github.com/flynn/noise"
|
"github.com/flynn/noise"
|
||||||
"github.com/rcrowley/go-metrics"
|
"github.com/rcrowley/go-metrics"
|
||||||
|
"github.com/slackhq/nebula/config"
|
||||||
"github.com/slackhq/nebula/cpupick"
|
"github.com/slackhq/nebula/cpupick"
|
||||||
"github.com/slackhq/nebula/firewall"
|
"github.com/slackhq/nebula/firewall"
|
||||||
"github.com/slackhq/nebula/header"
|
"github.com/slackhq/nebula/header"
|
||||||
"github.com/slackhq/nebula/noiseutil"
|
"github.com/slackhq/nebula/noiseutil"
|
||||||
"github.com/slackhq/nebula/overlay/batch"
|
"github.com/slackhq/nebula/overlay/batch"
|
||||||
"github.com/slackhq/nebula/overlay/tio"
|
"github.com/slackhq/nebula/overlay/tio"
|
||||||
|
"github.com/slackhq/nebula/test"
|
||||||
"github.com/slackhq/nebula/udp"
|
"github.com/slackhq/nebula/udp"
|
||||||
"github.com/slackhq/nebula/util"
|
"github.com/slackhq/nebula/util"
|
||||||
"github.com/stretchr/testify/require"
|
"github.com/stretchr/testify/require"
|
||||||
@@ -433,6 +435,72 @@ func TestFlowStagedTXInlineOnlyWhenEmpty(t *testing.T) {
|
|||||||
require.Equal(t, want, decryptWire(t, receiver, sender.conn.captured()))
|
require.Equal(t, want, decryptWire(t, receiver, sender.conn.captured()))
|
||||||
}
|
}
|
||||||
|
|
||||||
|
// TestFlowStagedTXInlineBelowZero: with inline_below 0 an idle reader never sends a batch itself, in either
|
||||||
|
// direction: every read goes through the workers and the ordered sender or writer.
|
||||||
|
func TestFlowStagedTXInlineBelowZero(t *testing.T) {
|
||||||
|
defer goleak.VerifyNone(t, goleak.IgnoreCurrent())
|
||||||
|
l := test.NewLogger()
|
||||||
|
c := config.NewC(l)
|
||||||
|
c.Settings = map[string]any{"tun": map[string]any{"staged": map[string]any{"workers": 2, "inline_below": 0}}}
|
||||||
|
sc := parseStagedConfig(c, l)
|
||||||
|
if !sc.tx {
|
||||||
|
t.Skip("transmit stays inline in this build")
|
||||||
|
}
|
||||||
|
sender, receiver := newFlowTestPair(t, noise.CipherChaChaPoly, sc)
|
||||||
|
batches, want := flowTestBatches(20, 2, 1, 4)
|
||||||
|
txInline := metrics.GetOrRegisterCounter("flow.tx.inline", nil)
|
||||||
|
tx := metrics.GetOrRegisterCounter("flow.tx.batches", nil)
|
||||||
|
rxInline := metrics.GetOrRegisterCounter("flow.rx.inline", nil)
|
||||||
|
txInline0, tx0, rxInline0, rx0 := txInline.Count(), tx.Count(), rxInline.Count(), rxBatches.Count()
|
||||||
|
sender.f.listenIn(newFlowBatchQueue(batches), 0)
|
||||||
|
wire := sender.conn.captured()
|
||||||
|
require.Equal(t, want, decryptWire(t, receiver, wire))
|
||||||
|
require.Zero(t, txInline.Count()-txInline0)
|
||||||
|
require.Equal(t, int64(len(batches)), tx.Count()-tx0)
|
||||||
|
receiver.receive(&rxConn{wire: wire, sizes: []int{1, 2, 4}})
|
||||||
|
require.Equal(t, want, receiver.tun.segments(t))
|
||||||
|
require.Zero(t, rxInline.Count()-rxInline0)
|
||||||
|
require.Positive(t, rxBatches.Count()-rx0)
|
||||||
|
}
|
||||||
|
|
||||||
|
// TestFlowStagedTXDisabled: with tx false the reader never builds a staged pipeline, even on a queue that could hand
|
||||||
|
// off its batches. Receive stays staged.
|
||||||
|
func TestFlowStagedTXDisabled(t *testing.T) {
|
||||||
|
defer goleak.VerifyNone(t, goleak.IgnoreCurrent())
|
||||||
|
l := test.NewLogger()
|
||||||
|
c := config.NewC(l)
|
||||||
|
c.Settings = map[string]any{"tun": map[string]any{"staged": map[string]any{"workers": 2, "tx": false}}}
|
||||||
|
sc := parseStagedConfig(c, l)
|
||||||
|
require.False(t, sc.tx)
|
||||||
|
require.True(t, sc.rx)
|
||||||
|
sender, receiver := newFlowTestPair(t, noise.CipherChaChaPoly, sc)
|
||||||
|
batches, want := flowTestBatches(4, 8, 1, 45)
|
||||||
|
tx := metrics.GetOrRegisterCounter("flow.tx.batches", nil)
|
||||||
|
txInline := metrics.GetOrRegisterCounter("flow.tx.inline", nil)
|
||||||
|
tx0, txInline0, rx0 := tx.Count(), txInline.Count(), rxBatches.Count()
|
||||||
|
q := &swapCountQueue{flowBatchQueue: newFlowBatchQueue(batches)}
|
||||||
|
sender.f.listenIn(q, 0)
|
||||||
|
wire := sender.conn.captured()
|
||||||
|
require.Equal(t, want, decryptWire(t, receiver, wire))
|
||||||
|
require.Zero(t, q.swaps, "newStagedTx always takes the queue's buffer, so it never ran")
|
||||||
|
require.Equal(t, tx0, tx.Count())
|
||||||
|
require.Equal(t, txInline0, txInline.Count())
|
||||||
|
receiver.receive(&rxConn{wire: wire, batchLen: 512})
|
||||||
|
require.Equal(t, want, receiver.tun.segments(t))
|
||||||
|
require.Greater(t, rxBatches.Count(), rx0)
|
||||||
|
}
|
||||||
|
|
||||||
|
// swapCountQueue counts SwapRxBuf calls.
|
||||||
|
type swapCountQueue struct {
|
||||||
|
*flowBatchQueue
|
||||||
|
swaps int
|
||||||
|
}
|
||||||
|
|
||||||
|
func (q *swapCountQueue) SwapRxBuf(buf []byte) []byte {
|
||||||
|
q.swaps++
|
||||||
|
return q.flowBatchQueue.SwapRxBuf(buf)
|
||||||
|
}
|
||||||
|
|
||||||
// TestFlowStagedTXAdaptiveBudget: a fast reader's adaptive sends must stop spending credit until another reader's
|
// TestFlowStagedTXAdaptiveBudget: a fast reader's adaptive sends must stop spending credit until another reader's
|
||||||
// earlier reservation reaches the wire.
|
// earlier reservation reaches the wire.
|
||||||
func TestFlowStagedTXAdaptiveBudget(t *testing.T) {
|
func TestFlowStagedTXAdaptiveBudget(t *testing.T) {
|
||||||
|
|||||||
@@ -150,6 +150,19 @@ func TestParseStagedConfig(t *testing.T) {
|
|||||||
c.Settings["tun"] = map[string]any{"staged": map[string]any{"workers": 2, "tx_slots": 3, "rx_slots": 1}}
|
c.Settings["tun"] = map[string]any{"staged": map[string]any{"workers": 2, "tx_slots": 3, "rx_slots": 1}}
|
||||||
got := parseStagedConfig(c, l)
|
got := parseStagedConfig(c, l)
|
||||||
require.Equal(t, []int{3, 2}, []int{got.txSlots, got.rxSlots}, "overrides apply, down to the minimum")
|
require.Equal(t, []int{3, 2}, []int{got.txSlots, got.rxSlots}, "overrides apply, down to the minimum")
|
||||||
|
|
||||||
|
c = config.NewC(l)
|
||||||
|
c.Settings["tun"] = map[string]any{"staged": map[string]any{"workers": 2, "tx": false, "inline_below": 0}}
|
||||||
|
got = parseStagedConfig(c, l)
|
||||||
|
require.False(t, got.tx, "tx: false keeps transmit inline")
|
||||||
|
require.True(t, got.rx)
|
||||||
|
require.Zero(t, got.inlineBelow, "inline_below: 0 hands every batch off")
|
||||||
|
|
||||||
|
c = config.NewC(l)
|
||||||
|
c.Settings["tun"] = map[string]any{"staged": map[string]any{"workers": 2, "inline_below": 32}}
|
||||||
|
require.Equal(t, 32, parseStagedConfig(c, l).inlineBelow)
|
||||||
|
c.Settings["tun"] = map[string]any{"staged": map[string]any{"workers": 2, "inline_below": -1}}
|
||||||
|
require.Zero(t, parseStagedConfig(c, l).inlineBelow, "a negative threshold is 0")
|
||||||
}
|
}
|
||||||
|
|
||||||
func TestStagedSlots(t *testing.T) {
|
func TestStagedSlots(t *testing.T) {
|
||||||
|
|||||||
Reference in new issue
Block a user