36
1 ow scalable is the capacity of (electronic) IP routers? Nick McKeown Professor of Electrical Engineering and Computer Science, Stanford University [email protected] http://www.stanford.edu/~nickm

1 How scalable is the capacity of (electronic) IP routers? Nick McKeown Professor of Electrical Engineering and Computer Science, Stanford University

Embed Size (px)

DESCRIPTION

3 Why it’s hard for capacity to keep up with link rates Packet processing power Link rate

Citation preview

Page 1: 1 How scalable is the capacity of (electronic) IP routers? Nick McKeown Professor of Electrical Engineering and Computer Science, Stanford University

1

Hi gh Pe rf orm a nceSwi tc hi ng and Routi ngTe lec om Ce nter W orks ho p: Sep t 4 , 19 97.

How scalable is the capacity of(electronic) IP routers?

Nick McKeownProfessor of Electrical Engineering and Computer Science, Stanford [email protected]://www.stanford.edu/~nickm

Page 2: 1 How scalable is the capacity of (electronic) IP routers? Nick McKeown Professor of Electrical Engineering and Computer Science, Stanford University

2

Why ask the question?

Widely held assumption: Electronic IP routers will not keep up with link capacity.

Background: Router Capacity = (number of lines) x (line-rate)

• Biggest router capacity 4 years ago ~= 10Gb/s• Biggest router capacity 2 years ago ~= 40Gb/s• Biggest router capacity today ~= 160Gb/s• Next couple of generations: ~1-40Tb/s

Page 3: 1 How scalable is the capacity of (electronic) IP routers? Nick McKeown Professor of Electrical Engineering and Computer Science, Stanford University

3

Why it’s hard for capacity to keep up with link rates

Packet processing

power

Link rate

Page 4: 1 How scalable is the capacity of (electronic) IP routers? Nick McKeown Professor of Electrical Engineering and Computer Science, Stanford University

4

0,1

1

10

100

1000

10000

1985 1990 1995 2000

Spec

95In

t CPU

resu

lts

Why it’s hard for capacity to keep up with link rates

0,1

1

10

100

1000

10000

1985 1990 1995 2000

Fibe

r Cap

acity

(Gbi

t/s)

TDM DWDM

Packet processing Power Link Speed

2x / 2 years 2x / 7 months

Source: SPEC95Int & David Miller, Stanford.

Page 5: 1 How scalable is the capacity of (electronic) IP routers? Nick McKeown Professor of Electrical Engineering and Computer Science, Stanford University

5

Instructions per packet

time

Instructionsper packet

What we’d like: (more features)QoS, Multicast, Security, …

What will happen

Page 6: 1 How scalable is the capacity of (electronic) IP routers? Nick McKeown Professor of Electrical Engineering and Computer Science, Stanford University

6

What limits a router’s capacity?• It’s a packet switch:

– Must be able to buffer every packet for an unpredictable amount of time.

• Hop-by-hop routing:– Once per ~1000bits it must index into

a forwarding table with ~100k entries.

• [Optional QoS support– Very complex per-packet processing]

Limited by memory random access time

Limited by memory random access time

Page 7: 1 How scalable is the capacity of (electronic) IP routers? Nick McKeown Professor of Electrical Engineering and Computer Science, Stanford University

7

What really limits the capacity?

• At first glance: the random access time to memory.

• In fact, this can be solved by more parallelism (replication and pipelining).

• Dilemma: But parallelism requires more power and space.

Page 8: 1 How scalable is the capacity of (electronic) IP routers? Nick McKeown Professor of Electrical Engineering and Computer Science, Stanford University

8

What really limits the capacity?

Suggestion: – Don’t assume optics will oust CMOS in

IP routers because of increased system capacity.

– It might oust CMOS because of reduced (power x space) for a given capacity.

Page 9: 1 How scalable is the capacity of (electronic) IP routers? Nick McKeown Professor of Electrical Engineering and Computer Science, Stanford University

9

Outline

• A brief history of IP routers• Where they will go next

– Incorporating optics into routers– More parallelism (with or without

optics)

Page 10: 1 How scalable is the capacity of (electronic) IP routers? Nick McKeown Professor of Electrical Engineering and Computer Science, Stanford University

10

RouteTableCPU Buffer

Memory

LineInterface

MAC

LineInterface

MAC

LineInterface

MAC

Typically <0.5Gb/s aggregate capacity

First Generation RoutersShared Backplane

Line Interface

CPUMemory

Page 11: 1 How scalable is the capacity of (electronic) IP routers? Nick McKeown Professor of Electrical Engineering and Computer Science, Stanford University

11

First Generation RoutersQueueing Structure: Centralized Shared

MemoryLarge, single dynamically allocated memory buffer:N writes per “cell” timeN reads per “cell” time.

Limited by memory bandwidth.

Numerous work has proven and made possible QoS:– Fairness– Delay Guarantees– Delay Variation Control– Loss Guarantees– Statistical Guarantees

MemoryController

Output 1Output 2

Output N

Input 1Input 2

Input N

Page 12: 1 How scalable is the capacity of (electronic) IP routers? Nick McKeown Professor of Electrical Engineering and Computer Science, Stanford University

12

Second Generation RoutersRouteTableCPU

LineCard

BufferMemory

LineCard

MAC

BufferMemory

LineCard

MAC

BufferMemory

FwdingCache

FwdingCache

FwdingCache

MAC

BufferMemory

Typically <5Gb/s aggregate capacity

Page 13: 1 How scalable is the capacity of (electronic) IP routers? Nick McKeown Professor of Electrical Engineering and Computer Science, Stanford University

13

Second Generation RoutersQueueing Structure: Combined Input and

Output Queueing

Bus

1 write per “cell” time 1 read per “cell” timeRate of writes/reads determined by bus speed

Page 14: 1 How scalable is the capacity of (electronic) IP routers? Nick McKeown Professor of Electrical Engineering and Computer Science, Stanford University

14

Third Generation Routers

LineCard

MAC

LocalBuffer

Memory

CPUCard

LineCard

MAC

LocalBuffer

Memory

Switched Backplane

Line Interface

CPUMemory Fwding

Table

RoutingTable

FwdingTable

Typically <50Gb/s aggregate capacity

Page 15: 1 How scalable is the capacity of (electronic) IP routers? Nick McKeown Professor of Electrical Engineering and Computer Science, Stanford University

15

Arbiter

Third Generation RoutersQueueing Structure

Switch

1 write per “cell” time 1 read per “cell” timeRate of writes/reads determined by switch

fabric speedup

Per-flow/class or per-output queues (VOQs)

Per-flow/class or per-input queues

Flow-controlbackpressure

Page 16: 1 How scalable is the capacity of (electronic) IP routers? Nick McKeown Professor of Electrical Engineering and Computer Science, Stanford University

16

Third Generation Routers

19” or 23”

7’

• Size-constrained: 19” or 23” wide.

• Power-constrained.

Page 17: 1 How scalable is the capacity of (electronic) IP routers? Nick McKeown Professor of Electrical Engineering and Computer Science, Stanford University

17

Complex linecards

PhysicalLayer

Framing&

Maintenance

PacketProcessing

Buffer Mgmt&

Scheduling

Buffer Mgmt&

Scheduling

Buffer & StateMemory

Buffer & StateMemory

Typical IP Router Linecard

OC192c linecard:~10-30M gates~2Gbits of memory~2 square feet>$10k cost100’s of Watts

LookupTables

“Backplane”

SwitchFabric

Arbitration

Optics

Page 18: 1 How scalable is the capacity of (electronic) IP routers? Nick McKeown Professor of Electrical Engineering and Computer Science, Stanford University

18

Fourth Generation Routers/Switches

Optics inside a router for the first time

Switch Core Linecards

Optical links

1000’sof feet

The LCS Protocol

0.3 - 10Tb/s routers in development

Page 19: 1 How scalable is the capacity of (electronic) IP routers? Nick McKeown Professor of Electrical Engineering and Computer Science, Stanford University

19

Where next?

• Incorporating (more) optics into a router.

• More parallelism (with or without optics).

Page 20: 1 How scalable is the capacity of (electronic) IP routers? Nick McKeown Professor of Electrical Engineering and Computer Science, Stanford University

20

Incorporating optics into a router

• Replacing the switch fabric with an optical datapath.

• Increasing the internal “cell” size to reduce rate of arbitration and reconfiguration.

Page 21: 1 How scalable is the capacity of (electronic) IP routers? Nick McKeown Professor of Electrical Engineering and Computer Science, Stanford University

21

Replacing the switch fabric with optics

SwitchFabric

Arbitration

PhysicalLayer

Framing&

Maintenance

PacketProcessing

Buffer Mgmt&

Scheduling

Buffer Mgmt&

Scheduling

Buffer & StateMemory

Buffer & StateMemory

Typical IP Router LinecardLookupTables

OpticsPhysical

LayerFraming

& Maintenance

PacketProcessing

Buffer Mgmt&

Scheduling

Buffer Mgmt&

Scheduling

Buffer & StateMemory

Buffer & StateMemory

Typical IP Router LinecardLookupTables

Opticselectrical

SwitchFabric

Arbitration

PhysicalLayer

Framing&

Maintenance

PacketProcessing

Buffer Mgmt&

Scheduling

Buffer Mgmt&

Scheduling

Buffer & StateMemory

Buffer & StateMemory

Typical IP Router LinecardLookupTables

OpticsPhysical

LayerFraming

& Maintenance

PacketProcessing

Buffer Mgmt&

Scheduling

Buffer Mgmt&

Scheduling

Buffer & StateMemory

Buffer & StateMemory

Typical IP Router LinecardLookupTables

Optics

optical

Req/Grant Req/Grant

Candidate technologies 1. MEMs2. Fast tunable lasers + passive optical

couplers

Page 22: 1 How scalable is the capacity of (electronic) IP routers? Nick McKeown Professor of Electrical Engineering and Computer Science, Stanford University

22

Replacing the switch fabric with optics

• Most common internal “cell” size is 64 bytes (50ns @ OC192, 12ns @ OC768)

• Too fast for arbitration • Too fast for reconfiguration• What we’ll see:

– Increased cell length– E.g. switch bursts of cells – But less efficient.

Page 23: 1 How scalable is the capacity of (electronic) IP routers? Nick McKeown Professor of Electrical Engineering and Computer Science, Stanford University

23

More parallelism

• Parallel packet buffers• Parallel lookup tables

• Multiple parallel routers

Page 24: 1 How scalable is the capacity of (electronic) IP routers? Nick McKeown Professor of Electrical Engineering and Computer Science, Stanford University

24

Multiple parallel routers

What we’d like:R

R R

R

The building blocks we’d like to use:

R

RR

R

NxN

IP Router capacity 100s of Tb/s

Page 25: 1 How scalable is the capacity of (electronic) IP routers? Nick McKeown Professor of Electrical Engineering and Computer Science, Stanford University

25

Why this might be a good idea

• Larger overall capacity• Faster line rates• Redundancy• Familiarity

– “After all, this is how the Internet is built”

Page 26: 1 How scalable is the capacity of (electronic) IP routers? Nick McKeown Professor of Electrical Engineering and Computer Science, Stanford University

26

Multiple parallel routers Load Balancing architectures

R R

R

12……k

R

RR

R/k R/k

R

RR

Page 27: 1 How scalable is the capacity of (electronic) IP routers? Nick McKeown Professor of Electrical Engineering and Computer Science, Stanford University

27

Method #1: Random packet load-balancing

Method: As packets arrive they are randomly distributed, packet by packet over each router.

Advantages: – Almost unlimited capacity– Load-balancer is simple– Load-balancer needs no packet buffering

Disadvantages:– Random fluctuations in traffic each router is loaded

differently • Packets within a flow may become mis-sequenced• It is not possible to predict the system performance

Page 28: 1 How scalable is the capacity of (electronic) IP routers? Nick McKeown Professor of Electrical Engineering and Computer Science, Stanford University

28

Method #2: Random flow load-balancing

Method: Each new flow (e.g. TCP connection) is randomly assigned to a router. All packets in a

flow follow the same path.Advantages:

– Almost unlimited capacity– Load-balancer is simple (e.g. hashing of flow ID).– Load-balancer needs no packet buffering.– No mis-sequencing of packets within a flow.

Disadvantages:– Random fluctuations in traffic each router is loaded

differently • It is not possible to predict the system performance

Page 29: 1 How scalable is the capacity of (electronic) IP routers? Nick McKeown Professor of Electrical Engineering and Computer Science, Stanford University

29

Observations

• Random load-balancing: It’s hard to predict system performance.

• Flow-by-flow load-balancing: Worst-case performance is very poor.

If designers, system builders, network operators etc. need to know the worst case performance, random load-balancing will not suffice.

Page 30: 1 How scalable is the capacity of (electronic) IP routers? Nick McKeown Professor of Electrical Engineering and Computer Science, Stanford University

30

Method #3: Intelligent packet load-balancing

Goal: Each new packet is carefully assigned to a router so that:

• Packets are not mis-sequenced.• The throughput is maximized and

understood.• Delay of each packet can be controlled.

We call this “Parallel Packet Switching”

Page 31: 1 How scalable is the capacity of (electronic) IP routers? Nick McKeown Professor of Electrical Engineering and Computer Science, Stanford University

31

Method #3: Intelligent packet load-balancing

Parallel Packet Switching

1

2

k

1

N

rate, R

rate, R

rate, R

rate, R

1

N

Router

Bufferless

R/k R/k

Page 32: 1 How scalable is the capacity of (electronic) IP routers? Nick McKeown Professor of Electrical Engineering and Computer Science, Stanford University

32

Parallel Packet Switching

• Advantages– Single-stage of buffering– No excess link capacity– kpower per subsystem – kmemory bandwidth – klookup rate

Page 33: 1 How scalable is the capacity of (electronic) IP routers? Nick McKeown Professor of Electrical Engineering and Computer Science, Stanford University

33

Precise Emulation of a Shared Memory Switch

N N

Shared Memory Switch1

N

Parallel Packet Switch

= ?

1

N

1

N

Page 34: 1 How scalable is the capacity of (electronic) IP routers? Nick McKeown Professor of Electrical Engineering and Computer Science, Stanford University

34

Parallel Packet SwitchTheorem

1. If S > 2k/(k+2) 2 then a parallel packet switch can precisely emulate a FCFS shared memory switch for all traffic.

Page 35: 1 How scalable is the capacity of (electronic) IP routers? Nick McKeown Professor of Electrical Engineering and Computer Science, Stanford University

35

Example of an IP Router with Parallel Packet Switching

1

2

16

1

1024

160Gb/s

160Gb/s

rate, R

rate, R

1

1024

10Tb/s routerR/k R/k

Overall capacity 160Tb/s

Page 36: 1 How scalable is the capacity of (electronic) IP routers? Nick McKeown Professor of Electrical Engineering and Computer Science, Stanford University

36

My conclusions

• The capacity of electronic IP routers will scale a long way yet.

• The opportunity of optics is to reduce power and space– By using optics within the router.– By replacing routers with circuit

switches.