Green Domino Incentives: Impact of Energy-aware Adaptive Link Rate - - PowerPoint PPT Presentation

Green Domino Incentives: Impact of Energy-aware Adaptive Link Rate Policies in Routers

Cyriac James Niklas Carlsson University of Calgary Linköping University Canada Sweden Presented by Martin Arlitt, HP Labs

2

Motivation

— Energy savings in Internet routers

— Over-provisioned to meet peak traffic — Hence, often under utilized

— Effect on downstream routers

— Positive or negative — Energy and Delay

3

Contribution

— Evaluation Framework

— Router Model — Policy Model — Energy Model — Traffic Model — Trace based simulation

— Capture real traffic characteristics

— Analysis on immediate downstream router

— Delay — Improvement in energy savings

4

Adaptive Link Rate (ALR)

— Energy saving techniques — Rate scaling — Active/idle toggling — IEEE 802.3az — Commercial — Cisco Catalyst 4500E Switch

48-port Line Card (Photo Courtesy: Cisco)

Symbolic representation of port operation

5

Policy Parameters & Delay

100 200 300 400 500 600 700 800 900 1000 10

−2

10

−1

10 10

1

10

2

Active Link Rate (Mbps) Per Router Packet Delay (ms)

10

2

10

3

10

4

10

5

10 20 30 40 50 60 70

Threshold Value (bytes) Per Router Packet Delay (ms)

Rate Scaling Active/Idle Toggling

• Rate scaling
• Service rate or port speed
• Reduction in speed Energy Savings
• Active/Idle Toggling
• Queue threshold
• Amount of idle time Energy Savings

6

Evaluation Framework

Design Issues Router Model Energy Model Traffic Model Policy Model

7

Policy Model

— Tail delay (99th percentile) — Between .01ms and 100ms — Vary policy parameters

— Port rate — Queue threshold

— Hybrid

— Port rate — Queue threshold < Smallest packet

8

Router Model

— Delay — Switch Fabric — Queue — Transmit — Model by Hohn et al. 2009 — Switch fabric delay: 10 – 50 microseconds — Delay constraints in milliseconds — Delay = Queue delay + Transmit delay — Infinite queue — Tail delay

Router

9

Energy Model

— Proportional Model

— Interested in Relative energy consumption — NOT absolute — Relative increase/decrease in energy savings

— At R2, R3 and R4

— R1 runs green techniques — R1 does not

10

Traffic Model

— Traffic scenarios

— Dispersion: 1*2 — Aggregation: 2*1 — Multiplexing: 1*1, 2*2 (shown), 3*3

— Packet traces (public)

— Waikato trace (edge) — MAWI (core)

11

Simple Back-to-Back Case

— Past studies on tandem queues

— Increased delay at R2 for (utilization < 60%) — Continuous and independent service time

— Our results:

12

10

−4

10

−3

10

−2

10

−1

10 10

1

10

2

0.1 0.2 0.3 0.4 0.5 0.6 0.7 0.8 0.9 1

Per Router Packet Delay (ms) Empirical CDF

R1 (1.2%) R2 (1.2%) R1 (15%) R2 (15%)

Bimodal Distribution

200 400 600 800 1000 1200 1400 1600 0.1 0.2 0.3 0.4 0.5 0.6 0.7 0.8 0.9 1

Packet Size (bytes) Empirical CDF

Edge: Outgoing Core: Direction−A Edge: Incoming Core: Direction−B

• Most packet sizes are either small (<100 bytes) or large (>1400

bytes)

• Incoming edge traffic has more large packets

13

Small Medium Large Small 0.39 0.11 0.04 Medium 0.10 0.06 0.03 Large 0.05 0.02 0.20 Small Medium Large Small 0.23 0.05 0.07 Medium 0.04 0.02 0.04 Large 0.08 0.03 0.45 Edge, Outgoing Core, one direction

Back-to-Back Probability

Small:<= 100 byes Large: >=1400 bytes Medium: > 100 and < 1400

14

Example Scenario

— Small packet has negligible processing delay — Small packet experience larger delay at R2 than R1

15

Proportional Energy Savings

— Reduced delay at R2 More energy savings at R2 — Increase in multiplexing impact energy savings — Relative savings at R2?

16

10

−2

10

−1

10 10

1

10

2

10 20 30 40 50 60 70 80 90 100 Target Per Router Packet Delay (ms) Proportional Energy Savings (%) 1 by 1: R1 3 by 3: R1 1 by 1: R2 3 by 3: R2

Cascading (Domino) Effect

17

• Improvement in energy savings
• Rate Scaling: Up to 35%
• Active/Idle Toggling: Up to 15%

Rate Scaling: Core Active/Idle: Edge

10

−2

10

−1

10 10

1

10

2

5 10 15 20 25 30 35 40 Target Per Router Packet Delay (ms) Improvement in Energy Savings (%) 1 by 1: Direction−A 3 by 3: Direction−A 2 by 2: Direction−A 10

−2

10

−1

10 10

1

10

2

5 10 15 Target Per Router Packet Delay (ms) Improvement in Energy Savings (%) 2 by 2: Outgoing 3 by 3: Outgoing 1 by 1: Outgoing

Hybrid Case

Hybrid: Edge

• Improvement of up to 10% observed for hybrid
• Multiplexing reduces improvement in all three

classes of algorithms

18

10−2 10−1 100 101 102 2 4 6 8 10 12 Target Per Router Packet Delay (ms) Improvement in Energy Saving 1 by 1: Outgoing 2 by 2: Outgoing 3 by 3: Outgoing

Conclusion

— Performance evaluation framework — Trace based analysis — Effect of ALR policies on neighboring routers

— Cascading (domino) energy improvement — Up to 30% energy savings (rate scaling) — Influenced by traffic characteristics

— Future Work:

— Variability — Large scale deployment study — Interactions with higher layer protocols & applications

19

Thank You

Green Domino Incentives: Impact of Energy-aware Adaptive Link Rate Policies in Routers Cyriac James

Niklas Carlsson University of Calgary Linköping University Canada Sweden cyriac.james@ucalgary.ca nikca@ida.liu.se

20