Upload
others
View
1
Download
0
Embed Size (px)
Citation preview
Stochastic Forecasts Achieve High Throughputand Low Delay over Cellular Networks
Keith Winstein, Anirudh Sivaraman, and Hari Balakrishnan
M.I.T. CSAIL
http://alfalfa.mit.edu
April 5, 2013
Cellular networks are variable
0
500
1000
1500
2000
0:00 0:30 1:00 1:30
thro
ugh
pu
t(k
bp
s)
Verizon LTE uplink throughput
Keith Winstein, Anirudh Sivaraman, and Hari Balakrishnan M.I.T. CSAIL http://alfalfa.mit.edu
Stochastic Forecasts Achieve High Throughput and Low Delay over Cellular Networks
Cellular networks are too reliable
0.2
0.3
2
3
0.1
1
10
0 50 100 150 200 250
Round-triptime(s)
Time (s)
(Verizon LTE, one TCP download.)
Keith Winstein, Anirudh Sivaraman, and Hari Balakrishnan M.I.T. CSAIL http://alfalfa.mit.edu
Stochastic Forecasts Achieve High Throughput and Low Delay over Cellular Networks
Interactive apps work poorly
I We measured cellular networks while driving:
I Verizon LTEI Verizon 3G (1xEV-DO)I AT&T LTEI T-Mobile 3G (UMTS)
I Then ran apps across replayed network trace:
I Skype (Windows 7)I Google Hangout (Chrome on Windows 7)I Apple Facetime (OS X)
Keith Winstein, Anirudh Sivaraman, and Hari Balakrishnan M.I.T. CSAIL http://alfalfa.mit.edu
Stochastic Forecasts Achieve High Throughput and Low Delay over Cellular Networks
Performance summary
0
1000
2000
3000
4000
5000
6000
7000
8000
100200300500100020005000
Th
rou
gh
pu
t(k
bp
s)
Self-inflicted delay (ms)
Verizon LTE Downlink
Skype
Bette
r
Keith Winstein, Anirudh Sivaraman, and Hari Balakrishnan M.I.T. CSAIL http://alfalfa.mit.edu
Stochastic Forecasts Achieve High Throughput and Low Delay over Cellular Networks
Why is performance so bad?
I Exiting schemes react to congestion signals.
I Packet loss.I Increase in round-trip time.
I Feedback comes too late.
I The killer: self-inflicted queueing delay.
I Throughput overshoot means a queue filling up.
Keith Winstein, Anirudh Sivaraman, and Hari Balakrishnan M.I.T. CSAIL http://alfalfa.mit.edu
Stochastic Forecasts Achieve High Throughput and Low Delay over Cellular Networks
Sprout’s goal
I Most throughput
I Bounded risk of delay > 100 ms
Keith Winstein, Anirudh Sivaraman, and Hari Balakrishnan M.I.T. CSAIL http://alfalfa.mit.edu
Stochastic Forecasts Achieve High Throughput and Low Delay over Cellular Networks
Bounded risk of delay
I Infer link speed from interarrival distribution.
I Predict future link speed.
I Don’t wait for congestion.
I Control: Send as much as possible, but require:
I 95% chance all packets arrive within 100 ms.
Keith Winstein, Anirudh Sivaraman, and Hari Balakrishnan M.I.T. CSAIL http://alfalfa.mit.edu
Stochastic Forecasts Achieve High Throughput and Low Delay over Cellular Networks
Infer: link speed from flicker noise process
0.0001
0.001
0.01
0.1
1
10
100
(< 0.5)
39041 10 100 1000
Per
cen
tin
tera
rriv
als
interarrival time (ms)
t−3.27
(Verizon LTE, phone stationary.)
Keith Winstein, Anirudh Sivaraman, and Hari Balakrishnan M.I.T. CSAIL http://alfalfa.mit.edu
Stochastic Forecasts Achieve High Throughput and Low Delay over Cellular Networks
Predict: future link speed
I Model evolution of speed as random walk.
I (Brownian motion)
I Cautious forecast: 5th percentile cumulative packets
I Receiver makes forecast; sends back to sender in ack
I Almost all precalculated
Keith Winstein, Anirudh Sivaraman, and Hari Balakrishnan M.I.T. CSAIL http://alfalfa.mit.edu
Stochastic Forecasts Achieve High Throughput and Low Delay over Cellular Networks
Sprout’s model
Sender Queue Receiver
Poisson process
Rate λ controls
λ
σ
Brownian motion
λz
If in an outage,
drains queue
Poisson process
of σ√t varies λ λz is escape rate.
Keith Winstein, Anirudh Sivaraman, and Hari Balakrishnan M.I.T. CSAIL http://alfalfa.mit.edu
Stochastic Forecasts Achieve High Throughput and Low Delay over Cellular Networks
Parameters
Volatility σ: fixed @ 200 pkts/s√s
Expected outage time 1/λz : 1 sTick length: 20 msForecast length: 160 msDelay target: 100 msRisk tolerance: 5%
All source code was frozen before data collection began.
Keith Winstein, Anirudh Sivaraman, and Hari Balakrishnan M.I.T. CSAIL http://alfalfa.mit.edu
Stochastic Forecasts Achieve High Throughput and Low Delay over Cellular Networks
Control: fill up 100 ms forecast window
0
10
20
30
40
50
60
70
0 20 40 60 80 100 120 140 160
Cum
ulat
ive
pack
ets
sent
time (ms)
Cautious fo
recast
Keith Winstein, Anirudh Sivaraman, and Hari Balakrishnan M.I.T. CSAIL http://alfalfa.mit.edu
Stochastic Forecasts Achieve High Throughput and Low Delay over Cellular Networks
Control: fill up 100 ms forecast window
0
10
20
30
40
50
60
70
0 20 40 60 80 100 120 140 160
Cum
ulat
ive
pack
ets
sent
time (ms)
100 ms
Cautious fo
recast
Keith Winstein, Anirudh Sivaraman, and Hari Balakrishnan M.I.T. CSAIL http://alfalfa.mit.edu
Stochastic Forecasts Achieve High Throughput and Low Delay over Cellular Networks
Control: fill up 100 ms forecast window
0
10
20
30
40
50
60
70
0 20 40 60 80 100 120 140 160
Cum
ulat
ive
pack
ets
sent
time (ms)
Sen
d 50
pkt
s
100 ms
Cautious fo
recast
Keith Winstein, Anirudh Sivaraman, and Hari Balakrishnan M.I.T. CSAIL http://alfalfa.mit.edu
Stochastic Forecasts Achieve High Throughput and Low Delay over Cellular Networks
Control: fill up 100 ms forecast window
0
10
20
30
40
50
60
70
0 20 40 60 80 100 120 140 160
Cum
ulat
ive
pack
ets
sent
time (ms)
Sen
d 50
pkt
s
100 ms
100 ms
Cautious fo
recast
Keith Winstein, Anirudh Sivaraman, and Hari Balakrishnan M.I.T. CSAIL http://alfalfa.mit.edu
Stochastic Forecasts Achieve High Throughput and Low Delay over Cellular Networks
Control: fill up 100 ms forecast window
0
10
20
30
40
50
60
70
0 20 40 60 80 100 120 140 160
Cum
ulat
ive
pack
ets
sent
time (ms)
Sen
d 50
pkt
s
Sen
d 5
100 ms
100 ms
Cautious fo
recast
Keith Winstein, Anirudh Sivaraman, and Hari Balakrishnan M.I.T. CSAIL http://alfalfa.mit.edu
Stochastic Forecasts Achieve High Throughput and Low Delay over Cellular Networks
Control: fill up 100 ms forecast window
0
10
20
30
40
50
60
70
0 20 40 60 80 100 120 140 160
Cum
ulat
ive
pack
ets
sent
time (ms)
Sen
d 50
pkt
s
Sen
d 5
100 ms
100 ms100 ms
Cautious fo
recast
Keith Winstein, Anirudh Sivaraman, and Hari Balakrishnan M.I.T. CSAIL http://alfalfa.mit.edu
Stochastic Forecasts Achieve High Throughput and Low Delay over Cellular Networks
Control: fill up 100 ms forecast window
0
10
20
30
40
50
60
70
0 20 40 60 80 100 120 140 160
Cum
ulat
ive
pack
ets
sent
time (ms)
Sen
d 50
pkt
s
Sen
d 5
Sen
d 3 100 ms
100 ms100 ms
Cautious fo
recast
Keith Winstein, Anirudh Sivaraman, and Hari Balakrishnan M.I.T. CSAIL http://alfalfa.mit.edu
Stochastic Forecasts Achieve High Throughput and Low Delay over Cellular Networks
0
1000
2000
3000
4000
5000
6000
7000
8000
100200300500100020005000
Th
rou
gh
pu
t(k
bp
s)
Self-inflicted delay (ms)
Verizon LTE Downlink
Skype
Bette
r
Keith Winstein, Anirudh Sivaraman, and Hari Balakrishnan M.I.T. CSAIL http://alfalfa.mit.edu
Stochastic Forecasts Achieve High Throughput and Low Delay over Cellular Networks
0
1000
2000
3000
4000
5000
6000
7000
8000
100200300500100020005000
Th
rou
gh
pu
t(k
bp
s)
Self-inflicted delay (ms)
Verizon LTE Downlink
SkypeFacetime
Google Hangout
Bette
r
Keith Winstein, Anirudh Sivaraman, and Hari Balakrishnan M.I.T. CSAIL http://alfalfa.mit.edu
Stochastic Forecasts Achieve High Throughput and Low Delay over Cellular Networks
0
1000
2000
3000
4000
5000
6000
7000
8000
100200300500100020005000
Th
rou
gh
pu
t(k
bp
s)
Self-inflicted delay (ms)
Verizon LTE Downlink
Compound TCP
LEDBAT
SkypeFacetime
Google Hangout
Vegas
Bette
r
Keith Winstein, Anirudh Sivaraman, and Hari Balakrishnan M.I.T. CSAIL http://alfalfa.mit.edu
Stochastic Forecasts Achieve High Throughput and Low Delay over Cellular Networks
0
1000
2000
3000
4000
5000
6000
7000
8000
100200300500100020005000
Th
rou
gh
pu
t(k
bp
s)
Self-inflicted delay (ms)
Verizon LTE Downlink
Compound TCP
LEDBAT
Cubic
SkypeFacetime
Google Hangout
Vegas
Bette
r
Keith Winstein, Anirudh Sivaraman, and Hari Balakrishnan M.I.T. CSAIL http://alfalfa.mit.edu
Stochastic Forecasts Achieve High Throughput and Low Delay over Cellular Networks
0
1000
2000
3000
4000
5000
6000
7000
8000
100200300500100020005000
Th
rou
gh
pu
t(k
bp
s)
Self-inflicted delay (ms)
Verizon LTE Downlink
Compound TCP
LEDBAT
Cubic
SkypeFacetime
Google Hangout
Vegas
Sprout
Bette
r
Keith Winstein, Anirudh Sivaraman, and Hari Balakrishnan M.I.T. CSAIL http://alfalfa.mit.edu
Stochastic Forecasts Achieve High Throughput and Low Delay over Cellular Networks
0
1000
2000
3000
4000
5000
6000
7000
8000
100200300500100020005000
Th
rou
gh
pu
t(k
bp
s)
Self-inflicted delay (ms)
Verizon LTE Downlink
Sprout-EWMA
Compound TCP
LEDBAT
Cubic
SkypeFacetime
Google Hangout
Vegas
Sprout
Bette
r
Keith Winstein, Anirudh Sivaraman, and Hari Balakrishnan M.I.T. CSAIL http://alfalfa.mit.edu
Stochastic Forecasts Achieve High Throughput and Low Delay over Cellular Networks
0
1000
2000
3000
4000
5000
300500100020003000500010000
Th
rou
gh
pu
t(k
bp
s)
Self-inflicted delay (ms)
Verizon LTE Uplink
Sprout-EWMA
Compound TCP
LEDBAT
Cubic
Skype Facetime
Google Hangout
Vegas
Sprout
Keith Winstein, Anirudh Sivaraman, and Hari Balakrishnan M.I.T. CSAIL http://alfalfa.mit.edu
Stochastic Forecasts Achieve High Throughput and Low Delay over Cellular Networks
150
200
250
300
350
400
450
500
550
200030005000100002000050000100000
Th
rou
gh
pu
t(k
bp
s)
Self-inflicted delay (ms)
Verizon 3G (1xEV-DO) Downlink
Sprout-EWMACompound TCP
LEDBAT
Cubic
Skype
FacetimeGoogle Hangout
Vegas
Sprout
Keith Winstein, Anirudh Sivaraman, and Hari Balakrishnan M.I.T. CSAIL http://alfalfa.mit.edu
Stochastic Forecasts Achieve High Throughput and Low Delay over Cellular Networks
200
300
400
500
600
200300500100020003000500010000
Th
rou
gh
pu
t(k
bp
s)
Self-inflicted delay (ms)
Verizon 3G (1xEV-DO) Uplink
Sprout-EWMA
Compound TCP
LEDBAT
Cubic
Skype
Facetime
Google Hangout
Vegas
Sprout
Keith Winstein, Anirudh Sivaraman, and Hari Balakrishnan M.I.T. CSAIL http://alfalfa.mit.edu
Stochastic Forecasts Achieve High Throughput and Low Delay over Cellular Networks
500
1000
1500
2000
2500
3000
3500
4000
3050100200300500100020005000
Th
rou
gh
pu
t(k
bp
s)
Self-inflicted delay (ms)
AT&T LTE Downlink
Sprout-EWMA
Compound TCPLEDBATCubic
Skype
Facetime
Google Hangout
Vegas
Sprout
Keith Winstein, Anirudh Sivaraman, and Hari Balakrishnan M.I.T. CSAIL http://alfalfa.mit.edu
Stochastic Forecasts Achieve High Throughput and Low Delay over Cellular Networks
200
300
400
500
600
700
800
900
2003005001000200050001000020000
Th
rou
gh
pu
t(k
bp
s)
Self-inflicted delay (ms)
AT&T LTE Uplink
Sprout-EWMA
Compound TCP
LEDBATCubic
SkypeFacetime
Google Hangout
Vegas
Sprout
Keith Winstein, Anirudh Sivaraman, and Hari Balakrishnan M.I.T. CSAIL http://alfalfa.mit.edu
Stochastic Forecasts Achieve High Throughput and Low Delay over Cellular Networks
200
400
600
800
1000
1200
1400
1600
3005001000200030005000
Th
rou
gh
pu
t(k
bp
s)
Self-inflicted delay (ms)
T-Mobile 3G (UMTS) Downlink
Sprout-EWMA
Compound TCPLEDBAT
Cubic
SkypeFacetime
Google Hangout
Vegas
Sprout
Keith Winstein, Anirudh Sivaraman, and Hari Balakrishnan M.I.T. CSAIL http://alfalfa.mit.edu
Stochastic Forecasts Achieve High Throughput and Low Delay over Cellular Networks
200
300
400
500
600
700
800
900
1000
2003005001000200050001000030000
Th
rou
gh
pu
t(k
bp
s)
Self-inflicted delay (ms)
T-Mobile 3G (UMTS) Uplink
Sprout-EWMA
Compound TCP
LEDBAT
Cubic
Skype
Facetime
Google Hangout
Vegas
Sprout
Keith Winstein, Anirudh Sivaraman, and Hari Balakrishnan M.I.T. CSAIL http://alfalfa.mit.edu
Stochastic Forecasts Achieve High Throughput and Low Delay over Cellular Networks
Overall results
Sprout vs. Avg. speedup Delay reduction
Skype 2.2× 7.9×Hangout 4.4× 7.2×Facetime 1.9× 8.7×Compound 1.3× 4.8×TCP Vegas 1.1× 2.1×LEDBAT Same 2.8×Cubic 0.91× 79×
Keith Winstein, Anirudh Sivaraman, and Hari Balakrishnan M.I.T. CSAIL http://alfalfa.mit.edu
Stochastic Forecasts Achieve High Throughput and Low Delay over Cellular Networks
Varying risk tolerance
200
300
400
500
600
700
800
900
1000
2003005001000300050001000030000
Th
rou
gh
pu
t(k
bp
s)
Self-inflicted delay (ms)
Compound TCP
LEDBAT
Cubic
Skype
Facetime
Google Hangout
Vegas
Sprout (5%)
25%
50%
75%
95%
Keith Winstein, Anirudh Sivaraman, and Hari Balakrishnan M.I.T. CSAIL http://alfalfa.mit.edu
Stochastic Forecasts Achieve High Throughput and Low Delay over Cellular Networks
Competes with AQM even though end-to-end
0
20
40
60
80
100
2003005001000300050001000030000
Uti
lizat
ion
(per
cen
t)
Self-inflicted delay (ms)
Sprout
Sprout-EWMA
Cubic
Cubic-over-CoDel
Keith Winstein, Anirudh Sivaraman, and Hari Balakrishnan M.I.T. CSAIL http://alfalfa.mit.edu
Stochastic Forecasts Achieve High Throughput and Low Delay over Cellular Networks
Competing traffic inside Sprout tunnel
Direct via Sprout Benefit
Cubic throughput 8336 kbps 3776 kbps 0.5× (= worse)Skype throughput 78 kbps 490 kbps 6×Skype 95% delay 6.0 s 0.17 s 35×
Keith Winstein, Anirudh Sivaraman, and Hari Balakrishnan M.I.T. CSAIL http://alfalfa.mit.edu
Stochastic Forecasts Achieve High Throughput and Low Delay over Cellular Networks
Replication by Stanford students (February–March 2013)
I Alterman & Quach reproduced some of our measurements
I http://ReproducingNetworkResearch.wordpress.com/2013/03/12/1216/
I Won best project award in Stanford networking class!
Keith Winstein, Anirudh Sivaraman, and Hari Balakrishnan M.I.T. CSAIL http://alfalfa.mit.edu
Stochastic Forecasts Achieve High Throughput and Low Delay over Cellular Networks
M.I.T. 6.829 contest (March–April 2013)
I Turnkey network emulator, evaluation
I Sender, receiver run in Linux containers
I 4th prize: $20
I 3rd prize: $30
I 2nd prize: $40
I (If beat Sprout) 1st prize:
Co-authorship on future paper
Keith Winstein, Anirudh Sivaraman, and Hari Balakrishnan M.I.T. CSAIL http://alfalfa.mit.edu
Stochastic Forecasts Achieve High Throughput and Low Delay over Cellular Networks
M.I.T. 6.829 contest (March–April 2013)
I Turnkey network emulator, evaluation
I Sender, receiver run in Linux containers
I 4th prize: $20
I 3rd prize: $30
I 2nd prize: $40
I (If beat Sprout) 1st prize: Co-authorship on future paper
Keith Winstein, Anirudh Sivaraman, and Hari Balakrishnan M.I.T. CSAIL http://alfalfa.mit.edu
Stochastic Forecasts Achieve High Throughput and Low Delay over Cellular Networks
Baseline
Keith Winstein, Anirudh Sivaraman, and Hari Balakrishnan M.I.T. CSAIL http://alfalfa.mit.edu
Stochastic Forecasts Achieve High Throughput and Low Delay over Cellular Networks
Land of 3,000 student protocols
Keith Winstein, Anirudh Sivaraman, and Hari Balakrishnan M.I.T. CSAIL http://alfalfa.mit.edu
Stochastic Forecasts Achieve High Throughput and Low Delay over Cellular Networks
Sprout is on the frontier
Keith Winstein, Anirudh Sivaraman, and Hari Balakrishnan M.I.T. CSAIL http://alfalfa.mit.edu
Stochastic Forecasts Achieve High Throughput and Low Delay over Cellular Networks
Limitations
I Only evaluated long-running flows.
I All testing data from Boston.
I User should wrap competing flows inside Sprout.
I If queue is full of another user’s packets, an end-to-endscheme can’t help.
I Fortunately, cells have per-device queues. . .I . . . but Wi-Fi generally doesn’t.
I What about when the cell link isn’t the bottleneck?
Keith Winstein, Anirudh Sivaraman, and Hari Balakrishnan M.I.T. CSAIL http://alfalfa.mit.edu
Stochastic Forecasts Achieve High Throughput and Low Delay over Cellular Networks
Our approach
I Pick a model, any model.
I All models are wrong, but they help anyway!
I See if it lands on the frontier.*
* (On a large set of real network paths or newly-collectedtraces.)
I Kaizen for congestion
Keith Winstein, Anirudh Sivaraman, and Hari Balakrishnan M.I.T. CSAIL http://alfalfa.mit.edu
Stochastic Forecasts Achieve High Throughput and Low Delay over Cellular Networks
Thank you
I Lakshminarayanan Subramanian
I Shuo Deng
I Jonathan Perry
I Katrina LaCurts
I Andrew McGregor
I Tim Shepard
I Dave Taht
I Michael Welzl
I Hannes Tschofenig
I Wireless@MIT members (http://wireless.csail.mit.edu)
I NSF & Shannon family (fellowship)
Keith Winstein, Anirudh Sivaraman, and Hari Balakrishnan M.I.T. CSAIL http://alfalfa.mit.edu
Stochastic Forecasts Achieve High Throughput and Low Delay over Cellular Networks
Sprout for controlled delay over cellular networks
I Infer link speed from interarrival distribution
I Predict future link speed
I Control risk of large delay with cautious forecast
I Yields 2–4× throughput of Skype, Facetime, Hangout
I Achieves 7–9× reduction in self-inflicted delay
I Matches active queue management without router changes
I Code and directions at http://alfalfa.mit.edu
Keith Winstein, Anirudh Sivaraman, and Hari Balakrishnan M.I.T. CSAIL http://alfalfa.mit.edu
Stochastic Forecasts Achieve High Throughput and Low Delay over Cellular Networks