Comparison%20of%20MaxNet%20and%20XCP:%20Network%20Congestion%20Control%20using%20explicit%20signalling%20Speaker:%20Bartek%20Wydrowski

1
Comparison of MaxNet and XCP Network Congestion
Control using explicit signallingSpeaker
Bartek Wydrowski
Compiled from work by Lachlan Andrew (2), Steven
Low (1), Iven Mareels (2), Bartek Wydrowski (1),
Moshe Zukerman (2).
(2)
(1)
2
Talk Overview

• MaxNet XCP Overview.
• Steady state Rate allocation properties.
• Summary of Maxnet and XCP.
• Maxnet A little more details
• Stability.
• Convergence Speed.

3
Network Congestion Control
Sources transmit at a rate controlled by a
congestion signal
Links generate the congestion signal based on
level of congestion at link
Congestion level of end-to-end path is fed back
to source
4
Network Congestion Control
Congestion signal on the Internet is implicit,
and can be modelled as the sum of the end-to-end
link congestion levels this is where XCP,
MaxNet differs.







S

p

p

p


i
2
1
N


Link 2

Link N

Link 1

Source

Destination



Link l drops packets at rate pl Link l ECN
marks packets at rate pl Link l delays packets
for time pl
Link 1

Link 2

Link 1

Link 2

Link 1

Link 2

T1
T2
5
MaxNet Overview
6
MaxNet Quick Overview

• MaxNet is
• A Fully distributed flow control architecture
  for large networks.
• Max-Min fair in principle.
• Stable for networks of arbitrary topology,
  number of users, capacity and delay.
• Fast convergence properties.
• Addresses short-flow control.
• Philosophy
• Simple Architecture.
• Ability to scale.
• Simplicity ? ability to design/predict.

7
MaxNet Packet Format
Packet
Data
CongestionSignal N Bits (price_k)
8
MaxNet Source Algorithm
Source Algorithm Demand Function. Each source
can have a different demand function which
determines the sources relative need for
capacity.
Xi D(price_k)
Congestion Feedback from ACK k
Source rate
Source demand function
9
MaxNet Packet Marking
Source 1
Packet Signal max(Packet Signal,p1(t))
Source 2
Packet Signal max(Packet Signal ,p2(t))
Packet Signal max(Packet Signal ,p3(t))
Signal max(p2,p3)
Signal max(p1,p2,p3)
10
MaxNet Link Algorithm
Router Algorithm Packet marking according to
Price_k max ( Price_k , pl(t) )
Link price updated at each control interval,
say every 10ms. (single price for all flows on
link)
Congestion signal in pkt k
pl(t1) pl(t) b(y(t)-aC)
Link capacity
Constant convergence speed
Aggregate input rate
Constant to control Link utilization
11
MaxNet Steady State Properties
q0 p1 max(p1)
q1 p1 max(p1,p2)
q2 p1 max(p1,p2,p3)
q3 p3 max(p2, p3)
p1
p2
p3
Mbps
1.33
S3
0.66
S0,S1,S2
q0, q1, q2
q3
Price
12
MaxNet Steady State Properties
Link 2 capacity
Link 2 capacity
3 Mbps
3 Mbps
1 Mbps
1 Mbps
T1
T2
T1
T2
13
XCP Overview
14
XCP Architecture
XCP Packet Header
H_cwnd H_rtt H_feedback
Receiver
Sender
router
router
1. Initializes pkt k H_throughput_k H_rtt_k H_fee
dback_k
2. Each Router Computes Feedback H_feedback_k
min(H_feedback_k,H_lk) Where H_lk link ls
feedback for pkt k. Thus, feedback from router
with minimum feedback signal is obtained from
source to destination path.
3. Send header back to sender in ACK.
15
XCP Architecture
Source Algorithm

• Rate is governed by window
• Source sends packet containing XCP header
• Source receives feedback in ACK and adjusts
  window

Feedback from ACK
Change in source window
Source transmission rate
16
XCP Architecture
Router Algorithm Feedback computed for each
packet
H_feedback_k min (H_feedback_k,H_feedback_i)
Round trip time of source i in packet
Feedback in Pkt k header
Window of source i in packet
Packet size
Mean of all RTTs
Sum over control interval
Aggregate input rate
Link capacity
Queue
17
MaxNet, XCP Steady State Properties
18
MaxNet Steady State Properties
MaxNet is Max-Min fair for homogenous sources.
If all sources have the same demand function
(homogenous),then MaxNet results in a max-min
rate allocation.Max-min fairness maximises the
minimum rate allocation,and maximizes each
subsequently larger rate without reducingthe
smaller rates.
19
MaxNet Steady State Properties
For general demand functions, MaxNet is weighted
min-max fair. (Min-Max price fair)
Sources can prioritizetheir rate allocation
bychanging their demandfunctions. Roughly
speaking,their rate allocation will be in
proportion to the magnitude of the demand
function.
Transmission rate
x1 x2
Link price
20
XCP Steady State Properties

• Analysis to compute XCP equilibrium rates for
  arbitrary topology Steven H. Low, Lachlan L. H.
  Andrew, Bartek P. Wydrowski, Understanding XCP
  Equilibrium and Fairness.
• Rate allocation is a solution to a max-min
  problem with additional constraints
• Effects of additional constraint
• Utilization can be below 100.
• Rates can be arbitrarily small fraction of
  max-min fair rates
• In some topologies, residual terms are redundant.

21
XCP Steady State Properties

• Given a topology, our analysis can predict rate
  allocation.
• Matches NS2 results very precisely
• Predicts interesting pathological cases

22
XCP Steady State Properties

• Utilization of a link varies with number of
  sources bottlenecked at other links.
• Lower and upper bound are
• ?l fraction of flows at link l not bottlenecked
  at link l
• ?l fraction of traffic at link l not
  bottlenecked at link l
• ? shuffling parameter ? , ? XCP parameters
  (conv speed,buffer)
• With standard alpha and gamma parameters,
  utilization is at least 80.

23
XCP Scenario 1
C1155 Mbps C2200 Mbps Alpha 0.4 Beta 0.226
Gamma 0.1
24
XCP Utilisation
25
XCP Scenario 1
Rate allocation can be arbitrarily smaller than
max-minfair rates.
Eg C1155 Mbps C2C1(n-1)/n in2-1 j1
Alpha 0.4 Beta 0.226 Gamma 0.1
26
XCP Max-Min Fairness
27
XCP- Stability counter-example
Sources 0..9
Sink
Source 10
200Mbps 1x 50ms 5x 250ms 10x 500ms
100Mbps 50ms
28
(No Transcript)
29
MaxNet XCP comparison
Criteria MaxNet XCP
Rate Allocation MaxMin Weighted MaxMin Constrained MaxMin (less than MaxMin)
Bits per Packet Naïve encoding 40 Bits/pkt with naïve linear encoding. Smarter encoding 4 Bits/pkt (effectively) Every nth packet carries signal, say n10, and exponential encoding of price. 96 Bits/pkt from BSD implementation.
Router operations per packet 2 1 addition 1 max 12 3 multiplications 1 division 6 additions 2 comparisons
30
XCP MaxNet Research status
Criteria MaxNet XCP
Stability Linear stability for networks of arbitrary size, RTTs, capacity and number of flows proven. Linear stability for single link and aggregate of flows, all with same RTT. Have counter example for more general case.
Convergence Speed Linear analysis shows faster convergence than ECN, loss (RENO), delay (FAST,VEGAS) based schemes. No control analysis available. Some simulation results show faster than TCP-RENO.
Implementation progress Custom Simulation, TCP-FAST can be adopted. NS2 BSD
31
MaxNet Stability Properties
32
MaxNet Stability
MaxNet is stable (local proven) over arbitrary
network dimensions of Number of sources,
links, hops, delay, capacity
Same properties as were shown for SumNet in F.
Paganini, J.C. Doyle and S.H. Low, Scalable laws
for stable network congestion control, in Proc.
IEEE Conf. Decision Contr. (CDC), (Orlando, FL),
2001, pp. 185-90.
33
Network Control Model
Physical Network
Control Model Network
Model quantities are small signal variations
about equilibrium.
S1
Source Rate x
Aggregate price q
S2
S3
L1
0
0
0
0
L2
0
0
L3
0
0
Link price d
Aggregate Rate y
34
Network Control Model
MaxNet open-loop transfer function.
S1
S2
S3
L1
0
0
0
0
L2
0
0
L3
0
0
Source Gain
Link Gain
Link Integrator Action
Backward Routing Matrix
Forward Routing Matrix
35
MaxNet Stability Requirements
Source Gain
Constrains slope Of source demand function
Link Gain
Constrains speedof link control law
pl(t1) pl(t) b(y(t)-aC)
36
MaxNet Convergence Properties
37
MaxNet Convergence Speed
MaxNet has faster asymptotic convergence than
the SumNet architecture. (MaxNet is able to
place the dominant pole further to the left than
SumNet.)
38
SumNet, MaxNet simulations
39
Conclusion

• MaxNet steady state, stability and speed
  properties have been investigated.
• XCP steady state properties were recently
  analyzed.
• MaxNet offers (at least) steady state and
  implementation simplicity, advantages over XCP.