Professional Documents
Culture Documents
Congestion Control and Traffic Management in High Speed Networks
Congestion Control and Traffic Management in High Speed Networks
Introduction
Congestion: Effects
Congestion is undesirable because it
can cause:
Increased delay, due to queueing
within the network
Packet loss, due to buffer overflow
Reduced throughput, due to packet
loss and retransmission
Analogy: rush hour traffic
Congestion: Causes
The basic cause of congestion is that
the input traffic demands exceed the
capacity of the network
In typical packet switching networks,
this can occur quite easily when:
- output links are slower than inputs
- multiple traffic sources competing
for same output link at the same time
Buffering: A Solution?
Buffering in switches can help alleviate
short term or transient congestion
problems, but...
Under sustained overload, buffers will
still fill up, and packets will be lost
Motivation
The congestion control problem is even
more acute in high speed networks
Faster link speeds mean that congestion
can happen faster than before
e.g., 64 kilobyte buffer
@ 64 kbps: 8.2 seconds
@ 10 Mbps: 52 milliseconds
@ 1 Gbps: 0.52 milliseconds
Motivation (Contd)
Motivation (Contd)
Motivation (Contd)
Traffic is bursty
- high peak-to-mean ratio, peak rates
- e.g., data traffic: 10-to-1, 1-10 Mbps
- e.g., video traffic: 20-to-1, 5-100 Mbps
- can statistically multiplex several
channels, but if too many are active at
the same time, congestion is inevitable
Motivation (Contd)
Reactive versus
There
Preventive
are two fundamental approaches
Preventive: reservation-based
prevent congestion from ever happening in
the first place, by reserving resources
11
12
13
Call-Level Control
An example of the call-level approach
to congestion control is call admission
control (to be discussed later this
semester)
Tries to prevent congestion by not
allowing new calls or connections into
the network unless the network has
sufficient capacity to support them
14
15
16
Problems:
Can be unfair
- denial of service, long access delay
Hard to specify resource requirements
and QOS parameters precisely
- may not know, or may cheat
- congestion can still occur
17
Cell-Level Control
Also called input rate control
Control the input rate of traffic sources
to prevent, reduce, or control the level
of congestion
Many possible mechanisms:
Traffic shaping, traffic policing, UPC
Leaky bucket (token bucket)
Cell tagging (colouring), cell discarding
Cell scheduling disciplines
18
19
Time Scale
20
Short
Term
usec
Time Scale
21
Short
Term
Months, years
usec
Time Scale
22
Call
Duration
Propagation
Delay Time
Cell Time
Time
Admission Control
Routing, Load Balancing
Cell Time
Time
Propagation
Delay Time
Time Scale
25
Admission Control
Routing, Load Balancing
Time Scale
26
Time Scale
27
Call
Duration
Propagation
Delay Time
Cell Time
Time
Admission Control
Routing, Load Balancing
Preventive controls:
Resource provisioning
Connection admission control
Call routing and load balancing
Usage parameter control
Priority control
Traffic shaping
Fast reservation protocol
29
Reactive controls:
Adaptive admission control
Call routing and load balancing
Adaptive usage parameter control
Explicit congestion notification
(forward or backward)
Node to node flow control
Selective cell discarding
30
Leaky Bucket
One of the cell-level control
mechanisms that has been proposed is
the leaky bucket (a.k.a. token bucket)
Has been proposed as a traffic policing
mechanism for Usage Parameter
Control (UPC), to check conformance of
a source to its traffic descriptor
Can also be used as a traffic shaper
31
32
33
Bucket
34
Bucket
35
Bucket
Hole
36
Bucket
Hole
37
38
Drip
39
40
41
42
Constant
rate stream of
drips, all nicely
spaced, periodic
43
44
45
Incoming Cells
(generated by
traffic source
with rate X)
46
To
Network
Incoming Cells
4 32
47
To
Network
Incoming Cells
5
4 32
48
To
Network
Incoming Cells
5
43 2
49
To
Network
Incoming Cells
5
43
50
To
Network
Incoming Cells
5
51
2 1
To
Network
Incoming Cells
X
4
52
2 1
To
Network
Incoming Cells
XX
5
53
To
3 2 1 Network
Incoming Cells
XX
54
To
3 2 1 Network
55
56
57
To
Network
58
59
60
Variations
There are several different variations
of the basic leaky bucket concept
described in the literature, such as the
virtual leaky bucket, spacer, others
Basic idea: rather than strictly
enforcing rates, allow senders to
occasionally exceed their prescribed
rate, as long as they mark or tag their
extra cells
61
62
63
64
65
66
67
68
69
70
71
72
73
74
75
76
77
78
79
80
81
82
83
84
85
86
87
88
Explicit Congestion
Notification
There are some proposals to use
reactive congestion control
approaches for end-to-end flow control
in ATM
One of the mechanisms proposed is
called Explicit Forward Congestion
Notification (EFCN) (or EFCI, for
Explicit Forward Congestion Indication)
89
90
Traffic
Source
Switch
Switch
91
Switch
Traffic
Source
Switch
Switch
Buffer
92
Switch
Traffic
Source
Switch
Switch
Switch
Occupied
Unoccupied
93
Traffic
Source
Switch
Switch
EFCI Threshold
94
Switch
Traffic
Source
Switch
Switch
Data
Cell
EFCI Threshold
95
Switch
Traffic
Source
Switch
Switch
EFCI Threshold
96
Switch
Traffic
Source
Switch
Switch
EFCI Threshold
97
Switch
Traffic
Source
Switch
Switch
EFCI Threshold
98
Switch
Traffic
Source
Switch
Switch
EFCI Threshold
99
Switch
Traffic
Source
Switch
Switch
EFCI Threshold
100
Switch
Traffic
Source
Switch
Switch
EFCI Threshold
101
Switch
Traffic
Source
Switch
Switch
EFCI Threshold
102
Switch
Traffic
Source
Switch
Switch
Switch
!!!
EFCI Threshold
103
Traffic
Source
Switch
Switch
EFCI Threshold
104
Switch
Traffic
Sink
Traffic
Source
Switch
Switch
EFCI Threshold
105
Switch
Traffic
Source
Switch
Switch
EFCI Threshold
106
Switch
Traffic
Source
Switch
Switch
EFCI Threshold
107
Switch
Traffic
Source
Switch
Switch
!!!
EFCI Threshold
108
Switch
Traffic
Source
Switch
Switch
EFCI Threshold
109
Switch
Traffic
Source
Switch
Switch
EFCI Threshold
110
Switch
Traffic
Source
Switch
Switch
EFCI Threshold
111
Switch
Traffic
Source
Switch
Switch
EFCI Threshold
112
Switch
Traffic
Source
Switch
Switch
EFCI Threshold
113
Switch
EFCI Issues
How to set EFCI threshold
What should sources do when EFCI
signal is seen
What should sources do when no
EFCI signal is seen
Forward versus backward notification
Effect of feedback delay
Delay x bandwidth product
114
Summary
Congestion control in high speed
ATM networks is a difficult problem
Lots of good ideas of how to do it,
but no real standard (yet?)
Will likely require a combination of
schemes at different time scales and
for different classes of traffic
Lots more remains to be done
115