Engineering for QoS and the limits of service differentiation

About This Presentation

Title:

Engineering for QoS and the limits of service differentiation

Description:

France T l com R&D. Engineering for QoS: a probabilistic point of view ... France T l com R&D. Traffic on a US backbone link (Thomson et al, 1997) ... – PowerPoint PPT presentation

Number of Views:68

Avg rating:3.0/5.0

Slides: 92

Provided by: csC76

Learn more at: http://www.cs.cmu.edu

Category:

more less

Transcript and Presenter's Notes

Title: Engineering for QoS and the limits of service differentiation

1
Engineering for QoS and the limits of service
differentiation
IWQoS June 2000

Jim Roberts
(james.roberts_at_francetelecom.fr)

2
The central role of QoS
feasible technology

quality of service
transparency
response time
accessibility

service model
resource sharing
priorities,...

network engineering
provisioning
routing,...

a viable business model
3
Engineering for QoS a probabilistic point of view

statistical characterization of traffic
notions of expected demand and random processes
for packets, bursts, flows, aggregates
QoS in statistical terms
transparency Pr packet loss, mean delay, Pr
delay x,...
response time E response time,...
accessibility Pr blocking,...
QoS engineering, based on a three-way
relationship

performance
demand
capacity
4
Outline

traffic characteristics
QoS engineering for streaming flows
QoS engineering for elastic traffic
service differentiation

5
Internet traffic is self-similar

a self-similar process
variability at all time scales
due to
infinite variance of flow size
TCP induced burstiness
a practical consequence
difficult to characterize a traffic aggregate

Ethernet traffic, Bellcore 1989
6
Traffic on a US backbone link (Thomson et al,
1997)

traffic intensity is predictable ...
... and stationary in the busy hour

7
Traffic on a French backbone link

traffic intensity is predictable ...
... and stationary in the busy hour

tue wed thu fri
sat sun mon
12h 18h
00h 06h
8
IP flows

a flow one instance of a given application
a "continuous flow" of packets
basically two kinds of flow, streaming and
elastic

9
IP flows

a flow one instance of a given application
a "continuous flow" of packets
basically two kinds of flow, streaming and
elastic
streaming flows
audio and video, real time and playback
rate and duration are intrinsic characteristics
not rate adaptive (an assumption)
QoS ? negligible loss, delay, jitter

10
IP flows

a flow one instance of a given application
a "continuous flow" of packets
basically two kinds of flow, streaming and
elastic
streaming flows
audio and video, real time and playback
rate and duration are intrinsic characteristics
not rate adaptive (an assumption)
QoS ? negligible loss, delay, jitter
elastic flows
digital documents ( Web pages, files, ...)
rate and duration are measures of performance
QoS ? adequate throughput (response time)

11
Flow traffic characteristics

streaming flows
constant or variable rate
compressed audio (O103 bps) and video (O106
bps)
highly variable duration
a Poisson flow arrival process (?)

12
Flow traffic characteristics

streaming flows
constant or variable rate
compressed audio (O103 bps) and video (O106
bps)
highly variable duration
a Poisson flow arrival process (?)
elastic flows
infinite variance size distribution
rate adaptive
a Poisson flow arrival process (??)

variable rate video
13
Modelling traffic demand

stream traffic demand
arrival rate x bit rate x duration
elastic traffic demand
arrival rate x size
a stationary process in the "busy hour"
eg, Poisson flow arrivals, independent flow size

traffic demand
Mbit/s
busy hour
time of day
14
Outline

traffic characteristics
QoS engineering for streaming flows
QoS engineering for elastic traffic
service differentiation

15
Open loop control for streaming traffic

a "traffic contract"
QoS guarantees rely on
traffic descriptors admission control
policing
time scale decomposition for performance
analysis
packet scale
burst scale
flow scale

user-network interface
user-network interface
network-network interface
16
Packet scale a superposition of constant rate
flows

constant rate flows
packet size/inter-packet interval flow rate
maximum packet size MTU

17
Packet scale a superposition of constant rate
flows

constant rate flows
packet size/inter-packet interval flow rate
maximum packet size MTU
buffer size for negligible overflow?
over all phase alignments...
...assuming independence between flows

18
Packet scale a superposition of constant rate
flows

constant rate flows
packet size/inter-packet interval flow rate
maximum packet size MTU
buffer size for negligible overflow?
over all phase alignments...
...assuming independence between flows
worst case assumptions
many low rate flows
MTU-sized packets

buffer size
increasing number, increasing pkt size
log Pr saturation
19
Packet scale a superposition of constant rate
flows

constant rate flows
packet size/inter-packet interval flow rate
maximum packet size MTU
buffer size for negligible overflow?
over all phase alignments...
...assuming independence between flows
worst case assumptions
many low rate flows
MTU-sized packets
? buffer sizing for M/DMTU/1 queue
Pr queue x C e -r x

buffer size
M/DMTU/1
increasing number, increasing pkt size
log Pr saturation
20
The "negligible jitter conjecture"

constant rate flows acquire jitter
notably in multiplexer queues

21
The "negligible jitter conjecture"

constant rate flows acquire jitter
notably in multiplexer queues
conjecture
if all flows are initially CBR and in all queues
S flow rates
they never acquire sufficient jitter to become
worse for performance than a Poisson stream of
MTU packets

22
The "negligible jitter conjecture"

constant rate flows acquire jitter
notably in multiplexer queues
conjecture
if all flows are initially CBR and in all queues
S flow rates
they never acquire sufficient jitter to become
worse for performance than a Poisson stream of
MTU packets
M/DMTU/1 buffer sizing remains conservative

23
Burst scale fluid queueing models

assume flows have an intantaneous rate
eg, rate of on/off sources

packets
arrival rate
24
Burst scale fluid queueing models

assume flows have an intantaneous rate
eg, rate of on/off sources
bufferless or buffered multiplexing?
Pr arrival rate
E arrival rate

25
Buffered multiplexing performance impact of
burst parameters
Pr rate overload
26
Buffered multiplexing performance impact of
burst parameters
longer
burst length
shorter
27
Buffered multiplexing performance impact of
burst parameters
more variable
burst length
less variable
28
Buffered multiplexing performance impact of
burst parameters
long range dependence
burst length
short range dependence
29
Choice of token bucket parameters?

the token bucket is a virtual queue
service rate r
buffer size b

r
b
30
Choice of token bucket parameters?

the token bucket is a virtual queue
service rate r
buffer size b
non-conformance depends on
burst size and variability
and long range dependence

r
b
31
Choice of token bucket parameters?

the token bucket is a virtual queue
service rate r
buffer size b
non-conformance depends on
burst size and variability
and long range dependence
a difficult choice for conformance
r mean rate...
...or b very large

b'
b
non- conformance probability
r
b
32
Bufferless multiplexing alias "rate envelope
multiplexing"

provisioning and/or admission control to ensure
Pr LtC
performance depends only on stationary rate
distribution
loss rate ? E (Lt -C) / E Lt
insensitivity to self-similarity

output rate C
combined input rate Lt
33
Efficiency of bufferless multiplexing

small amplitude of rate variations ...
peak rate

34
Efficiency of bufferless multiplexing

small amplitude of rate variations ...
peak rate
... or low utilisation
overall mean rate

35
Efficiency of bufferless multiplexing

small amplitude of rate variations ...
peak rate
... or low utilisation
overall mean rate
we may have both in an integrated network
priority to streaming traffic
residue shared by elastic flows

36
Flow scale admission control

accept new flow only if transparency preserved
given flow traffic descriptor
current link status
no satisfactory solution for buffered
multiplexing
(we do not consider deterministic guarantees)
unpredictable statistical performance
measurement-based control for bufferless
multiplexing
given flow peak rate
current measured rate (instantaneous rate, mean,
variance,...)

37
Flow scale admission control

accept new flow only if transparency preserved
given flow traffic descriptor
current link status
no satisfactory solution for buffered
multiplexing
(we do not consider deterministic guarantees)
unpredictable statistical performance
measurement-based control for bufferless
multiplexing
given flow peak rate
current measured rate (instantaneous rate, mean,
variance,...)
uncritical decision threshold if streaming
traffic is light
in an integrated network

38
Provisioning for negligible blocking

"classical" teletraffic theory assume
Poisson arrivals, rate l
constant rate per flow r
mean duration 1/m
? mean demand, A l/m r bits/s
blocking probability for capacity C
B E(C/r,A/r)
E(m,a) is Erlang's formula
E(m,a)
? scale economies

39
Provisioning for negligible blocking

"classical" teletraffic theory assume
Poisson arrivals, rate l
constant rate per flow r
mean duration 1/m
? mean demand, A l/m r bits/s
blocking probability for capacity C
B E(C/r,A/r)
E(m,a) is Erlang's formula
E(m,a)
? scale economies
generalizations exist
for different rates
for variable rates

40
Outline

traffic characteristics
QoS engineering for streaming flows
QoS engineering for elastic traffic
service differentiation

41
Closed loop control for elastic traffic

reactive control
end-to-end protocols (eg, TCP)
queue management
time scale decomposition for performance
analysis
packet scale
flow scale

42
Packet scale bandwidth and loss rate

a multi-fractal arrival process

43
Packet scale bandwidth and loss rate

a multi-fractal arrival process
but loss and bandwidth related by TCP (cf. Padhye
et al.)

congestion avoidance
loss rate p
B(p)
44
Packet scale bandwidth and loss rate

a multi-fractal arrival process
but loss and bandwidth related by TCP (cf. Padhye
et al.)

congestion avoidance
loss rate p
B(p)
45
Packet scale bandwidth and loss rate

a multi-fractal arrival process
but loss and bandwidth related by TCP (cf. Padhye
et al.)
thus, p B-1(p) ie, loss rate depends on
bandwidth share

congestion avoidance
loss rate p
B(p)
46
Packet scale bandwidth sharing

reactive control (TCP, scheduling) shares
bottleneck bandwidth unequally
depending on RTT, protocol implementation, etc.
and differentiated services parameters

47
Packet scale bandwidth sharing

reactive control (TCP, scheduling) shares
bottleneck bandwidth unequally
depending on RTT, protocol implementation, etc.
and differentiated services parameters
optimal sharing in a network objectives and
algorithms...
max-min fairness, proportional fairness, maximal
utility,...

48
Packet scale bandwidth sharing

reactive control (TCP, scheduling) shares
bottleneck bandwidth unequally
depending on RTT, protocol implementation, etc.
and differentiated services parameters
optimal sharing in a network objectives and
algorithms...
max-min fairness, proportional fairness, maximal
utility,...
... but response time depends more on traffic
process than the static sharing algorithm!

Example a linear network
route 0
route 1
route L
49
Flow scale performance of a bottleneck link

assume perfect fair shares
link rate C, n elastic flows ?
each flow served at rate C/n

50
Flow scale performance of a bottleneck link

assume perfect fair shares
link rate C, n elastic flows ?
each flow served at rate C/n
assume Poisson flow arrivals
an M/G/1 processor sharing queue
load, r arrival rate x size / C

? a processor sharing queue
51
Flow scale performance of a bottleneck link

assume perfect fair shares
link rate C, n elastic flows ?
each flow served at rate C/n
assume Poisson flow arrivals
an M/G/1 processor sharing queue
load, r arrival rate x size / C
performance insensitive to size distribution
Pr n transfers rn(1-r)
E response time size / C(1-r)

52
Flow scale performance of a bottleneck link
link capacity C

assume perfect fair shares
link rate C, n elastic flows ?
each flow served at rate C/n
assume Poisson flow arrivals
an M/G/1 processor sharing queue
load, r arrival rate x size / C
performance insensitive to size distribution
Pr n transfers rn(1-r)
E response time size / C(1-r)
instability if r 1
i.e., unbounded response time
stabilized by aborted transfers...
... or by admission control

fair shares
? a processor sharing queue
throughput
C
r
0
0
1
53
Generalizations of PS model

non-Poisson arrivals
Poisson sessions
Bernoulli feedback

processor sharing
infinite server
54
Generalizations of PS model

non-Poisson arrivals
Poisson sessions
Bernoulli feedback
discriminatory processor sharing
weight fi for class i flows
service rate ? fi

55
Generalizations of PS model

non-Poisson arrivals
Poisson sessions
Bernoulli feedback
discriminatory processor sharing
weight fi for class i flows
service rate ? fi
rate limitations (same for all flows)
maximum rate per flow (eg, access rate)
minimum rate per flow (by admission control)

56
Admission control can be useful
57
Admission control can be useful
58
Admission control can be useful ...
... to prevent disasters at sea !
59
Admission control can also be useful for IP flows

improve efficiency of TCP
reduce retransmissions overhead ...
... by maintaining throughput
prevent instability
due to overload (r 1)...
...and retransmissions
avoid aborted transfers
user impatience
"broken connections"
a means for service differentiation...

60
Choosing an admission control threshold

N the maximum number of flows admitted
negligible blocking when rwhen r1

61
Choosing an admission control threshold

N the maximum number of flows admitted
negligible blocking when rwhen r1
M/G/1/N processor sharing system
min bandwidth C/N
Pr blocking rN(1 - r)/(1 - rN1) ? (1 - 1/r)
, for r1

1 .8 .6 .4 .2 0
300 200 100 0
Blocking probability
E Response time/size
0 100 200
N
0 100 200
N
62
Choosing an admission control threshold

N the maximum number of flows admitted
negligible blocking when rwhen r1
M/G/1/N processor sharing system
min bandwidth C/N
Pr blocking rN(1 - r)/(1 - rN1) ? (1 - 1/r)
, for r1
uncritical choice of threshold
eg, 1 of link capacity (N100)

63
Impact of access rate on backbone sharing

TCP throughput is limited by access rate...
modem, DSL, cable
... and by server performance

64
Impact of access rate on backbone sharing

TCP throughput is limited by access rate...
modem, DSL, cable
... and by server performance
? backbone link is a bottleneck only if
saturated!
ie, if r 1

65
Provisioning for negligible blocking for elastic
flows

"elastic" teletraffic theory assume
Poisson arrivals, rate l
mean size s
blocking probability for capacity C
utilization r ls/C
m admission control limit
B(r,m) rm(1-r)/(1-rm1)

66
Provisioning for negligible blocking for elastic
flows

"elastic" teletraffic theory assume
Poisson arrivals, rate l
mean size s
blocking probability for capacity C
utilization r ls/C
m admission control limit
B(r,m) rm(1-r)/(1-rm1)
impact of access rate
C/access rate m
B(r,m) ? E(m,rm)

utilization (r) for B 0.01
r
0.8
E(m,rm)
0.6
0.4
0.2
m
0 20 40 60 80 100
67
Outline

traffic characteristics
QoS engineering for streaming flows
QoS engineering for elastic traffic
service differentiation

68
Service differentiation

discriminating between stream and elastic flows
transparency for streaming flows
response time for elastic flows
discriminating between stream flows
different delay and loss requirements
... or the best quality for all?
discriminating between elastic flows
different response time requirements
... but how?

69
Integrating streaming and elastic traffic

priority to packets of streaming flows
low utilization ? negligible loss and delay

70
Integrating streaming and elastic traffic

priority to packets of streaming flows
low utilization ? negligible loss and delay
elastic flows use all remaining capacity
better response times
per flow fair queueing (?)

71
Integrating streaming and elastic traffic

priority to packets of streaming flows
low utilization ? negligible loss and delay
elastic flows use all remaining capacity
better response times
per flow fair queueing (?)
to prevent overload
flow based admission control...
...and adaptive routing

72
Integrating streaming and elastic traffic

priority to packets of streaming flows
low utilization ? negligible loss and delay
elastic flows use all remaining capacity
better response times
per flow fair queueing (?)
to prevent overload
flow based admission control...
...and adaptive routing
an identical admission criterion for streaming
and elastic flows
available rate R

73
Differentiation for stream traffic

different delays?
priority queues, WFQ, ...
but what guarantees?

delay
delay
74
Differentiation for stream traffic

different delays?
priority queues, WFQ, ...
but what guarantees?
different loss?
different utilization (CBQ, ...)
"spatial queue priority"
partial buffer sharing, push out

delay
delay
loss
loss
75
Differentiation for stream traffic

different delays?
priority queues, WFQ, ...
but what guarantees?
different loss?
different utilization (CBQ, ...)
"spatial queue priority"
partial buffer sharing, push out
or negligible loss and delay for all
elastic-stream integration ...
... and low stream utilization

delay
delay
loss
loss
loss delay
76
Differentiation for elastic traffic

different utilization
separate pipes
class based queuing

77
Differentiation for elastic traffic

different utilization
separate pipes
class based queuing
different per flow shares
WFQ
impact of RTT,...

78
Differentiation for elastic traffic
throughput

different utilization
separate pipes
class based queuing
different per flow shares
WFQ
impact of RTT,...
discrimination in overload
impact of aborts (?)
or by admission control

C
access rate
r
0
0
1
1st class
3rd class
2nd class
throughput
C
access rate
r
0
0
1
79
Different accessibility

block class 1 when 100 flows in progress
- block
class 2 when N2 flows in progress

1 0
Blocking probability
r 1.5
r 0.9
0 100 200
N
80
Different accessibility

block class 1 when 100 flows in progress
- block
class 2 when N2 flows in progress

81
Different accessibility

block class 1 when 100 flows in progress
- block
class 2 when N2 flows in progress
in underload both classes have negligible
blocking (B1 B2 0)

B2?B1?0
82
Different accessibility

block class 1 when 100 flows in progress
- block
class 2 when N2 flows in progress
in underload both classes have negligible
blocking (B1 B2 0)
in overload discrimination is effective
if r1 (r1r2-1)/r2

1
r1 r2 0.4
B2?B1?0
0
0
N2
83
Different accessibility

block class 1 when 100 flows in progress
- block
class 2 when N2 flows in progress
in underload both classes have negligible
blocking (B1 B2 0)
in overload discrimination is effective
if r1 (r1r2-1)/r2
if 1 1

84
Service differentiation and pricing