As per Relevance of the word simulation, we have this rfc below:
Network Working Group O.
Request for Comments: 2963
Category: Informational S. De
October 2000
A Rate Adaptive Shaper for Differentiated
Status of this
This memo provides information for the Internet community. It
not specify an Internet standard of any kind. Distribution of
memo is unlimited
Copyright
Copyright (C) The Internet Society (2000). All Rights Reserved
This memo describes several Rate Adaptive Shapers (RAS) that can
used in combination with the single rate Three Color Markers (srTCM
and the two rate Three Color Marker (trTCM) described in RFC2697
RFC2698, respectively. These RAS improve the performance of TCP
a TCM is used at the ingress of a diffserv network by reducing
burstiness of the traffic. With TCP traffic, this reduction of
burstiness is accompanied by a reduction of the number of
packets and by an improved TCP goodput. The proposed RAS can be
at the ingress of Diffserv networks providing the Assured
Per Hop Behavior (AF PHB). They are especially useful when a TCM
used to mark traffic composed of a small number of TCP connections
1.
In DiffServ networks [RFC2475], the incoming data traffic, with
AF PHB in particular, could be subject to marking where the
of this marking is to provide a low drop probability to a
part of the traffic whereas the excess will have a larger
probability. Such markers are mainly token bucket based such as
single rate Three Color Marker (srTCM) and two rate Three
Marker (trTCM) described in [RFC2697] and [RFC2698], respectively
Similar markers were proposed for ATM networks and simulations
shown that their performance with TCP traffic was not
satisfactory and several researchers have shown that
performance problems could be solved in two ways
Bonaventure & De Cnodder Informational [Page 1]
RFC 2963 A Rate Adaptive Shaper October 2000
1. increasing the burst size, i.e. increasing the Committed
Size (CBS) and the Peak Burst Size (PBS) in case of the trTCM,
2. shaping the traffic such that a part of the burstiness is removed
The first solution has as major disadvantage that the traffic sent
the network can be very bursty and thus engineering the network
provide a low packet loss ratio can become difficult. To
support bursty traffic, additional resources such as buffer space
needed. Conversely, the major disadvantage of shaping is that
traffic encounters additional delay in the shaper's buffer
In this document, we propose two shapers that can reduce
burstiness of the traffic upstream of a TCM. By reducing
burstiness of the traffic, the adaptive shapers increase
percentage of packets marked as green by the TCM and thus the
goodput of the users attached to such a shaper
Such rate adaptive shapers will probably be useful at the edge of
network (i.e. inside access routers or even network adapters).
simulation results in [Cnodder] show that these shapers
particularly useful when a small number of TCP connections
processed by a TCM
The structure of this document follows the structure proposed
[Nichols]. We first describe two types of rate adaptive shapers
section two. These shapers correspond to respectively the srTCM
the trTCM. In section 3, we describe an extension to the
shapers that can provide a better performance. We briefly
simulation results in the appendix
2. Description of the rate adaptive
2.1. Rate adaptive
The rate adaptive shaper is based on a similar shaper proposed
[Bonaventure] to improve the performance of TCP with the
Frame Rate [TM41] service category in ATM networks. Another type
rate adaptive shaper suitable for differentiated services was
discussed in [Azeem]. A RAS will typically be used as shown
figure 1 where the meter and the marker are the TCMs proposed
[RFC2697] and [RFC2698].
Bonaventure & De Cnodder Informational [Page 2]
RFC 2963 A Rate Adaptive Shaper October 2000
+----------+
| |
|
+--------+ +-------+ +--------+
Incoming | | | | | |
Packet ==>| RAS |==>| Meter |==>| Marker |==>
Stream | | | | | |
+--------+ +-------+ +--------+
Figure 1. Rate adaptive
The presentation of the rate adaptive shapers in Figure 1 is
different as described in [RFC2475] where the shaper is placed
the meter. The main objective of the shaper is to produce at
output a traffic that is less bursty than the input traffic, but
shaper avoids to discard packets in contrast with classical
bucket based shapers. The shaper itself consists of a tail-drop
queue which is emptied at a variable rate. The shaping rate, i.e
the rate at which the queue is emptied, is a function of
occupancy of the FIFO queue. If the queue occupancy increases,
shaping rate will also increase in order to prevent loss and
large delays through the shaper. The shaping rate is also a
of the average rate of the incoming traffic. The shaper was
to be used in conjunction with meters such as the TCMs proposed
[RFC2697] and [RFC2698].
There are two types of rate adaptive shapers. The single rate
adaptive shaper (srRAS) will typically be used upstream of a
while the two rates rate adaptive shaper (trRAS) will usually be
upstream of a trTCM
2.2. Configuration of the
The srRAS is configured by specifying four parameters: the
Information Rate (CIR), the Maximum Information Rate (MIR) and
buffer thresholds: CIR_th (Committed Information Rate threshold)
MIR_th (Maximum Information Rate threshold). The CIR shall
specified in bytes per second and MUST be configurable. The
shall be specified in the same unit as the CIR and SHOULD
configurable. To achieve a good performance, the CIR of a srRAS
usually be set to the same value as the CIR of the downstream srTCM
A typical value for the MIR would be the line rate of the output
of the shaper. When the CIR and optionally the MIR are configured
the srRAS MUST ensure that the following relation is verified
Bonaventure & De Cnodder Informational [Page 3]
RFC 2963 A Rate Adaptive Shaper October 2000
CIR <= MIR <= line
The two buffer thresholds, CIR_th and MIR_th shall be specified
bytes and SHOULD be configurable. If these thresholds
configured, then the srRAS MUST ensure that the following
holds
CIR_th <= MIR_th <= buffer size of the
The chosen values for CIR_th and MIR_th will usually depend on
values chosen for CBS and PBS in the downstream srTCM. However,
dependency does not need to be standardized
2.3. Behavior of the
The output rate of the shaper is based on two factors. The first
is the (long term) average rate of the incoming traffic.
average rate can be computed by several means. For example,
function proposed in [Stoica] can be used (i.e. EARnew = [(1-exp(-
T/K))*L/T] + exp(-T/K)*EARold where EARold is the previous value
the Estimated Average Rate, EARnew is the updated value, K
constant, L the size of the arriving packet and T the amount of
since the arrival of the previous packet). Other averaging
can be used as well
The second factor is the instantaneous occupancy of the FIFO
of the shaper. When the buffer occupancy is below CIR_th, the
rate of the shaper is set to the maximum of the estimated
rate (EAR(t)) and the CIR. This ensures that the shaper buffer
be emptied at least at a rate equal to CIR. When the
occupancy increases above CIR_th, the output rate of the shaper
computed as the maximum of the EAR(t) and a linear function F of
buffer occupancy for which F(CIR_th)=CIR and F(MIR_th)=MIR. When
buffer occupancy reaches the MIR_th threshold, the output rate of
shaper is set to the maximum information rate. The computation
the shaping rate is illustrated in figure 2. We expect that
implementations will only use an approximate function to compute
shaping rate
Bonaventure & De Cnodder Informational [Page 4]
RFC 2963 A Rate Adaptive Shaper October 2000
^
Shaping rate |
|
|
MIR | =========
| //
| //
EAR(t) |----------------//
| //
| //
CIR |============
|
|
|
|------------+---------+----------------------->
CIR_th MIR_th Buffer
Figure 2. Computation of shaping rate for
2.4. Configuration of the
The trRAS is configured by specifying six parameters: the
Information Rate (CIR), the Peak Information Rate (PIR), the
Information Rate (MIR) and three buffer thresholds: CIR_th, PIR_
and MIR_th. The CIR shall be specified in bytes per second and
be configurable. To achieve a good performance, the CIR of a
will usually be set at the same value as the CIR of the
trTCM. The PIR shall be specified in the same unit as the CIR
MUST be configurable. To achieve a good performance, the PIR of
trRAS will usually be set at the same value as the PIR of
downstream trRAS. The MIR SHOULD be configurable and shall
specified in the same unit as the CIR. A typical value for the
will be the line rate of the output link of the shaper. When
values for CIR, PIR and optionally MIR are configured, the trRAS
ensure that the following relation is verified
CIR <= PIR <= MIR <= line
The three buffer thresholds, CIR_th, PIR_th and MIR_th shall
specified in bytes and SHOULD be configurable. If these
are configured, then the trRAS MUST ensure that the
relation is verified
CIR_th <= PIR_th <= MIR_th <= buffer size of the
The CIR_th, PIR_th and MIR_th will usually depend on the
chosen for the CBS and the PBS in the downstream trTCM. However
this dependency does not need to be standardized
Bonaventure & De Cnodder Informational [Page 5]
RFC 2963 A Rate Adaptive Shaper October 2000
2.5. Behavior of the
The output rate of the trRAS is based on two factors. The first
the (long term) average rate of the incoming traffic. This
rate can be computed as for the srRAS
The second factor is the instantaneous occupancy of the FIFO
of the shaper. When the buffer occupancy is below CIR_th, the
rate of the shaper is set to the maximum of the estimated
rate (EAR(t)) and the CIR. This ensures that the shaper will
send traffic at least at the CIR. When the buffer
increases above CIR_th, the output rate of the shaper is computed
the maximum of the EAR(t) and a piecewise linear function F of
buffer occupancy. This piecewise function can be defined as follows
The first piece is between zero and CIR_th where F is equal to CIR
This means that when the buffer occupancy is below a
threshold CIR_th, the shaping rate is at least CIR. The second
is between CIR_th and PIR_th where F increases linearly from CIR
PIR. The third part is from PIR_th to MIR_th where F
linearly from PIR to the MIR and finally when the buffer occupancy
above MIR_th, the shaping rate remains constant at the MIR.
computation of the shaping rate is illustrated in figure 3.
expect that real implementations will use an approximation of
function shown in this figure to compute the shaping rate
^
Shaping rate |
|
MIR | ======
| ///
| ///
PIR | ///
| //
| //
EAR(t) |----------------//
| //
| //
CIR |============
|
|
|
|------------+---------+--------+-------------------->
CIR_th PIR_th MIR_th Buffer
Figure 3. Computation of shaping rate for
Bonaventure & De Cnodder Informational [Page 6]
RFC 2963 A Rate Adaptive Shaper October 2000
3. Description of the green RAS
3.1. The green rate adaptive
The srRAS and the trRAS described in the previous section are
aware of the status of the meter. This entails that a RAS
unnecessarily delay a packet although there are sufficient
available to color the packet green. This delay could mean that
takes more time to increase its congestion window and this may
the performance with TCP traffic. The green RAS shown in figure 4
solves this problem by coupling the shaper with the meter
Status
+----------+ +----------+
| | | |
V | |
+--------+ +-------+ +--------+
Incoming | green | | | | |
Packet ==>| RAS |==>| Meter |==>| Marker |==>
Stream | | | | | |
+--------+ +-------+ +--------+
Figure 4. green
The two rate adaptive shapers described in section 2 calculate
shaping rate, which is defined as the maximum of the
average incoming data rate and some function of the buffer occupancy
Using this shaping rate, the RAS computes the time schedule at
the packet at the head of the queue of the shaper is to be released
The main idea of the green RAS is to couple the shaper with
downstream meter so that the green RAS knows at what time the
at the head of its queue would be accepted as green by the meter.
this time instant is earlier than the release time computed from
current shaping rate, then the packet can be released at this
instant. Otherwise, the packet at the head of the queue of the
RAS will be released at the time instant calculated from the
shaping rate
3.2. Configuration of the Green single rate Rate Adaptive
(GsrRAS
The G-srRAS must be configured in the same way as the srRAS (
section 2.2).
Bonaventure & De Cnodder Informational [Page 7]
RFC 2963 A Rate Adaptive Shaper October 2000
3.3. Behavior of the G-
First of all, the shaping rate of the G-srRAS is calculated in
same way as for the srRAS. With the srRAS, this shaping
determines a time schedule, T1, at which the packet at the head
the queue is to be released from the shaper
A second time schedule, T2, is calculated as the earliest
instant at which the packet at the head of the shaper's queue
be colored as green by the downstream srTCM. Suppose that a
of size B bytes is at the head of the shaper and that CIR is
Committed Information Rate of the srTCM in bytes per second. If
denote the current time by t and by Tc(t) the amount of green
in the token bucket of the srTCM at time t, then T2 is equal
max(t, t+(B-Tc(t))/CIR). If B is larger than CBS, the
Burst Size of the srTCM, then T2 is set to infinity
When a packet arrives at the head of the queue of the shaper, it
leave this queue not sooner than min(T1, T2) from the shaper
3.4 Configuration of the Green two rates Rate Adaptive Shaper (G-trRAS
The G-trRAS must be configured in the same way as the trRAS (
section 2.4).
3.5. Behavior of the G-
First of all, the shaping rate of the G-trRAS is calculated in
same way as for the trRAS. With the trRAS, this shaping
determines a time schedule, T1, at which the packet at the head
the queue is to be released from the shaper
A second time schedule, T2, is calculated as the earliest
instant at which the packet at the head of the shaper's queue
be colored as green by the downstream trTCM. Suppose that a
of size B bytes is at the head of the shaper and that CIR is
Committed Information Rate of the srTCM in bytes per second. If
denote the current time by t and by Tc(t) (resp. Tp(t)) the amount
green (resp. yellow) tokens in the token bucket of the trTCM at
t, then T2 is equal to max(t, t+(B-Tc(t))/CIR,t+(B-Tp(t))/PIR). If
is larger than CBS, the committed burst size, or PBS, the peak
size, of the srTCM, then T2 is set to infinity
When a packet arrives at the head of the queue of the shaper, it
leave this queue not sooner than min(T1, T2) from the shaper
Bonaventure & De Cnodder Informational [Page 8]
RFC 2963 A Rate Adaptive Shaper October 2000
4.
The shapers discussed in this document assume that the
traffic is dominated by protocols such as TCP that
appropriately to congestion by decreasing their transmission rate
The proposed shapers do not provide a performance gain if the
is composed of protocols that do not react to congestion
decreasing their transmission rate
5. Example
The shapers discussed in this document can be used where the
proposed in [RFC2697] and [RFC2698] are used. In fact,
briefly discussed in Appendix A show that the performance of TCP
be improved when a rate adaptive shaper is used upstream of a TCM
We expect such rate adaptive shapers to be particularly useful at
edge of the network, for example inside (small) access routers
even network adapters
6. The rate adaptive shaper combined with other
This document explains how the idea of a rate adaptive shaper can
combined with the srTCM and the trTCM. This resulted in the
and the G-srRAS for the srTCM and in the trRAS and the G-trRAS
the trTCM. Similar adaptive shapers could be developed to
other traffic markers such as the Time Sliding Window Three
Marker (TSWTCM) [Fang]. However, the exact definition of such
adaptive shapers and their performance is outside the scope of
document
7. Security
The shapers described in this document have no known
concerns
8. Intellectual Property
The IETF has been notified of intellectual property rights claimed
regard to some or all of the specification contained in
document. For more information consult the online list of
rights
9.
We would like to thank Emmanuel Desmet for his comments
Bonaventure & De Cnodder Informational [Page 9]
RFC 2963 A Rate Adaptive Shaper October 2000
10.
[Azeem] Azeem, F., Rao, A., Lu, X. and S. Kalyanaraman, "TCP
Friendly Traffic Conditioners for
Services", Work in Progress
[RFC2475] Blake S., Black, D., Carlson, M., Davies, E., Wang, Z
and W. Weiss, "An Architecture for
Services", RFC 2475, December 1998.
[Bonaventure] Bonaventure O., "Integration of ATM under TCP/IP
provide services with a minimum guaranteed bandwidth",
Ph. D. thesis, University of Liege, Belgium,
1998.
[Clark] Clark D. and Fang, W., "Explicit Allocation of Best
Effort Packet Delivery Service", IEEE/ACM Trans.
Networking, Vol. 6, No. 4, August 1998.
[Cnodder] De Cnodder S., "Rate Adaptive Shapers for Data
in DiffServ Networks", NetWorld+Interop 2000
Conference, Las Vegas, Nevada, USA, May 10-11, 2000.
[Fang] Fang W., Seddigh N. and B. Nandy, "A Time
Window Three Colour Marker (TSWTCM)", RFC 2859,
2000.
[Floyd] Floyd S. and V. Jacobson, "Random Early
Gateways for Congestion Avoidance", IEEE/
Transactions on Networking, August 1993.
[RFC2697] Heinanen J. and R. Guerin, "A Single Rate Three
Marker", RFC 2697, September 1999.
[RFC2698] Heinanen J. and R. Guerin, "A Two Rate Three
Marker", RFC 2698, September 1999.
[RFC2597] Heinanen J., Baker F., Weiss W. and J. Wroclawski
"Assured Forwarding PHB Group", RFC 2597, June 1999.
[Nichols] Nichols K. and B. Carpenter, "Format for
Working Group Traffic Conditioner Drafts", Work
Progress
Bonaventure & De Cnodder Informational [Page 10]
RFC 2963 A Rate Adaptive Shaper October 2000
[Stoica] Stoica I., Shenker S. and H. Zhang, "Core-
fair queueuing: achieving approximately fair
allocations in high speed networks", ACM SIGCOMM98, pp
118-130, Sept. 1998
[TM41] ATM Forum, Traffic Management Specification,
4.1, 1999
Bonaventure & De Cnodder Informational [Page 11]
RFC 2963 A Rate Adaptive Shaper October 2000
A. Simulation
We briefly discuss simulations showing the benefits of the
shapers in simple network environments. Additional simulation
may be found in [Cnodder].
A.1 description of the
To evaluate the rate adaptive shaper through simulations, we use
simple network model depicted in Figure A.1. In this network,
consider that a backbone network is used to provide a
Interconnection service to ten pairs of LANs. Each LAN
to an uncongested switched 10 Mbps LAN with ten workstations
to a customer router (C1-C10 in figure A.1). The delay on the
links is set to 1 msec. The MSS size of the workstations is set
1460 bytes. The workstations on the left hand side of the
send traffic to companion workstations located on the right hand
of the figure. All traffic from the LAN attached to customer
C1 is sent to the LAN attached to customer router C1'. There are
workstations on each LAN and each workstation implements SACK-
with a maximum window size of 64 KBytes
Bonaventure & De Cnodder Informational [Page 12]
RFC 2963 A Rate Adaptive Shaper October 2000
2.5 msec, 34 Mbps 2.5 msec, 34
<--------------> <-------------->
\+---+ +---+/
-| C1|--------------+ +--------------|C1'|-
/+---+ | | +---+\
\+---+ | | +---+/
-| C2|------------+ | | +------------|C2'|-
/+---+ | | | | +---+\
\+---+ | | | | +---+/
-| C3|----------+ | | | | +----------|C3'|-
/+---+ | | | | | | +---+\
\+---+ | | | | | | +---+/
-| C4|--------+ +-+----------+ +----------+-+ +--------|C4'|-
/+---+ | | | | | | +---+\
\+---+ +---| | | |---+ +---+/
-| C5|------------| ER1 |-----| ER2 |------------|C5'|-
/+---+ +---| | | |---+ +---+\
\+---+ | | | | | | +---+/
-| C6|--------+ +----------+ +----------+ +--------|C6'|-
/+---+ |||| |||| +---+\
\+---+ |||| <-------> |||| +---+/
-| C7|------------+||| 70 Mbps |||+------------|C7'|-
/+---+ ||| 10 msec ||| +---+\
\+---+ ||| ||| +---+/
-| C8|-------------+|| ||+-------------|C8'|-
/+---+ || || +---+\
\+---+ || || +---+/
-| C9|--------------+| |+--------------|C9'|-
/+---+ | | +---+\
\+---+ | | +----+/
-|C10|---------------+ +---------------|C10'|-
/+---+ +----+\
Figure A.1. the simulation model
The customer routers are connected with 34 Mbps links to the
network which is, in our case, composed of a single bottleneck 70
Mbps link between the edge routers ER1 and ER2. The delay on all
customer-edge 34 Mbps links has been set to 2.5 msec to model a
or small WAN environment. These links and the customer routers
not a bottleneck in our environment and no losses occurs inside
edge routers. The customer routers are equipped with a
[Heinanen2] and mark the incoming traffic. The parameters of
trTCM are shown in table A.1.
Bonaventure & De Cnodder Informational [Page 13]
RFC 2963 A Rate Adaptive Shaper October 2000
Table A.1: configurations of the
Router CIR PIR Line
C1 2 Mbps 4 Mbps 34
C2 4 Mbps 8 Mbps 34
C3 6 Mbps 12 Mbps 34
C4 8 Mbps 16 Mbps 34
C5 10 Mbps 20 Mbps 34
C6 2 Mbps 4 Mbps 34
C7 4 Mbps 8 Mbps 34
C8 6 Mbps 12 Mbps 34
C9 8 Mbps 16 Mbps 34
C10 10 Mbps 20 Mbps 34
All customer routers are equipped with a trTCM where the CIR are 2
Mbps for router C1 and C6, 4 Mbps for C2 and C7, 6 Mbps for C3
C8, 8 Mbps for C4 and C9 and 10 Mbps for C5 and C10. Routers C6-C10
also contain a trRAS in addition to the trTCM while routers C1-C
only contain a trTCM. In all simulations, the PIR is always twice
large as the CIR. Also the PBS is the double of the CBS. The
will be varied in the different simulation runs
The edge routers, ER1 and ER2, are connected with a 70 Mbps
which is the bottleneck link in our environment. These two
implement the RIO algorithm [Clark] that we have extended to
three drop priorities instead of two. The thresholds of
parameters are 100 and 200 packets (minimum and maximum threshold
respectively) for the red packets, 200 and 400 packets for the
packets and 400 and 800 for the green packets. These thresholds
reasonable since there are 100 TCP connections crossing each
router. The parameter maxp of RIO for green, yellow and red
respectively set to 0.02, 0.05, and 0.1. The weight to calculate
average queue length which is used by RED or RIO is set to 0.002
[Floyd].
The simulated time is set to 102 seconds where the first two
are not used to gather TCP statistics (the so-called warm-up time
such as goodput
A.2 Simulation results for the
For our first simulations, we consider that routers C1-C5
utilize a trTCM while routers C6-C10 utilize a rate adaptive
in conjunction with a trTCM. All routers use a CBS of 3 KBytes.
table A.2, we show the total throughput achieved by the
attached to each LAN as well as the total throughput for the
and the yellow packets as a function of the CIR of the trTCM used
the customer router attached to this LAN. The throughput of the
Bonaventure & De Cnodder Informational [Page 14]
RFC 2963 A Rate Adaptive Shaper October 2000
packets is equal to the difference between the total traffic and
green and the yellow traffic. In table A.3, we show the
throughput achieved by the workstations attached to customer
with a rate adaptive shaper
Table A.2: throughput in Mbps for the unshaped traffic
green yellow
2Mbps [C1] 1.10 0.93 2.25
4Mbps [C2] 2.57 1.80 4.55
6Mbps [C3] 4.10 2.12 6.39
8Mbps [C4] 5.88 2.32 8.33
10Mbps [C5] 7.57 2.37 10.0
Table A.3: throughput in Mbps for the adaptively
traffic
green yellow
2Mbps [C6] 2.00 1.69 3.71
4Mbps [C7] 3.97 2.34 6.33
6Mbps [C8] 5.93 2.23 8.17
8Mbps [C9] 7.84 2.28 10.1
10Mbps [C10] 9.77 2.14 11.9
This first simulation shows clearly that the workstations attached
an edge router with a rate adaptive shaper have a clear advantage
from a performance point of view, with respect to
attached to an edge router with only a trTCM. The
improvement is the result of the higher proportion of packets
as green by the edge routers when the rate adaptive shaper is used
To evaluate the impact of the CBS on the TCP goodput, we
additional simulations were we varied the CBS of all
routers
Table A.4 shows the total goodput for workstations attached to
respectively, routers C1 (trTCM with 2 Mbps CIR, no
shaping), C6 (trRAS with 2 Mbps CIR and adaptive shaping), C3 (
with 6 Mbps CIR, no adaptive shaping), and C8 (trRAS with 6 Mbps
and adaptive shaping) for various values of the CBS. From
table, it is clear that the rate adaptive shapers provide
performance benefit when the CBS is small. With a very large CBS
the performance decreases when the shaper is in use. However, a
of a few hundred KBytes is probably too large in many environments
Bonaventure & De Cnodder Informational [Page 15]
RFC 2963 A Rate Adaptive Shaper October 2000
Table A.4: goodput in Mbps (link rate is 70 Mbps) versus
in KBytes
CBS 2_Mbps_unsh 2_Mbps_sh 6_Mbps_unsh 6_Mbps_
3 1.88 3.49 5.91 7.77
10 2.97 2.91 6.76 7.08
25 3.14 2.78 7.07 6.73
50 3.12 2.67 7.20 6.64
75 3.18 2.56 7.08 6.58
100 3.20 2.64 7.00 6.62
150 3.21 2.54 7.11 6.52
200 3.26 2.57 7.07 6.53
300 3.19 2.53 7.13 6.49
400 3.13 2.48 7.18 6.43
A.3 Simulation results for the Green
We use the same scenario as in A.2 but now we use the Green
(G-trRAS).
Table A.5 and Table A.6 show the results of the same scenario as
Table A.2 and Table A.3 but the shaper is now the G-trRAS. We
that the shaped traffic performs again much better, also compared
the previous case (i.e. where the trRAS was used). This is
the amount of yellow traffic increases with the expense of a
decrease in the amount of green traffic. This can be explained
the fact that the G-trRAS introduces some burstiness
Table A.5: throughput in Mbps for the unshaped traffic
green yellow
2Mbps [C1] 1.10 0.95 2.26
4Mbps [C2] 2.41 1.66 4.24
6Mbps [C3] 3.94 1.97 6.07
8Mbps [C4] 5.72 2.13 7.96
10Mbps [C5] 7.25 2.29 9.64
Table A.6: throughput in Mbps for the adaptively
traffic
green yellow
2Mbps [C6] 1.92 1.75 3.77
4Mbps [C7] 3.79 3.24 7.05
6Mbps [C8] 5.35 3.62 8.97
8Mbps [C9] 6.96 3.48 10.4
10Mbps [C10] 8.69 3.06 11.7
The impact of the CBS is shown in Table A.7 which is the
scenario as Table A.4 with the only difference that the shaper is
the G-trRAS. We see that the shaped traffic performs much
than the unshaped traffic when the CBS is small. When the CBS
Bonaventure & De Cnodder Informational [Page 16]
RFC 2963 A Rate Adaptive Shaper October 2000
large, the shaped and unshaped traffic performs more or less
same. This is in contrast with the trRAS, where the performance
the shaped traffic was slightly worse in case of a large CBS
Table A.7: goodput in Mbps (link rate is 70 Mbps) versus
in KBytes
CBS 2_Mbps_unsh 2_Mbps_sh 6_Mbps_unsh 6_Mbps_
3 1.90 3.44 5.62 8.44
10 2.95 3.30 6.70 7.20
25 2.98 3.01 7.03 6.93
50 3.06 2.85 6.81 6.84
75 3.08 2.80 6.87 6.96
100 2.99 2.78 6.85 6.88
150 2.98 2.70 6.80 6.81
200 2.96 2.70 6.82 6.97
300 2.94 2.70 6.83 6.86
400 2.86 2.62 6.83 6.84
A.4 Conclusion
From these simulations, we see that the shaped traffic has
higher throughput compared to the unshaped traffic when the CBS
small. When the CBS is large, the shaped traffic performs
less than the unshaped traffic due to the delay in the shaper.
G-trRAS solves this problem. Additional simulation results may
found in [Cnodder
Bonaventure & De Cnodder Informational [Page 17]
RFC 2963 A Rate Adaptive Shaper October 2000
Authors'
Olivier
Infonet research
Institut d'Informatique (CS Dept
Facultes Universitaires Notre-Dame de la
Rue Grandgagnage 21, B-5000 Namur, Belgium
EMail: Olivier.Bonaventure@info.fundp.ac.
URL: http://www.infonet.fundp.ac.
Stefaan De
Alcatel Network Strategy
Fr. Wellesplein 1, B-2018 Antwerpen, Belgium
Phone: 32-3-240-8515
Fax: 32-3-240-9932
EMail: stefaan.de_cnodder@alcatel.
Bonaventure & De Cnodder Informational [Page 18]
RFC 2963 A Rate Adaptive Shaper October 2000
Full Copyright
Copyright (C) The Internet Society (2000). All Rights Reserved
This document and translations of it may be copied and furnished
others, and derivative works that comment on or otherwise explain
or assist in its implementation may be prepared, copied,
and distributed, in whole or in part, without restriction of
kind, provided that the above copyright notice and this paragraph
included on all such copies and derivative works. However,
document itself may not be modified in any way, such as by
the copyright notice or references to the Internet Society or
Internet organizations, except as needed for the purpose
developing Internet standards in which case the procedures
copyrights defined in the Internet Standards process must
followed, or as required to translate it into languages other
English
The limited permissions granted above are perpetual and will not
revoked by the Internet Society or its successors or assigns
This document and the information contained herein is provided on
"AS IS" basis and THE INTERNET SOCIETY AND THE INTERNET
TASK FORCE DISCLAIMS ALL WARRANTIES, EXPRESS OR IMPLIED,
BUT NOT LIMITED TO ANY WARRANTY THAT THE USE OF THE
HEREIN WILL NOT INFRINGE ANY RIGHTS OR ANY IMPLIED WARRANTIES
MERCHANTABILITY OR FITNESS FOR A PARTICULAR PURPOSE
Funding for the RFC Editor function is currently provided by
Internet Society
Bonaventure & De Cnodder Informational [Page 19]
if you see any problems within the linking, don't worry be happy,
this is version 0.1 of the Relevance System and you gotta expect some crappy subroutines sometimes,
just be content we did not write this in Java, which would have made this "bigger and better" HAHAHHA.
RFC documents can be found at I.E.T.F.
Relevance System Copyright © 2002 Spectrum WorldResearch
other technical nosh by ServerMasters Corporation
collaboration of BobX
