One document matched: draft-ietf-intserv-ctrl-load-svc-02.txt
Differences from draft-ietf-intserv-ctrl-load-svc-01.txt
Internet Engineering Task Force Integrated Services WG
INTERNET-DRAFT J. Wroclawski
draft-ietf-intserv-ctrl-load-svc-02.txt MIT LCS
June, 1996
Expires: 12/96
Specification of the Controlled-Load Network Element Service
Status of this Memo
This document is an Internet-Draft. Internet-Drafts are working
documents of the Internet Engineering Task Force (IETF), its areas,
and its working groups. Note that other groups may also distribute
working documents as Internet-Drafts.
Internet-Drafts are draft documents valid for a maximum of six months
and may be updated, replaced, or obsoleted by other documents at any
time. It is inappropriate to use Internet-Drafts as reference
material or to cite them other than as "work in progress".
To learn the current status of any Internet-Draft, please check the
"1id-abstracts.txt" listing contained in the Internet- Drafts Shadow
Directories on ftp.is.co.za (Africa), nic.nordu.net (Europe),
munnari.oz.au (Pacific Rim), ds.internic.net (US East Coast), or
ftp.isi.edu (US West Coast).
This draft is a product of the Integrated Services Working Group of
the Internet Engineering Task Force. Comments are solicited and
should be addressed to the working group's mailing list at int-
serv@isi.edu and/or the author(s).
Abstract
This memo specifies the network element behavior required to
deliver Controlled-Load service in the Internet. Controlled-load
service provides the client data flow with a quality of service
closely approximating the QoS that same flow would receive from an
unloaded network element, but uses capacity (admission) control to
assure that this service is received even when the network element
is overloaded.
J. Wroclawski Expires 12/96 [Page 1]
INTERNET-DRAFT draft-ietf-intserv-ctrl-load-svc-02.txt June, 1996
1. Introduction
This document defines the requirements for network elements that
support the Controlled-Load service. This memo is one of a series of
documents that specify the network element behavior required to
support various qualities of service in IP internetworks. Services
described in these documents are useful both in the global Internet
and private IP networks.
This document is based on the service specification template given in
[1]. Please refer to that document for definitions and additional
information about the specification of qualities of service within
the IP protocol family.
2. End-to-End Behavior
The end-to-end behavior provided to an application by a series of
network elements providing controlled-load service tightly
approximates the behavior visible to applications receiving best-
effort service *under unloaded conditions* from the same series of
network elements. Assuming the network is functioning correctly,
these applications may assume that:
- A very high percentage of transmitted packets will be
successfully delivered by the network to the receiving end-nodes.
(The percentage of packets not successfully delivered must closely
approximate the basic packet error rate of the transmission
medium).
- The transit delay experienced by a very high percentage of the
delivered packets will not greatly exceed the minimum transmit
delay experienced by any successfully delivered packet. (This
minimum transit delay includes speed-of-light delay plus the fixed
processing time in routers and other communications devices along
the path.)
To ensure that these conditions are met, clients requesting
controlled-load service provide the intermediate network elements
with a estimation of the data traffic they will generate; the TSpec.
In return, the service ensures that network element resources
adequate to process traffic falling within this descriptive envelope
will be available to the client. Should the client's traffic
generation properties fall outside of the region described by the
TSpec parameters, the QoS provided to the client may exhibit
characteristics indicative of overload, including large numbers of
delayed or dropped packets. The service definition does not require
that the precise characteristics of this overload behavior match
those which would be received by a best-effort data flow traversing
J. Wroclawski Expires 12/96 [Page 2]
INTERNET-DRAFT draft-ietf-intserv-ctrl-load-svc-02.txt June, 1996
the same path under overloaded conditions.
NOTE: In this memo, the term "unloaded" is used in the sense of
"not heavily loaded or congested" rather than in the sense of "no
other network traffic whatsoever".
3. Motivation
The controlled load service is intended to support a broad class of
applications which have been developed for use in today's Internet,
but are highly sensitive to overloaded conditions. Important members
of this class are the "adaptive real-time applications" currently
offered by a number of vendors and researchers. These applications
have been shown to work well on unloaded nets, but to degrade quickly
under overloaded conditions. A service which mimics unloaded nets
serves these applications well.
The controlled-load service is intentionally minimal, in that there
are no optional functions or capabilities in the specification. The
service offers only a single function, and system and application
designers can assume that all implementations will be identical in
this respect.
Internally, the controlled-load service is suited to a wide range of
implementation techniques, including evolving scheduling and
admission control algorithms that allow implementations to be highly
efficient in the use of network resources. It is equally amenable to
extremely simple implementation in circumstances where maximum
utilization of network resources is not the only concern.
4. Network Element Data Handling Requirements
Each network element accepting a request for controlled-load service
must ensure that adequate bandwidth and packet processing resources
are available to handle the requested level of traffic, as given by
the requestor's TSpec. This must be accomplished through active
admission control. All resources important to the operation of the
network element must be considered when admitting a request. Common
examples of such resources include link bandwidth, router or switch
port buffer space, and computational capacity of the packet
forwarding engine.
The controlled-load service does not accept or make use of specific
target values for control parameters such as delay or loss. Instead,
acceptance of a request for controlled-load service is defined to
imply a commitment by the network element to provide the requestor
with service closely equivalent to that provided to uncontrolled
(best-effort) traffic under lightly loaded conditions.
J. Wroclawski Expires 12/96 [Page 3]
INTERNET-DRAFT draft-ietf-intserv-ctrl-load-svc-02.txt June, 1996
The definition of "closely equivalent to unloaded best-effort
service" is necessarily imprecise. It is easiest to define this
quality of service by describing the events which are expected to
*not* occur with any frequency. A flow receiving controlled-load
service at a network element may expect to experience:
- Little or no average packet queueing delay over all timescales
significantly larger than the "burst time". The burst time is
defined as the time required for the flow's maximum size data burst
to be transmitted at the flow's requested transmission rate, where
the burst size and rate are given by the flow's TSpec, as described
below.
- Little or no congestion loss over all timescales significantly
larger than the "burst time" defined above. In this context,
congestion loss includes packet losses due to shortage of any
required processing resource, such as buffer space or link
bandwidth. Although occasional congestion losses may occur, any
substantial sustained loss represents a failure of the admission
control algorithm.
The basic effect of this language is to establish an expectation on
the *duration* of a disruption in delivery service. Events of shorter
duration are viewed as statistical effects which may occur in normal
operation. Events of longer duration are indicative of failure to
allocate adequate capacity to the controlled-load flow.
A network element may employ statistical approaches to decide whether
adequate capacity is available to accept a service request. For
example, a network element processing a number of flows with long-
term characteristics predicted through measurement of past behavior
may be able to overallocate its resources to some extent without
reducing the level of service delivered to the flows.
A network element may employ any appropriate scheduling means to
ensure that admitted flows receive appropriate service.
NOTE: The flexibility implied by the above paragraph exists within
definite limits. Readers should observe that the specification's
requirement that the delay and loss behavior described above
imposes concrete requirements on implementations.
Perhaps the most important requirement is that the implementation
has to make bandwidth greater than the Tspec token rate available
to the flow in certain situations. The requirement for the
availability of extra bandwidth may be derived from the fluid
model of traffic scheduling (e.g. [7]). If a flow receives exactly
its promised token rate at all times, queueing caused by an over-
J. Wroclawski Expires 12/96 [Page 4]
INTERNET-DRAFT draft-ietf-intserv-ctrl-load-svc-02.txt June, 1996
rate burst arriving at the network element may never clear,
causing the traffic queueing delay to permanantly increase. This
will happen if the flow continues to generate traffic at exactly
the token rate after emitting the burst.
To control the long-term effects of traffic bursts, a Controlled
Load implementation has several options. At minimum, a mechanism
must be present to "borrow" bandwidth needed to clear bursts from
the network. There are a number of ways to implement such a
mechanism, ranging from explicit borrowing schemes within the
traffic scheduler to implicit schemes based on statistical
multiplexing and measurement-based admission control. The
specification does not prefer any method over any other, but does
require that some such mechanism must exist.
Similarly, the requirement for low congestion loss for in-Tspec
traffic implies that buffer management must have some flexibility.
Because the controlled-load service does not reshape traffic to
its token-bucket parameters at every node, traffic flowing through
the network will be distorted as it traverses queueing points.
This distortion is particularly likely to occur during traffic
bursts, precisely when buffering is most heavily used. In these
circumstances, rigidly restricting the buffering capacity to a
size equal to the flow's TSpec burst size may lead to congestion
loss. An implementaton should be prepared to make additional
buffering available to bursting flows. Again, this may be
accomplished in a number of ways. One obvious choice is
statistical multiplexing of a shared buffer pool.
Links are not permitted to fragment packets which receive the
controlled-load service. Packets larger than the MTU of the link must
be treated as nonconformant to the TSpec. This implies that they will
be forwarded according to the rules described in the Policing section
below.
Implementations of controlled-load service are not required to
provide any control of short-term packet delay jitter beyond that
described above. However, the use of packet scheduling algorithms
that provide additional jitter control is not prohibited by this
specification.
Packet losses due to non-congestion-related causes, such as link
errors, are not bounded by this service.
5. Invocation Information
The controlled-load service is invoked by specifying the data flow's
desired traffic parameters (TSpec) to the network element. Requests
J. Wroclawski Expires 12/96 [Page 5]
INTERNET-DRAFT draft-ietf-intserv-ctrl-load-svc-02.txt June, 1996
placed for a new flow will be accepted if the network element has the
capacity to forward the flow's packets as described above. Requests
to change the TSpec for an existing flow should be treated as a new
invocation, in the sense that admission control must be reapplied to
the flow. Requests that reduce the TSpec for an existing flow (in the
sense that the new TSpec is strictly smaller than the old TSpec
according to the ordering rules given below) should never be denied
service.
The TSpec takes the form of a token bucket specification plus a
minimum policed unit (m) and a maximum packet size (M).
The token bucket specification includes a bucket rate r and a bucket
depth, b. Both r and b must be positive. The rate, r, is measured
in bytes of IP datagrams per second. Values of this parameter may
range from 1 byte per second to 40 terabytes per second. Network
elements MUST return an error for requests containing values outside
this range. Network elements MUST return an error for any request
containing a value within this range which cannot be supported by the
element. In practice, only the first few digits of the r parameter
are significant, so the use of floating point representations,
accurate to at least 0.1% is encouraged.
The bucket depth, b, is measured in bytes. Values of this parameter
may range from 1 byte to 250 gigabytes. Network elements MUST return
an error for requests containing values outside this range. Network
elements MUST return an error for any request containing a value
within this range which cannot be supported by the element. In
practice, only the first few digits of the b parameter are
significant, so the use of floating point representations, accurate
to at least 0.1% is encouraged.
The range of values allowed for these parameters is intentionally
large to allow for future network technologies. Any given network
element is not expected to support the full range of values.
The minimum policed unit, m, is an integer measured in bytes. All IP
datagrams less than size m will be counted against the token bucket
as being of size m. The maximum packet size, M, is the biggest packet
that will conform to the traffic specification; it is also measured
in bytes. Network elements MUST reject a service request if the
requested maximum packet size is larger than the MTU of the link.
Both m and M must be positive, and m must be less then or equal to M.
The preferred concrete representation for the TSpec is two floating
point numbers in single-precision IEEE floating point format followed
by two 32-bit integers in network byte order. The first value is the
rate (r), the second value is the bucket size (b), the third is the
J. Wroclawski Expires 12/96 [Page 6]
INTERNET-DRAFT draft-ietf-intserv-ctrl-load-svc-02.txt June, 1996
minimum policed unit (m), and the fourth is the maximum packet size
(M). For the parameters (r) and (b), only bit-patterns which
represent valid non-negative floating point numbers are allowed.
Negative numbers (including "negative zero), infinities, and NAN's
are not allowed.
NOTE: An implementation which utilizes general-purpose hardware or
software IEEE floating-point support may wish to verify that
arriving parameters meet this requirement before using the
parameters in floating-point computations, in order to avoid
unexpected exceptions or traps.
The controlled-load service is assigned service_name 5.
The controlled-load traffic specification parameter (TSpec) is
assigned parameter_name 1, as indicated in the listing of well-known
parameter name assignments given in [1].
6. Exported Information
The controlled-load service has no required characterization
parameters. Individual implementations may export appropriate
implementation-specific measurement and monitoring information.
7. Policing
The controlled-load service is provided to a flow on the basis that
the flow's traffic conforms to a TSpec given at flow setup time. This
section defines the meaning of conformance to the controlled-load
TSpec, describes the circumstances under which a controlled-load
flow's traffic might *not* conform to the TSpec, and specifies the
network element's action in those circumstances.
Controlled-load service modules provide QoS control for traffic
conforming to the TSpec given at setup time. The TSpec's token
bucket parameters require that traffic must obey the rule that over
all time periods, the amount of data sent does not exceed rT+b, where
r and b are the token bucket parameters and T is the length of the
time period. For the purposes of this accounting, links must count
packets that are smaller than the minimal policing unit m to be of
size m. Packets that arrive at an element and cause a violation of
the the rT+b bound are considered nonconformant.
Additionally, packets bigger than the outgoing link MTU are
considered nonconformant. It is expected that this situation will
not arise with any frequency, because flow setup mechanisms are
expected to notify the sending application of the appropriate path
MTU.
J. Wroclawski Expires 12/96 [Page 7]
INTERNET-DRAFT draft-ietf-intserv-ctrl-load-svc-02.txt June, 1996
In the presence of nonconformant packets arriving for one or more
controlled-load flows, each network element must ensure locally that
the following requirements are met:
1) The network element MUST continue to provide the contracted
quality of service to those controlled-load flows not experiencing
excess traffic.
2) The network element SHOULD prevent excess controlled-load
traffic from unfairly impacting the handling of arriving best-
effort traffic. This requirement is discussed further in Section 9
of this document (Guidelines for Implementors).
3) Consistent with points 1 and 2, the network element MUST attempt
to forward the excess traffic on a best-effort basis if sufficient
resources are available.
Network elements must not assume that that arrival of nonconformant
traffic for a specific controlled-load flow will be unusual, or
indicative of error. In certain circumstances (particularly, routers
acting as the "split points" of a multicast distribution tree
supporting a shared reservation) large numbers of packets will fail
the conformance test *as a matter of normal operation*.
Network elements must not assume that data sources or upstream
elements have taken action to "police" controlled-load flows by
limiting their traffic to conform to the flow's TSpec. Each network
element providing controlled-load service MUST independently ensure
that the requirements given above are met in the presence of
nonconformant arriving traffic for one or more controlled-load flows.
Network elements may use any appropriate implementation mechanism to
meet the requirements given above. Examples of such mechanisms
include token-bucket policing filters and per-flow scheduling
algorithms. However, it is insufficient to simply place all
controlled-load flows into the same shared resource pool, without
first ensuring that non-conformant flows are prevented from starving
conformant flows of the necessary processing resources.
Further discussion of this issue may be found in Section 11 of this
note.
Beyond requirements 2 and 3 above, the controlled-load service does
not define the QoS behavior delivered to flows with non-conformant
arriving traffic. Specifically, it is permissible either to degrade
the service delivered to all of the flow's packets equally, or to
sort the flow's packets into a conformant set and a nonconformant set
and deliver different levels of service to the two sets. This point
J. Wroclawski Expires 12/96 [Page 8]
INTERNET-DRAFT draft-ietf-intserv-ctrl-load-svc-02.txt June, 1996
is discussed further in Section 9 of this note.
When resources are available, network elements at points within the
interior of the network SHOULD be prepared to accommodate packet
bursts somewhat larger than the actual TSpec. This requirement
derives from the traffic distortion effect described in Section 4. As
described there, it may be met either through explicit means or
statistical multiplexing of shared buffering resources.
To accomplish this goal, it is permissible to allow some delaying of
a packet if that delay would allow it to pass the policing function.
(In other words, to reshape the traffic). However, the overall
requirement for limiting the duration of any such traffic distortion
must be considered. The challenge is to define a viable reshaping
function.
Intuitively, a plausible approach is to allow a delay of (roughly) up
to the maximum queueing delay experienced by completely conforming
packets before declaring that a packet has failed to pass the
policing function. The merit of this approach, and the precise
wording of the specification that describes it, require further
study.
8. Ordering and Merging
The controlled-load service TSpec is ordered according to the
following rule: TSpec A is a substitute for ("as good or better
than") TSpec B if and only if
(1) both the token bucket depth and rate for TSpec A are greater
than or equal to those of TSpec B,
(2) the minimum policed unit m is at least as small for TSpec A as
it is for TSpec B, and
(3) the maximum packet size M is at least as large for TSpec A as
it is for TSpec B.
A merged TSpec may be calculated over a set of TSpecs by taking the
largest token bucket rate, largest bucket size, smallest minimal
policed unit, and largest maximum packet size across all members of
the set. This use of the word "merging" is similar to that in the
RSVP protocol; a merged TSpec is one that is adequate to describe the
traffic from any one of a number of flows.
The sum of n controlled-load service TSpecs is used when computing
the TSpec for a shared reservation of n flows. It is computed by
J. Wroclawski Expires 12/96 [Page 9]
INTERNET-DRAFT draft-ietf-intserv-ctrl-load-svc-02.txt June, 1996
taking:
- The minimum across all TSpecs of the minimum policed unit
parameter m.
- The maximum across all TSpecs of the maximum packet size
parameter M.
- The sum across all TSpecs of the token bucket rate parameter r.
- The sum across all TSpecs of the token bucket size parameter b.
The perfect minimum of two TSpecs is defined as a TSpec which would
view as compliant any traffic flow that complied with both of the
original TSpecs, but would reject any flow that was non-compliant
with at least one of the original TSpecs. This perfect minimum can be
computed only when the two original TSpecs are ordered, in the sense
described above.
A definition for computing the minimum of two unordered TSpecs is:
- The minimum of the minimum policed units m.
- The maximum of the maximum packet sizes M.
- The minimum of the token bucket rates r.
- The maximum of the token bucket sizes b.
NOTE: The proper definition the minimum TSpec function is a topic
of current discussion. The definition above is provisional and
subject to change.
9. Guidelines for Implementors
REQUIREMENTS PLACED ON ADMISSION CONTROL ALGORITHM: The intention of
this service specification is that network elements deliver a level
of service closely approximating best-effort service under unloaded
conditions. As with best-effort service under these conditions, it is
not required that every single packet must be successfully delivered
with zero queueing delay. Network elements providing controlled-load
service are permitted to oversubscribe the available resources to
some extent, in the sense that the bandwidth and buffer requirements
indicated by summing the TSpec token buckets of all controlled-load
flows may exceed the maximum capabilities of the network element.
However, this oversubscription may only be done in cases where the
element is quite sure that actual utilization is far less than the
sum of the token buckets would suggest. The most conservative
J. Wroclawski Expires 12/96 [Page 10]
INTERNET-DRAFT draft-ietf-intserv-ctrl-load-svc-02.txt June, 1996
approach, rejection of new flows whenever the addition of their
traffic would cause the strict sum of the token buckets to exceed the
capacity of the network element (including consideration of resources
needed to maintain the delay and loss characteristics specified by
the service) may be appropriate in other circumstances.
Specific issues related to this subject are discussed in the
"Evaluation Criteria" and "Examples of Implementation" sections
below.
INTERACTION WITH BEST-EFFORT TRAFFIC: Implementors of this service
should clearly understand that in certain circumstances (routers
acting as the "split points" of a multicast distribution tree
supporting a shared reservation) large numbers of a flow's packets
may fail the TSpec conformance test *as a matter of normal
operation*. According to the requirements of Section 7, these
packets should be forwarded on a best-effort basis if resources
permit.
If the network element's best-effort queueing algorithm does not
distinguish between these packets and elastic best-effort traffic
such as TCP flows, THE EXCESS CONTROLLED-LOAD PACKETS WILL "BACK OFF"
THE ELASTIC TRAFFIC AND DOMINATE THE BEST-EFFORT BANDWIDTH USAGE. The
integrated services framework does not currently address this issue.
However, several possible solutions to the problem are known [RED,
xFQ]. Network elements supporting the controlled load service should
implement some mechanism in their best-effort queueing path to
discriminate between classes of best-effort traffic and provide
elastic traffic with protection from inelastic best-effort flows.
Two basic approaches are available to meet this requirement. The
network element can maintain separate resource allocations for
different classes of best-effort traffic, so that no one class will
excessively dominate the loaded best-effort mix. Alternatively, an
element can process excess controlled-load traffic at somewhat lower
priority than elastic best-effort traffic, so as to completely avoid
the back-off effect discussed above.
If most or all controlled-load traffic arises from non-rate-adaptive
real-time applications, the use of priority mechanisms might be
desirable. If most controlled-load traffic arises from rate-adaptive
realtime or elastic applications attempting to establish a bounded
minimum level of service, the use of separate resource classes might
be preferable. However, this is not a firm guideline. In practice,
the network element designer's choice of mechanism will depend
heavily on both the goals of the design and the implementation
techniques appropriate for the designer's platform. This version of
the service specification does not specify one or the other behavior,
J. Wroclawski Expires 12/96 [Page 11]
INTERNET-DRAFT draft-ietf-intserv-ctrl-load-svc-02.txt June, 1996
but leaves the choice to the implementor.
FORWARDING BEHAVIOR IN PRESENCE OF NONCONFORMANT TRAFFIC: As
indicated in Section 7, the controlled-load service does not define
the QoS behavior delivered to flows with non-conformant arriving
traffic. It is permissible either to degrade the service delivered
to all of the flow's packets equally, or to sort the flow's packets
into a conformant set and a nonconformant set and deliver different
levels of service to the two sets.
In the first case, expected queueing delay and packet loss
probability will rise for all packets in the flow, but packet
delivery reordering will, in general, remain at low levels. This
behavior is preferable for those applications or transport protocols
which are sensitive to excessive packet reordering. A possible
example is an unmodified TCP connection, which would see reordering
as lost packets, triggering duplicate acks and hence excessive
retransmissions.
In the second case, some subset of the flow's packets will be
delivered with low loss and delay, while some other subset will be
delivered with higher loss and potentially higher delay. The delayed
packets will appear to the receiver to have been reordered in the
network, while the non-delayed packets will, on average, arrive in a
more timely fashion than if all packets were treated equally. This
might be preferable for applications which are highly time-sensitive,
such as interactive conferencing tools.
10. Evaluation Criteria
The basic requirement placed on an implementation of controlled-load
service is that, under all conditions, it provide accepted data flows
with service closely similar to the service that same flow would
receive using best-effort service under unloaded conditions.
This suggests a simple two-step evaluation strategy. Step one is to
compare the service given best-effort traffic and controlled-load
traffic under underloaded conditions.
- Measure the packet loss rate and delay characteristics of a test
flow using best-effort service and with no load on the network
element.
- Compare those measurements with measurements of the same flow
receiving controlled-load service with no load on the network
element.
Closer measurements indicate higher evaluation ratings. A
J. Wroclawski Expires 12/96 [Page 12]
INTERNET-DRAFT draft-ietf-intserv-ctrl-load-svc-02.txt June, 1996
substantial difference in the delay characteristics, such as the
smoothing which would be seen in an implementation which scheduled
the controlled-load flow using a fixed, constant-bitrate algorithm,
should result in a somewhat lower rating.
Step two is to observe the change in service received by a
controlled-load flow as the load increases.
- Increase the background traffic load on the network element,
while continuing to measuring the loss and delay characteristics of
the controlled-load flow. Characteristics which remain essentially
constant as the element is driven into overload indicate a high
evaluation rating. Minor changes in the delay distribution indicate
a somewhat lower rating. Significant increases in delay or loss
indicate a poor evaluation rating.
This simple model is not adequate to fully evaluate the performance
of controlled-load service. Three additional variables affect the
evaluation. The first is the short-term burstiness of the traffic
stream used to perform the tests outlined above. The second is the
degree of long-term change in the controlled-load traffic within the
bounds of its TSpec. (Changes in this characteristic will have great
effect on the effectiveness of certain admission control algorithms.)
The third is the ratio of controlled-load traffic to other traffic at
the network element (either best effort or other controlled
services).
The third variable should be specifically evaluated using the
following procedure.
With no controlled-load flows in place, overload the network
element with best-effort traffic (as indicated by substantial
packet loss and queueing delay).
Execute requests for controlled-load service giving TSpecs with
increasingly large rate and burst parameters. If the request is
accepted, verify that traffic matching the TSpec is in fact handled
with characteristics closely approximating the unloaded
measurements taken above.
Repeat these experiments to determine the range of traffic
parameter (rate, burst size) values successfully handled by the
network element. The useful range of each parameter must be
determined for several settings of the other parameter, to map out
a two-dimensional "region" of successfully handled TSpecs. When
compared with network elements providing similar capabilities, this
region indicates the relative ability of the elements to provide
controlled-load service under high load. A larger region indicates
J. Wroclawski Expires 12/96 [Page 13]
INTERNET-DRAFT draft-ietf-intserv-ctrl-load-svc-02.txt June, 1996
a higher evaluation rating.
11. Examples of Implementation
One possible implementation of controlled-load service is to provide
a queueing mechanism with two priority levels; a high priority one
for controlled-load and a lower priority one for best effort service.
An admission control algorithm is used to limit the amount of traffic
placed into the high-priority queue. This algorithm may be based
either on the specified characteristics of the high-priority flows
(using information provided by the TSpecs), or on the measured
characteristics of the existing high-priority flows and the TSpec of
the new request.
Another possible implementation of controlled-load service is based
on the existing capabilities of network elements which support
"traffic classes" based on mechanisms such as weighted fair queueing
or class-based queueing [6]. In this case, it is sufficient to map
data flows accepted for controlled-load service into an existing
traffic class with adequate capacity to avoid overload. This
requirement is enforced by an admission control algorithm which
considers the characteristics of the traffic class, the
characteristics of the traffic already admitted to the class, and the
TSpec of the new flow requesting service. Again, the admission
control algorithm may be based either on the TSpec-specified or the
measured characteristics of the existing traffic.
A specific case of the above approach is to employ a scheduler which
implements weighted fair queueing or similar load-management scheme,
allocating a separate scheduling queue with correctly chosen weight
to each individual controlled-load flow. In this circumstance, the
traffic scheduler also plays the role of the policing function, by
ensuring that nonconformant traffic arriving for one controlled-load
flow does not affect either other controlled-load flows or the best-
effort traffic. This elimination of mechanism is balanced by the
drawback that the approach does not benefit from any performance or
resource usage gain arising from statistical aggregation of several
flows into a single queueing class.
Admission control algorithms based on specified characteristics are
likely be appropriate when the number of flows in the high-priority
class is small, or the traffic characteristics of the flows appear
highly variable. In these situations the measured behavior of the
aggregate controlled-load traffic stream may not serve as an
effective predictor of future traffic, leading a measurement-based
admission control algorithm to produce incorrect results. Conversely,
in situations where the past behavior of the aggregate controlled-
load traffic *is* a good predictor of future behavior, a
J. Wroclawski Expires 12/96 [Page 14]
INTERNET-DRAFT draft-ietf-intserv-ctrl-load-svc-02.txt June, 1996
measurement-based admission control algorithm may allow more traffic
to be admitted to the controlled-load service class with no
degradation in performance. An implementation may choose to switch
between these two approaches depending on the nature of the traffic
stream at a given time.
A variety of techniques may be used to provide the desired isolation
between excess (nonconformant) controlled-load traffic and other
best-effort traffic. Use of a low priority queue for nonconformant
controlled-load traffic is simple, but other approaches may provide
superior service or fit better into existing architectures. Variants
of fair queueing or weighted fair queueing may be used to allocate a
percentage of the available resources to different best-effort
traffic classes. One approach would be to allocate each controlled-
load flow a a 1/N "fair share" percentage of the available best-
effort bandwidth for its excess traffic. An alternate approach would
be to provide a single WFQ resource class for all excess controlled-
load traffic. Finally, alternate mechanisms such as RED [xxx] may be
used to provide the same overall function.
12. Examples of Use
The controlled-load service may be used by any application which can
make use of best-effort service, but is best suited to those
applications which can usefully characterize their traffic
requirements. Applications based on the transport of "continuous
media" data, such as digitized audio or video, are an important
example of this class.
The controlled-load service is not isochronous and does not provide
any explicit information about transmission delay. For this reason,
applications with end-to-end timing requirements, including the
continuous-media class mentioned above, provide an application-
specific timing recovery mechanism, similar or identical to the
mechanisms required when these applications use best-effort service.
A protocol useful to applications requiring this capability is the
IETF Real-Time Transport Protocol [2].
Load-sensitive applications may choose to request controlled-load
service whenever they are run. Alternatively, these applications may
monitor their own performance and request controlled-load service
from the network only when best-effort service is not providing
acceptable performance. The first strategy provides higher assurance
that the level of quality delivered to the user will not change over
the lifetime of an application session. The second strategy provides
greated flexibility and offers cost savings in environments where
levels of service above best-effort incur a charge.
J. Wroclawski Expires 12/96 [Page 15]
INTERNET-DRAFT draft-ietf-intserv-ctrl-load-svc-02.txt June, 1996
13. Security Considerations
Security considerations are not discussed in this memo.
J. Wroclawski Expires 12/96 [Page 16]
INTERNET-DRAFT draft-ietf-intserv-ctrl-load-svc-02.txt June, 1996
Appendix 1: RSVP Messages used with Controlled-Load Service
This appendix describes the RSVP [3] protocol objects used to request
controlled load service from a series of network elements. The
formatting of these objects follows the integrated service data
object formatting rules specified in [4].
RSVP FLOWSPEC
The RSVP FLOWSPEC object used to request controlled-load service
carries a controlled-load traffic specification (TSpec) specifying
the traffic parameters of the flow for which controlled-load service
is being requested. This TSpec originates at the receiver making the
RSVP reservation request.
The format of the controlled-load FLOWSPEC object is shown below.
Each of the TSpec fields is represented using the preferred concrete
representation specified in the 'Invocation Information' section of
this memo.
31 24 23 16 15 8 7 0
+-+-+-+-+-+-+-+-+-+-+-+-+-+-+-+-+-+-+-+-+-+-+-+-+-+-+-+-+-+-+-+-+
| 0 (a) | Unused | 5 (b) |
+-+-+-+-+-+-+-+-+-+-+-+-+-+-+-+-+-+-+-+-+-+-+-+-+-+-+-+-+-+-+-+-+
| 5 (c) | 4 (d) | 1 (e) | 0 (f) |
+-+-+-+-+-+-+-+-+-+-+-+-+-+-+-+-+-+-+-+-+-+-+-+-+-+-+-+-+-+-+-+-+
| Token Bucket Rate [r] (32-bit IEEE floating point number) |
+-+-+-+-+-+-+-+-+-+-+-+-+-+-+-+-+-+-+-+-+-+-+-+-+-+-+-+-+-+-+-+-+
| Token Bucket Size [b] (32-bit IEEE floating point number) |
+-+-+-+-+-+-+-+-+-+-+-+-+-+-+-+-+-+-+-+-+-+-+-+-+-+-+-+-+-+-+-+-+
| Minimum Policed Unit [m] (32-bit integer) |
+-+-+-+-+-+-+-+-+-+-+-+-+-+-+-+-+-+-+-+-+-+-+-+-+-+-+-+-+-+-+-+-+
| Maximum Packet Size [M] (32-bit integer) |
+-+-+-+-+-+-+-+-+-+-+-+-+-+-+-+-+-+-+-+-+-+-+-+-+-+-+-+-+-+-+-+-+
(a) - Version number (0)
(b) - Overall length (5 words not including header)
(c) - Service header, service number 5 (controlled-load)
(d) - Length of per-service data, 4 words not including header
(e) - Parameter ID, parameter 1 (TSpec)
(f) - Parameter 1 flags (none set)
RSVP SENDER_TSPEC
The RSVP SENDER_TSPEC object describes the traffic being generated by
a sender. The exact format of the SENDER_TSPEC object depends on
J. Wroclawski Expires 12/96 [Page 17]
INTERNET-DRAFT draft-ietf-intserv-ctrl-load-svc-02.txt June, 1996
whether the sender wishes to allow only the use of controlled-load
service (and/or best-effort service) reservations, or wishes to allow
the receiver to select the traffic control service desired.
For senders wishing to allow only controlled-load service
reservations, the format of the RSVP SENDER_TSPEC object is given
below. The service-specific header indicates service_name 5, the
controlled_load service. The remainder of the data is a
controlled_load service TSpec, represented using the preferred
concrete representation specified in the 'Invocation Information'
section of this memo.
31 24 23 16 15 8 7 0
+-+-+-+-+-+-+-+-+-+-+-+-+-+-+-+-+-+-+-+-+-+-+-+-+-+-+-+-+-+-+-+-+
| 0 (a) | Unused | 5 (b) |
+-+-+-+-+-+-+-+-+-+-+-+-+-+-+-+-+-+-+-+-+-+-+-+-+-+-+-+-+-+-+-+-+
| 5 (c) | 4 (d) | 1 (e) | 0 (f) |
+-+-+-+-+-+-+-+-+-+-+-+-+-+-+-+-+-+-+-+-+-+-+-+-+-+-+-+-+-+-+-+-+
| Token Bucket Rate [r] (32-bit IEEE floating point number) |
+-+-+-+-+-+-+-+-+-+-+-+-+-+-+-+-+-+-+-+-+-+-+-+-+-+-+-+-+-+-+-+-+
| Token Bucket Size [b] (32-bit IEEE floating point number) |
+-+-+-+-+-+-+-+-+-+-+-+-+-+-+-+-+-+-+-+-+-+-+-+-+-+-+-+-+-+-+-+-+
| Minimum Policed Unit [m] (32-bit integer) |
+-+-+-+-+-+-+-+-+-+-+-+-+-+-+-+-+-+-+-+-+-+-+-+-+-+-+-+-+-+-+-+-+
| Maximum Packet Size [M] (32-bit integer) |
+-+-+-+-+-+-+-+-+-+-+-+-+-+-+-+-+-+-+-+-+-+-+-+-+-+-+-+-+-+-+-+-+
(a) - Version number (0)
(b) - Overall length (5 words not including header)
(c) - Service header, service number 5 (controlled-load)
(d) - Length of per-service data, 4 words not including header
(e) - Parameter ID, parameter 1 (TSpec)
(f) - Parameter 1 flags (none set)
For senders wishing to allow the receiver to select the reservation
service desired, the TSpec contained in the SENDER_TSPEC object
should be a generic TSPEC, indicated by a service_specific header
specifying service 1. At present, the format of the generic TSpec has
not been formally defined. However, FOR EXPERIMENTAL USE ONLY it is
permissible to use the following SENDER_TSPEC object to support
multi-service receivers.
NOTE: This format may change in the next version of this draft
J. Wroclawski Expires 12/96 [Page 18]
INTERNET-DRAFT draft-ietf-intserv-ctrl-load-svc-02.txt June, 1996
31 24 23 16 15 8 7 0
+-+-+-+-+-+-+-+-+-+-+-+-+-+-+-+-+-+-+-+-+-+-+-+-+-+-+-+-+-+-+-+-+
| 0 (a) | Unused | 5 (b) |
+-+-+-+-+-+-+-+-+-+-+-+-+-+-+-+-+-+-+-+-+-+-+-+-+-+-+-+-+-+-+-+-+
| 1 (c) | 4 (d) | 1 (e) | 0 (f) |
+-+-+-+-+-+-+-+-+-+-+-+-+-+-+-+-+-+-+-+-+-+-+-+-+-+-+-+-+-+-+-+-+
| Token Bucket Rate [r] (32-bit IEEE floating point number) |
+-+-+-+-+-+-+-+-+-+-+-+-+-+-+-+-+-+-+-+-+-+-+-+-+-+-+-+-+-+-+-+-+
| Token Bucket Size [b] (32-bit IEEE floating point number) |
+-+-+-+-+-+-+-+-+-+-+-+-+-+-+-+-+-+-+-+-+-+-+-+-+-+-+-+-+-+-+-+-+
| Peak Data Rate [p] (32-bit IEEE floating point number) |
+-+-+-+-+-+-+-+-+-+-+-+-+-+-+-+-+-+-+-+-+-+-+-+-+-+-+-+-+-+-+-+-+
| Minimum Policed Unit [m] (32-bit integer) |
+-+-+-+-+-+-+-+-+-+-+-+-+-+-+-+-+-+-+-+-+-+-+-+-+-+-+-+-+-+-+-+-+
| Maximum Packet Size [M] (32-bit integer) |
+-+-+-+-+-+-+-+-+-+-+-+-+-+-+-+-+-+-+-+-+-+-+-+-+-+-+-+-+-+-+-+-+
(a) - Version number (0)
(b) - Overall length (5 words not including header)
(c) - Service header, service number 1 (generic information)
(d) - Length of per-service data, 4 words not including header
(e) - Parameter ID, parameter 1 (TSpec)
(f) - Parameter 1 flags (none set)
RSVP ADSPEC
The RSVP ADSPEC object carries characterization parameters and
composition variables used in the process of end-to-end service
characterization. The controlled-load service does not export any
characterization parameters and does not provide any service-specific
end-to-end characterizations. Therefore no information is placed into
the RSVP ADSPEC message by a controlled-load service module.
RSVP ADSPEC messages generated and received by network elements
supporting the controlled-load service may contain other information;
particularly the general characterization parameters defined in [5].
Any such information will follow the format given in [4], with an
identifying service header indicating a service *other* than
controlled-load (Service ID Number other than 5).
OTHER RSVP OBJECTS
No other RSVP objects carry data with formats specific to the
controlled-load service.
J. Wroclawski Expires 12/96 [Page 19]
INTERNET-DRAFT draft-ietf-intserv-ctrl-load-svc-02.txt June, 1996
References
[1] S. Shenker and J. Wroclawski. "Network Element Service
Specification Template", Internet Draft, June 1995, <draft-ietf-
intserv-svc-template-01.txt>
[2] H. Schulzrinne, S. Casner, R. Frederick, and V. Jacobson. "RTP:
A Transport Protocol for Real-Time Applications", Internet Draft,
March 1995, <draft-ietf-avt-svc-rtp-07.txt>
[3] B. Braden, L. Zhang, S. Berson, S. Herzog, and J. Wroclawski.
"Resource Reservation Protocol (RSVP) - Version 1 Functional
Specification", Internet Draft, November 1995, <draft-ietf-rsvp-
spec-08.txt>
[4] J. Wroclawski. "Standard Data Encoding for Integrated Services
Objects", Internet Draft, November 1995, <draft-ietf-intserv-data-
encoding-01.txt>
[5] S. Shenker. "Specification of General Characterization
Parameters", Internet Draft, November 1995, <draft-ietf-intserv-
charac-00.txt>
[6] S. Floyd, and V. Jacobson. "Link-sharing and Resource Management
Models for Packet Networks," IEEE/ACM Transactions on Networking,
Vol. 3 No. 4, pp. 365-386, August 1995.
[7] A. K. J. Parekh. "A Generalized Processor Sharing Approach to
Flow Control in Integrated Service Networks". MIT Laboratory for
Information and Decision Systems, Report LIDS-TH-2089, February 1992
Authors' Address:
John Wroclawski
MIT Laboratory for Computer Science
545 Technology Sq.
Cambridge, MA 02139
jtw@lcs.mit.edu
617-253-7885
617-253-2673 (FAX)
J. Wroclawski Expires 12/96 [Page 20]
| PAFTECH AB 2003-2026 | 2026-04-21 20:37:35 |