One document matched: draft-ietf-tsvwg-byte-pkt-congest-07.xml
<?xml version="1.0" encoding="US-ASCII"?>
<!DOCTYPE rfc SYSTEM "rfc2629.dtd">
<?xml-stylesheet type='text/xsl' href='http://xml.resource.org/authoring/rfc2629.xslt' ?>
<!-- Alterations to I-D/RFC boilerplate -->
<?rfc private="" ?>
<!-- Default private="" Produce an internal memo 2.5pp shorter than an I-D or RFC -->
<?rfc rfcprocack="yes" ?>
<!-- Default rfcprocack="no" add a short sentence acknowledging xml2rfc -->
<?rfc strict="no" ?>
<!-- Default strict="no" Don't check I-D nits -->
<?rfc rfcedstyle="yes" ?>
<!-- Default rfcedstyle="yes" attempt to closely follow finer details from the latest observable RFC-Editor style -->
<!-- IETF process -->
<?rfc iprnotified="no" ?>
<!-- Default iprnotified="no" I haven't disclosed existence of IPR to IETF -->
<!-- ToC format -->
<?rfc toc="yes" ?>
<!-- Default toc="no" No Table of Contents -->
<!-- Cross referencing, footnotes, comments -->
<?rfc symrefs="yes" ?>
<!-- Default symrefs="no" Don't use anchors, but use numbers for refs -->
<?rfc sortrefs="yes"?>
<!-- Default sortrefs="no" Don't sort references into order -->
<?rfc comments="no" ?>
<!-- Default comments="yes" Don't render comments -->
<?rfc inline="no" ?>
<!-- Default inline="no" if comments is "yes", then render comments inline; otherwise render them in an `Editorial Comments' section -->
<?rfc editing="no"?>
<!-- Default editing="no" Don't insert editing marks for ease of discussing draft versions -->
<!-- Pagination control -->
<?rfc compact="yes"?>
<!-- Default compact="no" Start sections on new pages -->
<?rfc subcompact="no"?>
<!-- Default subcompact="(as compact setting)" yes/no is not quite as compact as yes/yes -->
<!-- HTML formatting control -->
<?rfc emoticonic="yes" ?>
<!-- Default emoticonic="no" Doesn't prettify HTML format -->
<rfc category="bcp" docName="draft-ietf-tsvwg-byte-pkt-congest-07"
ipr="trust200902" updates="2309">
<front>
<title abbrev="Byte and Packet Congestion Notification">Byte and Packet
Congestion Notification</title>
<author fullname="Bob Briscoe" initials="B." surname="Briscoe">
<organization>BT</organization>
<address>
<postal>
<street>B54/77, Adastral Park</street>
<street>Martlesham Heath</street>
<city>Ipswich</city>
<code>IP5 3RE</code>
<country>UK</country>
</postal>
<phone>+44 1473 645196</phone>
<email>bob.briscoe@bt.com</email>
<uri>http://bobbriscoe.net/</uri>
</address>
</author>
<author fullname="Jukka Manner" initials="J." surname="Manner">
<organization abbrev="Aalto University">Aalto University</organization>
<address>
<postal>
<street>Department of Communications and Networking
(Comnet)</street>
<street>P.O. Box 13000</street>
<code>FIN-00076 Aalto</code>
<country>Finland</country>
</postal>
<phone>+358 9 470 22481</phone>
<email>jukka.manner@aalto.fi</email>
<uri>http://www.netlab.tkk.fi/~jmanner/</uri>
</address>
</author>
<date day="20" month="February" year="2012" />
<area>Transport</area>
<workgroup>Transport Area Working Group</workgroup>
<keyword>Active queue management (AQM)</keyword>
<keyword>Availability</keyword>
<keyword>Denial of Service</keyword>
<keyword>Quality of Service (QoS)</keyword>
<keyword>Congestion Control</keyword>
<keyword>Fairness</keyword>
<keyword>Incentives</keyword>
<keyword>Protocol</keyword>
<keyword>Architecture layering</keyword>
<abstract>
<t>This memo concerns dropping or marking packets using active queue
management (AQM) such as random early detection (RED) or pre-congestion
notification (PCN). We give three strong recommendations: (1) packet
size should be taken into account when transports read and respond to
congestion indications, (2) packet size should not be taken into account
when network equipment creates congestion signals (marking, dropping),
and therefore (3) the byte-mode packet drop variant of the RED AQM
algorithm that drops fewer small packets should not be used.</t>
</abstract>
</front>
<middle>
<section anchor="pktb_Introduction" title="Introduction">
<t>This memo concerns how we should correctly scale congestion control
functions with packet size for the long term. It also recognises that
expediency may be necessary to deal with existing widely deployed
protocols that don't live up to the long term goal.</t>
<t>When notifying congestion, the problem of how (and whether) to take
packet sizes into account has exercised the minds of researchers and
practitioners for as long as active queue management (AQM) has been
discussed. Indeed, one reason AQM was originally introduced was to
reduce the lock-out effects that small packets can have on large packets
in drop-tail queues. This memo aims to state the principles we should be
using and to outline how these principles will affect future protocol
design, taking into account the existing deployments we have
already.</t>
<t>The question of whether to take into account packet size arises at
three stages in the congestion notification process: <list
style="hanging">
<t hangText="Measuring congestion:">When a congested resource
measures locally how congested it is, should it measure its queue
length in bytes or packets?</t>
<t
hangText="Encoding congestion notification into the wire protocol:">When
a congested network resource notifies its level of congestion,
should it drop / mark each packet dependent on the byte-size of the
particular packet in question?</t>
<t
hangText="Decoding congestion notification from the wire protocol:">When
a transport interprets the notification in order to decide how much
to respond to congestion, should it take into account the byte-size
of each missing or marked packet?</t>
</list></t>
<t>Consensus has emerged over the years concerning the first stage:
whether queues are measured in bytes or packets, termed byte-mode queue
measurement or packet-mode queue measurement. <xref
target="pktb_Measure_Rec"></xref> of this memo records this consensus in
the RFC Series. In summary the choice solely depends on whether the
resource is congested by bytes or packets.</t>
<t>The controversy is mainly around the last two stages: whether to
allow for the size of the specific packet notifying congestion i) when
the network encodes or ii) when the transport decodes the congestion
notification.</t>
<t>Currently, the RFC series is silent on this matter other than a paper
trail of advice referenced from <xref target="RFC2309"></xref>, which
conditionally recommends byte-mode (packet-size dependent) drop <xref
target="pktByteEmail"></xref>. Reducing drop of small packets certainly
has some tempting advantages: i) it drops less control packets, which
tend to be small and ii) it makes TCP's bit-rate less dependent on
packet size. However, there are ways of addressing these issues at the
transport layer, rather than reverse engineering network forwarding to
fix the problems.</t>
<!-- of one specific transport, as byte-mode variant of RED was
designed to do.</t>
-->
<!--
<t>The primary purpose of this memo is to build a definitive consensus
against deliberate preferential treatment for small packets in AQM
algorithms and to record this advice within the RFC series.
-->
<t>This memo updates <xref target="RFC2309"></xref> to deprecate
deliberate preferential treatment of small packets in AQM algorithms. It
recommends that (1) packet size should be taken into account when
transports read congestion indications, (2) not when network equipment
writes them.</t>
<t>In particular this means that the byte-mode packet drop variant of
Random early Detection (RED) should not be used to drop fewer small
packets, because that creates a perverse incentive for transports to use
tiny segments, consequently also opening up a DoS vulnerability.
Fortunately all the RED implementers who responded to our admittedly
limited survey (<xref target="pktb_Coding_Status_Summary"></xref>) have
not followed the earlier advice to use byte-mode drop, so the position
this memo argues for seems to already exist in implementations.</t>
<t>However, at the transport layer, TCP congestion control is a widely
deployed protocol that doesn't scale with packet size. To date this
hasn't been a significant problem because most TCP implementations have
been used with similar packet sizes. But, as we design new congestion
control mechanisms, the current recommendation is that we should build
in scaling with packet size rather than assuming we should follow TCP's
example.</t>
<t>This memo continues as follows. First it discusses terminology and
scoping. <xref target="pktb_Recommendations"></xref> gives the concrete
formal recommendations, followed by motivating arguments in <xref
target="pktb_Motivation"></xref>. We then critically survey the advice
given previously in the RFC series and the research literature (<xref
target="pktb_Critique_Advice"></xref>), referring to an assessment of
whether or not this advice has been followed in production networks
(<xref target="pktb_SotA"></xref>). To wrap up, outstanding issues are
discussed that will need resolution both to inform future protocol
designs and to handle legacy (<xref target="pktb_Issues"></xref>). Then
security issues are collected together in <xref
target="pktb_Security_Considerations"></xref> before conclusions are
drawn in <xref target="pktb_Conclusions"></xref>. The interested reader
can find discussion of more detailed issues on the theme of byte vs.
packet in the appendices.</t>
<t>This memo intentionally includes a non-negligible amount of material
on the subject. For the busy reader <xref
target="pktb_Recommendations"></xref> summarises the recommendations for
the Internet community.</t>
<section anchor="pktb_term" title="Terminology and Scoping">
<t>The key words "MUST", "MUST NOT", "REQUIRED", "SHALL", "SHALL NOT",
"SHOULD", "SHOULD NOT", "RECOMMENDED", "MAY", and "OPTIONAL" in this
document are to be interpreted as described in <xref
target="RFC2119"></xref>.</t>
<!-- Old section 3 below ================================================================
<section anchor="pktb_Congestion_Definition"
title="Working Definition of Congestion Notification">
-->
<t><list style="hanging">
<t hangText="Congestion Notification:">Congestion notification is
a changing signal that aims to communicate the probability that
the network resource(s) will not be able to forward the level of
traffic load offered (or that there is an impending risk that they
will not be able to).<vspace blankLines="1" /> The `impending
risk' qualifier is added, because AQM systems (e.g. RED, PCN <xref
target="RFC5670"></xref>) set a virtual limit smaller than the
actual limit to the resource, then notify when this virtual limit
is exceeded in order to avoid uncontrolled congestion of the
actual capacity.<vspace blankLines="1" />Congestion notification
communicates a real number bounded by the range [0,1]. This ties
in with the most well-understood measure of congestion
notification: drop probability.</t>
<t hangText="Explicit and Implicit Notification:">The byte vs.
packet dilemma concerns congestion notification irrespective of
whether it is signalled implicitly by drop or using explicit
congestion notification (ECN <xref target="RFC3168"></xref> or PCN
<xref target="RFC5670"></xref>). Throughout this document, unless
clear from the context, the term marking will be used to mean
notifying congestion explicitly, while congestion notification
will be used to mean notifying congestion either implicitly by
drop or explicitly by marking.</t>
<t hangText="Bit-congestible vs. Packet-congestible:">If the load
on a resource depends on the rate at which packets arrive, it is
called packet-congestible. If the load depends on the rate at
which bits arrive it is called bit-congestible.<vspace
blankLines="1" />Examples of packet-congestible resources are
route look-up engines and firewalls, because load depends on how
many packet headers they have to process. Examples of
bit-congestible resources are transmission links, radio power and
most buffer memory, because the load depends on how many bits they
have to transmit or store. Some machine architectures use fixed
size packet buffers, so buffer memory in these cases is
packet-congestible (see <xref
target="pktb_Fixed_Buffers"></xref>).<vspace
blankLines="1" />Currently a design goal of network processing
equipment such as routers and firewalls is to keep packet
processing uncongested even under worst case packet rates with
runs of minimum size packets. Therefore, packet-congestion is
currently rare [<xref format="counter" target="RFC6077"></xref>;
§3.3], but there is no guarantee that it will not become more
common in future.<vspace blankLines="1" />Note that information is
generally processed or transmitted with a minimum granularity
greater than a bit (e.g. octets). The appropriate granularity for
the resource in question should be used, but for the sake of
brevity we will talk in terms of bytes in this memo.</t>
<t hangText="Coarser Granularity:">Resources may be congestible at
higher levels of granularity than bits or packets, for instance
stateful firewalls are flow-congestible and call-servers are
session-congestible. This memo focuses on congestion of
connectionless resources, but the same principles may be
applicable for congestion notification protocols controlling
per-flow and per-session processing or state.</t>
<t hangText="RED Terminology:">In RED whether to use packets or
bytes when measuring queues is called respectively "packet-mode
queue measurement" or "byte-mode queue measurement". And whether
the probability of dropping a particular packet is independent or
dependent on its byte-size is called respectively "packet-mode
drop" or "byte-mode drop". The terms byte-mode and packet-mode
should not be used without specifying whether they apply to queue
measurement or to drop.</t>
</list></t>
</section>
<section anchor="pktb_Example"
title="Example Comparing Packet-Mode Drop and Byte-Mode Drop">
<t>A central question addressed by this document is whether to
recommend that AQM uses RED's packet-mode drop and to deprecate byte-mode drop.
<xref target="pktb_Tab_Example"></xref> compares how packet-mode and
byte-mode drop affect two flows of different size packets. For each it
gives the expected number of packets and of bits dropped in one
second. Each example flow runs at the same bit-rate of 48Mb/s, but one
is broken up into small 60 byte packets and the other into large 1500
byte packets.</t>
<t>To keep up the same bit-rate, in one second there are about 25
times more small packets because they are 25 times smaller. As can be
seen from the table, the packet rate is 100,000 small packets versus
4,000 large packets per second (pps).</t>
<?rfc needLines="18" ?>
<texttable anchor="pktb_Tab_Example" style="headers"
title="Example Comparing Packet-mode and Byte-mode Drop">
<ttcol>Parameter</ttcol>
<ttcol>Formula</ttcol>
<ttcol align="right">Small packets</ttcol>
<ttcol align="right">Large packets</ttcol>
<c>Packet size</c>
<c>s/8</c>
<c>60B</c>
<c>1,500B</c>
<c>Packet size</c>
<c>s</c>
<c>480b</c>
<c>12,000b</c>
<c>Bit-rate</c>
<c>x</c>
<c>48Mbps</c>
<c>48Mbps</c>
<c>Packet-rate</c>
<c>u = x/s</c>
<c>100kpps</c>
<c>4kpps</c>
<c> </c>
<c></c>
<c></c>
<c></c>
<c>Packet-mode Drop</c>
<c></c>
<c></c>
<c></c>
<c>Pkt loss probability</c>
<c>p</c>
<c>0.1%</c>
<c>0.1%</c>
<c>Pkt loss-rate</c>
<c>p*u</c>
<c>100pps</c>
<c>4pps</c>
<c>Bit loss-rate</c>
<c>p*u*s</c>
<c>48kbps</c>
<c>48kbps</c>
<c> </c>
<c></c>
<c></c>
<c></c>
<c>Byte-mode Drop</c>
<c>MTU, M=12,000b</c>
<c></c>
<c></c>
<c>Pkt loss probability</c>
<c>b = p*s/M</c>
<c>0.004%</c>
<c>0.1%</c>
<c>Pkt loss-rate</c>
<c>b*u</c>
<c>4pps</c>
<c>4pps</c>
<c>Bit loss-rate</c>
<c>b*u*s</c>
<c>1.92kbps</c>
<c>48kbps</c>
</texttable>
<t>For packet-mode drop, we illustrate the effect of a drop
probability of 0.1%, which the algorithm applies to all packets
irrespective of size. Because there are 25 times more small packets in
one second, it naturally drops 25 times more small packets, that is
100 small packets but only 4 large packets. But if we count how many
bits it drops, there are 48,000 bits in 100 small packets and 48,000
bits in 4 large packets—the same number of bits of small packets
as large.<list style="empty">
<t>The packet-mode drop algorithm drops any bit with the same
probability whether the bit is in a small or a large packet.</t>
</list></t>
<t>For byte-mode drop, again we use an example drop probability of
0.1%, but only for maximum size packets (assuming the link MTU is
1,500B or 12,000b). The byte-mode algorithm reduces the drop
probability of smaller packets proportional to their size, making the
probability that it drops a small packet 25 times smaller at 0.004%.
But there are 25 times more small packets, so dropping them with 25
times lower probability results in dropping the same number of
packets: 4 drops in both cases. The 4 small dropped packets contain 25
times less bits than the 4 large dropped packets: 1,920 compared to
48,000.<list style="empty">
<t>The byte-mode drop algorithm drops any bit with a probability
proportionate to the size of the packet it is in.</t>
</list></t>
</section>
</section>
<!-- ================================================================ -->
<section anchor="pktb_Recommendations" title="Recommendations">
<t>This section gives recommendations related to network equipment in Sections 2.1 and 2.2,
and in Sections 2.3 and 2.4 we discuss the implications on the transport protocols.</t>
<section anchor="pktb_Measure_Rec"
title="Recommendation on Queue Measurement">
<t>Queue length is usually the most correct and simplest way to
measure congestion of a resource. To avoid the pathological effects of
drop tail, an AQM function can then be used to transform queue length
into the probability of dropping or marking a packet (e.g. RED's
piecewise linear function between thresholds).</t>
<t>If the resource is bit-congestible, the implementation SHOULD
measure the length of the queue in bytes. If the resource is
packet-congestible, the implementation SHOULD measure the length of
the queue in packets. No other choice makes sense, because the number
of packets waiting in the queue isn't relevant if the resource gets
congested by bytes and vice versa.</t>
<t>What this advice means for the case of RED:<list style="numbers">
<!--
<t>Whether a resource is bit-congestible or packet-congestible is
a property of the resource, so an admin should not ever need to,
or be able to, configure the way a queue measures itself.</t>
-->
<t>A RED implementation SHOULD use byte mode queue measurement for
measuring the congestion of bit-congestible resources and packet
mode queue measurement for packet-congestible resources.</t>
<t>An implementation SHOULD NOT make it possible to configure the
way a queue measures itself, because whether a queue is
bit-congestible or packet-congestible is an inherent property of
the queue.</t>
</list></t>
<t>The recommended approach in less straightforward scenarios, such as
fixed size buffers, and resources without a queue, is discussed in
<xref target="pktb_Measure_Status"></xref>.</t>
</section>
<section anchor="pktb_Notify_Rec"
title="Recommendation on Encoding Congestion Notification">
<t>When encoding congestion notification (e.g. by drop, ECN &
PCN), a network device SHOULD treat all packets equally, regardless of
their size. In other words, the probability that network equipment
drops or marks a particular packet to notify congestion SHOULD NOT
depend on the size of the packet in question. As the example in <xref
target="pktb_Example"></xref> illustrates, to drop any bit with
probability 0.1% it is only necessary to drop every packet with
probability 0.1% without regard to the size of each packet.</t>
<t>This approach ensures the network layer offers sufficient
congestion information for all known and future transport protocols
and also ensures no perverse incentives are created that would
encourage transports to use inappropriately small packet sizes.</t>
<t>What this advice means for the case of RED: <list style="numbers">
<t>AQM algorithms such as RED SHOULD NOT use byte-mode drop, which
deflates RED's drop probability for smaller packet sizes. RED's
byte-mode drop has no enduring advantages. It is more complex, it
creates the perverse incentive to fragment segments into tiny
pieces and it reopens the vulnerability to floods of small-packets
that drop-tail queues suffered from and AQM was designed to
remove.</t>
<t>If a vendor has implemented byte-mode drop, and an operator has
turned it on, it is RECOMMENDED to turn it off. Note that RED as a
whole SHOULD NOT be turned off, as without it, a drop tail queue
also biases against large packets. But note also that turning off
byte-mode drop may alter the relative performance of applications
using different packet sizes, so it would be advisable to
establish the implications before turning it off.<vspace
blankLines="1" />Note well that RED's byte-mode queue drop is
completely orthogonal to byte-mode queue measurement and should
not be confused with it. If a RED implementation has a byte-mode
but does not specify what sort of byte-mode, it is most probably
byte-mode queue measurement, which is fine. However, if in doubt,
the vendor should be consulted.</t>
</list></t>
<!--
<t>The byte mode packet drop variant of RED was recommended in the
past (see <xref target="pktb_Network_Bias"></xref> for how thinking
evolved). However, our survey of 84 vendors across the industry (<xref
target="pktb_SotA"></xref>) has found that none of the 19% who
responded have implemented byte mode drop in RED. Given there appears
to be little, if any, installed base it is expected that
byte-mode drop can be deprecated with little, if any, incremental deployment
impact.</t>
-->
<t>A survey (<xref target="pktb_SotA"></xref>) showed that there
appears to be little, if any, installed base of the byte-mode drop
variant of RED. This suggests that deprecating byte-mode drop will
have little, if any, incremental deployment impact.</t>
</section>
<section anchor="pktb_Respond_Rec"
title="Recommendation on Responding to Congestion">
<!--
<t> A transport protocol SHOULD take into account the fraction of bytes that
indicate congestion when determining its sending rate, rather than the
fraction of packets indicating congestion.</t>
-->
<t>When a transport detects that a packet has been lost or congestion
marked, it SHOULD consider the strength of the congestion indication
as proportionate to the size in octets (bytes) of the missing or
marked packet.</t>
<t>In other words, when a packet indicates congestion (by being lost
or marked) it can be considered conceptually as if there is a
congestion indication on every octet of the packet, not just one
indication per packet.</t>
<t>Therefore, the IETF transport area should continue its programme
of;<list style="symbols">
<t>updating host-based congestion control protocols to take
account of packet size</t>
<t>making transports less sensitive to losing control packets like
SYNs and pure ACKs.</t>
</list></t>
<t>What this advice means for the case of TCP: <list style="numbers">
<t>If two TCP flows with different packet sizes are required to
run at equal bit rates under the same path conditions, this should
be done by altering TCP (<xref
target="pktb_Transport_Bias"></xref>), not network equipment (the
latter affects other transports besides TCP).</t>
<t>If it is desired to improve TCP performance by reducing the
chance that a SYN or a pure ACK will be dropped, this should be
done by modifying TCP (<xref
target="pktb_Transport_Robust_Ctrl_Loss"></xref>), not network
equipment.</t>
</list></t>
</section>
<section anchor="pktb_Respond_Split"
title="Recommendation on Handling Congestion Indications when Splitting or Merging Packets ">
<t>Packets carrying congestion indications may be split or merged in
some circumstances (e.g. at a RTCP transcoder or during IP fragment
reassembly). Splitting and merging only make sense in the context of
ECN, not loss.</t>
<t>The general rule to follow is that the number of octets in packets
with congestion indications SHOULD be equivalent before and after
merging or splitting. This is based on the principle used above; that
an indication of congestion on a packet can be considered as an
indication of congestion on each octet of the packet.</t>
<t>The above rule is not phrased with the word "MUST" to allow the
following exception. There are cases where pre-existing protocols were
not designed to conserve congestion marked octets (e.g. IP fragment
reassembly <xref target="RFC3168"></xref> or loss statistics in RTCP
receiver reports <xref target="RFC3550"></xref> before ECN was added
<xref target="I-D.ietf-avtcore-ecn-for-rtp"></xref>). When any such
protocol is updated, it SHOULD comply with the above rule to conserve
marked octets. However, the rule may be relaxed if it would otherwise
become too complex to interoperate with pre-existing implementations
of the protocol.</t>
<t>One can think of a splitting or merging process as if all the
incoming congestion-marked octets increment a counter and all the
outgoing marked octets decrement the same counter. In order to ensure
that congestion indications remain timely, even the smallest positive
remainder in the conceptual counter should trigger the next outgoing
packet to be marked (causing the counter to go negative).</t>
</section>
<!--
<section anchor="pktb_Research_Rec" title="Recommended Future Research">
<t>The above conclusions cater for the Internet as it is today with
most resources being primarily bit-congestible. A secondary conclusion
of this memo is that research is needed to determine whether there
might be more packet-congestible resources in the future. Then further
research would be needed to extend the Internet's congestion
notification (drop or ECN) so that it would be able to handle a more
even mix of bit-congestible and packet-congestible resources.</t>
</section>
-->
</section>
<!-- ================================================================ -->
<section anchor="pktb_Motivation" title="Motivating Arguments">
<t>This section is informative. It justifies the recommendations
given in the previous section.</t>
<section anchor="pktb_Avoiding_Perverse_Incentives"
title="Avoiding Perverse Incentives to (Ab)use Smaller Packets">
<t>Increasingly, it is being recognised that a protocol design must
take care not to cause unintended consequences by giving the parties
in the protocol exchange perverse incentives <xref
target="Evol_cc"></xref><xref target="RFC3426"></xref>. Given there
are many good reasons why larger path maximum transmission units (PMTUs)
would help solve a number of scaling issues, we do not want to create
any bias against large packets that is greater than their true
cost.</t>
<t>Imagine a scenario where the same bit rate of packets will
contribute the same to bit-congestion of a link irrespective of
whether it is sent as fewer larger packets or more smaller packets. A
protocol design that caused larger packets to be more likely to be
dropped than smaller ones would be dangerous in both the following cases:</t>
<t><list style="hanging">
<t hangText="Malicious transports:">A queue that gives an
advantage to small packets can be used to amplify the force of a
flooding attack. By sending a flood of small packets, the attacker
can get the queue to discard more traffic in large packets,
allowing more attack traffic to get through to cause further
damage. Such a queue allows attack traffic to have a
disproportionately large effect on regular traffic without the
attacker having to do much work.</t>
<t hangText="Non-malicious transports:">Even if a transport
designer is not actually malicious, if over time it is noticed
that small packets tend to go faster, designers will act in their
own interest and use smaller packets. Queues that give advantage
to small packets create an evolutionary pressure for transports to
send at the same bit-rate but break their data stream down into
tiny segments to reduce their drop rate. Encouraging a high volume
of tiny packets might in turn unnecessarily overload a completely
unrelated part of the system, perhaps more limited by
header-processing than bandwidth.</t>
</list></t>
<t>Imagine two unresponsive flows arrive at a bit-congestible
transmission link each with the same bit rate, say 1Mbps, but one
consists of 1500B and the other 60B packets, which are 25x smaller.
Consider a scenario where gentle RED <xref target="gentle_RED"></xref>
is used, along with the variant of RED we advise against, i.e. where
the RED algorithm is configured to adjust the drop probability of
packets in proportion to each packet's size (byte mode packet drop).
In this case, RED aims to drop 25x more of the larger packets than the
smaller ones. Thus, for example if RED drops 25% of the larger
packets, it will aim to drop 1% of the smaller packets (but in
practice it may drop more as congestion increases [<xref
format="counter" target="RFC4828"></xref>; Appx B.4]<cref
anchor="Note_Variation">The algorithm of the byte-mode drop variant of
RED switches off any bias towards small packets whenever the smoothed
queue length dictates that the drop probability of large packets
should be 100%. In the example in the Introduction, as the large
packet drop probability varies around 25% the small packet drop
probability will vary around 1%, but with occasional jumps to 100%
whenever the instantaneous queue (after drop) manages to sustain a
length above the 100% drop point for longer than the queue averaging
period.</cref>). Even though both flows arrive with the same bit rate,
the bit rate the RED queue aims to pass to the line will be 750kbps
for the flow of larger packets but 990kbps for the smaller packets
(because of rate variations it will actually be a little less than
this target).</t>
<t>Note that, although the byte-mode drop variant of RED amplifies
small packet attacks, drop-tail queues amplify small packet attacks
even more (see Security Considerations in <xref
target="pktb_Security_Considerations"></xref>). Wherever possible
neither should be used.</t>
</section>
<section anchor="pktb_Small.NE.Control" title="Small != Control">
<t>Dropping fewer control packets considerably improves performance.
It is tempting to drop small packets with lower probability in order
to improve performance, because many control packets are small (TCP
SYNs & ACKs, DNS queries & responses, SIP messages, HTTP GETs,
etc). However, we must not give control packets preference purely by
virtue of their smallness, otherwise it is too easy for any data
source to get the same preferential treatment simply by sending data
in smaller packets. Again we should not create perverse incentives to
favour small packets rather than to favour control packets, which is
what we intend.</t>
<t>Just because many control packets are small does not mean all small
packets are control packets.</t>
<t>So, rather than fix these problems in the network, we argue that
the transport should be made more robust against losses of control
packets (see 'Making Transports Robust against Control Packet Losses'
in <xref target="pktb_Transport_Robust_Ctrl_Loss"></xref>).</t>
</section>
<section anchor="pktb_Layering" title="Transport-Independent Network">
<t>TCP congestion control ensures that flows competing for the same
resource each maintain the same number of segments in flight,
irrespective of segment size. So under similar conditions, flows with
different segment sizes will get different bit-rates.</t>
<t>One motivation for the network biasing congestion notification by
packet size is to counter this effect and try to equalise the
bit-rates of flows with different packet sizes. However, in order to
do this, the queuing algorithm has to make assumptions about the
transport, which become embedded in the network. Specifically: <list
style="symbols">
<t>The queuing algorithm has to assume how aggressively the
transport will respond to congestion (see <xref
target="pktb_Coding_Status_Summary"></xref>). If the network
assumes the transport responds as aggressively as TCP NewReno, it
will be wrong for Compound TCP and differently wrong for Cubic
TCP, etc. To achieve equal bit-rates, each transport then has to
guess what assumption the network made, and work out how to
replace this assumed aggressiveness with its own
aggressiveness.</t>
<t>Also, if the network biases congestion notification by packet
size it has to assume a baseline packet size—all proposed
algorithms use the local MTU. Then transports have to guess which
link was congested and what its local MTU was, in order to know
how to tailor their congestion response to that link.</t>
</list></t>
<t>Even though reducing the drop probability of small packets (e.g.
RED's byte-mode drop) helps ensure TCP flows with different packet
sizes will achieve similar bit rates, we argue this correction should
be made to any future transport protocols based on TCP, not to the
network in order to fix one transport, no matter how predominant it
is. Effectively, favouring small packets is reverse engineering of
network equipment around one particular transport protocol (TCP),
contrary to the excellent advice in <xref target="RFC3426"></xref>,
which asks designers to question "Why are you proposing a solution at
this layer of the protocol stack, rather than at another layer?"</t>
<t>In contrast, if the network never takes account of packet size, the
transport can be certain it will never need to guess any assumptions
the network has made. And the network passes two pieces of information
to the transport that are sufficient in all cases: i) congestion
notification on the packet and ii) the size of the packet. Both are
available for the transport to combine (by taking account of packet
size when responding to congestion) or not. <xref
target="pktb_Ideal"></xref> checks that these two pieces of
information are sufficient for all relevant scenarios.</t>
<t>When the network does not take account of packet size, it allows
transport protocols to choose whether to take account of packet size
or not. However, if the network were to bias congestion notification
by packet size, transport protocols would have no choice; those that
did not take account of packet size themselves would unwittingly
become dependent on packet size, and those that already took account
of packet size would end up taking account of it twice.</t>
</section>
<section anchor="pktb_Scaling"
title="Scaling Congestion Control with Packet Size">
<t>Having so far justified only our recommendations for the network,
this section focuses on the host. We construct a scaling argument to
justify the recommendation that a host should respond to a dropped or
marked packet in proportion to its size, not just as a single
congestion event.</t>
<t>The argument assumes that we have already sufficiently justified
our recommendation that the network should not take account of packet
size. </t>
<t>Also, we assume bit-congestible links are the predominant source of
congestion. As the Internet stands, it is hard if not impossible to
know whether congestion notification is from a bit-congestible or a
packet-congestible resource (see <xref
target="pktb_bit_pkt-congestible"></xref>) so we have to assume the
most prevalent case (see <xref target="pktb_term"></xref>). If this
assumption is wrong, and particular congestion indications are
actually due to overload of packet-processing, there is no issue of
safety at stake. Any congestion control that triggers a multiplicative
decrease in response to a congestion indication will bring packet
processing back to its operating point just as quickly. The only issue
at stake is that the resource could be utilised more efficiently if
packet-congestion could be separately identified.</t>
<t><!-- Here we try to design a test to see which
approach scales with packet size.</t>
-->Imagine a bit-congestible link shared by many flows, so that each busy
period tends to cause packets to be lost from different flows.
Consider further two sources that have the same data rate but break
the load into large packets in one application (A) and small packets
in the other (B). Of course, because the load is the same, there will
be proportionately more packets in the small packet flow (B).</t>
<t>If a congestion control scales with packet size it should respond
in the same way to the same congestion notification, irrespective of
the size of the packets containing the bytes that contribute to
congestion.</t>
<t>A bit-congestible queue suffering congestion has to drop or mark
the same excess bytes whether they are in a few large packets (A) or
many small packets (B). So for the same amount of congestion overload,
the same amount of bytes has to be shed to get the load back to its
operating point. For smaller packets (B) more packets
will have to be discarded to shed the same bytes.</t>
<t>If both the transports interpret each drop/mark as a single loss
event irrespective of the size of the packet dropped, the flow of
smaller packets (B) will respond more times to the same congestion. On
the other hand, if a transport responds proportionately less when
smaller packets are dropped/marked, overall it will be able to respond
the same to the same amount of congestion.</t>
<t>Therefore, for a congestion control to scale with packet size it
should respond to dropped or marked bytes (as TFRC-SP <xref
target="RFC4828"></xref> effectively does), instead of dropped or
marked packets (as TCP does).</t>
<t>For the avoidance of doubt, this is not a recommendation that TCP
should be changed so that it scales with packet size. It is a
recommendation that any future transport protocol proposal should
respond to dropped or marked bytes if it wishes to claim that it is
scalable.</t>
</section>
<section anchor="pktb_Impl_Efficiency" title="Implementation Efficiency">
<t>Allowing for packet size at the transport rather than in the
network ensures that neither the network nor the transport needs to do
a multiply operation—multiplication by packet size is
effectively achieved as a repeated add when the transport adds to its
count of marked bytes as each congestion event is fed to it. This
isn't a principled reason in itself, but it is a happy consequence of
the other principled reasons.</t>
</section>
</section>
<!-- ================================================================ -->
<section anchor="pktb_Critique_Advice"
title="A Survey and Critique of Past Advice">
<t>This section is informative, not normative.</t>
<t>The original 1993 paper on RED <xref target="RED93"></xref> proposed
two options for the RED active queue management algorithm: packet mode
and byte mode. Packet mode measured the queue length in packets and
dropped (or marked) individual packets with a probability independent of
their size. Byte mode measured the queue length in bytes and marked an
individual packet with probability in proportion to its size (relative
to the maximum packet size). In the paper's outline of further work, it
was stated that no recommendation had been made on whether the queue
size should be measured in bytes or packets, but noted that the
difference could be significant.</t>
<t>When RED was recommended for general deployment in 1998 <xref
target="RFC2309"></xref>, the two modes were mentioned implying the
choice between them was a question of performance, referring to a 1997
email <xref target="pktByteEmail"></xref> for advice on tuning. A later
addendum to this email introduced the insight that there are in fact two
orthogonal choices: <list style="symbols">
<t>whether to measure queue length in bytes or packets (<xref
target="pktb_Measure_Status"></xref>)</t>
<t>whether the drop probability of an individual packet should
depend on its own size (<xref
target="pktb_Coding_Status"></xref>).</t>
</list>The rest of this section is structured accordingly.</t>
<!-- ________________________________________________________________ -->
<section anchor="pktb_Measure_Status"
title="Congestion Measurement Advice">
<t>The choice of which metric to use to measure queue length was left
open in RFC2309. It is now well understood that queues for
bit-congestible resources should be measured in bytes, and queues for
packet-congestible resources should be measured in packets <xref
target="pktByteEmail"></xref>.</t>
<!-- (see <xref
target="pktb_Measure" />).</t>
<t>Some modern queue implementations give a choice for setting RED's
thresholds in byte-mode or packet-mode. This may merely be an
administrator-interface preference, not altering how the queue itself
is measured but on some hardware it does actually change the way it
measures its queue. Whether a resource is bit-congestible or
packet-congestible is a property of the resource, so an admin should
not ever need to, or be able to, configure the way a queue measures
itself.</t>
-->
<t>Congestion in some legacy bit-congestible buffers is only
measured in packets not bytes. In such cases, the operator has to set
the thresholds mindful of a typical mix of packets sizes. Any AQM
algorithm on such a buffer will be oversensitive to high proportions
of small packets, e.g. a DoS attack, and undersensitive to high
proportions of large packets. However, there is no need to make
allowances for the possibility of such legacy in future protocol
design. This is safe because any undersensitivity during unusual
traffic mixes cannot lead to congestion collapse given the buffer will
eventually revert to tail drop, discarding proportionately more large
packets.</t>
<section anchor="pktb_Fixed_Buffers" title="Fixed Size Packet Buffers">
<t>The question of whether to measure queues in bytes or packets
seems to be well understood. However, measuring congestion is not
straightforward when the resource is bit congestible but the queue
is packet congestible or vice versa. This section outlines the
approach to take. There is no controversy over what should be done,
you just need to be expert in probability to work it out. And, even
if you know what should be done, it's not always easy to find a
practical algorithm to implement it.</t>
<t>Some, mostly older, queuing hardware sets aside fixed sized
buffers in which to store each packet in the queue. Also, with some
hardware, any fixed sized buffers not completely filled by a packet
are padded when transmitted to the wire. If we imagine a theoretical
forwarding system with both queuing and transmission in fixed,
MTU-sized units, it should clearly be treated as packet-congestible,
because the queue length in packets would be a good model of
congestion of the lower layer link.</t>
<t>If we now imagine a hybrid forwarding system with transmission
delay largely dependent on the byte-size of packets but buffers of
one MTU per packet, it should strictly require a more complex
algorithm to determine the probability of congestion. It should be
treated as two resources in sequence, where the sum of the
byte-sizes of the packets within each packet buffer models
congestion of the line while the length of the queue in packets
models congestion of the queue. Then the probability of congesting
the forwarding buffer would be a conditional
probability—conditional on the previously calculated
probability of congesting the line.</t>
<t>In systems that use fixed size buffers, it is unusual for all the
buffers used by an interface to be the same size. Typically pools of
different sized buffers are provided (Cisco uses the term 'buffer
carving' for the process of dividing up memory into these pools
<xref target="IOSArch"></xref>). Usually, if the pool of small
buffers is exhausted, arriving small packets can borrow space in the
pool of large buffers, but not vice versa. However, it is easier to
work out what should be done if we temporarily set aside the
possibility of such borrowing. Then, with fixed pools of buffers for
different sized packets and no borrowing, the size of each pool and
the current queue length in each pool would both be measured in
packets. So an AQM algorithm would have to maintain the queue length
for each pool, and judge whether to drop/mark a packet of a
particular size by looking at the pool for packets of that size and
using the length (in packets) of its queue.</t>
<t>We now return to the issue we temporarily set aside: small
packets borrowing space in larger buffers. In this case, the only
difference is that the pools for smaller packets have a maximum
queue size that includes all the pools for larger packets. And every
time a packet takes a larger buffer, the current queue size has to
be incremented for all queues in the pools of buffers less than or
equal to the buffer size used.</t>
<t>We will return to borrowing of fixed sized buffers when we
discuss biasing the drop/marking probability of a specific packet
because of its size in <xref target="pktb_Network_Bias"></xref>. But
here we can give a at least one simple rule for how to measure the
length of queues of fixed buffers: no matter how complicated the
scheme is, ultimately any fixed buffer system will need to measure
its queue length in packets not bytes.</t>
</section>
<section anchor="pktb_Measurement_NoQ"
title="Congestion Measurement without a Queue">
<t>AQM algorithms are nearly always described assuming there is a
queue for a congested resource and the algorithm can use the queue
length to determine the probability that it will drop or mark each
packet. But not all congested resources lead to queues. For
instance, wireless spectrum is usually regarded as bit-congestible
(for a given coding scheme). <!--, because interference increases with the rate at which bits
are transmitted. --> But wireless link protocols do not always
maintain a queue that depends on spectrum interference. Similarly,
power limited resources are also usually bit-congestible if energy
is primarily required for transmission rather than header
processing, but it is rare for a link protocol to build a queue as
it approaches maximum power.</t>
<t>Nonetheless, AQM algorithms do not require a queue in order to
work. For instance spectrum congestion can be modelled by signal
quality using target bit-energy-to-noise-density ratio. And, to
model radio power exhaustion, transmission power levels can be
measured and compared to the maximum power available. <xref
target="ECNFixedWireless"></xref> proposes a practical and
theoretically sound way to combine congestion notification for
different bit-congestible resources at different layers along an end
to end path, whether wireless or wired, and whether with or without
queues.</t>
</section>
</section>
<!-- ________________________________________________________________ -->
<section anchor="pktb_Coding_Status"
title="Congestion Notification Advice">
<!-- - - - - - - - - - - - - - - - - - - - - - - - - - - - - - - - - -->
<section anchor="pktb_Network_Bias" title="Network Bias when Encoding">
<section anchor="" title="Advice on Packet Size Bias in RED">
<t>The previously mentioned email <xref
target="pktByteEmail"></xref> referred to by <xref
target="RFC2309"></xref> advised that most scarce resources in the
Internet were bit-congestible, which is still believed to be true
(<xref target="pktb_term"></xref>). But it went on to offer advice
that is updated by this memo. It said that drop probability should
depend on the size of the packet being considered for drop if the
resource is bit-congestible, but not if it is packet-congestible.
The argument continued that if packet drops were inflated by
packet size (byte-mode dropping), "a flow's fraction of the packet
drops is then a good indication of that flow's fraction of the
link bandwidth in bits per second". This was consistent with a
referenced policing mechanism being worked on at the time for
detecting unusually high bandwidth flows, eventually published in
1999 <xref target="pBox"></xref>. However, the problem could and
should have been solved by making the policing mechanism count the
volume of bytes randomly dropped, not the number of packets.</t>
<t>A few months before RFC2309 was published, an addendum was
added to the above archived email referenced from the RFC, in
which the final paragraph seemed to partially retract what had
previously been said. It clarified that the question of whether
the probability of dropping/marking a packet should depend on its
size was not related to whether the resource itself was bit
congestible, but a completely orthogonal question. However the
only example given had the queue measured in packets but packet
drop depended on the byte-size of the packet in question. No
example was given the other way round.</t>
<t>In 2000, Cnodder et al <xref target="REDbyte"></xref> pointed
out that there was an error in the part of the original 1993 RED
algorithm that aimed to distribute drops uniformly, because it
didn't correctly take into account the adjustment for packet size.
They recommended an algorithm called RED_4 to fix this. But they
also recommended a further change, RED_5, to adjust drop rate
dependent on the square of relative packet size. This was indeed
consistent with one implied motivation behind RED's byte mode
drop—that we should reverse engineer the network to improve
the performance of dominant end-to-end congestion control
mechanisms. This memo makes a different recommendations in <xref
target="pktb_Recommendations"></xref>.</t>
<t>By 2003, a further change had been made to the adjustment for
packet size, this time in the RED algorithm of the ns2 simulator.
Instead of taking each packet's size relative to a `maximum packet
size' it was taken relative to a `mean packet size', intended to
be a static value representative of the `typical' packet size on
the link. We have not been able to find a justification in the
literature for this change, however Eddy and Allman conducted
experiments <xref target="REDbias"></xref> that assessed how
sensitive RED was to this parameter, amongst other things.
However, this changed algorithm can often lead to drop
probabilities of greater than 1 (which gives a hint that there is
probably a mistake in the theory somewhere).</t>
<t>On 10-Nov-2004, this variant of byte-mode packet drop was made
the default in the ns2 simulator. It seems unlikely that byte-mode
drop has ever been implemented in production networks (<xref
target="pktb_SotA"></xref>), therefore any conclusions based on
ns2 simulations that use RED without disabling byte-mode drop are
likely to behave very differently from RED in production
networks.</t>
</section>
<section title="Packet Size Bias Regardless of RED">
<t>The byte-mode drop variant of RED is, of course, not the only
possible bias towards small packets in queueing systems. We have
already mentioned that tail-drop queues naturally tend to lock-out
large packets once they are full. But also queues with fixed sized
buffers reduce the probability that small packets will be dropped
if (and only if) they allow small packets to borrow buffers from
the pools for larger packets. As was explained in <xref
target="pktb_Fixed_Buffers"></xref> on fixed size buffer carving,
borrowing effectively makes the maximum queue size for small
packets greater than that for large packets, because more buffers
can be used by small packets while less will fit large
packets.</t>
<t>In itself, the bias towards small packets caused by buffer
borrowing is perfectly correct. Lower drop probability for small
packets is legitimate in buffer borrowing schemes, because small
packets genuinely congest the machine's buffer memory less than
large packets, given they can fit in more spaces. The bias towards
small packets is not artificially added (as it is in RED's
byte-mode drop algorithm), it merely reflects the reality of the
way fixed buffer memory gets congested. Incidentally, the bias
towards small packets from buffer borrowing is nothing like as
large as that of RED's byte-mode drop.</t>
<t>Nonetheless, fixed-buffer memory with tail drop is still prone
to lock-out large packets, purely because of the tail-drop aspect.
So a good AQM algorithm like RED with packet-mode drop should be
used with fixed buffer memories where possible. If RED is too
complicated to implement with multiple fixed buffer pools, the
minimum necessary to prevent large packet lock-out is to ensure
smaller packets never use the last available buffer in any of the
pools for larger packets.</t>
</section>
</section>
<!-- - - - - - - - - - - - - - - - - - - - - - - - - - - - - - - - - -->
<section anchor="pktb_Transport_Bias"
title="Transport Bias when Decoding">
<t>The above proposals to alter the network equipment to bias
towards smaller packets have largely carried on outside the IETF
process. Whereas, within the IETF, there are many different
proposals to alter transport protocols to achieve the same goals,
i.e. either to make the flow bit-rate take account of packet size,
or to protect control packets from loss. This memo argues that
altering transport protocols is the more principled approach.</t>
<t>A recently approved experimental RFC adapts its transport layer
protocol to take account of packet sizes relative to typical TCP
packet sizes. This proposes a new small-packet variant of
TCP-friendly rate control <xref target="RFC5348"></xref> called
TFRC-SP <xref target="RFC4828"></xref>. Essentially, it proposes a
rate equation that inflates the flow rate by the ratio of a typical
TCP segment size (1500B including TCP header) over the actual
segment size <xref target="PktSizeEquCC"></xref>. (There are also
other important differences of detail relative to TFRC, such as
using virtual packets <xref target="CCvarPktSize"></xref> to avoid
responding to multiple losses per round trip and using a minimum
inter-packet interval.)</t>
<t>Section 4.5.1 of this TFRC-SP spec discusses the implications of
operating in an environment where queues have been configured to
drop smaller packets with proportionately lower probability than
larger ones. But it only discusses TCP operating in such an
environment, only mentioning TFRC-SP briefly when discussing how to
define fairness with TCP. And it only discusses the byte-mode
dropping version of RED as it was before Cnodder et al pointed out
it didn't sufficiently bias towards small packets to make TCP
independent of packet size.</t>
<t>So the TFRC-SP spec doesn't address the issue of which of the
network or the transport <spanx style="emph">should</spanx> handle
fairness between different packet sizes. In its Appendix B.4 it
discusses the possibility of both TFRC-SP and some network buffers
duplicating each other's attempts to deliberately bias towards small
packets. But the discussion is not conclusive, instead reporting
simulations of many of the possibilities in order to assess
performance but not recommending any particular course of
action.</t>
<t>The paper originally proposing TFRC with virtual packets
(VP-TFRC) <xref target="CCvarPktSize"></xref> proposed that there
should perhaps be two variants to cater for the different variants
of RED. However, as the TFRC-SP authors point out, there is no way
for a transport to know whether some queues on its path have
deployed RED with byte-mode packet drop (except if an exhaustive
survey found that no-one has deployed it!—see <xref
target="pktb_SotA"></xref>). Incidentally, VP-TFRC also proposed
that byte-mode RED dropping should really square the packet-size
compensation-factor (like that of Cnodder's RED_5, but apparently
unaware of it).</t>
<t>Pre-congestion notification <xref target="RFC5670"></xref> is an
IETF technology to use a virtual queue for AQM marking for packets
within one Diffserv class in order to give early warning prior to
any real queuing. The PCN marking algorithms have been designed not
to take account of packet size when forwarding through queues.
Instead the general principle has been to take account of the sizes
of marked packets when monitoring the fraction of marking at the
edge of the network, as recommended here.</t>
</section>
<!-- - - - - - - - - - - - - - - - - - - - - - - - - - - - - - - - - -->
<section anchor="pktb_Transport_Robust_Ctrl_Loss"
title="Making Transports Robust against Control Packet Losses">
<t>Recently, two RFCs have defined changes to TCP that make it more
robust against losing small control packets <xref
target="RFC5562"></xref> <xref target="RFC5690"></xref>. In both
cases they note that the case for these two TCP changes would be
weaker if RED were biased against dropping small packets. We argue
here that these two proposals are a safer and more principled way to
achieve TCP performance improvements than reverse engineering RED to
benefit TCP.</t>
<t>Although there are no known proposals, it would also be possible
and perfectly valid to make control packets robust against drop by
explicitly requesting a lower drop probability using their Diffserv
code point <xref target="RFC2474"></xref> to request a scheduling
class with lower drop.</t>
<!--{ToDo: If ConEx defines optional preferential drop,
add its protocol definition to the Diffserv ref above}-->
<t>Although not brought to the IETF, a simple proposal from Wischik
<xref target="DupTCP"></xref> suggests that the first three packets
of every TCP flow should be routinely duplicated after a short
delay. It shows that this would greatly improve the chances of short
flows completing quickly, but it would hardly increase traffic
levels on the Internet, because Internet bytes have always been
concentrated in the large flows. It further shows that the
performance of many typical applications depends on completion of
long serial chains of short messages. It argues that, given most of
the value people get from the Internet is concentrated within short
flows, this simple expedient would greatly increase the value of the
best efforts Internet at minimal cost.</t>
</section>
<!-- - - - - - - - - - - - - - - - - - - - - - - - - - - - - - - - - -->
<section anchor="pktb_Coding_Status_Summary"
title="Congestion Notification: Summary of Conflicting Advice">
<?rfc needLines="6" ?>
<texttable anchor="pktb_Tab_TFRC-SP"
title="Dependence of flow bit-rate per RTT on packet size, s, and drop probability, p, when network and/or transport bias towards small packets to varying degrees">
<ttcol align="right">transport cc</ttcol>
<ttcol align="center">RED_1 (packet mode drop)</ttcol>
<ttcol align="center">RED_4 (linear byte mode drop)</ttcol>
<ttcol align="center">RED_5 (square byte mode drop)</ttcol>
<c>TCP or TFRC</c>
<c>s/sqrt(p)</c>
<c>sqrt(s/p)</c>
<c>1/sqrt(p)</c>
<c>TFRC-SP</c>
<c>1/sqrt(p)</c>
<c>1/sqrt(sp)</c>
<c>1/(s.sqrt(p))</c>
</texttable>
<t><xref target="pktb_Tab_TFRC-SP"></xref> aims to summarise the
potential effects of all the advice from different sources. Each
column shows a different possible AQM behaviour in different queues
in the network, using the terminology of Cnodder et al outlined
earlier (RED_1 is basic RED with packet-mode drop). Each row shows a
different transport behaviour: TCP <xref target="RFC5681"></xref>
and TFRC <xref target="RFC5348"></xref> on the top row with TFRC-SP
<xref target="RFC4828"></xref> below. Each cell shows how the bits
per round trip of a flow depends on packet size, s, and drop
probability, p. In order to declutter the formulae to focus on
packet-size dependence they are all given per round trip, which
removes any RTT term.</t>
<t>Let us assume that the goal is for the bit-rate of a flow to be
independent of packet size. Suppressing all inessential details, the
table shows that this should either be achievable by not altering
the TCP transport in a RED_5 network, or using the small packet
TFRC-SP transport (or similar) in a network without any byte-mode
dropping RED (top right and bottom left). Top left is the `do
nothing' scenario, while bottom right is the `do-both' scenario in
which bit-rate would become far too biased towards small packets. Of
course, if any form of byte-mode dropping RED has been deployed on a
subset of queues that congest, each path through the network will
present a different hybrid scenario to its transport.</t>
<t>Whatever, we can see that the linear byte-mode drop column in the
middle would considerably complicate the Internet. It's a half-way
house that doesn't bias enough towards small packets even if one
believes the network should be doing the biasing. <xref
target="pktb_Recommendations"></xref> recommends that <spanx
style="emph">all</spanx> bias in network equipment towards small
packets should be turned off—if indeed any equipment vendors
have implemented it—leaving packet-size bias solely as the
preserve of the transport layer (solely the leftmost, packet-mode
drop column).</t>
<t>In practice it seems that no deliberate bias towards small
packets has been implemented for production networks. Of the 19% of
vendors who responded to a survey of 84 equipment vendors, none had
implemented byte-mode drop in RED (see <xref
target="pktb_SotA"></xref> for details).</t>
</section>
</section>
</section>
<!-- ================================================================ -->
<section anchor="pktb_Issues" title="Outstanding Issues and Next Steps">
<!-- ________________________________________________________________ -->
<section anchor="pktb_Bit-World" title="Bit-congestible Network">
<t>For a connectionless network with nearly all resources being
bit-congestible the recommended position is clear—that the
network should not make allowance for packet sizes and the transport
should. This leaves two outstanding issues: <list style="symbols">
<t>How to handle any legacy of AQM with byte-mode drop already
deployed;</t>
<t>The need to start a programme to update transport congestion
control protocol standards to take account of packet size.</t>
</list></t>
<t>A survey of equipment vendors (<xref
target="pktb_Coding_Status_Summary"></xref>) found no evidence that
byte-mode packet drop had been implemented, so deployment will be
sparse at best. A migration strategy is not really needed to remove an
algorithm that may not even be deployed.</t>
<t>A programme of experimental updates to take account of packet size
in transport congestion control protocols has already started with
TFRC-SP <xref target="RFC4828"></xref>.</t>
</section>
<!-- ________________________________________________________________ -->
<section anchor="pktb_Bit-Pkt-World"
title="Bit- & Packet-congestible Network">
<t>The position is much less clear-cut if the Internet becomes
populated by a more even mix of both packet-congestible and
bit-congestible resources (see <xref
target="pktb_bit_pkt-congestible"></xref>). This problem is not
pressing, because most Internet resources are designed to be
bit-congestible before packet processing starts to congest (see <xref
target="pktb_term"></xref>). </t>
<t>The IRTF Internet congestion control research group (ICCRG) has set
itself the task of reaching consensus on generic forwarding mechanisms
that are necessary and sufficient to support the Internet's future
congestion control requirements (the first challenge in <xref
target="RFC6077"></xref>). The research question of whether packet congestion might
become common and what to do if it does may in the future be explored in the IRTF
(the "Challenge 3: Packet Size" in <xref target="RFC6077"></xref>).</t>
</section>
</section>
<!-- ================================================================ -->
<section anchor="pktb_Security_Considerations"
title="Security Considerations">
<t>This memo recommends that queues do not bias drop probability towards
small packets as this creates a perverse incentive for transports to
break down their flows into tiny segments. One of the benefits of
implementing AQM was meant to be to remove this perverse incentive that
drop-tail queues gave to small packets.</t>
<!-- Of course, if
transports really want to make the greatest gains, they don't have to
respond to congestion anyway. But we don't want applications that are
trying to behave to discover that they can go faster by using smaller
packets.</t>
-->
<t>In practice, transports cannot all be trusted to respond to
congestion. So another reason for recommending that queues do not bias
drop probability towards small packets is to avoid the vulnerability to
small packet DDoS attacks that would otherwise result. One of the
benefits of implementing AQM was meant to be to remove drop-tail's DoS
vulnerability to small packets, so we shouldn't add it back again.</t>
<t>If most queues implemented AQM with byte-mode drop, the resulting
network would amplify the potency of a small packet DDoS attack. At the
first queue the stream of packets would push aside a greater proportion
of large packets, so more of the small packets would survive to attack
the next queue. Thus a flood of small packets would continue on towards
the destination, pushing regular traffic with large packets out of the
way in one queue after the next, but suffering much less drop
itself.</t>
<t><xref target="pktb_Policing_Congestion_Response"></xref> explains why
the ability of networks to police the response of <spanx style="emph">any</spanx>
transport to congestion depends on bit-congestible network resources
only doing packet-mode not byte-mode drop. In summary, it says that
making drop probability depend on the size of the packets that bits
happen to be divided into simply encourages the bits to be divided into
smaller packets. Byte-mode drop would therefore irreversibly complicate
any attempt to fix the Internet's incentive structures.</t>
</section>
<!-- ================================================================ -->
<section anchor="pktb_Conclusions" title="Conclusions">
<t>This memo identifies the three distinct stages of the congestion
notification process where implementations need to decide whether to
take packet size into account. The recommendations provided in Section 2 of this memo are
different in each case:<list style="symbols">
<t>When network equipment measures the length of a queue, whether it
counts in bytes or packets depends on whether the network resource
is congested respectively by bytes or by packets.</t>
<t>When network equipment decides whether to drop (or mark) a
packet, it is recommended that the size of the particular packet
should not be taken into account</t>
<t>However, when a transport algorithm responds to a dropped or
marked packet, the size of the rate reduction should be
proportionate to the size of the packet.</t>
</list>In summary, the answers are 'it depends', 'no' and 'yes'
respectively</t>
<t>For the specific case of RED, this means that byte-mode queue measurement
will often be appropriate although byte-mode drop is strongly deprecated.</t>
<t>At the transport layer the IETF should continue updating congestion
control protocols to take account of the size of each packet that
indicates congestion. Also the IETF should continue to make protocols
less sensitive to losing control packets like SYNs, pure ACKs and DNS
exchanges. Although many control packets happen to be small, the
alternative of network equipment favouring all small packets would be
dangerous. That would create perverse incentives to split data transfers
into smaller packets.</t>
<t>The memo develops these recommendations from principled arguments
concerning scaling, layering, incentives, inherent efficiency, security
and policeability. But it also addresses practical issues such as
specific buffer architectures and incremental deployment. Indeed a
limited survey of RED implementations is discussed, which shows there
appears to be little, if any, installed base of RED's byte-mode drop.
Therefore it can be deprecated with little, if any, incremental
deployment complications.</t>
<t>The recommendations have been developed on the well-founded basis
that most Internet resources are bit-congestible not packet-congestible.
We need to know the likelihood that this assumption will prevail longer
term and, if it might not, what protocol changes will be needed to cater
for a mix of the two. The IRTF Internet Congestion Control Research Group (ICCRG) is
currently working on these problems <xref target="RFC6077"></xref>.</t>
</section>
<!-- ================================================================ -->
<section anchor="pktb_Acknowledgements" title="Acknowledgements">
<t>Thank you to Sally Floyd, who gave extensive and useful review
comments. Also thanks for the reviews from Philip Eardley, David Black,
Fred Baker, Toby Moncaster, Arnaud Jacquet and Mirja Kuehlewind as well
as helpful explanations of different hardware approaches from Larry Dunn
and Fred Baker. We are grateful to Bruce Davie and his colleagues for
providing a timely and efficient survey of RED implementation in Cisco's
product range. Also grateful thanks to Toby Moncaster, Will Dormann,
John Regnault, Simon Carter and Stefaan De Cnodder who further helped
survey the current status of RED implementation and deployment and,
finally, thanks to the anonymous individuals who responded.</t>
<t>Bob Briscoe and Jukka Manner were partly funded by Trilogy, a research
project (ICT- 216372) supported by the European Community under its
Seventh Framework Programme. The views expressed here are those of the
authors only.</t>
</section>
<!-- ================================================================ -->
<section anchor="pktb_Comments_Solicited" title="Comments Solicited">
<t>Comments and questions are encouraged and very welcome. They can be
addressed to the IETF Transport Area working group mailing list
<tsvwg@ietf.org>, and/or to the authors.</t>
</section>
</middle>
<back>
<!-- ================================================================ -->
<references title="Normative References">
<?rfc include="reference.RFC.2119" ?>
<?rfc include="reference.RFC.2309" ?>
<?rfc include="reference.RFC.3168" ?>
<?rfc include="reference.RFC.3426" ?>
</references>
<references title="Informative References">
<?rfc include="localref.Floyd93.RED" ?>
<?rfc include="localref.Floyd97.REDPktByteEmail" ?>
<?rfc include="localref.Floyd99.Penalty_box" ?>
<!-- <?rfc include="localref.Crowcroft98.MulTCP" ?>
-->
<?rfc include="localref.Gibbens99.Evol_cc" ?>
<?rfc include="localref.Elloumi00.REDbyte" ?>
<?rfc include="localref.Vasallo00.PktSizeEquCC" ?>
<!-- <?rfc include="localref.Siris02a.Window_ECN" ?>
-->
<?rfc include="localref.Siris02.RscCtrlCDMA" ?>
<?rfc include="reference.RFC.2474" ?>
<?rfc include="reference.RFC.3714" ?>
<?rfc include="reference.RFC.5348" ?>
<?rfc include='reference.RFC.4828'?>
<?rfc include="localref.Eddy03.REDbias" ?>
<?rfc include="localref.Widmer04.CCvarPktSize" ?>
<!-- <?rfc include="localref.I-D.briscoe-tsvwg-re-ecn-tcp" ?>-->
<?rfc include="localref.Briscoe07.Rate_fair_Dis" ?>
<?rfc include="reference.RFC.5681" ?>
<!-- <?rfc include="reference.RFC.3465" ?> -->
<!-- <?rfc include="localref.I-D.falk-xcp-spec" ?>-->
<!-- <?rfc include="reference.RFC.4782" ?>-->
<?rfc include='localref.Floyd00.gentle_RED'?>
<!-- <?rfc include='reference.I-D.ietf-tcpm-ecnsyn'?>
<?rfc include='reference.I-D.floyd-tcpm-ackcc'?>
-->
<?rfc include='localref.Wischik07.ShortMsgs'?>
<?rfc include='localref.Shin08.DRQ'?>
<?rfc include='localref.Bolla00.Cisco_IOS_Arch'?>
<?rfc include='localref.Psounis01.CHOKe_Var_Pkt'?>
<!--
<reference anchor="I-D.irtf-iccrg-welzl">
<front>
<title>Open Research Issues in Internet Congestion Control</title>
<author fullname="Michael Welzl" initials="M" surname="Welzl">
<organization></organization>
</author>
<author fullname="Michael Scharf" initials="M" surname="Scharf">
<organization></organization>
</author>
<author fullname="Bob Briscoe" initials="B" surname="Briscoe">
<organization></organization>
</author>
<author fullname="Dimitri Papadimitriou" initials="D"
surname="Papadimitriou">
<organization></organization>
</author>
<date day="2" month="September" year="2010" />
<abstract>
<t>This document describes some of the open problems in Internet
congestion control that are known today. This includes several new
challenges that are becoming important as the network grows, as
well as some issues that have been known for many years. These
challenges are generally considered to be open research topics
that may require more study or application of innovative
techniques before Internet- scale solutions can be confidently
engineered and deployed. This document represents the work and the
consensus of the ICCRG.</t>
</abstract>
</front>
<seriesInfo name="Internet-Draft"
value="draft-irtf-iccrg-welzl-congestion-control-open-research-08" />
<format target="http://www.ietf.org/internet-drafts/draft-irtf-iccrg-welzl-congestion-control-open-research-08.txt"
type="TXT" />
</reference>
-->
<!--
<reference anchor="I-D.conex-concepts-uses">
<front>
<title>ConEx Concepts and Use Cases</title>
<author fullname="Bob Briscoe" initials="B" surname="Briscoe">
<organization></organization>
</author>
<author fullname="Richard Woundy" initials="R" surname="Woundy">
<organization></organization>
</author>
<author fullname="Toby Moncaster" initials="T" surname="Moncaster">
<organization></organization>
</author>
<author fullname="John Leslie" initials="J" surname="Leslie">
<organization></organization>
</author>
<date day="12" month="July" year="2010" />
<abstract>
<t>Internet Service Providers (ISPs) are facing problems where
localized congestion prevents full utilization of the path between
sender and receiver at today's "broadband" speeds. ISPs desire to
control this congestion, which often appears to be caused by a
small number of users consuming a large amount of bandwidth.
Building out more capacity along all of the path to handle this
congestion can be expensive and may not result in improvements for
all users so network operators have sought other ways to manage
congestion. The current mechanisms all suffer from difficulty
measuring the congestion (as distinguished from the total
traffic). The ConEx Working Group is designing a mechanism to make
congestion along any path visible at the Internet Layer. This
document describes example cases where this mechanism would be
useful.</t>
</abstract>
</front>
<seriesInfo name="Internet-Draft"
value="draft-moncaster-conex-concepts-uses-01" />
<format target="http://www.ietf.org/internet-drafts/draft-moncaster-conex-concepts-uses-01.txt"
type="TXT" />
</reference>
-->
<?rfc include='reference.RFC.3550'?>
<?rfc include='reference.RFC.5670'?>
<?rfc include='reference.RFC.6077'?>
<?rfc include='reference.RFC.5562'?>
<?rfc include='reference.RFC.5690'?>
<?rfc include='reference.I-D.ietf-avtcore-ecn-for-rtp'?>
<?rfc include='reference.I-D.ietf-conex-concepts-uses'?>
</references>
<!-- ================================================================ -->
<!-- ================================================================ -->
<!--
<section anchor="pktb_CN_Definition"
title="Congestion Notification Definition: Further Justification">
<t>In <xref target="pktb_term"></xref> on the definition of congestion
notification, load not capacity was used as the denominator. This also
has a subtle significance in the related debate over the design of new
transport protocols—typical new protocol designs (e.g. in XCP
<xref target="xcp-spec"></xref> & Quickstart <xref
target="RFC4782"></xref>) expect the sending transport to communicate
its desired flow rate to the network and network elements to
progressively subtract from this so that the achievable flow rate
emerges at the receiving transport.</t>
<t>Congestion notification with total load in the denominator can serve
a similar purpose (though in retrospect not in advance like XCP &
QuickStart). Congestion notification is a dimensionless fraction but
each source can extract necessary rate information from it because it
already knows what its own rate is. Even though congestion notification
doesn't communicate a rate explicitly, from each source's point of view
congestion notification represents the fraction of the rate it was
sending a round trip ago that couldn't (or wouldn't) be served by
available resources.</t>
</section>
-->
<!-- Old Section 5 ============================================ -->
<section anchor="pktb_SotA" title="Survey of RED Implementation Status">
<t>This Appendix is informative, not normative.</t>
<t>In May 2007 a survey was conducted of 84 vendors to assess how widely
drop probability based on packet size has been implemented in RED <xref
target="pktb_Tab_RED_Survey"></xref>. <!-- Prior to the survey, an individual approach to Cisco received
confirmation that, having checked the code-base for each of the
product ranges, Cisco has not implemented any discrimination based
on packet size in any AQM algorithm in any of its products. Also an
individual approach to Alcatel-Lucent drew a confirmation that it
was very likely that none of their products contained RED code that
implemented any packet-size bias.</t>
<t>Turning to the survey (<xref
target="pktb_Tab_RED_Survey"></xref>),
-->About 19% of those surveyed replied, giving a sample size of 16. Although
in most cases we do not have permission to identify the respondents, we
can say that those that have responded include most of the larger
equipment vendors, covering a large fraction of the market. The two who
gave permission to be identified were Cisco and Alcatel-Lucent. The
others range across the large network equipment vendors at L3 & L2,
firewall vendors, wireless equipment vendors, as well as large software
businesses with a small selection of networking products. All those who
responded confirmed that they have not implemented the variant of RED
with drop dependent on packet size (2 were fairly sure they had not but
needed to check more thoroughly). At the time the survey was conducted,
Linux did not implement RED with packet-size bias of drop, although we
have not investigated a wider range of open source code.</t>
<texttable anchor="pktb_Tab_RED_Survey"
title="Vendor Survey on byte-mode drop variant of RED (lower drop probability for small packets)">
<preamble></preamble>
<ttcol align="right">Response</ttcol>
<ttcol align="right">No. of vendors</ttcol>
<ttcol align="right">%age of vendors</ttcol>
<c>Not implemented</c>
<c>14</c>
<c>17%</c>
<c>Not implemented (probably)</c>
<c>2</c>
<c>2%</c>
<c>Implemented</c>
<c>0</c>
<c>0%</c>
<c>No response</c>
<c>68</c>
<c>81%</c>
<c>Total companies/orgs surveyed</c>
<c>84</c>
<c>100%</c>
<postamble></postamble>
</texttable>
<t>Where reasons have been given, the extra complexity of packet bias
code has been most prevalent, though one vendor had a more principled
reason for avoiding it—similar to the argument of this
document.</t>
<!--
<t>Finally, we repeat that RED's byte mode drop SHOULD be disabled,
but active queue management such as RED SHOULD be enabled wherever
possible if we are to eradicate bias towards small
packets—without any AQM at all, tail-drop tends to lock-out
large packets very effectively. </t>
-->
<t>Our survey was of vendor implementations, so we cannot be certain
about operator deployment. But we believe many queues in the Internet
are still tail-drop. The company of one of the co-authors (BT) has
widely deployed RED, but many tail-drop queues are bound to still exist,
particularly in access network equipment and on middleboxes like
firewalls, where RED is not always available.</t>
<t>Routers using a memory architecture based on fixed size buffers with
borrowing may also still be prevalent in the Internet. As explained in
<xref target="pktb_Network_Bias"></xref>, these also provide a marginal
(but legitimate) bias towards small packets. So even though RED
byte-mode drop is not prevalent, it is likely there is still some bias
towards small packets in the Internet due to tail drop and fixed buffer
borrowing.</t>
</section>
<section anchor="pktb_Ideal" title="Sufficiency of Packet-Mode Drop">
<t>This Appendix is informative, not normative.</t>
<t>Here we check that packet-mode drop (or marking) in the network gives
sufficiently generic information for the transport layer to use. We
check against a 2x2 matrix of four scenarios that may occur now or in
the future (<xref target="pktb_Tab_Main_Scenarios"></xref>). The
horizontal and vertical dimensions have been chosen because each tests
extremes of sensitivity to packet size in the transport and in the
network respectively.</t>
<t>Note that this section does not consider byte-mode drop at all.
Having deprecated byte-mode drop, the goal here is to check that
packet-mode drop will be sufficient in all cases.</t>
<?rfc needLines="6" ?>
<texttable anchor="pktb_Tab_Main_Scenarios"
title="Four Possible Congestion Scenarios">
<ttcol
align="left"> Transport
Network</ttcol>
<ttcol align="center">a) Independent of packet size of congestion
notifications</ttcol>
<ttcol align="center">b) Dependent on packet size of congestion
notifications</ttcol>
<c>1) Predominantly bit-congestible network</c>
<c>Scenario a1)</c>
<c>Scenario b1)</c>
<c>2) Mix of bit-congestible and pkt-congestible network</c>
<c>Scenario a2)</c>
<c>Scenario b2)</c>
</texttable>
<t><xref target="pktb_Size-Dependence_Transport"></xref> focuses on the
horizontal dimension of <xref target="pktb_Tab_Main_Scenarios"></xref>
checking that packet-mode drop (or marking) gives sufficient
information, whether or not the transport uses it—scenarios b) and
a) respectively.</t>
<t><xref target="pktb_bit_pkt-congestible"></xref> focuses on the
vertical dimension of <xref target="pktb_Tab_Main_Scenarios"></xref>,
checking that packet-mode drop gives sufficient information to the
transport whether resources in the network are bit-congestible or
packet-congestible (these terms are defined in <xref
target="pktb_term"></xref>).</t>
<t><list style="hanging">
<t hangText="Notation:">To be concrete, we will compare two flows
with different packet sizes, s_1 and s_2. As an example, we will
take s_1 = 60B = 480b and s_2 = 1500B = 12,000b.</t>
<t hangText="">A flow's bit rate, x [bps], is related to its packet
rate, u [pps], by <list style="empty">
<t>x(t) = s.u(t).</t>
</list></t>
<t>In the bit-congestible case, path congestion will be denoted by
p_b, and in the packet-congestible case by p_p. When either case is
implied, the letter p alone will denote path congestion.</t>
</list></t>
<section anchor="pktb_Size-Dependence_Transport"
title="Packet-Size (In)Dependence in Transports">
<t>In all cases we consider a packet-mode drop queue that indicates
congestion by dropping (or marking) packets with probability p
irrespective of packet size. We use an example value of loss
(marking) probability, p=0.1%.</t>
<t>A transport like RFC5681 TCP treats a congestion notification on
any packet whatever its size as one event. However, a network with
just the packet-mode drop algorithm does give more information if the
transport chooses to use it. We will use <xref
target="pktb_Tab_Absolute_and_Ratio"></xref> to illustrate this.</t>
<t>We will set aside the last column until later. The columns labelled
"Flow 1" and "Flow 2" compare two flows consisting of 60B and 1500B
packets respectively. The body of the table considers two separate
cases, one where the flows have equal bit-rate and the other with
equal packet-rates. In both cases, the two flows fill a 96Mbps link.
Therefore, in the equal bit-rate case they each have half the bit-rate
(48Mbps). Whereas, with equal packet-rates, flow 1 uses 25 times
smaller packets so it gets 25 times less bit-rate—it only gets
1/(1+25) of the link capacity (96Mbps/26 = 4Mbps after rounding). In
contrast flow 2 gets 25 times more bit-rate (92Mbps) in the equal
packet rate case because its packets are 25 times larger. The packet
rate shown for each flow could easily be derived once the bit-rate was
known by dividing bit-rate by packet size, as shown in the column
labelled "Formula".</t>
<texttable anchor="pktb_Tab_Absolute_and_Ratio" style="headers"
title="Absolute Loss Rates and Loss Ratios for Flows of Small and Large Packets and Both Combined">
<ttcol>Parameter</ttcol>
<ttcol>Formula</ttcol>
<ttcol align="right">Flow 1</ttcol>
<ttcol align="right">Flow 2</ttcol>
<ttcol align="right">Combined</ttcol>
<c>Packet size</c>
<c>s/8</c>
<c>60B</c>
<c>1,500B</c>
<c>(Mix)</c>
<c>Packet size</c>
<c>s</c>
<c>480b</c>
<c>12,000b</c>
<c>(Mix)</c>
<c>Pkt loss probability</c>
<c>p</c>
<c>0.1%</c>
<c>0.1%</c>
<c>0.1%</c>
<c> </c>
<c></c>
<c></c>
<c></c>
<c></c>
<c>EQUAL BIT-RATE CASE</c>
<c></c>
<c></c>
<c></c>
<c></c>
<c>Bit-rate</c>
<c>x</c>
<c>48Mbps</c>
<c>48Mbps</c>
<c>96Mbps</c>
<c>Packet-rate</c>
<c>u = x/s</c>
<c>100kpps</c>
<c>4kpps</c>
<c>104kpps</c>
<c>Absolute pkt-loss-rate</c>
<c>p*u</c>
<c>100pps</c>
<c>4pps</c>
<c>104pps</c>
<c>Absolute bit-loss-rate</c>
<c>p*u*s</c>
<c>48kbps</c>
<c>48kbps</c>
<c>96kbps</c>
<c>Ratio of lost/sent pkts</c>
<c>p*u/u</c>
<c>0.1%</c>
<c>0.1%</c>
<c>0.1%</c>
<c>Ratio of lost/sent bits</c>
<c>p*u*s/(u*s)</c>
<c>0.1%</c>
<c>0.1%</c>
<c>0.1%</c>
<c> </c>
<c></c>
<c></c>
<c></c>
<c></c>
<c>EQUAL PACKET-RATE CASE</c>
<c></c>
<c></c>
<c></c>
<c></c>
<c>Bit-rate</c>
<c>x</c>
<c>4Mbps</c>
<c>92Mbps</c>
<c>96Mbps</c>
<c>Packet-rate</c>
<c>u = x/s</c>
<c>8kpps</c>
<c>8kpps</c>
<c>15kpps</c>
<c>Absolute pkt-loss-rate</c>
<c>p*u</c>
<c>8pps</c>
<c>8pps</c>
<c>15pps</c>
<c>Absolute bit-loss-rate</c>
<c>p*u*s</c>
<c>4kbps</c>
<c>92kbps</c>
<c>96kbps</c>
<c>Ratio of lost/sent pkts</c>
<c>p*u/u</c>
<c>0.1%</c>
<c>0.1%</c>
<c>0.1%</c>
<c>Ratio of lost/sent bits</c>
<c>p*u*s/(u*s)</c>
<c>0.1%</c>
<c>0.1%</c>
<c>0.1%</c>
</texttable>
<t>So far we have merely set up the scenarios. We now consider
congestion notification in the scenario. Two TCP flows with the same
round trip time aim to equalise their packet-loss-rates over time.
That is the number of packets lost in a second, which is the packets
per second (u) multiplied by the probability that each one is dropped
(p). Thus TCP converges on the "Equal packet-rate" case, where both
flows aim for the same "Absolute packet-loss-rate" (both 8pps in the
table).</t>
<t>Packet-mode drop actually gives flows sufficient information to
measure their loss-rate in bits per second, if they choose, not just
packets per second. Each flow can count the size of a lost or marked
packet and scale its rate-response in proportion (as TFRC-SP does).
The result is shown in the row entitled "Absolute bit-loss-rate",
where the bits lost in a second is the packets per second (u)
multiplied by the probability of losing a packet (p) multiplied by the
packet size (s). Such an algorithm would try to remove any imbalance
in bit-loss-rate such as the wide disparity in the "Equal packet-rate"
case (4kbps vs. 92kbps). Instead, a packet-size-dependent algorithm
would aim for equal bit-loss-rates, which would drive both flows
towards the "Equal bit-rate" case, by driving them to equal
bit-loss-rates (both 48kbps in this example).</t>
<t>The explanation so far has assumed that each flow consists of
packets of only one constant size. Nonetheless, it extends naturally
to flows with mixed packet sizes. In the right-most column of <xref
target="pktb_Tab_Absolute_and_Ratio"></xref> a flow of mixed size
packets is created simply by considering flow 1 and flow 2 as a single
aggregated flow. There is no need for a flow to maintain an average
packet size. It is only necessary for the transport to scale its
response to each congestion indication by the size of each individual
lost (or marked) packet. Taking for example the "Equal packet-rate"
case, in one second about 8 small packets and 8 large packets are lost
(making closer to 15 than 16 losses per second due to rounding). If
the transport multiplies each loss by its size, in one second it
responds to 8*480b and 8*12,000b lost bits, adding up to 96,000 lost
bits in a second. This double checks correctly, being the same as 0.1%
of the total bit-rate of 96Mbps. For completeness, the formula for
absolute bit-loss-rate is p(u1*s1+u2*s2). </t>
<t>Incidentally, a transport will always measure the loss probability
the same irrespective of whether it measures in packets or in bytes.
In other words, the ratio of lost to sent packets will be the same as
the ratio of lost to sent bytes. (This is why TCP's bit rate is still
proportional to packet size even when byte-counting is used, as
recommended for TCP in <xref target="RFC5681"></xref>, mainly for
orthogonal security reasons.) This is intuitively obvious by comparing
two example flows; one with 60B packets, the other with 1500B packets.
If both flows pass through a queue with drop probability 0.1%, each
flow will lose 1 in 1,000 packets. In the stream of 60B packets the
ratio of bytes lost to sent will be 60B in every 60,000B; and in the
stream of 1500B packets, the loss ratio will be 1,500B out of
1,500,000B. When the transport responds to the ratio of lost to sent
packets, it will measure the same ratio whether it measures in packets
or bytes: 0.1% in both cases. The fact that this ratio is the same
whether measured in packets or bytes can be seen in <xref
target="pktb_Tab_Absolute_and_Ratio"></xref>, where the ratio of lost
to sent packets and the ratio of lost to sent bytes is always 0.1% in
all cases (recall that the scenario was set up with p=0.1%). </t>
<t>This discussion of how the ratio can be measured in packets or
bytes is only raised here to highlight that it is irrelevant to this
memo! Whether a transport depends on packet size or not depends on how
this ratio is used within the congestion control algorithm. </t>
<t>So far we have shown that packet-mode drop passes sufficient
information to the transport layer so that the transport can take
account of bit-congestion, by using the sizes of the packets that
indicate congestion. We have also shown that the transport can choose
not to take packet size into account if it wishes. We will now
consider whether the transport can know which to do.</t>
</section>
<section anchor="pktb_bit_pkt-congestible"
title="Bit-Congestible and Packet-Congestible Indications">
<t>As a thought-experiment, imagine an idealised congestion
notification protocol that supports both bit-congestible and
packet-congestible resources. It would require at least two ECN flags,
one for each of bit-congestible and packet-congestible resources.
<list style="numbers">
<t>A packet-congestible resource trying to code congestion level
p_p into a packet stream should mark the idealised `packet
congestion' field in each packet with probability p_p irrespective
of the packet's size. The transport should then take a packet with
the packet congestion field marked to mean just one mark,
irrespective of the packet size.</t>
<t>A bit-congestible resource trying to code time-varying
byte-congestion level p_b into a packet stream should mark the
`byte congestion' field in each packet with probability p_b, again
irrespective of the packet's size. Unlike before, the transport
should take a packet with the byte congestion field marked to
count as a mark on each byte in the packet.</t>
</list></t>
<t>This hides a fundamental problem—much more fundamental than
whether we can magically create header space for yet another ECN flag,
or whether it would work while being deployed incrementally.
Distinguishing drop from delivery naturally provides just one implicit
bit of congestion indication information—the packet is either
dropped or not. It is hard to drop a packet in two ways that are
distinguishable remotely. This is a similar problem to that of
distinguishing wireless transmission losses from congestive
losses.</t>
<t>This problem would not be solved even if ECN were universally
deployed. A congestion notification protocol must survive a transition
from low levels of congestion to high. Marking two states is feasible
with explicit marking, but much harder if packets are dropped. Also,
it will not always be cost-effective to implement AQM at every low
level resource, so drop will often have to suffice.</t>
<t>We are not saying two ECN fields will be needed (and we are not
saying that somehow a resource should be able to drop a packet in one
of two different ways so that the transport can distinguish which sort
of drop it was!). These two congestion notification channels are a
conceptual device to illustrate a dilemma we could face in the future.
<xref target="pktb_Motivation"></xref> gives four good reasons why it
would be a bad idea to allow for packet size by biasing drop
probability in favour of small packets within the network. The
impracticality of our thought experiment shows that it will be hard to
give transports a practical way to know whether to take account of the
size of congestion indication packets or not. </t>
<t>Fortunately, this dilemma is not pressing because by design most
equipment becomes bit-congested before its packet-processing becomes
congested (as already outlined in <xref target="pktb_term"></xref>).
Therefore transports can be designed on the relatively sound
assumption that a congestion indication will usually imply
bit-congestion.</t>
<t>Nonetheless, although the above idealised protocol isn't intended
for implementation, we do want to emphasise that research is needed to
predict whether there are good reasons to believe that packet
congestion might become more common, and if so, to find a way to
somehow distinguish between bit and packet congestion <xref
target="RFC3714"></xref>. </t>
<t>Recently, the dual resource queue (DRQ) proposal <xref
target="DRQ"></xref> has been made on the premise that, as network
processors become more cost effective, per packet operations will
become more complex (irrespective of whether more function in the
network is desirable). Consequently the premise is that CPU congestion
will become more common. DRQ is a proposed modification to the RED
algorithm that folds both bit congestion and packet congestion into
one signal (either loss or ECN).</t>
<t>Finally, we note one further complication. Strictly,
packet-congestible resources are often cycle-congestible. For
instance, for routing look-ups load depends on the complexity of each
look-up and whether the pattern of arrivals is amenable to caching or
not. This also reminds us that any solution must not require a
forwarding engine to use excessive processor cycles in order to decide
how to say it has no spare processor cycles.</t>
</section>
</section>
<section anchor="pktb_Policing_Congestion_Response"
title="Byte-mode Drop Complicates Policing Congestion Response">
<t>This section is informative, not normative.</t>
<t>There are two main classes of approach to policing congestion
response: i) policing at each bottleneck link or ii) policing at the
edges of networks. Packet-mode drop in RED is compatible with either,
while byte-mode drop precludes edge policing.</t>
<t>The simplicity of an edge policer relies on one dropped or marked
packet being equivalent to another of the same size without having to
know which link the drop or mark occurred at. However, the byte-mode
drop algorithm has to depend on the local MTU of the line—it needs
to use some concept of a 'normal' packet size. Therefore, one dropped or
marked packet from a byte-mode drop algorithm is not necessarily
equivalent to another from a different link. A policing function local
to the link can know the local MTU where the congestion occurred.
However, a policer at the edge of the network cannot, at least not
without a lot of complexity.</t>
<t>The early research proposals for type (i) policing at a bottleneck
link <xref target="pBox"></xref> used byte-mode drop, then detected
flows that contributed disproportionately to the number of packets
dropped. However, with no extra complexity, later proposals used packet
mode drop and looked for flows that contributed a disproportionate
amount of dropped bytes <xref target="CHOKe_Var_Pkt"></xref>.</t>
<t>Work is progressing on the congestion exposure protocol (ConEx <xref
target="I-D.ietf-conex-concepts-uses"></xref>), which enables a type
(ii) edge policer located at a user's attachment point. The idea is to
be able to take an integrated view of the effect of all a user's traffic
on any link in the internetwork. However, byte-mode drop would
effectively preclude such edge policing because of the MTU issue
above.</t>
<t>Indeed, making drop probability depend on the size of the packets
that bits happen to be divided into would simply encourage the bits to
be divided into smaller packets in order to confuse policing. In
contrast, as long as a dropped/marked packet is taken to mean that all
the bytes in the packet are dropped/marked, a policer can remain robust
against bits being re-divided into different size packets or across
different size flows <xref target="Rate_fair_Dis"></xref>.</t>
</section>
<section anchor="changelog" title="Changes from Previous Versions">
<t>To be removed by the RFC Editor on publication.</t>
<t>Full incremental diffs between each version are available at
<http://tools.ietf.org/wg/tsvwg/draft-ietf-tsvwg-byte-pkt-congest/>
(courtesy of the rfcdiff tool): <list style="hanging">
<t hangText="From -06 to -07:"><list style="symbols">
<t>A mix-up with the corollaries and their naming in 2.1 to 2.3 fixed.</t>
</list></t>
<t hangText="From -05 to -06:"><list style="symbols">
<t>Primarily editorial fixes.</t>
</list></t>
<t hangText="From -04 to -05:"><list style="symbols">
<t>Changed from Informational to BCP and highlighted
non-normative sections and appendices</t>
<t>Removed language about consensus</t>
<t>Added "Example Comparing Packet-Mode Drop and Byte-Mode
Drop"</t>
<t>Arranged "Motivating Arguments" into a more logical order and
completely rewrote "Transport-Independent Network" &
"Scaling Congestion Control with Packet Size" arguments. Removed
"Why Now?"</t>
<t>Clarified applicability of certain recommendations</t>
<t>Shifted vendor survey to an Appendix</t>
<t>Cut down "Outstanding Issues and Next Steps"</t>
<t>Re-drafted the start of the conclusions to highlight the
three distinct areas of concern</t>
<t>Completely re-wrote appendices</t>
<t>Editorial corrections throughout.</t>
</list></t>
<t hangText="From -03 to -04:"><list style="symbols">
<t>Reordered Sections 2 and 3, and some clarifications here and
there based on feedback from Colin Perkins and Mirja
Kuehlewind.</t>
</list></t>
<t hangText="From -02 to -03 (this version)"><list style="symbols">
<t>Structural changes: <list style="symbols">
<t>Split off text at end of "Scaling Congestion Control with
Packet Size" into new section "Transport-Independent
Network"</t>
<t>Shifted "Recommendations" straight after "Motivating
Arguments" and added "Conclusions" at end to reinforce
Recommendations</t>
<t>Added more internal structure to Recommendations, so that
recommendations specific to RED or to TCP are just
corollaries of a more general recommendation, rather than
being listed as a separate recommendation.</t>
<t>Renamed "State of the Art" as "Critical Survey of
Existing Advice" and retitled a number of subsections with
more descriptive titles.</t>
<t>Split end of "Congestion Coding: Summary of Status" into
a new subsection called "RED Implementation Status".</t>
<t>Removed text that had been in the Appendix "Congestion
Notification Definition: Further Justification".</t>
</list></t>
<t>Reordered the intro text a little.</t>
<t>Made it clearer when advice being reported is deprecated and
when it is not.</t>
<t>Described AQM as in network equipment, rather than saying "at
the network layer" (to side-step controversy over whether
functions like AQM are in the transport layer but in network
equipment).</t>
<t>Minor improvements to clarity throughout</t>
</list></t>
<t hangText="From -01 to -02:"><list style="symbols">
<t>Restructured the whole document for (hopefully) easier
reading and clarity. The concrete recommendation, in RFC2119
language, is now in <xref target="pktb_Conclusions"></xref>.</t>
</list></t>
<t hangText="From -00 to -01:"><list style="symbols">
<t>Minor clarifications throughout and updated references</t>
</list></t>
<t
hangText="From briscoe-byte-pkt-mark-02 to ietf-byte-pkt-congest-00:"><list
style="symbols">
<t>Added note on relationship to existing RFCs</t>
<t>Posed the question of whether packet-congestion could become
common and deferred it to the IRTF ICCRG. Added ref to the
dual-resource queue (DRQ) proposal.</t>
<t>Changed PCN references from the PCN charter &
architecture to the PCN marking behaviour draft most likely to
imminently become the standards track WG item.</t>
</list></t>
<t hangText="From -01 to -02:"><list style="symbols">
<t>Abstract reorganised to align with clearer separation of
issue in the memo.</t>
<t>Introduction reorganised with motivating arguments removed to
new <xref target="pktb_Motivation"></xref>.</t>
<t>Clarified avoiding lock-out of large packets is not the main
or only motivation for RED.</t>
<t>Mentioned choice of drop or marking explicitly throughout,
rather than trying to coin a word to mean either.</t>
<t>Generalised the discussion throughout to any packet
forwarding function on any network equipment, not just
routers.</t>
<t>Clarified the last point about why this is a good time to
sort out this issue: because it will be hard / impossible to
design new transports unless we decide whether the network or
the transport is allowing for packet size.</t>
<t>Added statement explaining the horizon of the memo is long
term, but with short term expediency in mind.</t>
<t>Added material on scaling congestion control with packet size
(<xref target="pktb_Scaling"></xref>).</t>
<t>Separated out issue of normalising TCP's bit rate from issue
of preference to control packets (<xref
target="pktb_Small.NE.Control"></xref>).</t>
<t>Divided up Congestion Measurement section for clarity,
including new material on fixed size packet buffers and buffer
carving (<xref target="pktb_Fixed_Buffers"></xref> & <xref
target="pktb_Network_Bias"></xref>) and on congestion
measurement in wireless link technologies without queues (<xref
target="pktb_Measurement_NoQ"></xref>).</t>
<t>Added section on 'Making Transports Robust against Control
Packet Losses' (<xref
target="pktb_Transport_Robust_Ctrl_Loss"></xref>) with existing
& new material included.</t>
<t>Added tabulated results of vendor survey on byte-mode drop
variant of RED (<xref target="pktb_Tab_RED_Survey"></xref>).</t>
</list></t>
<t hangText="From -00 to -01:"><list style="symbols">
<t>Clarified applicability to drop as well as ECN.</t>
<t>Highlighted DoS vulnerability.</t>
<t>Emphasised that drop-tail suffers from similar problems to
byte-mode drop, so only byte-mode drop should be turned off, not
RED itself.</t>
<t>Clarified the original apparent motivations for recommending
byte-mode drop included protecting SYNs and pure ACKs more than
equalising the bit rates of TCPs with different segment sizes.
Removed some conjectured motivations.</t>
<t>Added support for updates to TCP in progress (ackcc &
ecn-syn-ack).</t>
<t>Updated survey results with newly arrived data.</t>
<t>Pulled all recommendations together into the conclusions.</t>
<t>Moved some detailed points into two additional appendices and
a note.</t>
<t>Considerable clarifications throughout.</t>
<t>Updated references</t>
</list></t>
</list></t>
</section>
</back>
</rfc>
| PAFTECH AB 2003-2026 | 2026-04-23 12:04:20 |