Network Working Group V. Hilt
Internet-Draft I. Rimac
Intended status: Informational M. Tomsu
Expires: January 4, 2009 V. Gurbani
Bell Labs, Alcatel-Lucent
E. Marocco
Telecom Italia
July 3, 2008
A Survey on Research on the Application-Layer Traffic Optimization
(ALTO) Problem
draft-hilt-alto-survey-00
Status of this Memo
By submitting this Internet-Draft, each author represents that any
applicable patent or other IPR claims of which he or she is aware
have been or will be disclosed, and any of which he or she becomes
aware will be disclosed, in accordance with Section 6 of BCP 79.
Internet-Drafts are working documents of the Internet Engineering
Task Force (IETF), its areas, and its working groups. Note that
other groups may also distribute working documents as Internet-
Drafts.
Internet-Drafts are draft documents valid for a maximum of six months
and may be updated, replaced, or obsoleted by other documents at any
time. It is inappropriate to use Internet-Drafts as reference
material or to cite them other than as "work in progress."
The list of current Internet-Drafts can be accessed at
http://www.ietf.org/ietf/1id-abstracts.txt.
The list of Internet-Draft Shadow Directories can be accessed at
http://www.ietf.org/shadow.html.
This Internet-Draft will expire on January 4, 2009.
Copyright Notice
Copyright (C) The IETF Trust (2008).
Abstract
A significant part of the Internet traffic today is generated by
peer-to-peer (P2P) applications used traditionally for file-sharing,
and more recently for real-time communications and live media
Hilt, et al. Expires January 4, 2009 [Page 1]
Internet-Draft ALTO Survey July 2008
streaming. Such applications discover a route to each other through
an overlay network with little knowledge of the underlying network
topology. As a result, they may choose peers based on information
deduced from empirical measurements, which can lead to suboptimal
choices. We refer to this as the Application Layer Traffic
Optimization (ALTO) problem. In this draft we present a survey of
existing literature on discovering topology characteristics.
Table of Contents
1. Introduction . . . . . . . . . . . . . . . . . . . . . . . . . 3
2. Survey of Existing Literature . . . . . . . . . . . . . . . . 4
2.1. Application-Level Topology Estimation . . . . . . . . . . 4
2.2. Topology Estimation through Layer Cooperation . . . . . . 5
2.2.1. P4P Architecture . . . . . . . . . . . . . . . . . . . 5
2.2.2. Oracle-based ISP-P2P Collaboration . . . . . . . . . . 6
2.2.3. ISP-Driven Informed Path Selection (IDIPS) Service . . 7
3. Application-Level Topology Estimation and the ALTO Problem . . 7
4. Security Considerations . . . . . . . . . . . . . . . . . . . 8
5. Informative References . . . . . . . . . . . . . . . . . . . . 8
Authors' Addresses . . . . . . . . . . . . . . . . . . . . . . . . 11
Intellectual Property and Copyright Statements . . . . . . . . . . 12
Hilt, et al. Expires January 4, 2009 [Page 2]
Internet-Draft ALTO Survey July 2008
1. Introduction
A significant part of today's Internet traffic is generated by peer-
to-peer (P2P) applications, used originally for file sharing, and
more recently for realtime multimedia communications and live media
streaming. P2P applications are posing serious challenges to the
Internet infrastructure; by some estimates, P2P systems are so
popular that they make up anywhere between 40% to 85% of the entire
Internet traffic [Meeker], [Karag], [Light], [Linux], [Parker],
[Glasner].
P2P systems ensure that popular content is replicated at multiple
instances in the overlay. But perhaps ironically, a peer searching
for that content may ignore the topology of the latent overlay
network and instead select among available instances based on
information it deduces from empirical measurements, which, in some
particular situations may lead to suboptimal choices. For example, a
shorter round-trip time estimation is not indicative of the bandwidth
and reliability of the underlying links, which have more of an
influence than delay for large file transfer P2P applications.
Most distributed hash tables (DHT) -- the data structure that imposes
a specific ordering for P2P overlays -- use greedy forwarding
algorithms to reach their destination, making locally optimal
decisions that may not turn to be globally optimized [Gummadi-1].
This naturally leads to the Application-Layer Traffic Optimization
(ALTO) problem [I-D.marocco-alto-problem-statement]: how to best
provide the topology of the underlying network while at the same time
allowing the requesting node to use such information to effectively
reach the node on which the content resides. Thus, it would appear
that P2P networks with their application layer routing strategies
based on overlay topologies are in direct competition against the
Internet routing and topology.
One way to solve the ALTO problem is to build distributed
application-level services for location and path selection
[Francis-1], [Ng-1], [Dabek-1], [Costa-1], [Wong-1], [Madhyastha-1],
in order to enable peers to estimate their position in the network
and to efficiently select their neighbors. Similar solutions have
been embedded into P2P applications such as Azureus [Azureus]. A
slightly different approach is to have the Internet service provider
(ISP) take a pro-active role in the routing of P2P application
traffic; the means by which this can be achieved have been proposed
[Aggarwal-1], [Xie-1], [I-D.saucez-idips]. There is an intrinsic
struggle between the layers -- P2P overlay and network underlay --
when performing the same service (routing), however there are
strategies to mitigate this dichotomy [Seetharaman-1].
Hilt, et al. Expires January 4, 2009 [Page 3]
Internet-Draft ALTO Survey July 2008
2. Survey of Existing Literature
Gummadi et al. [Gummadi-1] compare popular DHT algorithms and
besides analyzing their resilience, provide an accurate evaluation of
how well the logical overlay topology maps on the physical network
layer. In their paper, relying only on measurements independently
performed by overlay nodes without the support of additional location
information provided by external entities, they demonstrate that the
most efficient algorithms in terms of resilience and proximity
performance are those based on the simplest geometric concept (i.e.
the ring geometry, rather than hypercubes, tree structures and
butterfly networks).
Regardless of the geometrical properties of the DHTs involved,
interactions between application-layer overlays and the underlying
networks are a rich area of investigation. The available literature
in this field can be taxonomixed in two categories: using
application-level techniques to estimate topology and using an
infrastructure of some sort.
2.1. Application-Level Topology Estimation
In order to provide P2P overlays with topology information essential
for optimizing node selection, different systems have been proposed.
Estimating network topology information on the application level has
been an area of active research. Early work on network distance
estimation based on clustering by Francis et al. [Francis-1] was
followed by the introduction of network coordinate systems such as
GNP by Ng et al. [Ng-1]. Network coordinate systems embed the
network topology in a low-dimensional coordinate space and enable
network distance estimations based on vector distance. Vivaldi
[Dabek-1] and PIC [Costa-1] propose distributed network coordinate
systems that do not need landmarks for coordinate calculation.
Vivaldi is now being used in the popular P2P application Azureus
[Azureus] and studies indicate that it scales well to very large
networks [Ledlie-1].
Coordinate systems require the embedding of the Internet topology
into a coordinate system. This is not always possible without
errors, which impacts the accuracy of distance estimations. For
example, it has proved to be difficult to embed the triangular
inequalities found in Internet path distances [Wang-07]. Thus,
Meridian [Wong-1] abandons the generality of network coordinate
systems and provides specific distance evaluation services. The Ono
project [Ono] take a different approach and uses network measurements
from content-distribution network (CDN) like Akamai to find nearby
peers [Su06]. Used as a plugin to the Azureus BitTorrent client, Ono
Hilt, et al. Expires January 4, 2009 [Page 4]
Internet-Draft ALTO Survey July 2008
provides 31% average download rate improvement.
Most of the work on estimating topology information focuses on
predicting network distance in terms of latency and does not provide
estimates for other metrics such as throughput. However, for many
P2P applications throughput is often more important than latency.
iPlane [Madhyastha-1] aims at creating an atlas of the Internet using
measurements that contains information about latency, bandwidth,
capacity and loss rates.
To determine features of the topology, network measurement tools,
e.g., based on packet dispersion techniques (packet pairs and packet
trains) as described by Dovrolis et al. in [DRM01] can be used.
Moreover, methods of active network probing or passive traffic
monitoring can also generate network statistics relating indirectly
to performance attributes that cannot be directly measured but need
to be inferred. An extensive study of such techniques that are
summarized under the notion of network tomography has been provided
by Coates et al. [CHNY02].
The Joost Video-on-Demand Service uses P2P technology to distribute
streaming video at a bit rate of about 600 kbit/s and higher. In
their experimental analysis, Lei et al. [LEI-07] conclude that the
system is heavily based on a media server infrastructure -- in
particular for channels with lower popularity -- and that a
geographical distance based on address prefix analysis is considered
during the server selection. They show that the peer selection
process today is unlikely based on topology locality. Instead the
peer's capacity influences the the creation of the peer lists similar
to BitTorrent: low capacity peers connect mostly with other low
capacity peers to avoid wasting the high capacity peers bandwidth.
2.2. Topology Estimation through Layer Cooperation
Instead of estimating topology information on the application level
through distributed measurements, this information could be provided
by the entities running the physical networks -- usually ISPs or
network operators. In fact, they have full knowledge of the topology
of the networks they administer and, in order to avoid congestion on
critical links, are interested in helping applications to optimize
the traffic they generate. The remainder of this section briefly
describes three recently proposed solutions that follow such an
approach to address the ALTO problem.
2.2.1. P4P Architecture
The architecture proposed by Xie et al. [Xie-1] have been adopted by
the DCIA P4P working group [P4P-1], an open group established by
Hilt, et al. Expires January 4, 2009 [Page 5]
Internet-Draft ALTO Survey July 2008
ISPs, P2P software distributors and technology researchers with the
dual goal of defining mechanisms to accelerate content distribution
and optimize utilization of network resources.
The main role in the P4P architecture is played by servers called
``iTrackers'', deployed by network providers and accessed by P2P
applications (or, in general, by elements of the P2P system) in order
to make optimal decisions when selecting a peer to connect. An
iTracker may offer three interfaces:
1. Info: Allows P2P elements (e.g. peers or trackers) to get opaque
information associated to an IP address. Such information is
kept opaque to hide the actual network topology, but can be used
to compute the network distance between IP addresses.
2. Policy: Allows P2P elements to obtain policies and guidelines of
the network, which specify how a network provider would like its
networks to be utilized at a high level, regardless of P2P
applications.
3. Capability: Allows P2P elements to request network providers'
capabilities.
The P4P architecture is under evaluation with simulations,
experiments on the PlanetLab distributed testbed and with field tests
with real users. Initial simulations and PlanetLab experiments
results [P4P-1] indicate that improvements in BitTorrent download
completion time and link utilization in the range of 50-70\% are
possible. Results observed in field tests conducted with a modified
version of the software used by the Pando content delivery network
[OpenP4P-1] show improvements in download rate by 23\% and a
significant drop in data delivery average hop count (from 5.5 to
0.89) in certain scenarios.
2.2.2. Oracle-based ISP-P2P Collaboration
The mechanism is fairly simple: a P2P user sends the list of
potential peers to the oracle hosted by its ISP, which ranks such a
list based on its local policies. For instance, the ISP can prefer
peers within its network, to prevent traffic from leaving its
network; further, it can pick higher bandwidth links, or peers that
are geographically closer. Once the application has obtained an
ordered list, it is up to it to establish connections with a number
of peers it can individually choose, but it has enough information to
perform an optimal choice.
Such a solution has been evaluated with simulations and experiments
run on the PlanetLab testbed and the results show both improvements
in content download time and a reduction of overall P2P traffic, even
when only a subset of the applications actually query the oracle to
Hilt, et al. Expires January 4, 2009 [Page 6]
Internet-Draft ALTO Survey July 2008
make their decisions.
2.2.3. ISP-Driven Informed Path Selection (IDIPS) Service
The IDIPS solution [I-D.saucez-idips] was presented during the SHIM6
session of the 71st IETF meeting. It is essentially a modified
version of the solution described in section Section 2.2.2, extended
to accept lists of source addresses other than destinations in order
to function also as a back end for protocols like SHIM6 and LISP
(which aim at optimizing path selection at the network layer). An
evaluation performed on IDIPS shows that costs for both providing and
accessing the service are negligible [Saucez-2].
3. Application-Level Topology Estimation and the ALTO Problem
The application-level techniques described in Section Section 2.1
provide tools for peer-to-peer applications to estimate parameters of
the underlying network topology. Although these techniques can
improve application performance, there are limitations of what can be
achieved by operating only on the application level.
Topology estimation techniques use abstractions of the network
topology which often hide features that would be of interest to the
application. Network coordinate systems, for example, are unable to
detect overlay paths shorter than the direct path in the Internet
topology. However, these paths frequently exist in the Internet
[Wang-07]. Similarly, application-level techniques may not
accurately estimate topologies with multipath routing.
When using network coordinates to estimate topology information the
underlying assumption is that distance in terms of latency determines
performance. However, for file sharing and content distribution
applications there is more to performance than just the network
latency between nodes. The utility of a long-lived data transfer is
determined by the throughput of the underlying TCP protocol, which
depends on the round-trip time as well as the loss rate experienced
on the corresponding path [PFTK98]. Hence, these applications
benefit from a richer set of topology information that goes beyond
latency including loss rate, capacity, available bandwidth.
Some of the topology estimation techniques used by peer-to-peer
applications need time to converge to a result. For example, current
BitTorrent clients implement local, passive traffic measurements and
a tit-for-tat bandwidth reciprocity mechanism to optimize peering
selection at a local level. Peers eventually settle on a set of
neighbors that maximizes their download rate but because peers cannot
reason about the value of neighbors without actively exchanging data
Hilt, et al. Expires January 4, 2009 [Page 7]
Internet-Draft ALTO Survey July 2008
with them and the number of concurrent data transfers is limited
(typically to 5-7), convergence is delayed and easily can be sub-
optimal.
Skype's P2P VoIP application chooses a relay node in cases where two
peers are behind NATs and cannot connect directly. Ren et al.
[REN-06] measured that the relay selection mechanism of Skype is (1)
not able to discover the best possible relay nodes in terms of
minimum RTT (2) requires a long setup and stabilization time, which
degrades the end user experience (3) is creating a non-negligible
amount of overhead traffic due to probing a large number of nodes.
They further showed that the quality of the relay paths could be
improved when the underlying network AS topology is considered.
Some features of the network topology are hard to infer through
application-level techniques and it may not be possible to infer them
at all. An example for such a features are service provider policies
and preferences such as the state and cost associated with
interdomain peering and transit links. Another example is the
traffic engineering policy of a service provider, which may
counteract the routing objective of the overlay network leading to a
poor overall performance [Seetharaman-1].
Finally, application-level techniques often require applications to
perform measurements on the topology. These measurements create
traffic overhead, in particular, if measurements are performed
individually by all applications interested in estimating topology.
4. Security Considerations
This draft is a survey of existing literature on topology estimation.
As such, it does not introduce any new security considerations to be
taken in account beyond what is already discussed in each paper
surveyed.
5. Informative References
[Aggarwal-1]
Aggarwal, V., Feldmann, A., and C. Scheidler, "Can ISPs
and P2P systems co-operate for improved performance?".
[Azureus] "Azureus BitTorrent Client", .
[CHNY02] Coates, M., Hero, A., Nowak, R., and B. Yu, "Internet
Tomography".
Hilt, et al. Expires January 4, 2009 [Page 8]
Internet-Draft ALTO Survey July 2008
[Costa-1] Costa, M., Castro, M., Rowstron, A., and P. Key, "PIC:
Practical Internet coordinates for distance estimation".
[DRM01] Dovrolis, C., Ramanathan, P., and D. Moore, "What do
packet dispersion techniques measure?".
[Dabek-1] Dabek, F., Cox, R., Kaashoek, F., and R. Morris, "Vivaldi:
A Decentralized Network Coordinate System".
[Francis-1]
Francis, P., Jamin, S., Jin, C., Jin, Y., Raz, D.,
Shavitt, Y., and L. Zhang, "IDMaps: A global Internet host
distance estimation service".
[Glasner] Glasner, J., "P2P fuels global bandwidth binge",
.
[Gummadi-1]
Gummadi, K., Gummadi, R., Gribble, S., Ratnasamy, S.,
Shenker, S., and I. Stoica, "The impact of DHT routing
geometry on resilience and proximity".
[I-D.marocco-alto-problem-statement]
Marocco, E. and V. Gurbani, "Application-Layer Traffic
Optimization (ALTO) Problem Statement",
draft-marocco-alto-problem-statement-00 (work in
progress), April 2008.
[I-D.saucez-idips]
Saucez, D., Donnet, B., and O. Bonaventure, "IDIPS : ISP-
Driven Informed Path Selection", draft-saucez-idips-00
(work in progress), February 2008.
[Karag] Karagiannis, T., Broido, A., Brownlee, N., Claffy, K., and
M. Faloutsos, "Is P2P dying or just hiding?".
[LEI-07] Lei, J., Shi, L., and X. Fu, "An experimental analysis of
Joost peer-topeer VoD service".
[Ledlie-1]
Ledlie, J., Gardner, P., and M. Seltzer, "Network
Coordinates in the Wild".
[Light] Lightreading, "Controlling P2P traffic", .
[Linux] linuxReviews.org, "Peer to peer network traffic may
Hilt, et al. Expires January 4, 2009 [Page 9]
Internet-Draft ALTO Survey July 2008
account for up to 85% of Interneta??s bandwidth usage",
.
[Madhyastha-1]
Madhyastha, H., Isdal, T., Piatek, M., Dixon, C.,
Anderson, T., Krishnamurthy, A., and A. Venkataramani.,
"iPlane: an information plane for distributed services".
[Meeker] Meeker, M. and D. Joseph, "The State of the Internet, Part
3", .
[Ng-1] Ng, T. and H. Zhang, "Predicting internet network distance
with coordinates-based approaches".
[Ono] "Northwestern University Ono Project",
.
[OpenP4P-1]
"OpenP4P Web Page", .
[P4P-1] "DCIA P4P Working group",
.
[PFTK98] Padhye, J., Firoiu, V., Towsley, D., and J. Kurose,
"Modeling TCP throughput: A simple model and its empirical
validation".
[Parker] Parker, A., "The true picture of peer-to-peer
filesharing", .
[REN-06] Ren, S., Guo, L., and X. Zhang, "ASAP: An AS-aware peer-
relay protocol for high quality VoIP".
[Saucez-2]
Saucez, D., Donnet, B., and O. Bonaventure,
"Implementation and Preliminary Evaluation of an ISP-
Driven Informed Path Selection".
[Seetharaman-1]
Seetharaman, S., Hilt, V., Hofmann, M., and M. Ammar,
"Preemptive Strategies to Improve Routing Performance of
Native and Overlay Layers".
[Su06] Su, A., Choffnes, D., Kuzmanovic, A., and F. Bustamante,
"Drafting behind Akamai (travelocity-based detouring)".
Hilt, et al. Expires January 4, 2009 [Page 10]
Internet-Draft ALTO Survey July 2008
[Wang-07] Wang, G., Zhang, B., and T. Ng, "Towards Network Triangle
Inequality Violation Aware Distributed Systems".
[Wong-1] Wong, B., Slivkins, A., and E. Sirer, "Meridian: A
lightweight network location service without virtual
coordinates".
[Xie-1] Xie, H., Krishnamurthy, A., Silberschatz, A., and Y. Yang,
"P4P: Explicit Communications for Cooperative Control
Between P2P and Network Providers",
.
Authors' Addresses
Volker Hilt
Bell Labs, Alcatel-Lucent
Email: volkerh@bell-labs.com
Ivica Rimac
Bell Labs, Alcatel-Lucent
Email: rimac@bell-labs.com
Marco Tomsu
Bell Labs, Alcatel-Lucent
Email: marco.tomsu@alcatel-lucent.com
Vijay K. Gurbani
Bell Labs, Alcatel-Lucent
Email: vkg@bell-labs.com
Enrico Marocco
Telecom Italia
Email: enrico.marocco@telecomitalia.it
Hilt, et al. Expires January 4, 2009 [Page 11]
Internet-Draft ALTO Survey July 2008
Full Copyright Statement
Copyright (C) The IETF Trust (2008).
This document is subject to the rights, licenses and restrictions
contained in BCP 78, and except as set forth therein, the authors
retain all their rights.
This document and the information contained herein are provided on an
"AS IS" basis and THE CONTRIBUTOR, THE ORGANIZATION HE/SHE REPRESENTS
OR IS SPONSORED BY (IF ANY), THE INTERNET SOCIETY, THE IETF TRUST AND
THE INTERNET ENGINEERING TASK FORCE DISCLAIM ALL WARRANTIES, EXPRESS
OR IMPLIED, INCLUDING BUT NOT LIMITED TO ANY WARRANTY THAT THE USE OF
THE INFORMATION HEREIN WILL NOT INFRINGE ANY RIGHTS OR ANY IMPLIED
WARRANTIES OF MERCHANTABILITY OR FITNESS FOR A PARTICULAR PURPOSE.
Intellectual Property
The IETF takes no position regarding the validity or scope of any
Intellectual Property Rights or other rights that might be claimed to
pertain to the implementation or use of the technology described in
this document or the extent to which any license under such rights
might or might not be available; nor does it represent that it has
made any independent effort to identify any such rights. Information
on the procedures with respect to rights in RFC documents can be
found in BCP 78 and BCP 79.
Copies of IPR disclosures made to the IETF Secretariat and any
assurances of licenses to be made available, or the result of an
attempt made to obtain a general license or permission for the use of
such proprietary rights by implementers or users of this
specification can be obtained from the IETF on-line IPR repository at
http://www.ietf.org/ipr.
The IETF invites any interested party to bring to its attention any
copyrights, patents or patent applications, or other proprietary
rights that may cover technology that may be required to implement
this standard. Please address the information to the IETF at
ietf-ipr@ietf.org.
Acknowledgment
Funding for the RFC Editor function is provided by the IETF
Administrative Support Activity (IASA).
Hilt, et al. Expires January 4, 2009 [Page 12]