wdiff rfc6875.original rfc6875.txt

P2PRG
Internet Research Task Force (IRTF) S. Kamei
Internet-Draft
Request for Comments: 6875 NTT Communications
Intended status:
Category: Informational T. Momose
Expires: April 18, 2013
ISSN: 2070-1721 Cisco Systems
T. Inoue
T. Nishitani
NTT Communications
October 15, 2012

ALTO-Like
February 2013

The P2P Network Experiment Council's Activities and Experiments with
Application-Layer Traffic Optimization (ALTO) in P2P Network Experiment Council
draft-kamei-p2p-experiments-japan-09 Japan

Abstract

This document introduces describes experiments to that clarify how ALTO-like an approach
similar to Application-Layer Traffic Optimization (ALTO) was
effective to reduce in reducing network traffic made traffic. These experiments were
performed in Japan by a the P2P Network Experiment Council in
Japan an
attempt to harmonize P2P peer-to-peer (P2P) technology with the network
infrastructure. And Based on what was learned from these experiments,
this
also document provides some suggestions that might be useful for the
ALTO architecture learned through our experiments. Especially, experiment and especially for application independent ALTO-like application-independent ALTO-
like server operation.

Status of this This Memo

This Internet-Draft document is submitted in full conformance with not an Internet Standards Track specification; it is
published for informational purposes.

This document is a product of the Internet Research Task Force
(IRTF). The IRTF publishes the
provisions results of BCP 78 Internet-related research
and BCP 79.

Internet-Drafts are working documents development activities. These results might not be suitable for
deployment. This RFC represents the individual opinion(s) of one or
more members of the Peer-to-Peer Research Group of the Internet Engineering
Research Task Force (IETF). Note that other groups may also distribute
working documents as Internet-Drafts. The list of current Internet-
Drafts is at http://datatracker.ietf.org/drafts/current/.

Internet-Drafts are draft documents valid (IRTF). Documents approved for publication by
the IRSG are not a maximum candidate for any level of Internet Standard; see
Section 2 of RFC 5741.

Information about the current status of six months this document, any errata,
and how to provide feedback on it may be updated, replaced, or obsoleted by other documents obtained at any
time. It is inappropriate to use Internet-Drafts as reference
material or to cite them other than as "work in progress."

This Internet-Draft will expire on April 18, 2013.
http://www.rfc-editor.org/info/rfc6875.

This document is subject to BCP 78 and the IETF Trust's Legal
Provisions Relating to IETF Documents
(http://trustee.ietf.org/license-info) in effect on the date of
publication of this document. Please review these documents
carefully, as they describe your rights and restrictions with respect
to this document. Code Components extracted from this document must
include Simplified BSD License text as described in Section 4.e of
the Trust Legal Provisions and are provided without warranty as
described in the Simplified BSD License.

Table of Contents

1. Introduction . . . . . . . . . . . . . . . . . . . . . . . . . 3
2. Background in Japan . . . . . . . . . . . . . . . . . . . . . 3 4
2.1. P2P traffic Traffic . . . . . . . . . . . . . . . . . . . . . . . 3 4
2.2. Impact on network infrastructure Network Infrastructure . . . . . . . . . . . . . 4
2.3. The object Overview of the P2P Network Experiment Council . . . . . . . 5
3. The object Objectives of the P2P Network Experiment Council . . . . . . . . . 5 6
4. The details Details of the experiments Experiment . . . . . . . . . . . . . . . . . . 7
4.1. Dummy Node . . . . . . . . . . . . . . . . . . . . . . . . 7
5. Hint Server ('08) Servers . . . . . . . . . . . . . . . . . . . . . . . . 8 . 9
6. High-Level Trial Results . . . . . . . . . . . . . . . . . . . 13
6.1. Peer Selection with P2P . . . . . . . . . . . . . . . . . 13
6.2. Peer Selection with the Hint Server . . . . . . . . . . . 13
7. Considerations . . . . . . . . . . . . . . . . . . . . . . . . 14
7.1. Next steps Steps . . . . . . . . . . . . . . . . . . . . . . . . 14
7.2. Feedback to the ALTO WG . . . . . . . . . . . . . . . . . . . 15
7.2.1. Hierarchical architecture Architecture for ALTO servers Servers . . . . . . 15
7.2.2. Measurement mechanism Mechanism . . . . . . . . . . . . . . . . 15
8. Security Considerations . . . . . . . . . . . . . . . . . . . 16
9. IANA Considerations . Acknowledgments . . . . . . . . . . . . . . . . . . . . 16
10. Acknowledgments . . . 16
10. Informative References . . . . . . . . . . . . . . . . . . . . 16
11. Informative References . . . . . . . . . . . . . . . . . . . . 16
Authors' Addresses . . . . . . . . . . . . . . . . . . . . . . . . 17

1. Introduction

An overlay network, which is used by P2P and other applications,
offers the advantage of allowing flexible provision provisioning of services
while hiding the lower layer lower-layer network. The downside disadvantage is that
inefficient
routes are often taken in routing without considering the lower IP network, thereby lower-layer network may
cause increasing the network load. Several proposals have been made
to build an overlay network that takes into account of the information
about the lower
layer network. lower-layer network [1] [2] [2]. Since the management of the
Internet is highly distributed, it is difficult to implement such proposals
proposals, and thus to optimize a network network, without the cooperation of
network providers.

Recently, the controversy between the overlay network and the network
providers about network resource wastefulness has been rekindled.
Under these circumstances, some researchers have studied overlay overlay-
network control technology that takes into account of the network
topology information obtained from network providers.

One of the activities concerning research effort regarding this issue has been made were experiments planned and
performed by the P2P Network Experiment Council in Japan. We planned some experiments in
the council. This
document reports on these experiments and the issues addressed and they addressed.

These experiments being made by the council.

This experiment made were performed from 2007 to 2008, because P2P
traffic had
reduced due to rivision of decreased after Japanese copyright law in Japan. And was revised. While
more recently, the dominant traffic is HTTP based flash streaming in Japan, U.S, the United States, and so
on. However, P2P
elsewhere has been HTTP-based flash streaming, a large amount of
traffic remains in large Asia (outside Japan) is still P2P traffic, like PPStreaming,
in Asia (except Japan)[3], P2P
streaming [3], and P2P technology is very userful useful in such a realtime real-time
streaming area.

Our experience in this experiment might be useful for ALTO
architecture, especially for application independent application-independent and multi multi-
application ALTO-like server operations. We suggest that a generic
measurement mechanism is important because each application has
different mechanism and mechanism, which makes it is difficult to compare the their
effectiveness.

This document is a product of the P2P RG. Research Group (RG). The views
in this document were considered controversial by the P2P RG RG, but the
RG reached a consensus that the document should still be published.

2. Background in Japan

2.1. P2P traffic Traffic

As of 2008, the world world's most popular P2P file sharing file-sharing application,
Bittorrent, isn't
BitTorrent, was not widely deployed in Japan. Instead, other Japan
specific file file-
sharing P2P applications specific to Japan, such as Winny [4], [4] and
Share [5],
and so on, still occupy account for 40% of the Internet traffic in Japan Japan,
even though many those P2P users were arrested for sharing illegal
files with these P2P apps. applications.

Each P2P file sharing file-sharing application has a unique protocol and none of
them have
a large market share share, therefore making it hard to
effectively control. control them
effectively.

2.2. Impact on network infrastructure Network Infrastructure

One of the advantage of using P2P technology for content delivery is that
peers exchange content directly among themselves without server
bottleneck. This reduces the load on servers. Also, P2P
applications can reduce upstream traffic from an origin content
server. This reduce reduces server cost dramatically.

It is also known that server cost could be reduced with P2P
technology. However, the story is quite different for network
providers. From the viewpoint of network providers, the traffic that
content servers generate has shifted to the edge network and the
amount of traffic has not necessarily been reduced with by using P2P
technology for reducing server cost. Another problem for network
providers is that an extremely inefficient routing may be selected has
been raised. It is
because overlay network systems are configured without any regard to
the structure of the lower layer lower-layer network or network geometry.

In some cases, the total amount of traffic on the Internet used to be
limited by the capacity of servers. For those cases, P2P technology
can improve the scalability of servers , however servers; however, it may exhaust
network resources. Moreover, using P2P applications remarkably
increases the volume of traffic per user remarkably. user.

Faced with an increase in the load on network infrastructure, network
providers are compelled to take actions to overcome the sudden
increase in facilities' cost. costs. Representative actions include
placing content in internet exchanges Internet Exchanges (IXs) or data centers,
introducing bandwidth control, and raising the access fees [6].

However, current

As mentioned above, the dominant traffic is HTTP based flash streaming currently in Japan, U.S, the US,
and so on. elsewhere, is HTTP-based flash streaming. However, P2P a large
amount of traffic remains in large Asia (outside Japan) is P2P traffic, like PPStreaming, in Asia (except Japan)[3], P2P
Streaming [3], and P2P technology is very userful useful in such a realtime streaming area. real-time
streaming. The increase in traffic arising from such a shift may be
a great threat to the network.

2.3. The object Overview of the P2P Network Experiment Council

In order to reduce Internet traffic and encourage legitimate use of
P2P technologies, in 2006 the Japanese government led to establish established a new
council called the P2P Network Experiment Council Council, in conjunction
with commercial P2P application vendors and ISPs in 2006.

Then the ISPs.

The council had started to develop developed regulations that include
several guidelines such like an as
giving advance notice to restrict bandwidth
to heavy traffic users. users before restricting their
bandwidth. In accordance with the regulations, some ISPs introduced
solutions that reduce traffic caused by P2P file
sharing file-sharing
applications.

Besides this activity,

In addition, the council also council, along with ISPs, carriers, contents
providers, and P2P system vendors, looked for new ways to control
traffic by commercial P2P applications with ISPs, carriers,
contents providers and P2P system vendors. applications. In this work, the council
had
performed experiments that introduced an ALTO-like system and
observed how the traffic was reduced by redirecting when it was redirected to proper
peers on the real Internet in Japan.

In our experiment, the council deployed hint servers, which are
described in section 4. Section 5. Hint servers have run a protocol offering that offers
network distance distances to peers, which is and these distances are disclosed to P2P
application vendors.

Using hint server, servers, P2P application vendors can introduce ALTO
concepts easily to into their P2P distribution systems. Because the
protocol provided of used by hint servers servers, as defined by the council, is
independent on of specific P2P application vendors like Bittorrent, the council defines the BitTorrent. The
protocol
to be able to use any P2P application vendors. It needs to gather network information from ISPs to offer so it can
provide network distance to peers,
however peers. However, many ISPs dislike to disclose
disclosing such information to others. Therefore, hint servers are
designed to offer little information about ISPs' an ISP's network
architecture to P2P application vendors.

To monitor the traffic of peers, the council also deployed a dummy
node, which are is described in section 3.1.

This Section 4.1.

The remainder of this memo describes the provides an overview of the experiments.

3. The object Objectives of the P2P Network Experiment Council

The Japanese Ministry of Internal Affairs and Communications Japan, Communications, which
has jurisdiction over information and communication systems in Japan,
held meetings of an advisory panel on network neutrality from in 2006 to and
2007 in order to study issues related to next generation next-generation networks,
such as how to ensure fairness in the use of networks and how to
define fairness in the cost burden. The panel took an interest in
P2P technology as a solution to the impending traffic saturation in
the backbone network resulting from the rapid expansion of broadband
access in Japan, and it formed a "Working Group on the P2P Network",
which carried out an intensive study of P2P networks.

The Working Group working group reported that it is would be necessary to undertake
the following four activities, which are intended to encourage the
government to adopt relevant policies [7]:

o Formulate guidelines on P2P file-delivery applications to be self-imposed self-
imposed by the industry on P2P
file delivery applications, industry.

o Promote feasibility tests of P2P networks, networks.

o Study the current state of traffic control and promote the sharing
of information, information.

o Hold working group meetings on about traffic control.

The first two proposals led to the establishment of the P2P Network
Experiment Council Council, supported by the Japanese Ministry of Internal
Affairs and Communications Japan [8]. [8] [9]. The Council, with membership
from P2P delivery providers, content holders, and network providers,
began a variety of delivery experiments, which were expected to
strengthen cooperative control between different layers. In contrast
to P4P, P4P (Proactive Network Provider Participation for P2P), which
takes a relatively top-down approach of adopting an architecture
based on a proposal from a university, the Council is characterized
by its bottom-up approach. The aim of establishing the Council has
been was
described as follows. follows (translated from [10]).

The rapid growth of broadband access enables content delivery
system
systems to deliver high-quality and high-volume videos securely
and efficiently. Although P2P technology is an effective
technology for this requirement, it still has some issues to be
coped with. Therefore, the "P2P Network Experiment Council" was
established with the support of the Japanese Ministry of Internal
Affairs and
Communications Communications, with its secretariat set up within the
Foundation for MultiMedia Communications (FMMC) (FMMC), in order to
formulate guidelines for providers and conduct feasibility tests
so that users can receive video delivery services safely.

The activities of the P2P Network Experiment Council can be
classified into two categories. The first is activities to formulate formulating guidelines
for the promotion of promoting the commercial use of P2P technology. These guidelines
will enable users to use P2P technology safely, safely and will give
providers
to have clear rules they must observe. The other second is feasibility
tests
testing of P2P technology. The next section Section 4 describes mainly experiments conducted from
in 2007 to and 2008.

4. The details Details of the experiments Experiment

The council has already Council investigated data offered by the members of the Council
and learned that the server cost could be reduced
with by using P2P
technology for contents delivering by investigating
data offered by the members of the council. content delivery. For example, the data
brought by from the
vendors shows as follows:

90% of traffic showed the following:

Traffic was reduced by 90% with UG Live UGLive by Utagoe Inc [9]. Utagoe, Inc. [11].

The costs cost of delivering to tens of thousand thousands of subscribers was
reduced to 1/5 by 80% with BBbroadcast with TV Bank Corp. [10] [12]

On the other hand, these reduced server costs may affect have affected the
network load. One of the goals of our experiments was to visualize
the
impacts impact and propose an architecture to reduce network load caused
by these new technologies.

In order to visualize the reduction of network cost, we had to
modelize modeled P2P
applications and a multi-ISP environment. It will This model was also needed
for visualizing the effectiveness of the ALTO-like approach.

4.1. Dummy Node

As mentioned before, above, while the effect of delivery using P2P technology on reducing to
reduce the traffic and the load on servers is well
known, known; however,
traffic behavior in the inter-ISP area is not known. In Japan,
there is the
ISPs and IXes cooperated to create a backbone traffic report cooperated with ISPs and IXes
[11]. [13].
However, this measurement requires to capture the measurements gathered for that report required capturing
packets on
subscribers line subscribers' lines in order to know determine the end user's activity. users'
activities. It is not realistic to measure the behavior of P2P
applications at user terminals connected to the Internet because that
would require a large-scale arrangement for measurement, such as
using Deep Packet Inspection deep packet inspection (DPI) on aggregated lines.

To solve these problems, we put several nodes called 'dummy nodes' in
the ISP's networks. The dummy nodes emulate an end user's PC and running
P2P
applications are running on the nodes. applications. Every P2P node provided by participating vendors
in the experiment was configured so it always contacted the hint
server.

By introducing dummy nodes, nodes and measuring the traffic on them, we can were
able to observe and evaluate how much the P2P applications have affected networks by measuring
the traffic on dummy
nodes. networks. Since this method can't measure every subscriber's
traffic, the accuracy would be is less than other methods. But this make However, using
dummy nodes makes it possible to adapt to situations in which many
different P2P applications coexist on a network. We can say this is decided that
using dummy nodes was suitable for these experiments.

A dummy node consists consisted of an Intel PC server, Linux(CentOS), VMWare server running Linux (CentOS),
VMWare, and Windows XP works on VMWare. With this configuration, all
packets can be captured without any impacts to impact on the behavior of the
network, nodes and application
behaviors. And it enable nodes, or applications. Also, this configuration enabled us
to use different P2P applications for
windows Windows and evaluate them
generally.

To see behaviors of the node, incoming and outgoing packets are
captured on Linux because every packets are packet is transmitted through it.
In To
see flow information in these experiments, we captured source/destination address, the source and
destination addresses, port number, amount of traffic traffic, and start/end time to see flow information. start and
end times.

We placed 60 Dummy dummy nodes are put on access networks that are closest subscriber of 40 different ISPs.
They were placed as close as possible to the subscriber in different 40 ISP networks. each
network.

+----------------------+
|+--------------------+|
||+------------------+||
||| P2P Application |||
||| WindowsXP Windows XP |||
||| +--+ |||
||+--------|N |------+||
|| VMware |e | ||
|+---------|t |-------+|
| Linux |IF| capture|
+----------| |--------+
+--+

Dummy nodes

Figure 1 1: Dummy node

5. Hint Server ('08)

In Servers

Since fiber to the home (FTTH) has rapidly spread all over Japan, bottleneck
bottlenecks in IP networks have been shifting from access networks to
backbone networks and equipments, equipment, such as bandwidth between ISPs and
capacity in IXs, since FTTH has rapidly spread all
over Japan. IXs. Under these circumstances, the Council proposed a
less restrictive and more flexible cooperation between ISPs than
existent P4P experiments [12]. [14]. The proposed method consists of the
following elements: (1) P2P clients, (2) P2P control servers, and (3)
a hint
server: server (specifically, a peer selection hint server. (1) server). P2P
clients and (2) control servers are existing
systems systems, but whether (2) exists depends on each application. (3) the P2P
control servers exist is application dependent. The hint server is a
server that provides a hint as to the for peer selection of a peer, and plays a role
equivalent to that of the ALTO Server. server. Note that this proposal was
based on results of experiments using dummy nodes. The results
showed that it was possible to reduce unnecessary traffic that flows
across the boundaries of geographical districts or ISPs through by providing
information about the physical network to P2P applications.

When a peer joins the network, it registers its location information
(IP address) and supplementary information (line speed, etc.) with&#
12288;the with
the hint server. The hint server calculate calculates the network distance
between peers (P2P client) clients) based on network topology information
obtained from the ISP and generates a priority table for peer
selection. The hint server returns the table to the peer.

If all information can be made publicly, is public, the above procedure can produce a result which is close to overall optimization. results
that are nearly optimal. However, some information held by ISPs can is
often be confidential. Besides, Also, in some cases, the volume of calculation
required to process all information can be excessive. To avoid these
problems, it the plan is planned to conduct experiments with a limited set of
functions, analyze
experiments the results, and gradually expand the scope of
optimization.

A control mechanism that makes use of all possible information is
difficult not only technically but also difficulties to achieve because it requires
coordination among providers. In consideration light of these difficulties, the
council has been limiting the implementation and experiments to the following scope since 2006.
technical scope.

Figure 2 shows an outline of the hint server.

+---------+ GetLocation +-------------GeoIP DB Server---------+
| | +-----------+ | +----------+ +-----------+ |
| |--|IP Address |-->| | GeoIP DB | |Quagga etc |BGP daemon | |
| | +-----------+ | +----------+ +-----------+ |
| | | +-------------+ +----------------+ |
| | +-----------+ | | District | | Routing | |
| |--|AS Code: |---| | information Information | |information(DGP)| |Information(BGP)| |
| | |Regional | | | | | | |
|P2P Peers| |Information| | | Range of | |AS Code(origin) | |
| or | +-----------+ | | IP address Addresses| | | |
|
| Contro| Control | | +-------------+ +----------------+ |
| Server | +-------------------------------------+
| | | ^
| | PeerSelection v |
| | +-----------+ +--------------------------------------+
| |--|IP Address |-->| +--Priority Node Selection System--+ |
| | | List | | | | |
| | +-----------+ | | Peer candidate ranking Candidate Ranking | |
| | +-----------+ | | | |
| |--| Ranking |-->| +----------------------------------+ |
| | +-----------+ +--------------------------------------+
+---------+

Peer selection hint server

Figure 2 2: Hint server for peer selection

The network information used by the hint server is not information
solicited from individual ISPs but is the AS Autonomous System (AS)
number and district information, which are more or less already public. public
already. Routing tables are not generated. Instead, peers within
the same ISP or the same district are selected with higher priority
in order to confine traffic to within the same ISP or the same
district.

When the hint server receives an IP address, it returns its attribute
information, in order to confine the traffic to achieve within the above. nearer ISP
or district. A peer can select a peer another based on the returned
information. This operation is called GetLocation. However, in
preparation for the time when it becomes necessary to hide topology
information, an interface is provided through which a priority order
is returned in response to an input of a list of candidate peers.
This operation is called PeerSelection.

Although the target node is selected based on the criterion that it
is within the same ISP or the same district, this type of selection
is not very effective if the number of participating peers is small.
Table 1 shows ratio the percentage of peers within the same AS or the same
prefecture calculated from the distribution of ASs ASes and prefectures
in the IP address space from one-day data on a Winny network.

+--------------------+--------+

+--------------------+------------+
| Conditions | ratio Percentage |
+--------------------+--------+
+--------------------+------------+
| AS matches | 6.70% |
| Prefecture matches | 12.76% |
| Both match | 2.09% |
| Neither match | 78.45% |
+--------------------+--------+
+--------------------+------------+

Table 1: AS and prefecture distributions

Since,

Because, in addition to the above, the presence/absence presence or absence of content
affects the result, the control of selecting a results, controlling peer selection within the same
district may be inadequate. Therefore, it is necessary to introduce
the weight of a continuous quantity that reflects the physical
distance or the AS path length as an indicator of the proximity of
the areas involved.

In consideration of the above, this, the following two measures are used
for the evaluation of to
evaluate the proximity between of peers in a hint server.

o AS path length (distance between ISPs)

AS path length is calculated from BGP full routes. Since a full
routing table retrieved at an ISP can show only a best path, it
may not get an accurate length if the AS hop count of both ISPs is
too large. To avoid this, we use multiple BGP information received from
different ISPs and combine them. Based on this concept, we used
BGP routing information's information offered by three ISPs operated by big
telecommunication couriers and made a topology tree. Then it
enables Then, we
were able to calculate the shortest path between given two given ASes.

o Geographical distance

Distances between peers are measured using the physical distance of
prefectural capitals that target peers belong to. The distance
between prefectural the capitals is used of the prefectures to calculate physical
distance. which the peers belong.
Distances between prefectural capitals are sorted into ascending
order, and then into bands, with weights 1 to 15 assigned to them
so that there are a more or less equal each band contains roughly the same number of "capital pairs" in each band.
pairs". If either of their location the peer's locations is indefinite, the
distance is equal to 15 and, 15; if they are in the same prefecture, the
distance is equal to 0.

Evaluation of distances between peers showed that the distribution
of distances was almost uniform when distances between peers are
normalized. This result suggests that using normalized distances
expands the area where the control by a Hint Server hint server is effective.
The geographical distance is only used only when the AS path length is
same.
the same between some candidates.

An example of the request and the response follows.

o Request

POST /PeerSelection HTTP/1.1
Host: ServerName
User-Agent: ClientName
Content-Type: text/plain; charset=utf-8

v=Version number
[application=Application identifier]
ip=IP address of physical interface
port=Port number of physical interface
[nat={no|upnp|unknown}]
[nat_ip=Global IP address using UPnP]
[nat_port= Global port number using UPnP]
[trans_id=transcation
[trans_id=transaction ID]
[pt=Flag of port type]
[ub=upload bandwidth]
[db=download bandwidth]

o Response

HTTP/1.1 200 OK
Date: Timestamp
Content-Type: text/plain; charset=utf-8
Cache-control: max-age=max age
Connection: close

v=Version number
ttl=ttl
server=hint server name
...
trans_id=transaction ID
pt=Flag of port type
client_ip=Peer IP address observed from server
client_port=Peer port number observed from server
numpeers=number of respond peer responding peers
n=[src address] dst address / cost / option

6. High-Level Trial Results

6.1. Peer Selection with P2P

Table 2 shows the result of the analysis of communication in a node
of an ISP installed in Tokyo, as an example of measurement results.

In these two experiments experiments, we evaluate evaluated different P2P applications, in
1st applications.
In the first experiment, the P2P topology is was generated by a tree algorithm, and
algorithm; in 2nd the second experiment, it is was generated by a mesh
algorithm. Both of them
result resulted in similar performance.

+-----------------------------------------+------------+------------+
| Conditions | Experiment | Experiment |
| | 1 | 2 |
+-----------------------------------------+------------+------------+
| *Peers Peers selected within the same ISP | 22% | 29% |
| *Peers | | |
| Peers selected within the same district | 19% | 23% |
| district | | |
| *Peers Peers selected within the same district | 5% | 7% |
| district and the same ISP | | |
+-----------------------------------------+------------+------------+

Table 2: Percentage of communication within the same ISP

The table

Table 2 shows that the probability of communication with peers in the
same ISP is proportional to the number of population size and the share of the
ISP in each district. The data show that peers were selected at
random. Note that the vendor of a P2P application used in these
experiments explained demonstrated that the mechanism of selection for selecting a peer
using network information can be implemented. However, peer
selection is normally based on past information because users often
cannot actually perceive the effect of using network information.

6.2. Peer Selection with the Hint Server

The main objective of these experiments was to verify the operations operation
of the hint server and P2P applications. The distances between a
dummy node and a peer were obtained from data on the dummy nodes. An
examination of the distances between a dummy node and a peer revealed
that the mean value of distance after the hint server was introduced
was reduced by 10% and that the 95th percentile was reduced by 5%.
The results show that introducing a hint server can reduce the
network loads by that result from P2P applications.

7. Considerations

We clarified followings throughout the following during our experiments.

1. Dispersed dummy nodes can figure out determine the behavior of peers and
traffic between inter-ISP networks, which peers are selected by networks and can determine the peer
that each peer. Therefore it peer selects. Therefore, this result proves that the
importance of peer
selection the peer-selection control mechanism that is
proposed in by ALTO.

2. Using our peer selection peer-selection control mechanism, called hint server,
could achieve servers,
can result in significant differences. Our hint server Hint servers can lead
each peer to select nearer a closer peer.

3. The result of 10% reduction of network cost is not satisfying
effect satisfactory for ISPs,
but the controllability for of P2P applicationis applications is the most important
point. When they ISPs apply this mechanism for to their real ISP network, networks,
they will set a very large cost for the most expensive network
link.

In the experimental result of peer selection results for peer-selection control, it the selection
is smaller in intra-ISP traffic than in other experiments [13] [15]. We
think that it this is because there are smaller fewer peers in each area of traffic
control. When there are many peers in one ISP, it is easy to select
peers in the same ISP. However, when there are small fewer peers in one
ISP, it is difficult to select peers in the same ISP. In the situation of our
experiments, there are many ISPs most of the ISPs had many peers belonging, and in their networks, i.e.,
there are
relatively smaller were a small number of ISPs that had few peers exist in same ISP. their
networks.

Moreover, we didn't force P2P vendors to limit their implementation
policy, therefore
policy; therefore, we can observe observed differences in how each implementations
weigh implementation
weighs the information from the hint servers. Especially, Specifically, in P2P
applications when a tree
overlay topology P2P applications, such is used, the hint-server mechanism
is very effective, effective; on the other hand, in when a mesh overlay system, topology is used,
it less effective.

7.1. Next steps

Recent Steps

In recent research, we've changed the to an ALTO-based communication
protocol to on hint servers to ALTO based because it the requirements of ALTO are
documented in RFC 6708 [16] and the ALTO protocol is nearly standardized. a work in
progress [17]. In our implementation, PIDs protocol identifiers (PIDs)
and the value of cost value are mapped to ISP subnets, subnets and to ISP distance distance,
respectively. We also implement services for compatibility required
by ALTO such as Service Capability and Map
Services. But the Services and Endpoint Cost Service. The Endpoint
Cost Service (defined in [17]) is mainly used because of backward
compatibility of with our experiments.

We are also study studying a hierarchical structure of hint server structure, servers, in
order to control
in traffic at a coarse inter-ISPs level (in inter-ISP areas) and in detail intra-ISP.
at a finer level (in intra-ISP areas). It is also effective for
limiting the area of areas where information disclose. is disclosed.

7.2. Feedback to the ALTO WG

This section describes what the authors learned with from these
experiments would that might be useful for to the ALTO WG.

7.2.1. Hierarchical architecture Architecture for ALTO servers Servers

In our experiments, we present the possibility of traffic control
among multi-ISPs multiple ISPs and multi-P2P multiple P2P applications using an ALTO
mechanism. On
the other hand, we We found several problems in ISP operations when ISPs try to adapt adopt the
mechanism. One is the granularity of network information from
council
Council members. Among inter-ISP area, areas, it is relatively easy to
treat
handle information for public purpose purposes by using BGP full route. routes. On
the other hand, among the intra-ISP area, areas, it may be difficult to
disclose the private information of each ISP. [14] propose Kiesel [18] proposes
some modification modifications for the ALTO protocol in order to hide ISP
information. We propose hierarchical structures. From the viewpoint
of cooperation between ISPs, fine-grained information is not
necessarily required and
moreover required. Moreover, it is difficult to exchange the
fine-grained information between ISPs. Considering this situation, the authors use
we used only coarse-grained information to control backbone traffic
in this
experiments, though these experiments; however, in the future, there may be a demand of
for controlling traffic within an ISP using fine-grained information may arise in future. Therefore it led us
that introducing information.
Therefore, we decided to introduce hierarchical structure structures into ALTO is necessary
in order to cope with both situations. Actually, to adapt adopting a
hierarchical control mechanism which include that includes the following two steps
will be useful.

o In the first step, First, use coarse-grained information about whole the network is used to
select ISPs.

o Next, Second, use fine-grained information within the ISP is used to select a
peer.

7.2.2. Measurement mechanism Mechanisms

In the these experiments, there were two difficulties as follows: follows.

o Evaluating the effect of introducing a hint server was difficult,
since difficult
because the P2P applications had their own measurement mechanisms.

o How to treat the priority orders order of peers suggested by a hint
server could not be predetermined for P2P applications.

From these experiences, the authors consider that clarifying the
requirements about measurement mechanisms for P2P applications are is
necessary also in ALTO.

8. Security Considerations

This document does not propose any kind of protocol, practice practice, or
standard.

9. IANA Considerations

No need to describe any request regarding number assignment.

10. Acknowledgments

Thanks

The P2P Network Experiment Council was established thanks to strong
support by MIC (Ministry the Japanese Ministry of Internal Affairs and
Communications of Japanese government), the council was established.
Communications. These experiments were performed under with cooperation
among the P2P Network Experiment Council members, and members. DREAMBOAT co.,ltd., Bitmedia Co.,
Ltd., Bitmedia, Inc., Utagoe, Inc.,
Utagoe. Inc. and Toyama IX have especially
supported the analyses of the experiments. The authors appreciate
Tohru Asami, Hiroshi Esaki Esaki, and Tatsuya Yamshita Yamashita for their
constructive comments.

And the

The authors would also like to thank Martin Stiemerling, Stefano
Previdi
Previdi, and Vijay K.Gurbani K. Gurbani for the their comments on this document.

11.

10. Informative References

[1] R.Kawahara, E.K.Lua, M.Uchida, S.Kamei, H.Yoshino, Kawahara, R., Lua, E., Uchida, M., Kamei, S., and H. Yoshino,
"On the Quality of Triangle Inequality Violation Aware Routing
Overlay Architecture", INFOCOM 2009: 2009, pages 2761-2765.

[2] Z.Li, Li, Z. and P. Mohapatra, "QRON: QoS-aware routing in overlay
networks", IEEE
JOURNAL ON SELECTED AREAS IN COMMUNICATIONS, VOL. Journal on Selected Areas in
Communications, Vol. 22, NO. No. 1,
JANUARY January 2004.

[3] Sandvine Corp, Sandvine, Inc., "Global Internet Phenomena Report: 1H 2H 2012",
September 2012,
<http://www.sandvine.com/news/global_broadband_trends.asp>.

[4] "Winny on Wikipedia", <http://en.wikipedia.org/wiki/Winny>. Wikipedia, "Winny", July 2012, <http://en.wikipedia.org/w/
index.php?title=Winny&oldid=500744660>.

[5] Wikipedia, "Share on Wikipedia",
<http://en.wikipedia.org/wiki/Share_(P2P)>. (P2P)", January 2013,
<http://en.wikipedia.org/w/index.php?title=Share_(P2P)&
oldid=532999898>.

[6] Taniwaki, Y., "Broadband Competition Policy in Japan",
March 2008,
<http://www.smartireland.jp/en/forum/may-2009/>. <http://unpan1.un.org/intradoc/groups/public/
documents/apcity/unpan040329.pdf>.

[7] Ministry of Internal Affairs and Communications, "Disclosure of
the Report `Working 'Working Group on P2P Networks'",
http://www.soumu.go.jp/menu_news/s-news/2007/070629_11.html,
2007 Networks'" (in Japanese). Japanese),
2007,
<http://www.soumu.go.jp/menu_news/s-news/2007/070629_11.html>.

[8] The Foundation for MultiMedia Communications, "The P2P Network
Experiment Council", http://www.fmmc.or.jp/P2P/about.htm, 2007 Council" (in Japanese). Japanese), 2007,
<http://www.fmmc.or.jp/P2P/about.htm>.

[9] Utagoe Inc., "UGLive technology introduction",
http://www.utagoe.com/en/technology/grid/live/index.html,
March, 2011. Ministry of Internal Affairs and Communications, "P2P Network
Experiment Council Symposium to Be Held", February 2008,
<http://www.soumu.go.jp/main_sosiki/joho_tsusin/eng/Releases/
Telecommunications/news080201_1.html>.

[10] TVBank, The Foundation for MultiMedia Communications, "The Aim of P2P
Network Experiment Council" (in Japanese), 2007,
<http://www.fmmc.or.jp/p2p_web/aim.html>.

[11] Shudo, K., "A Review of ALM Software in Practical Use", IRTF
SAMRG (Scalable Adaptive Multicast Research Group)
meeting, Proceedings of IETF 76, November 2009,
<http://www.ietf.org/proceedings/76/slides/SAMRG-6.pdf>.

[12] TV Bank Corp., "Live Delivery using `BB Broadcast'Achieving Using 'BB Broadcast' Achieved a
96% Saving in Traffic!", http:.wwww.tv-bank.com/jp/20081031.html, 2008 Traffic!" (in
Japanese).

[11] Japanese), October 2008,
<http://www.tv-bank.com/jp/20081031.html>.

[13] Cho, K., Fukuda, K., Esaki, H., and A. Kato, "The Impact and
Implications of the Growth in Residential User-to-User
Traffic", SIGCOMM2006,
pp207-218, Pisa, Italy, SIGCOMM '06, pages 207-218, September 2006.

[12] Open P4P, "P4P Field Tests: Yale-Pando-Verizon",
http://www.openp4p.net/front/, 2009.

[13] "RFC5632: Comcast's

[14] Xie, H., Yang, R., Krishnamurthy, A., Liu, Y., and A.
Silberscatz, "P4P: Provider Portal for Applications", SIGCOMM
'08, pages 351-362, 2008, <http://www.cs.yale.edu/homes/yry/
projects/p4p/p4p-sigcomm08.pdf>.

[15] Griffiths, C., Livingood, J., Popkin, L., Woundy, R., and Y.
Yang, "Comcast's ISP Experiences in a Proactive Network
Provider Participation for P2P (P4P) Technical Trial",
RFC 5632, September 2009.

[14]

[16] Kiesel, S., Previdi, S., Stiemerling, M., Woundy, R., and Y.
Yang, "Application-Layer Traffic Optimization (ALTO)
Requirements", RFC 6708, September 2012.

[17] Alimi, R., Ed., Penno, R., Ed., and Y. Yang, Ed., "ALTO H12,draft-kiesel-alto-h12-02 (work
Protocol", Work in progress)", Progress, September 2012.

[18] Kiesel, S. and M. Stiemerling, "ALTO H12", Work in Progress,
March 2010.

Authors' Addresses

Satoshi Kamei
NTT Communications Corporation
Granpark Tower 17F, 16F, 3-4-1 Shibaura
Minato-ku, Tokyo 108-8118
JP
Japan

Phone: +81-50-3812-4697
Email:
EMail: skame@nttv6.jp

Tsuyoshi Momose
Cisco Systems G.K.
9-7-1 Akasaka
Minato-ku, Tokyo 107-6227
JP
Japan

Phone: +81-3-6738-5154
Email:
EMail: tmomose@cisco.com

Takeshi Inoue
NTT Communications
3-4-1, Shibaura
Minato-ku, Tokyo 108-8118
JP Corporation
Kuredo Hakushima Building 3F, 14-15 Higashihakushimacho
Chuo-ku, Hiroshima-City, Hiroshima 730-0004
Japan

Phone: +81-3-6733-7177
Email: +81-82-563-5030
EMail: inoue@jp.ntt.net

Tomohiro Nishitani
NTT Communications Corporation
1-1-6, Uchisaiwaicho
Chiyodaku, Tokyo 100-8019
JP
Japan

Phone: +81-50-3812-4742
Email:
EMail: tomohiro.nishitani@ntt.com