Connecting Networks

Articles tagged with: transit

History and impact of IXP growth

on Friday, 26 July 2019 Posted in News Rezopole, News LyonIX, News GrenoblIX

History and impact of IXP growth

It is 1990: the Internet has a few million users and the first commercial companies have recently adopted this new distributed infrastructure.


The routing of network traffic from one region to another generally depends on the major transit providers (level 1). These levels 1 are at the top of the hierarchy, composed of a few thousand existing AS, forming what is called the network of networks.


A lot has changed since those early days, when small ASs paid the biggest for connectivity. This dependence on intermediaries has resulted in transit costs, indirect routes, long round trip times and a general lack of control over the quality of service. The bypassing of intermediaries by direct peering interconnections became the obvious answer, and Internet Exchange Points (IXPs) then appeared as the default solution for establishing connections.


Between 2008 and 2016, the number of IXPs and members almost tripled. At the same time, accessibility via these facilities has stagnated at around 80% of the announced address space (IPv4) while resilience has increased due to increasing redundancy.


In almost all regions, particularly in Europe and North America, IXP members have grown richer with an increasing number of members and greater accessibility. However, the regional ecosystems were distinct. For example, European IXPs had the largest number of members but the smallest AS (in terms of accessibility), Asia-Pacific was at the opposite extreme.


This growth raises the question of the observable impact of IXPs on the Internet. To answer this question, Queen Mary University in London, in collaboration with researchers from Roma Tre Univ, the GARR Consortium and the University of Tokyo, extracted a large collection of traceroutes covering the same period and identified IXPs crossed.


The IXPs have had a clear impact on reducing the average length of access paths at AS level, particularly for large (hypergiant) global networks. Given that these networks are traffic-intensive, it is likely that a large proportion of Internet traffic has benefited from a substantial reduction in the number of AS crossed.


They have also clearly helped to bypass level 1 transit providers. However, their impact on reducing the number of transit links (not necessarily level 1) visible on the route is more moderate.


Despite these changes, a clear hierarchy remains, with a small number of networks playing a central role. It is interesting to note that there is a small group of very central networks, regardless of whether the paths cross an IXP or not.


In addition, the Internet hierarchy has changed: large central networks have reduced their use of public peerings while IXPs have been adopted by smaller and less central ASs. This is probably due to the increasing popularity of private network interconnections (NIBPs), which are generally favoured by AS when large volumes of traffic are exchanged.


Overall, the increase in the number of IXPs since 2008 has had a clear impact on the evolution of the Internet, shortening paths (mainly) to hypergiants and reducing dependence on Tier 1 transit providers.


The results must be interpreted in the light of the constraints of existing data, and there are a number of areas where work is possible. For example, topological data are independent of traffic volumes and total visibility on the Internet is impossible to achieve.


In addition, content distribution network (CDN) redirection strategies are not included in the traceroutes; it is assumed that accounting for the increasing traffic volumes delivered by these networks would likely support these conclusions.





 Read the article


Source : RIPE





Peering and central DCs: essential?

on Friday, 14 June 2019 Posted in Archives Rezopole, Archives GrenoblIX, Archives LyonIX

Peering and central DCs: essential?

Central data centres are connectivity relays, real marketplaces. They bring together almost all the players in the digital value chain. The challenge is therefore to know how to identify them, to be able to recognize them in order to open a PoP (Point Of Presence).


There are three types of data centers: hyperscale, edge and core. Usually organized in a loop, each one has a very specific role in the organization of an IT architecture. It is very common to see players hosting their application in a hyperscale, deploying their IT in an edge and ensuring an optimized network path by creating peering links in a core.


Central DCs have a very specific importance and are therefore becoming real performance levers that determine many infrastructure choices.

But how to identify them? The easiest way is to consult the referencing databases of network players such as PEERING DB and to search for the data centre with the largest number of members. If they have differentiating elements such as the number of members and network ports available, cushioned network equipment or an extremely wide choice of actors, it is in peering that their main attraction lies.


In a central DC everyone is on an equal footing: everyone shares data via a physical connection from point A to point B. Regardless of the nature of the interconnection: peering, direct interconnection or transit, I know that everyone is within cable distance of my rack. I will therefore benefit from clustering effect. And the effect is virtuous, the more actors a central data center brings together, the more interconnection there is, the cheaper it is.


Peering is a strong trend that is becoming essential. A study published by Arcep in 2017 related to traffic measurement among ISPs in France indicates that the data exchanged on the territory are distributed in this way: 50% for transit, 46% for private peering and 4% for public peering. The same ratios were observed by the Journal du Net in one of its central data centers. The share of transit decreases very significantly between 2017 and 2018. Public peering is growing and private peering is increasing very significantly. Three main consequences follow from this dynamic: content players will get as close as possible to end customers by bypassing hosters and forwarders in the short and medium term, freight forwarders seeing their business decline will try to recover the margins they are losing on the CDN link, and finally ISPs will try to get closer to the end customer themselves by including content in their offers.


Several good practices deserve to be shared to move to live traffic. First, start with the application. Before choosing where to host your IT, it is necessary to consider the nature of the IT. Depending on the answer, you have to organize your architecture. The challenge is to create network accesses that facilitate the user experience and reduce costs. Depending on their priority and the level of security required, the applications will therefore be divided between core, edge and hyperscale.

Secondly, how to bring the user closer to these applications? The alternative is quite simple: either use peering or direct interconnections, or put the application locally in its data center and set up a private network link to the end user.


The meaning of the story seems to be moving towards a transformation of the IT agent into a buyer. IT managers are now able to organize these outsourcing choices in these three types of data centers. Business choices therefore become business choices.


 Read the article


Source : Journal du Net





Data interconnection barometer

on Wednesday, 26 December 2018 Posted in Archives Rezopole, Archives GrenoblIX, Archives LyonIX

Data interconnection barometer

By publishing this barometer of data interconnection in France 2018, the Autorité de Régulation des Communications Electroniques et des Postes (Arcep) proposes to popularize the subject in order to better understand the state and developments of this market.

The first part of this report presents this ecosystem of the Internet: what is the purpose of data interconnection, who are the main actors, how are they interconnected, what are the issues and modes of interconnection, etc.

In the second part, the Arcep makes an inventory of the interconnection situation in France. The data collected are aggregated results for the period from the first half of 2012 to the first half of 2018. They thus make it possible to see the growth of incoming and outgoing traffic, the increase in installed capacity, the evolution of interconnection methods, the distribution of traffic by interconnection mode, the breakdown of traffic by origin and the range of current tariffs.




 Read the article


Source : Arcep





FaLang translation system by Faboba