Software Defined Networking (SDN) promises to ease design, operation and management of communication networks. However, SDN comes with its own set challenges, including incremental deployability, robustness, scalability. Those challenges make a full deployment difficult in the short-term possibly inconvenient longer-term. In this paper, we explore hybrid models that combine more traditional networking approach based on distributed protocols. We show number use cases which can mitigate...

Centralizing routing decisions offers tremendous flexibility, but sacrifices the robustness of distributed protocols. In this paper, we present Fibbing, an architecture that achieves both flexibility and through central control over routing. Fibbing introduces fake nodes links into underlying link-state protocol, so routers compute their own forwarding tables based on augmented topology. is expressive, readily supports flexible load balancing, traffic engineering, backup routes. Based...

SDN simplifies network management by relying on declarativity (high-level interface) and expressiveness (network flexibility). We propose a solution to support those features while preserving high robustness scalability as needed in carrier-grade networks. Our is based (i) two-layer architecture separating connectivity optimization tasks; (ii) centralized optimizer called framework, which translates high-level goals expressed almost natural language into compliant configurations. evaluation...

Computer networks have become a critical infrastructure. In fact, should not only meet strict requirements in terms of correctness, availability, and performance but they also be very flexible support fast updates, e.g., due to policy changes, increasing traffic, or failures. This paper presents structured survey mechanism protocols update computer consistent manner. particular, we identify discuss the different desirable consistency properties that provided throughout network update,...

The support for safe network updates, i.e., live modification of device behavior without service disruption, is a critical primitive current and future networks. Several techniques have been proposed by previous works to implement such primitive. Unfortunately, existing are not generally applicable any architecture, typically require high overhead (e.g., additional memory) guarantee strong consistency (i.e., traversal either initial or final paths, but never mix them) during the update. In...

We propose FLIP, a new algorithm for SDN network updates that preserve forwarding policies. FLIP builds upon the dualism between replacements and additions of switch flow-table rules. It identifies constraints on rule independently prevent policy violations from occurring during update. Moreover, it keeps track alternative constraints, avoiding same violation. Then, progressively explores solution space by swapping with their alternatives, until reaches satisfiable set constraints. Extensive...

Network-wide migrations of a running network, such as the replacement routing protocol or modification its configuration, can improve performance, scalability, manageability, and security entire network. However, are an important source concerns for network operators reconfiguration campaign lead to long service-affecting outages.

Monitoring Internet performance and measuring user quality of experience are drawing increased attention from both research industry. To match this interest, large-scale measurement infrastructures have been constructed. We believe that effort must be combined with a critical review calibrarion the tools being used to measure performance.

Link-state routing protocols (e.g., OSPF and IS-IS) are widely used because they scalable, robust, based on simple abstractions. Unfortunately, these also relatively inflexible, since direct all traffic over shortest paths. In contrast, Software Defined Networking (SDN) offers fine-grained control routing, at the expense of controller overhead, failover latency, deployment challenges.

In this paper, we study how to perform traffic engineering at an extremely-small time scale with segment routing, addressing a critical need for modern wide area networks. Prior work has shown that routing enables better engineer traffic, thanks its ability program detours in forwarding paths, scale. Two main approaches have been explored respectively based on integer linear programming and constraint programming. However, no previous deeply investigated quickly those can react unexpected...

SDN simplifies network management by relying on declarativity (high-level interface) and expressiveness (network flexibility). We propose a solution to support those features while preserving high robustness scalability as needed in carrier-grade networks. Our is based (i) two-layer architecture separating connectivity optimization tasks; (ii) centralized optimizer called framework, which translates high-level goals expressed almost natural language into compliant configurations. evaluation...

To guarantee correct operation of their networks, operators have to promptly detect and diagnose data-plane issues, like broken interface cards or link failures. Networks are becoming more complex, with a growing number Equal Cost MultiPath (ECMP) bundles. Hence, some problems (e.g. silent packet dropping at one router) can hardly be detected control-plane protocols simple monitoring tools ping traceroute. In this paper, we propose new technique, called SCMon, that enables continuous the...

Network operators often face the problem of remote outages in transit networks leading to significant (sometimes on order minutes) downtimes. The issue is that BGP, Internet routing protocol, converges slowly upon such outages, as large bursts messages have be processed and propagated router by router.

In this paper, we propose a pragmatic approach to improve reproducibility of experimental analyses traffic engineering (TE) algorithms, whose implementation, evaluation and comparison are currently hard replicate. Our envisioned goal is enable universally-checkable experiments existing future TE algorithms. We describe the design implementation REPETITA, software framework that implements common functions, automates setup, eases comparisons (in terms solution quality, execution time, etc.)...

Centralizing routing decisions offers tremendous flexibility, but sacrifices the robustness of distributed protocols. In this paper, we present Fibbing, an architecture that achieves both flexibility and through central control over routing. Fibbing introduces fake nodes links into underlying link-state protocol, so routers compute their own forwarding tables based on augmented topology. is expressive, readily supports flexible load balancing, traffic engineering, backup routes. Based...

Network operators can and do deploy multiple routing control-planes, e.g., by running different protocols or instances of the same protocol. With rise SDN, control-planes are likely to become even more popular, enable hybrid SDN multi-controller deployments. Unfortunately, previous works not apply arbitrary combinations centralized distributed control-planes. In this paper, we develop a general theory for coexisting We provide novel, exhaustive classification existing future (e.g., OSPF,...

Routing hijack attacks have plagued the Internet for decades. After many failed mitigation attempts, recent Internet-wide BGP monitoring infrastructures relying on distributed route collection systems, called collectors, give us hope that future monitor systems can quickly detect and ultimately mitigate hijacks. In this paper, we investigate effectiveness of public collectors with respect to attackers deliberately engineering longer hijacks avoid being recorded by collectors. Our extensive...

Network-wide migrations of a running network, such as the replacement routing protocol or modification its configuration, can improve performance, scalability, manageability, and security entire network. However, are an important source concerns for network operators reconfiguration campaign lead to long, service-disrupting outages. In this paper, we propose methodology that addresses problem seamlessly modifying configuration link-state Interior Gateway Protocols (IGPs). We illustrate...

One of the main concerns on SDN is relative to its ability quickly react network failures, while limiting both control-plane overhead and additional forwarding state kept by data-plane devices. Despite practical importance, this concern often overlooked in OpenFlow-based proposals. In paper, we propose a new architecture, called IBSDN, which distributed routing protocol flanks OpenFlow improve robustness, reaction controller scalability. deeply exploring idea, complement our architecture...

Disruption-free updates are a key primitive to effectively operate SDN networks and maximize the benefits of their programmability. In this paper, we study how implement safely (with respect forwarding correctness policies), efficiently (in terms consumed network resources) robustly unpredictable factors, such as delayed message delivery processing. First, analyze fundamental limitations prior proposals, which either: 1) progressively replace initial flow rules with new ones or 2) instruct...

Motivated by conversations with operators and possibilities to unlock future Internet-based applications, we study how enable Internet Service Providers (ISPs) reliably offer connectivity through disjoint paths as an advanced, value-added service. As ISPs are increasingly deploying Segment Routing (SR), focus on implementing such service SR. We introduce the concept of robustly paths, pairs that constructed remain even after input set failures, no external intervention (e.g., configuration...