Rapid recovery from link failures in software-defined networks

Thorat, Pankaj; Raza, Syed M.; Kim, Dongsoo S.; Choo, Hyunseung

doi:10.1109/jcn.2017.000105

Cited by 24 publications

(12 citation statements)

References 34 publications

Supporting

Mentioning

Contrasting

Order By: Relevance

“…Iperf is used to generate the traffic and the traffic used in the experiments is UDP. UDP traffic is more overloading conditions due to vulnerable of delays, control messages, packet loss, and other traffic issues especially in a reactive mode of network 45 . The reason behind using the UDP traffic is that the TCP traffic has a handshake mechanism which relative secure and ensure reliability to some extent.…”

Section: Performance Evaluationmentioning

confidence: 99%

Minimize the delays in software defined network switch controller communication

Iqbal

Qureshi

Shoaib

et al. 2020

Concurrency and Computation

View full text Add to dashboard Cite

Software Defined Networks (SDN) is now the leading framework for the existing network infrastructure. Increasing Internet traffic leads to attract SDN infrastructure in large networks like enterprise or data centers by using logical centralize control concept. This abstraction, flexibility, and agility enable the network managers to view the global picture of the network and flow the traffic in an efficient way to avoid congestion and traffic delay issues. However, besides the benefits, the internal mechanism of SDN has some serious challenges, which leads flow table overflow, congestions, controller and switch overloading, link failure and latency issues. This research focus on the delays produced during communication between control plane and data plane due to the parameters like rule formation, mismatches, buffer/queue constraints, flow entries, controller resource utilization or duplicate flow packets, and unordered packets. These delays become more critical in large networks especially in-case of reactive modes. Furthermore, the frequent rule composition and installation causes extra burden at the controller, this control communication needs prompt reply to forward the traffic in a stipulated time. This article presents the Efficient Resource Management Scheme (ERMS), which efficiently handle the inter-communication delay and minimize the network overheads. The experiment results depict the better performance of ERMS during the communication between controller and switch by efficient packet handling and flow rules management while minimizes the overheads on controller.The proposed solution enhances the performance of SDN networks by improving the quality of services parameters.

show abstract

Section: Performance Evaluationmentioning

confidence: 99%

Minimize the delays in software defined network switch controller communication

Iqbal

Qureshi

Shoaib

et al. 2020

Concurrency and Computation

View full text Add to dashboard Cite

show abstract

“…In order to offload the controller from managing some events, one has to add some intelligence at data plane. For example, multiple paths are installed at the switch for the flow so that if one path at the switch gets failed then the switch reroutes the data over another path. By installing multiple paths at a switch, the controller can overflow the small TCAM‐based flow tables at the switch.…”

Section: Future Research Directionsmentioning

confidence: 99%

Solutions for adopting software defined network in practice

Shah

Giaccone

Rawat

et al. 2019

Int J Communication

View full text Add to dashboard Cite

Software defined networking (SDN) has emerged as a new network paradigm, which decouples both control and management planes from data plane by implementing control and management at a (logically) centralized node, i.e., the controller. The data plane communicates with controller by using an open programming interface (like Openflow protocol 1 ). The reference SDN architecture is given in Figure 1 and explained as follows.Data plane: The data plane consists of standard switching devices, acting as routers, switches, and access points depending on the how they are programmed. A forwarding table is available in each switching device. When a data packet arrives at the switching device, the latter looks up its forwarding table whether an entry exists for the corresponding flow. If yes, then the data packet is forwarded/dropped as per action specified in the entry. Otherwise, the switching device buffers the data packet and sends a message to the controller to ask for instructions on how to process the packet. The controller sends back a forwarding rule to install in the forwarding table, which programs the action that the switching device must apply for the buffered data packet, and eventually for the future packets belonging to the same flow.Control plane: The controller acts as the "network brain" and is responsible for computing the forwarding behavior for the data packets based on the network topology, the network requirements (e.g., specified throughout access control list (ACL) policies), and the configuration of other network management functions (e.g., load balancing). The controller computes the forwarding decision and installs the corresponding rules in the forwarding tables present in the switching devices.Management plane: The management plane specifies the network applications (like load balancing, firewall, and monitoring) developed by the network operator.Plane interfaces: These planes in SDN interact with each other through standardized interfaces. The basic interfaces are (a) the southbound interface, used for communication between data plane and control plane, and (b) the northbound interface, used for communication between control plane and management plane.The SDN architecture has several advantages over the traditional networks. First, it centralizes the control in the SDN controller allowing a single and coherent view of the network state, simplifying the development of complex network applications and enabling the network administrator to push specific policies across the entire network. Second, the SDN architecture allows to evolve the control plane without changing the switching devices, since their actual behavior is programmed at the controller and can be reprogrammed at wish. Third, in traditional networks, the network administrator has to utilize management systems and/or manually define and implement security policies (e.g., ACL) at several switching devices. Instead, in SDN, security and/or traffic engineering policies can be defined just at the controller, and these will be forced in th...

show abstract

“…The authors show how their proposed method reduced the number of flow rules and accelerates the process of recovery, which fully satisfy the carrier-grade recovery requirements. This method was extended in (Thorat et al, 2017), where the authors considered two methods to enhance their previous work in terms of fast failure recovery. Firstly, the authors proposed the Local Immediate (LIm) recovery strategy, in which the controller will utilise the fast failover to install the alternative paths and the VLAN tagging feature to tag the arriving packets with the outgoing link ID that should be used for the transmission.…”

Section: /26mentioning

confidence: 99%

Software-defined networks: A walkthrough guide from occurrence To data plane fault tolerance

Malik

Aziz

Al-Haj

et al. 2019

Preprint

View full text Add to dashboard Cite

In recent years, the emerging paradigm of software-defined networking has become a hot and thriving topic that grabbed the attention of industry sector as well as the academic research community. The decoupling between the network control and data planes means that software-defined networking architecture is programmable, adjustable and dynamically re-configurable. As a result, a large number of leading companies across the world have latterly launched software-defined solutions in their data centers and it is expected that most of the service providers will do so in the near future due to the new opportunities enabled by software-defined architectures. Nonetheless, each emerging technology is accompanied by new issues and concerns, and fault tolerance and recovery is one such issue that faces software-defined networking. Although there have been numerous studies that have discussed this issue, gaps still exist and need to be highlighted. In this paper, we start by tracing the evolution of networking systems from the mid 1990's until the emergence of programmable networks and software-defined networking, and then define a taxonomy for software-defined networking dependability by means of fault tolerance of data plane to cover all aspects, challenges and factors that need to be considered in future solutions. We discuss in a detailed manner current state-of-the-art literature in this area. Finally, we analyse the current gaps in current research and propose possible directions for future work.

show abstract

Rapid recovery from link failures in software-defined networks

Cited by 24 publications

References 34 publications

Minimize the delays in software defined network switch controller communication

Minimize the delays in software defined network switch controller communication

Solutions for adopting software defined network in practice

Software-defined networks: A walkthrough guide from occurrence To data plane fault tolerance

Contact Info

Product

Resources

About