In-Band Synchronization for Distributed SDN Control Planes

Schiff, Liron; Schmid, Stefan; Kuznetsov, Petr

doi:10.1145/2875951.2875957

Cited by 62 publications

(36 citation statements)

References 18 publications

Supporting

Mentioning

Contrasting

Unclassified

Order By: Relevance

“…DevoFlow [17] was one of the first works proposing a modification of the OpenFlow model, namely to push responsibility for most flows to switches and adding [45] shows that in recent OpenFlow versions, interesting network functions (such as anycast or network traversals) can readily be implemented in-band. More closely related to our paper, [46] shows that it is possible to implement atomic readmodify-write operations on an OpenFlow switch, which can serve as a powerful synchronization and coordination primitive also for distributed control planes; however, such an atomic operation is not required in our system: a controller can claim a switch with a simple write operation. In this paper, we presented a first discussion of how to implement a strong notion of fault-tolerance, namely a self-stabilizing SDN [20,18].…”

Section: Related Workmentioning

confidence: 70%

“…Bibliographic note. We reported on preliminary insights on the design of in-band control planes in two short papers on Medieval [46,47]. However, Medieval is not self-stabilizing, because its design depends on the presence of non-corrupted configuration data, e.g., related to the controllers' IP addresses, which goes against the idea self-stabilization.…”

Section: Related Workmentioning

confidence: 99%

See 1 more Smart Citation

Renaissance: A Self-Stabilizing Distributed SDN Control Plane

Canini

Salem

Schiff

et al. 2018

2018 IEEE 38th International Conference on Distributed Computing Systems (ICDCS)

Self Cite

View full text Add to dashboard Cite

By introducing programmability, automated verification, and innovative debugging tools, Software-Defined Networks (SDNs) are poised to meet the increasingly stringent dependability requirements of today's communication networks. However, the design of fault-tolerant SDNs remains an open challenge.This paper considers the design of dependable SDNs through the lenses of self-stabilizationa very strong notion of fault-tolerance. In particular, we develop algorithms for an in-band and distributed control plane for SDNs, called Renaissance, which tolerate a wide range of (concurrent) controller, link, and communication failures. Our self-stabilizing algorithms ensure that after the occurrence of an arbitrary combination of failures, (i) every non-faulty SDN controller can reach any switch (or another controller) in the network within a bounded communication delay (in the presence of a bounded number of concurrent failures) and (ii) every switch is managed by at least one controller (as long as at least one controller is not faulty).We evaluate Renaissance through a rigorous worst-case analysis as well as a prototype implementation (based on OVS and Floodlight), and we report on our experiments using Mininet. IntroductionContext and Motivation. Software-Defined Network (SDN) technologies have emerged as a promising alternative to the vendor-specific, complex, and hence error-prone, operation of traditional communication networks. In particular, by outsourcing and consolidating the control over the data plane elements to a logically centralized software, SDNs support a programmatic verification and enable new debugging tools. Furthermore, the decoupling of the control plane from the data plane, allows the former to evolve independently of the constraints of the latter, enabling faster innovations.However, while the literature articulates well the benefits of the separation between control and data plane and the need for distributing the control plane (e.g., for performance and fault-tolerance), the question of how connectivity between these two planes is maintained (i.e., the communication channels from controllers to switches and between controllers) has not received much attention. Providing such connectivity is critical for ensuring the availability and robustness of SDNs.Guaranteeing that each switch is managed, at any time, by at least one controller is challenging especially if control is in-band, i.e., if control and data traffic is forwarded along the same links and devices and hence arrives at the same ports. In-band control is desirable as it avoids the need to 1 arXiv:1712.07697v2 [cs.NI] 26 Feb 2019 build, operate, and ensure the reliability of a separate out-of-band management network. Moreover, in-band management can in principle improve the resiliency of a network, by leveraging a higher path diversity (beyond connectivity to the management port).The goal of this paper is the design of a highly fault-tolerant distributed and in-band control plane for SDNs. In particular, we aim to develop a self-stabilizi...

show abstract

Section: Related Workmentioning

confidence: 70%

Section: Related Workmentioning

confidence: 99%

Renaissance: A Self-Stabilizing Distributed SDN Control Plane

Canini

Salem

Schiff

et al. 2018

2018 IEEE 38th International Conference on Distributed Computing Systems (ICDCS)

Self Cite

View full text Add to dashboard Cite

show abstract

“…radio spectrum access [20]), we foresee multiple models of managing access to SDN resources. Based on an extensive review of existing literature on software-defined networking [21,13,11,22,19], as well as earlier classifications of access to resources in distributed systems [20,23], we next propose a taxonomy of SDN resource access models (see Figure 4). While this scheme covers the access models and use cases identified in the reviewed literature, it can be extended with novel and emerging access models in the future.…”

Section: Access Classification Schemementioning

confidence: 99%

SDN Access Control for the Masses

Paladi

Gehrmann

2019

Computers & Security

View full text Add to dashboard Cite

The evolution of Software-Defined Networking (SDN) has so far been predominantly geared towards defining and refining the abstractions on the forwarding and control planes. However, despite a maturing southbound interface and a range of proposed network operating systems, the network management application layer is yet to be specified and standardized. It has currently poorly defined access control mechanisms that could be exposed to network applications. Available mechanisms allow only rudimentary control and lack procedures to partition resource access across multiple dimensions.We address this by extending the SDN north-bound interface to provide control over shared resources to key stakeholders of network infrastructure: network providers, operators and application developers. We introduce a taxonomy of SDN access models, describe a comprehensive design for SDN access control and implement the proposed solution as an extension of the ONOS network controller intent framework.

show abstract

“…We extend it with additional functional elements to enable a BFT and unavailabilitytolerant system operation. The control plane communication between the switches and controllers (S2C, C2S) and between controllers (C2C) is realized via an in-band control channel [25]. Furthermore, all the communication between different elements (i.e.…”

Section: Morph System Modelmentioning

confidence: 99%

MORPH: An Adaptive Framework for Efficient and Byzantine Fault-Tolerant SDN Control Plane

Sakic

Ðerić

Kellerer

2018

IEEE J. Select. Areas Commun.

View full text Add to dashboard Cite

Current approaches to tackling the single point of failure in SDN entail a distributed operation of SDN controller instances. Their state synchronization process is reliant on the assumption of a correct decision-making in the controllers. Successful introduction of SDN in the critical infrastructure networks also requires catering to the issue of unavailable, unreliable (e.g. buggy) and malicious controller failures. We propose MORPH, a framework tolerant to unavailability and Byzantine failures, that distinguishes and localizes faulty controller instances and appropriately reconfigures the control plane. Our controller-switch connection assignment leverages the awareness of the source of failure to optimize the number of active controllers and minimize the controller and switch reconfiguration delays. The proposed re-assignment executes dynamically after each successful failure identification. We require 2FM +FA+1 controllers to tolerate FM malicious and FA availability-induced failures. After a successful detection of FM malicious controllers, MORPH reconfigures the control plane to require a single controller message to forward the system state. Next, we outline and present a solution to the practical correctness issues related to the statefulness of the distributed SDN controller applications, previously ignored in the literature. We base our performance analysis on a resource-aware routing application, deployed in an emulated testbed comprising up to 16 controllers and up to 34 switches, so to tolerate up to 5 unique Byzantine and additional 5 availability-induced controller failures (a total of 10 unique controller failures). We quantify and highlight the dynamic decrease in the packet and CPU load and the response time after each successful failure detection.1) If the PRIMARY controller receives the client request, the task (e.g., path finding) is executed locally. 2) If a SECONDARY controller receives the client request, the request is proxied by the SECONDARY to the PRI-MARY controller, which then proceeds with request handling. If the PRIMARY controller fails, a new PRIMARY that handles the client request, is re-elected [9], [10].However, an occurrence of a Byzantine failure of the PRI-MARY controller (i.e. because of a corrupted [1], manipulated [11], or buggy [12] internal state), may lead to incorrect computation decisions in the controller logic. With Byzantine failures, there is incomplete information on whether the controller has truly failed. Thus, the controller may appear as both failed and correct to the failure-detection systems, presenting different symptoms to different observers (i.e. switches). Additionally, a malicious adversary may interfere with or modify the controller logic for the purpose of taking control of the network or re-routing the network traffic [11].On the other hand, availability-related controller failures lead to the controllers becoming inactive. In contrast to Byzantine failures, such controllers do not actively perform malicious actions nor do they try to hide their...

show abstract

In-Band Synchronization for Distributed SDN Control Planes

Cited by 62 publications

References 18 publications

Renaissance: A Self-Stabilizing Distributed SDN Control Plane

Renaissance: A Self-Stabilizing Distributed SDN Control Plane

SDN Access Control for the Masses

MORPH: An Adaptive Framework for Efficient and Byzantine Fault-Tolerant SDN Control Plane

Contact Info

Product

Resources

About