Past

Stephens, Brent; Cox, Alan L.; Felter, Wes; Dixon, Colin; Carter, John

doi:10.1145/2413176.2413183

Cited by 120 publications

(12 citation statements)

References 24 publications

Supporting

Mentioning

Contrasting

Order By: Relevance

“…Port-6 is chosen for the source 2, because it is the default port. We can now build the compressed table by adding all rules that have ports different than their corresponding aggregate rules: (0, 4, 4), (1,5,4), (2,4,4), (2,5,5). Then, we add all aggregate rules with a port different from the default port: (0, * , 5).…”

Section: Minnie: Compression Modulementioning

confidence: 99%

See 1 more Smart Citation

Minnie : An SDN world with few compressed forwarding rules

et al. 2017

View full text Add to dashboard Cite

International audienceSoftware Defined Networking (SDN) is gaining momentum with the support of major manufacturers. While it brings flexibility to the management of flows within the data center fabric, this flexibility comes at the cost of smaller routing table capacities. Indeed, the Ternary Content-Addressable Memory (TCAM) needed by SDN devices has smaller capacities than CAMs used in legacy hardware. In this paper, we investigate compression techniques to maximize the utility of SDN switches forwarding tables. We validate our algorithm, called MINNIE, with intensive simulations for well-known data center topologies, to study its efficiency and compression ratio for a large number of forwarding rules. Our results indicate that MINNIE scales well, being able to deal with around a million of different flows with less than 1000 forwarding entries per SDN switch, requiring negligible computation time. To assess the operational viability of MINNIE in real networks, we deployed a testbed able to emulate a k = 4 Fat-Tree data center topology. We demonstrate on the one hand, that even with a small number of clients, the limit in terms of number of rules is reached if no compression is performed, increasing the delay of new incoming flows. MINNIE, on the other hand, reduces drastically the number of rules that need to be stored, with no packet losses, nor detectable extra delays if routing lookups are done in the Application-Specific Integrated Circuits (ASICs). Hence, both simulations and experimental results suggest that MINNIE can be safely deployed in real networks, providing compression ratios between 70% and 99%

show abstract

Section: Minnie: Compression Modulementioning

confidence: 99%

“…Consequently, the available TCAM memory in routers is limited. Indeed, a typical switch supports between around a couple of thousands to no more than 25 thousands of 12-tuples forwarding rules, as reported in [2].…”

Section: Introductionmentioning

confidence: 99%

Minnie : An SDN world with few compressed forwarding rules

et al. 2017

View full text Add to dashboard Cite

show abstract

“…For instance, to ensure a flow protection it is necessary to install 4 OpenFlow rules in each core switch (2 rules to forward and 2 rules to backward flow). Taking the example of the HP ProVision 10Gbps Ethernet switch [16], [17], which supports 1500 flows in TCAM, just 375 flows could be fully protected. Beyond that, the flow rules will be stored out of the TCAM in slower memories (SRAM), significantly impacting the latency variability [18].…”

Section: Failure Recovery Timementioning

confidence: 99%

Programmable residues defined networks for edge data centres

Martinello

Liberato

Beldachi

et al. 2017

2017 13th International Conference on Network and Service Management (CNSM)

View full text Add to dashboard Cite

“…Furthermore, in Openflow-enabled network, flow entries are used to route the flows through its pre-defined paths. However, the flow entries are stored in Ternary Content Addressable Memory (TCAM), which is an expensive and limited hardware with high-energy consumption [11]. For example, N.Katta reported that TCAMs are 400 times more expensive [12] and 100 times more power consuming per Mbit than RAM-based storage [13].…”

Section: Introductionmentioning

confidence: 99%

Backup-resource based failure recovery approach in SDN data plane

Zhang

Wang

et al. 2016

2016 18th Asia-Pacific Network Operations and Management Symposium (APNOMS)

View full text Add to dashboard Cite

Software Defined Networking (SDN) enables the underlying infrastructure to be abstracted from the network services and controlled by one or more controllers. If a link or a node fails, the switches that can detect the failure have to either inform controller to update flow tables or transform the data to pre-configured paths to recover the failure. However, existing failure recovery approaches mainly consider the recovery delay and packet loss, and ignore the storage resources consumption for backup paths in case of link or node failure. Moreover, the Ternary Content Addressable Memory (TCAM) that stores flow entries is expensive and limited with high-energy consumption. Thus in order to minimize the consumption of backup resources and meet the required failure recovery delay, a backup-resource based failure recovery approach is proposed. Two metrics are proposed to grade physical links, and three kinds of strategies for different graded links are provided, based on which the approach tries to use less flow entries to recover link failure and meets the required failure recovery delay, while guaranteeing the reliability of the network. Simulations show that backup-resource based approach can use as less flow entries as possible to ensure the performance of failure recovery and satisfy the required delay of important traffic at the same time. Moreover, the approach has good and steady performance in networks of different scales and connectivity.

show abstract

Past

Cited by 120 publications

References 24 publications

Minnie : An SDN world with few compressed forwarding rules

Minnie : An SDN world with few compressed forwarding rules

Programmable residues defined networks for edge data centres

Backup-resource based failure recovery approach in SDN data plane

Contact Info

Product

Resources

About