Delayed Installation and Expedited Eviction: An Alternative Approach to Reduce Flow Table Occupancy in SDN Switches

Shirali-Shahreza, Sajad; Ganjali, Yashar

doi:10.1109/tnet.2018.2841397

Cited by 29 publications

(11 citation statements)

References 35 publications

Supporting

Mentioning

Contrasting

Order By: Relevance

“…This submission is not peculiar to this paper. Other network researchers have noticed that the majority of traffic flows are very small [30], although some flows are large, which carry a considerable portion of the total packets, which was similarly observed from our analyses. The ratio of the TCP traffic flows is quite high, which amounts to 85%.…”

Section: Traffic Flow Patternsupporting

confidence: 88%

Adaptive and Hybrid Idle–Hard Timeout Allocation and Flow Eviction Mechanism Considering Traffic Characteristics

et al. 2020

View full text Add to dashboard Cite

Software-defined networking (SDN) enables flexible fine-grained networking policies by allowing the SDN controller to install packet handling rules on distributed switches. The behaviour of SDN depends on the set of forwarding entries installed at the switch flow table. The increasing number of traffics from the proliferation of the Internet of Thing (IoT) devices increase the processing load on the controller and generates an additional number of entries stored in the flow table. However, the switch flow table memory (TCAM) cannot accommodate many entries. Packets from multimedia flows are usually large in size and thus suffer processing delay and require more flow set up requests. The SDN controller may be overloaded and face some scalability problems because it supports a limited number of requests from switches. OpenFlow uses timeout configuration to manage flow setup request. The conventional fixed timeout cannot cope up with the dynamic nature of traffic flows. This paper controls the frequent flow setup requests by proposing an adaptive and hybrid idle–hard timeout allocation (AH-IHTA). The algorithm considers traffic patterns, flow table usage ratio, and returns appropriate the timeout to different flows. The performance evaluations conducted have shown a 28% and 39% reduction in the flow setup request and flow eviction, respectively.

show abstract

Section: Traffic Flow Patternsupporting

confidence: 88%

Adaptive and Hybrid Idle–Hard Timeout Allocation and Flow Eviction Mechanism Considering Traffic Characteristics

et al. 2020

View full text Add to dashboard Cite

show abstract

“…Flow table usage can be presented as the table size, hit ratio, and the number of capacity misses. Such objectives may be jointly optimized to find the best flow entry timeouts [27][28][29].…”

Section: Multi-objective Problemsmentioning

confidence: 99%

“…Heuristic search finds a good or acceptable solution within a reasonable amount of time and memory space instead. Heuristic search is widely used to improve the flow table usage [28], control channel bandwidth consumption [27], and flow classification over SDNs [25][26].…”

Section: Heuristic Searchmentioning

confidence: 99%

Flow Entry Timeouts Optimization over Software Defined Networks Supporting Elephant Flow Classification

Zhao¹,

Zhao²,

Liao³

et al. 2022

Journal of Internet Technology

View full text Add to dashboard Cite

<p>Elephant flow (elephant) classification is significant for network performance management and resource optimization. Classifying elephants over Software Defined Networks (SDNs) often relies on statistics counted by switches and transferred to controllers, leading to a huge control channel bandwidth occupation that degrades network latency and user experience. Classifying elephants using flow packets forwarded to controllers completely avoids moving statistics from switches to controllers, but couples flow entry timeouts to elephant classification accuracy, time efficiency, flow table size, control channel bandwidth usage, and network latency. This paper aims to find the best flow entry timeouts to optimize the objectives by modeling the objectives and formulating a multi-objective optimization problem. The number of objectives is further reduced to 3 and the problem is solved by Machine Learning (ML) approaches. Extensive evaluations are made over real packet traces. To the best of our knowledge, this work is the first effort that explores all the objectives related to flow entry timeouts when using flow packets forwarded to controllers to classify elephants over SDNs.</p> <p> </p>

show abstract

“…The concept in [32] is follow a similar approach for solving the problem of SDN scalability, which presents a hybrid flow rule placement approach, where the flow hit ratio and flow table occupancy are used for flow classification. Based on the classification, two schemes focusing on TCP flows and non-TCP flows are proposed, respectively.…”

Section: B Previous Workmentioning

confidence: 99%

“…Therefore, the TCP needs to fully terminate the connection by a 4-way handshake and to allow incomplete data transfer after receiving a first FIN message from other side. As analyzed in [32]: there are more than 97% of TCP flows arriving at most 2 packets after receiving FIN message, and a FIN message is the last packet of TCP flows in half of these cases. In order to support the halfclosed mechanism, there are special provisions in determining whether the TCP connection is really terminated.…”

Section: A Expedited Invalid Tcp Flow Detection and Eviction Schemementioning

confidence: 99%

Deploying a Fast Detection and Eviction Mechanism of Invalid Connection-Oriented Flow-Entries in SDNs: A Scalability Approach

2020

View full text Add to dashboard Cite

As a new paradigm of network architecture, Software Defined Networking (SDN) has been used in a large number of scenarios because it realizes flexible and efficient fine-grained flow control of the network, and promotes the evolution of the network to a programmable and scalable direction. However, the transition of the traditional networking model to SDN architectures poses scalability issues due to the limitation of the flow-table in size. Facing the traffic explosion on future networks with resourceconstrained architectures, the storage space of the flow-table is not enough to bear so many flow-entries so that it not only causes performance degradation in data delivery but also results in scalability and costefficiency issues. To address this issue, in this article, we propose a solution to expedited evict the invalid flow-entries by detecting the disconnect messages of connection-oriented protocols such as Transmission Control Protocol (TCP) and Stream Control Transmission Protocol (SCTP) based on SDN controller and OpenFlow or programming protocol-independent packet processors (P4) switches. The behavior of detection is achieved by adding a specific SDN ruleset within the transport-layer in between the controller and switches. Different from the original timeout solutions, our scheme can delete invalid flow-entries in time according to the transmission layer disconnection instead of relying on the original timeout mechanism. Through a series of simulation results. we also demonstrate the superiority of our proposed solution in reducing the flow-entries occupancy and control overhead on controller, and improving the table-miss rate.

show abstract

Delayed Installation and Expedited Eviction: An Alternative Approach to Reduce Flow Table Occupancy in SDN Switches

Cited by 29 publications

References 35 publications

Adaptive and Hybrid Idle–Hard Timeout Allocation and Flow Eviction Mechanism Considering Traffic Characteristics

Adaptive and Hybrid Idle–Hard Timeout Allocation and Flow Eviction Mechanism Considering Traffic Characteristics

Flow Entry Timeouts Optimization over Software Defined Networks Supporting Elephant Flow Classification

Deploying a Fast Detection and Eviction Mechanism of Invalid Connection-Oriented Flow-Entries in SDNs: A Scalability Approach

Contact Info

Product

Resources

About