Browsing by Author "Chu, Yu Huang"

Now showing 1 - 3 of 3

A Weighted ECMP Load Balancing Scheme for Data Centers Using P4 Switches
(2018-01-01)
Ye, Jin-Li
;
Chen, Chien
;
Chu, Yu Huang
;
資訊工程學系
;
資訊技術服務中心
This paper proposes a weighted Equal-cost multipath (W-ECMP) scheme in datacenters using a Programmable Data plane. Nowadays, data center networks face ongoing challenges for higher performance and greater efficiency. Equal-cost multi-path (ECMP) routing, the most common load-balancing scheme used on data center networks, tries to balance the traffic without awareness of the network congestion. To overcome this problem, CONGA and HULA are proposed successively. CONGA has implemented customized ASIC as a part of the switch fabric to collect congestion information distributively. Nevertheless, ASICs solution shows a lack of scalability and flexibility. However, although HULA solves some problems of CONGA by using p4 switch, best path selection strategy in HULA only selects and records the best path, which makes it easy to congest the best path, and HULA uses probes that waste bandwidth and deteriorate the performance. To solve the problems of HULA, W-ECMP chooses a path with a weighted probability to avoid congesting a path quickly. W-ECMP encapsulates the path congestion information into the normal traffic similar to the concept of Inband Network Telemetry (INT) in P4, which increases updating speed as the network loading increases. From experimental results, W-ECMP performs better than HULA does in average flow completion time (FCT).
Elephant Flow Detection in Datacenters Using OpenFlow-based Hierarchical Statistics Pulling
(2014)
Lin, Chun-Yu
;
Chen, Chien
;
Chang, Je-Wei
;
Chu, Yu Huang
;
資訊工程學系
This paper proposes an effective elephant flow detection in datacenters. Equal Cost MultiPath (ECMP) is a popular routing mechanism to achieve load balancing in datacenter networks. However, ECMP only considers equally distributing the flows over equal-length paths, but does not take the size of the flows into account. Previous studies show that detecting and rerouting elephant flows (flows that transfer significant amount of data) effectively can lead to a 113% improvement in aggregate throughput compared with the simple use of ECMP. A naive way to detect the elephant flows is to pull statistics from each flow independently. Since "the elephant and mouse phenomenon" suggests that there are only very few elephant flows in a datacenter network, it\'s not efficient to collect information from each flow. Therefore, we propose a Hierarchical Statistics Pulling (HSP) mechanism using OpenFlow protocol to save bandwidth consumption and processing time. In order to further improve the performance of HSP, two supplement functions called elephant store and range splitting are developed. Our approaches can detect elephant flows with only a small amount of network bandwidth consumption. We use Mininet emulator and mathematical analysis to verify our methods. Both of them confirm the benefits of our approaches.
Weighted Routing in Hierarchical Multi-domain SDN Controllers
(2015)
Huang, Jian-Jhong
;
Chen, Ying-Yu
;
Chen, Chien
;
Chu, Yu Huang
;
資訊工程學系
In the common implementation of software defined networking where only one controller is used, tasks required by various applications may overwhelm the controller as the network grows, leading to degradation of the network performance. Some multi-controller architectures have been proposed to remedy such scalability issue. In this paper, we present our design and implementation of a routing application under a hierarchical multi-controller architecture. In this architecture, a network is partitioned into multiple domains, each of which is managed by a dedicated local controller, which is managed by a common global controller. The routing application is executed on the local and global controllers, jointly providing a routing service for each new flow. We provide effective mechanisms to reduce the link state that should be kept by the global controller. We propose a weight function on the links so that a weighted shortest path can be found that avoids the congested links on the network. Experiments results show that our routing application in the hierarchical multi-controller architecture has a great improvement over that of the single-controller architecture in terms various performance metrics.