With the vigorous development of network applications, typical SDN (Software Defined Networks) such as data centers are gradually carrying more and more complex network traffic. This poses a great challenge for networ...
详细信息
ISBN:
(纸本)9781538625880
With the vigorous development of network applications, typical SDN (Software Defined Networks) such as data centers are gradually carrying more and more complex network traffic. This poses a great challenge for network monitoring - how to realize real-time, high-accuracy capture of traffic changes at low cost. In this paper, we propose a trigger-based monitoring approach called EffiView. This approach provides three ways to monitor flowstatistics, including flow-stat triggering, flowRemoved parsing and active polling. The flow-stat triggering can occur on all multiples of the presupposed flow-stat threshold for each flow entry. The latter two ways are complementary to the flow-stat triggering. flowRemoved parsing is used to acquire flowstatistics from flowRemoved messages and active polling is conditionally carried out by the controller at the expiration of monitoring period. EffiView achieves low-cost monitoring by combining the three ways efficiently, while ensuring high accuracy and fine granularity. Based on the NetMagic platform, We implement EffiView and evaluate its monitoring performance. The experimental results show that EffiView can reach great advantages over traditional monitoring approaches.
With the rapid development of cloud computing, thousands of servers and various cloud applications are involved in data center. These changes result in more and more complex flows in data center, which motivates the n...
详细信息
ISBN:
(纸本)9781509066117
With the rapid development of cloud computing, thousands of servers and various cloud applications are involved in data center. These changes result in more and more complex flows in data center, which motivates the need for faster, lower overhead, more scalable large flow detection technology. This paper firstly shows the shortcomings of the traditional large flow detection technologies. Then it proposes a new method named EffiEye, which efficiently realizes application-aware large flow detection in the controller. EffiEye mainly replies on two different mechanisms: one is the flow classification based on the pre-classification of cloud applications in App Info module, which can ensure the fast detecting speed;the other is the flow-stat triggering supported by Openflow 1.5, which can ensure the high detecting accuracy.
暂无评论