Understanding data center traffic characteristics

Abstract

As data centers become more and more central in Internet communications, both research and operations communities have begun to explore how to better design and manage them. In this paper, we present a preliminary empirical study of end-to-end traffic patterns in data center networks that can inform and help evaluate research and operational approaches. We analyze SNMP logs collected at 19 data centers to examine temporal and spatial variations in link loads and losses. We find that while links in the core are heavily utilized the ones closer to the edge observe a greater degree of loss. We then study packet traces collected at a small number of switches in one data center and find evidence of ON-OFF traffic behavior. Finally, we develop a framework that derives ON-OFF traffic parameters for data center traffic sources that best explain the SNMP data collected for the data center. We show that the framework can be used to evaluate data center traffic engineering approaches. We are also applying the framework to design network-level traffic generators for data centers.

Power-Thermal Modeling and Control of Energy-Efficient Servers and Datacenters

“…Accordingly, OFF period is defined as a period between two on periods. As presented in [7], ON/OFF period and interarrival time are time-varying and uncertain while each of them forms lognormal distribution.…”

“…[56] performed the evaluation using server utilization traces from an actual datacenter setup. It used CPU utilization traces of 40 VMs where each sample is collected at every 5 min for a day while synthesizing fine-grained utilization per 5 s with a lognormal random number generator [7], whose mean is the same as the sampled value for the corresponding 5-min sample. It targeted an Intel Xeon E5410 server configuration which consists of eight cores and two frequency levels (2.0 GHz and 2.3 GHz) and used the power model in [33] to compare the power consumption results among various solutions.…”

Green Data Center Networks: Challenges and Opportunities

“…DCNs typically experience an average load of not more than 25% of the peak load. Moreover, around 70% of the time, a considerable number of the links remain idle within data centers [13]. However, the links do not remain idle constantly for long periods of time.…”

“…Benson et al analyzed data center traffic over a period of ten days and observed that the set of idle links continuously varied for the entire time period. Moreover, it also was observed that 80% of the links remained idle only for 0.002% of the time [13]. Therefore, it is important to consider the traffic characteristic within a data center prior to applying ALR or other energy saving techniques.…”

Novel flat datacenter network architecture based on scalable and flow-controlled optical switch system

“…To investigate the dynamic operation of the flow control and the payload switching of the system, optical packets are generated with a typical DC traffic load of 0.5 at the clusters side [17]. Figure 3 shows the dynamic generation/retransmission of the label and the payload from both clusters (each color represents one client).…”