Search

Traffic engineering (TE) attracts extensive researches over the years. Operators expect to design a TE scheme which accommodates traffic dynamics well and achieves good TE performance with little overhead. Some approaches like oblivious routing compute an optimal static routing based on a large traffic matrix (TM) range, which usually leads to much performance loss. Many approaches compute routings based on one or a few representative TMs obtained from observed historical TMs. However, they may suffer performance degradation for unexpected TMs and usually induce much overhead of system operating. In this paper, we propose ALTE, an adaptive and low-cost TE scheme based on TM classification. We develop a novel clustering algorithm to properly group a set of historical TMs into several clusters and compute a candidate routing for each TM cluster. A machine learning classifier is trained to infer the proper candidate routing online based on the features extracted from some easily measured statistics. We implement a system prototype of ALTE and do extensive simulations and experiments using both real and synthetic traffic traces. The results show that ALTE achieves near-optimal performance for dynamic traffic and introduces small overhead of routing updates.

Load balancing in datacenter networks (DCNs) is an important and challenging task for datacenter managers. A number of sophisticated technologies have been proposed to improve load balancing performance in a complicated circumstance, i.e., with various traffic characteristics. Many approaches need a high cost to implement, such as changing switch hardware. The efficiency problem has not been well addressed. MPTCP was proposed as a low-cost approach to improve data transmission in DCNs, which uses subflows to balance workloads across multiple paths. However, current MPTCP is not satisfying, especially when there are rack-local flows or many-to-one short flows. In this paper, we propose DCMPTCP to improve the efficacy of MPTCP. We gradually develop three mechanisms. First, DCMPTCP identifies rack-local traffic and eliminates unnecessary subflows to reduce the overhead. Second, DCMPTCP estimates flow length and establishes subflows in a smarter way. Third, DCMPTCP strengthens explicit congestion notification to improve the congestion control performance on inter-rack manyto-one short flows. DCMPTCP has a good compatibility and is easy to deploy. We implement DCMPTCP in ns-3 simulator and evaluate the performance by comprehensive simulations. The results show that DCMPTCP achieves ~65-771X and ~10-15X better FCT than MPTCP for rack-local and inter-rack traffic respectively.

A variety of wireless communication links today, such as HSPA+ access in high speed trains, balloon-based aerial wireless networks and satellite Internet connections have high loss rates. In such environments, Multipath TCP (MPTCP) offers a robust solution compared to regular TCP. However, MPTCP and existing schedulers suffer from performance degradation for both constant bit rate (CBR) and bulk traffic. To tackle this challenge, we develop LAMPS, a novel scheduler for MPTCP, which considers both the loss and delay when selecting subflows and chooses segments based on subflows' state. The design goal of LAMPS is to achieve a steady performance for different traffic and significantly reduce the unnecessary bandwidth consumption, especially in case of bursty losses. We have implemented LAMPS and evaluated its performance for Dynamic Adaptive Streaming over HTTP (DASH), CBR, and bulk traffic. Our experiment results show that LAMPS preserves application latency, keeps low memory consumption, and significantly reduces extra bandwidth consumption in the presence of high packet loss rate.

The vast majority of application traffic in modern data center networks (DCNs) can be classified into two categories: throughput-sensitive large flows and latency-sensitive small flows. These two types of flows have the conflicting requirements on link buffer occupancy. Existing data transfer proposals either do not fully utilize the path diversity of DCNs to improve the throughput of large flows, or cannot achieve a controllable link buffer occupancy to meet the low latency requirement of small flows. Aiming to balance throughput with latency, we develop the eXplicit MultiPath (XMP) congestion control scheme for DCNs. XMP comprises two components: the BOS algorithm brings link queue buffers consumed by large flows under control, while the TraSh algorithm is responsible for shifting traffic from more congested paths to less congested ones, thus achieving high throughput. We implemented XMP and evaluated its performance on traffic shifting, fairness, goodput, buffer occupancy and link utilization by conducting comprehensive experiments and simulations. The results show that XMP outperforms existing schemes and achieves a reasonable tradeoff between throughput and latency.