Distributed Information-Agnostic Flow Scheduling in Data Centers Based on Wait-Time

Cloud applications have reshaped the model of services and infrastructure of the Internet. Search engines, social networks, content delivery and retail and e-commerce sites belong to this group of applications. An important element in the architecture of data centers where these applications run is the communication infrastructure, commonly known as data center networks (DCNs). A critical challenge DCNs have to address is the processing of the traffic of cloud applications, which due to its properties is essentially different to the traffic of other Internet applications. In order to improve the responsiveness and throughput of applications, DCNs should be able to prioritize short flows (a few kB) over long flows (several MB). However, given the time and space variations the traffic presents, the information about flow sizes is not available in advance in order to plan the flow scheduling. There has been a wealth of solutions developed in this space, and prior work includes flow scheduling mechanisms optimizing for a specific workload but fall short when workloads are not known in advance, or comprise a collection of applications changing dynamically. In this paper, we present an adaptable mechanism called Adaptable Workload-Agnostic Flow Scheduling (AWAFS). It is an adaptable approach that can adjust in an agnostic way the scheduling configuration of DCN forwarding devices. This agnostic adjustment contributes to reduce the Flow Completion Time (FCT) of those short flows, representing around 85% of the traffic handled by cloud applications. AWAFS operates by observing the traffic and detecting statistical properties that provide a hint to adapt the scheduling parameters. Our evaluation results based on simulation show that AWAFS can reduce the average FCT of short flows between 16.9% and 45.2% when compared to the best existing agnostic non-adaptable solution, without inducing starvation on long flows. Indeed, it can provide improvements as high as 39% for long flows. Additionally, AWAFS can improve the FCT for short flows in scenarios with high heterogeneity in the traffic present in the network, with a reduction up to 5% for the average FCT and 15% for the tail FCT.

In the data center environment, meeting the dissimilar requirements of transmission performance for long and short data flows is crucial for guaranteeing the data center service quality. It is well known that optimizing the network transmission performance is the key. Abundant research studies have reported that designing an effective load-balancing scheme can boost the network performance by enhancing the path utilization of multirooted data center networks. Unfortunately, the existing data center load-balancing schemes fail to provide satisfying flow-level transmission performance since they choose to ignore the constant changing path status and blindly assign paths to data flows regardless of their different performance requirements. In order to solve these issues, we propose a data center load-balancing scheme called TAM to meet the performance requirements of long and short flows simultaneously. In detail, TAM leverages the traffic-aware ECN marking mechanism to force long flows to proactively maintain the switch queue length at a low level and release bandwidth to short flows when they compete for the bottleneck link. On the contrary, TAM carries out the coarse-grained routing or rerouting for short and long flows, respectively, in real time by perceiving the path status. In this way, the short flows achieve low delay transmission while the long flows obtain high throughput. The simulation results based on NS2 tests show that TAM achieves up to 60% lower FCTs for short flows and a 40% improvement in goodput for long flows.

Today’s datacenter networks (DCNs) have been built upon multipath topologies where each path contains multiple links. However, flow scheduling schemes proposed to minimize flow completion times (FCT) in DCNs are based on algorithms which are optimum or close-to-optimum only over single link. Moreover, most of these scheduling schemes seek either fully centralized approaches having overhead of communicating to a central entity or fully distributed approaches requiring changes in the fabric.Motivated by these shortcomings, we present HyLine a simple scheduling design for commodity DCNs which is equipped with a joint load-balancing and flow scheduling (path-aware) design exploiting the multipath nature of DCNs. HyLine takes a hybrid approach and uses the global-awareness of centralized and agility of distributed techniques without requiring any changes in the fabric. To that end, it determines a threshold margin identifying flows for which using centralized approach is beneficial.We have shown through extensive ns2 simulations that despite HyLine’s simplicity, it significantly outperforms existing schemes and achieves lower average and 99th percentile FCTs. For instance, compared to Qjump–state-of-the-art practical scheme– and pFabric–one of the best performing flow scheduling schemes– HyLine reduces average FCT up to 68% and 31%, respectively, under a production datacenter workload.

With the proliferation of distributed applications in data centers and the increase in latency-sensitive flows, it has become increasingly important to provide deterministic latency guarantees for business flows. The main component of business flow latency in the data center is queuing latency. Existing congestion control methods work in a passive reaction working approach, which can neither determine the queuing delay nor guarantee zero data loss. In this situation, this paper proposes a mechanism to deploy asynchronous traffic shapers on the Layer 3 switches of the data center network from the network side perspective. This mechanism shapes the data flow at each hop switch, which can prevent buffer overflow and packet loss, thus improving the deterministic performance of the data center network latency guarantee. We built a large Layer 2 data center network for simulation to verify the asynchronous traffic shaping mechanism based on laboratory conditions and we found that the shaping mechanism has deterministic delay guarantee capability, which can improve the delay deterministic performance of the network.KeywordsAsynchronous Traffic ShapingData Center NetworkDeterministic Latency

In this paper we analyze the problem of optimal task scheduling for data centers. Given the available resources and tasks, we propose a fast distributed iterative algorithm, which operates over a large scale network of nodes, and allows each of the interconnected nodes to reach agreement to an optimal solution in a finite number of time steps. More specifically, the algorithm (i) is guaranteed to converge to the exact optimal scheduling plan in a finite number of time steps and, (ii) once the goal of task scheduling is achieved, it exhibits distributed stopping capabilities (i.e., it allows the nodes to distributely determine whether they can terminate the operation of the algorithm). Furthermore, the proposed algorithm operates exclusively with quantized values (i.e., the information stored, processed and exchanged between neighboring agents is subject to deterministic uniform quantization) and relies on event-driven updates (e.g., to reduce energy consumption, communication bandwidth, network congestion, and/or processor usage). We also provide examples to illustrate the operation, performance, and potential advantages of the proposed algorithm. Finally, by using extensive empirical evaluations through simulations we show that the operation of our proposed algorithm is suitable for large scale networks such as data centers.

Modern datacenters provide a wide variety of application services, which generate a mix of delay-sensitive short flows and throughput-oriented long flows, transmitting in the multi-path datacenter network. Though the existing load balancing designs successfully make full use of available parallel paths and attain high bisection network bandwidth, they reroute flows regardless of their dissimilar performance requirements. The short flows suffer from the problems of large queuing delay and packet reordering, while the long flows fail to obtain high throughput due to low link utilization and packet reordering. To address these inefficiency, we design a fine-grained load balancing scheme, namely TR (Traffic-aware Rerouting), which identifies flow types and executes flexible and traffic-aware rerouting to balance the performances of both short and long flows. Besides, to avoid packet reordering, TR leverages the reverse ACKs to estimate the switch-to-switch delay, thus excluding paths that potentially cause packet reordering. Moreover, TR is only deployed on the switch without any modification on end-hosts. The experimental results of large-scale NS2 simulations show that TR reduces the average and tail flow completion time for short flows by up to 60% and 80%, as well as provides up to 3.02x gain in throughput of long flows compared to the state-of-the-art load balancing schemes.

We propose a deadline-aware flow scheduling scheme, called Preemptive Efficient Queuing (PEQ), which takes both the deadlines and sizes of the flows into account for efficient flow scheduling of flows in a data-center network in this paper. PEQ benefits from evaluating the deadlines and flow sizes of flows to improve application throughput. Our results show that PEQ outperforms the state-of-the-art deadline-aware transport schemes in terms of the application throughput and average flow completion time, under traffic with different deadline distributions. Results also show that PEQ yields a near-optimal application throughput in cases where short flows have long deadlines and long flows have strict deadlines. In other words, PEQ attains higher performance than the counterpart schemes on traffic with broader distribution of deadlines and flow sizes.

Numerous scheduling approaches have been proposed to improve user experiences in a data center network (DCN) by reducing flow completion time (FCT). Mimicking the shortest job first (SJF) has been proved to be the prominent way to improve FCT. To do so, some approaches require flow size or completion time information in advance, which is not possible in scenarios like HTTP chunk transfer or database query response. Some information-agnostic schemes require involving end-hosts for counting the number of bytes sent. We present Longer Stay Less Priority (LSLP), an information-agnostic flow scheduling scheme, like Multi-Level Feedback Queue (MLFQ) scheduler in operating systems, that aims to mimic SJF using P4 switches in a DCN. LSLP considers all the flows as short flows initially and assigns them to the highest priority queue, and flows get demoted to the lower priority queues over time. LSLP estimates the active time of a flow by leveraging the state-of-the-art P4 switch’s programmable nature. LSLP estimates the active time of a group of new flows that arrive during a time interval and assigns their packets to the highest priority. At the beginning of the next time interval, arriving packets of old flows are placed one priority lower except for those already in the lowest priority queue. Therefore, short flows can be completed in the few higher priority queues while long flows are demoted to lower priority queues. We have evaluated LSLP via a series of tests and shown that its performance is comparable to the existing scheduling schemes.

The potential advantages of optics at high link speeds have led to significant interest in deploying optical switching technology in data-center networks. Initial efforts have focused on hybrid approaches that rely on millisecond-scale circuit switching in the core of the network, while maintaining the flexibility of electrical packet switching at the edge. Recent demonstrations of microsecond-scale optical circuit switches motivate considering circuit switching for more dynamic traffic such as that generated from a top-of-rack (ToR) switch. Based on these technology trends, we propose a prototype hybrid ToR, called REACToR, which utilizes a combination of packet switching and circuit switching to appear to end-hosts as a packet-switched ToR.In this paper, we describe a prototype REACToR control plane which synchronizes end host transmissions with end-to-end circuit assignments. This control plane can react to rapid, bursty changes in the traffic from end hosts on a time scale of 100s of microseconds, several orders of magnitude faster than previous hybrid approaches. Using the experimental data from a system of eight end hosts, we calibrate a hybrid network simulator and use this simulator to predict the performance of larger-scale hybrid networks.

Fault tolerance, performance, and throughput have been major areas of research and development since the evolution of large-scale networks. Internet-based applications are rapidly growing, including large-scale computations, search engines, high-definition video streaming, e-commerce, and video on demand. In recent years, energy efficiency and fault tolerance have gained significant importance in data center networks and various studies directed the attention towards green computing. Data centers consume a huge amount of energy and various architectures and techniques have been proposed to improve the energy efficiency of data centers. However, there is a tradeoff between energy efficiency and fault tolerance. The objective of this study is to highlight a better tradeoff between the two extremes: (a) high energy efficiency and (b) ensuring high availability through fault tolerance and redundancy. The main objective of the proposed Energy-Aware Fault-Tolerant (EAFT) approach is to keep one level of redundancy for fault tolerance while scheduling resources for energy efficiency. The resultant energy-efficient data center network provides availability as well as fault tolerance at reduced operating cost. The main contributions of this article are: (a) we propose an Energy-Aware Fault-Tolerant (EAFT) data center network scheduler; (b) we compare EAFT with energy efficient resource scheduling techniques to provide analysis of parameters such as, workload distribution, average task per servers, and energy consumption; and (c) we highlight effects of energy efficiency techniques on the network performance of the data center.

TCP is widely used in the communications between servers in data centers. However, TCP has scaling limit that its ability to provide fair sharing at bottleneck link is reduced as the number of competing flows increases. Such limit is common in current data center networks and causes unfairness among TCP flows on a small time scale. The unfairness would add unpredictable delay to short flows, which would affect the user experiences of soft real-time applications. In this paper, we propose a simple and cost-effective method — shrinking MTU — to improve the fairness among TCP flows. Through model analysis and extensive simulations, the fairness on a small time scale is improved and the completion time of short flows is reduced by decreasing MTU size.

Data centers (DCs), owing to the exponential growth of Internet services, have emerged as an irreplaceable and crucial infrastructure to power this ever-growing trend. A DC typically houses a large number of computing and storage nodes, interconnected by a specially designed network, namely, DC network (DCN). The DCN serves as a communication backbone and plays a pivotal role in optimizing DC operations. However, compared to the traditional network, the unique requirements in the DCN, for example, large scale, vast application diversity, high power density, and high reliability, pose significant challenges to its infrastructure and operations. We have observed from the premium publication venues (e.g., journals and system conferences) that increasing research efforts are being devoted to optimize the design and operations of the DCN. In this paper, we aim to present a systematic taxonomy and survey of recent research efforts on the DCN. Specifically, we propose to classify these research efforts into two areas: 1) DCN infrastructure and 2) DCN operations. For the former aspect, we review and compare the list of transmission technologies and network topologies used or proposed in the DCN infrastructure. For the latter aspect, we summarize the existing traffic control techniques in the DCN operations, and survey optimization methods to achieve diverse operational objectives, including high network utilization, fair bandwidth sharing, low service latency, low energy consumption, high resiliency, and etc., for efficient DC operations. We finally conclude this survey by envisioning a few open research opportunities in DCN infrastructure and operations.

Resource competition and conflicts in datacenter networks (DCNs) are frequent and intense. They become inevitable when mixing elephant and mice flows on shared transmission paths, resulting in arbitration between throughput and latency and performance degradation. We propose a novel flow scheduling scheme, Freeway, that leverages on path diversity in the DCN topology to guarantee, simultaneously, mice flow completion within deadline and high network utilization. Freeway adaptively partitions the available paths into low latency and high throughput paths and provides different transmission services for each category. A M/G/1-based model is developed to theoretically obtain the highest value of average delay over the path that will guarantee for 99% of mice flows their completion time before the deadline. Based on this bound, Freeway proposes a dynamic path partitioning algorithm to adjust dynamically with varying traffic load the number of low latency and high throughput paths. While mice flows are transmitted over low latency paths using a simple equal cost multiple path (ECMP) scheduling, Freeway load balances elephant flows on different high-throughput paths. We evaluate Freeway in a series of simulation on a large scale topology and use real traces. Our evaluation results show that Freeway significantly reduces the mice flows completion time within deadlines, while achieving remarkable throughput compared with current schemes. It is remarkable that Freeway does not need any change of DCN switch fabrics or scheduling algorithms and can be deployed easily on any generic datacenter network with switches implementing VLANs and trunking.

The number of data centers has been increased for various reasons such as cloud computing, big-data analysis, multimedia service, etc. With public interests on data center, many novel technologies for data center networks have been proposed and deployed to support data center operations more efficiently and effectively. However, the construction of data center network incurs significant costs. Moreover, various technologies interplay each other to achieve multiple objectives, and it makes difficult to validate and/or verify characteristics of data center network. In addition, it difficult to perform experiments with a number of hosts and switches. Therefore, it is necessary to observe the characteristics of target data center network before building it. A common approach to evaluate data center is to run simulations that should be similar with real-world data center environment. However, generating traffic with the characteristics of data center networks is not matured yet. People still employ a traffic generator based on the characteristics of Internet traffic. We design a traffic generator that shows more accurate characteristics of data center network traffic. Various traffic characteristics exploited explored by several studies are considered. The proposed method generates flow-level network traffic matrix based on Poisson Shot-Noise model. We implemented the traffic generator using Python programming language to create traffic matrix. To evaluate the proposed method, we compare the results with real data center network traffic. Our results show that the generated traffic owns similar characteristics with the real network traffic in terms of flow size, duration, and the mean and variance of total traffic rate.

Spatio-temporal thermal-aware job scheduling to minimize energy consumption in virtualized heterogeneous data centers