Search

Flow routing over inter-datacenter networks is a well-known problem where the network assigns a path to a newly arriving flow potentially according to the network conditions and the properties of the new flow. An essential system-wide performance metric for a routing algorithm is the flow completion times, which affect the performance of applications running across multiple datacenters. Current static and dynamic routing approaches do not take advantage of flow size information in routing, which is practical in a controlled environment such as inter-datacenter networks that are managed by the datacenter operators. In this paper, we discuss Best Worst-case Routing (BWR), which aims at optimizing the tail completion times of long-running flows over inter-datacenter networks with non-uniform link capacities. Since finding the path with the best worst-case completion time for a new flow is NP-Hard, we investigate two heuristics, BWRH and BWRHF, which use two different upper bounds on the worst-case completion times for routing. We evaluate BWRH and BWRHF against several real WAN topologies and multiple traffic patterns. Although BWRH better models the BWR problem, BWRH and BWRHF show negligible difference across various system-wide performance metrics, while BWRHF being significantly faster. Furthermore, we show that compared to other popular routing heuristics, BWRHF can reduce the mean and tail flow completion times by over $1.5\times$ and $2\times$, respectively., Comment: Accepted for publication in the 2019 57th Annual Allerton Conference on Communication, Control, and Computing (Allerton)

Bulk transfers from one to multiple datacenters can have many different completion time objectives ranging from quickly replicating some $k$ copies to minimizing the time by which the last destination receives a full replica. We design an SDN-style wide-area traffic scheduler that optimizes different completion time objectives for various requests. The scheduler builds, for each bulk transfer, one or more multicast forwarding trees which preferentially use lightly loaded network links. Multiple multicast trees are used per bulk transfer to insulate destinations that have higher available bandwidth and can hence finish quickly from congested destinations. These decisions--how many trees to construct and which receivers to serve using a given tree--result from an optimization problem that minimizes a weighted sum of transfers' completion time objectives and their bandwidth consumption. Results from simulations and emulations on Mininet show that our scheduler, Iris, can improve different completion time objectives by about $2.5\times$., Comment: Accepted to Elsevier Computer Networks

Several organizations have built multiple datacenters connected via dedicated wide area networks over which large inter-datacenter transfers take place. This includes tremendous volumes of bulk multicast traffic generated as a result of data and content replication. Although one can perform these transfers using a single multicast forwarding tree, that can lead to poor performance as the slowest receiver on each tree dictates the completion time for all receivers. Using multiple trees per transfer each connected to a subset of receivers alleviates this concern. The choice of multicast trees also determines the total bandwidth usage. To further improve the performance, bandwidth over dedicated inter-datacenter networks can be carved for different multicast trees over specific time periods to avoid congestion and minimize the average receiver completion times. In this paper, we break this problem into the three sub-problems of partitioning, tree selection, and rate allocation. We present an algorithm called QuickCast which is computationally fast and allows us to significantly speed up multiple receivers per bulk multicast transfer with control over extra bandwidth consumption. We evaluate QuickCast against a variety of synthetic and real traffic patterns as well as real WAN topologies. Compared to performing bulk multicast transfers as separate unicast transfers, QuickCast achieves up to $3.64\times$ reduction in mean completion times while at the same time using $0.71\times$ the bandwidth. Also, QuickCast allows the top $50\%$ of receivers to complete between $3\times$ to $35\times$ faster on average compared with when a single forwarding multicast tree is used for data delivery.

Long flows contribute huge volumes of traffic over inter-datacenter WAN. The Flow Completion Time (FCT) is a vital network performance metric that affects the running time of distributed applications and the users' quality of experience. Flow routing techniques based on propagation or queuing latency or instantaneous link utilization are insufficient for minimization of the long flows' FCT. We propose a routing approach that uses the remaining sizes and paths of all ongoing flows to minimize the worst-case completion time of incoming flows assuming no knowledge of future flow arrivals. Our approach can be formulated as an NP-Hard graph optimization problem. We propose BWRH, a heuristic to quickly generate an approximate solution. We evaluate BWRH against several real WAN topologies and two different traffic patterns. We see that BWRH provides solutions with an average optimality gap of less than $0.25\%$. Furthermore, we show that compared to other popular routing heuristics, BWRH reduces the mean and tail FCT by up to $1.46\times$ and $1.53\times$, respectively., Comment: Accepted for publication in IEEE Communications Letters

Machine Learning (ML) is increasingly being used for computer aided diagnosis of brain related disorders based on structural magnetic resonance imaging (MRI) data. Most of such work employs biologically and medically meaningful hand-crafted features calculated from different regions of the brain. The construction of such highly specialized features requires a considerable amount of time, manual oversight and careful quality control to ensure the absence of errors in the computational process. Recent advances in Deep Representation Learning have shown great promise in extracting highly non-linear and information-rich features from data. In this paper, we present a novel large-scale deep unsupervised approach to learn generic feature representations of structural brain MRI scans, which requires no specialized domain knowledge or manual intervention. Our method produces low-dimensional representations of brain structure, which can be used to reconstruct brain images with very low error and exhibit performance comparable to FreeSurfer features on various classification tasks.

Inter-datacenter networks connect dozens of geographically dispersed datacenters and carry traffic flows with highly variable sizes and different classes. Adaptive flow routing can improve efficiency and performance by assigning paths to new flows according to network status and flow properties. A popular approach widely used for traffic engineering is based on current bandwidth utilization of links. We propose an alternative that reduces bandwidth usage by up to at least 50% and flow completion times by up to at least 40% across various scheduling policies and flow size distributions., Comment: Accepted into IEEE INFOCOM 2018 Poster Sessions, Honolulu, HI, USA

Large inter-datacenter transfers are crucial for cloud service efficiency and are increasingly used by organizations that have dedicated wide area networks between datacenters. A recent work uses multicast forwarding trees to reduce the bandwidth needs and improve completion times of point-to-multipoint transfers. Using a single forwarding tree per transfer, however, leads to poor performance because the slowest receiver dictates the completion time for all receivers. Using multiple forwarding trees per transfer alleviates this concern--the average receiver could finish early; however, if done naively, bandwidth usage would also increase and it is apriori unclear how best to partition receivers, how to construct the multiple trees and how to determine the rate and schedule of flows on these trees. This paper presents QuickCast, a first solution to these problems. Using simulations on real-world network topologies, we see that QuickCast can speed up the average receiver's completion time by as much as $10\times$ while only using $1.04\times$ more bandwidth; further, the completion time for all receivers also improves by as much as $1.6\times$ faster at high loads., Comment: [Extended Version] Accepted for presentation in IEEE INFOCOM 2018, Honolulu, HI

Datacenters provide cost-effective and flexible access to scalable compute and storage resources necessary for today's cloud computing needs. A typical datacenter is made up of thousands of servers connected with a large network and usually managed by one operator. To provide quality access to the variety of applications and services hosted on datacenters and maximize performance, it deems necessary to use datacenter networks effectively and efficiently. Datacenter traffic is often a mix of several classes with different priorities and requirements. This includes user-generated interactive traffic, traffic with deadlines, and long-running traffic. To this end, custom transport protocols and traffic management techniques have been developed to improve datacenter network performance. In this tutorial paper, we review the general architecture of datacenter networks, various topologies proposed for them, their traffic properties, general traffic control challenges in datacenters and general traffic control objectives. The purpose of this paper is to bring out the important characteristics of traffic control in datacenters and not to survey all existing solutions (as it is virtually impossible due to massive body of existing research). We hope to provide readers with a wide range of options and factors while considering a variety of traffic control mechanisms. We discuss various characteristics of datacenter traffic control including management schemes, transmission control, traffic shaping, prioritization, load balancing, multipathing, and traffic scheduling. Next, we point to several open challenges as well as new and interesting networking paradigms. At the end of this paper, we briefly review inter-datacenter networks that connect geographically dispersed datacenters which have been receiving increasing attention recently and pose interesting and novel research problems., Comment: Accepted for Publication in IEEE Communications Surveys and Tutorials

Datacenter-based Cloud Computing services provide a flexible, scalable and yet economical infrastructure to host online services such as multimedia streaming, email and bulk storage. Many such services perform geo-replication to provide necessary quality of service and reliability to users resulting in frequent large inter- datacenter transfers. In order to meet tenant service level agreements (SLAs), these transfers have to be completed prior to a deadline. In addition, WAN resources are quite scarce and costly, meaning they should be fully utilized. Several recently proposed schemes, such as B4, TEMPUS, and SWAN have focused on improving the utilization of inter-datacenter transfers through centralized scheduling, however, they fail to provide a mechanism to guarantee that admitted requests meet their deadlines. Also, in a recent study, authors propose Amoeba, a system that allows tenants to define deadlines and guarantees that the specified deadlines are met, however, to admit new traffic, the proposed system has to modify the allocation of already admitted transfers. In this paper, we propose Rapid Close to Deadline Scheduling (RCD), a close to deadline traffic allocation technique that is fast and efficient. Through simulations, we show that RCD is up to 15 times faster than Amoeba, provides high link utilization along with deadline guarantees, and is able to make quick decisions on whether a new request can be fully satisfied before its deadline., Comment: World Automation Congress (WAC), IEEE, 2016

Datacenters provide the infrastructure for cloud computing services used by millions of users everyday. Many such services are distributed over multiple datacenters at geographically distant locations possibly in different continents. These datacenters are then connected through high speed WAN links over private or public networks. To perform data backups or data synchronization operations, many transfers take place over these networks that have to be completed before a deadline in order to provide necessary service guarantees to end users. Upon arrival of a transfer request, we would like the system to be able to decide whether such a request can be guaranteed successful delivery. If yes, it should provide us with transmission schedule in the shortest time possible. In addition, we would like to avoid packet reordering at the destination as it affects TCP performance. Previous work in this area either cannot guarantee that admitted transfers actually finish before the specified deadlines or use techniques that can result in packet reordering. In this paper, we propose DCRoute, a fast and efficient routing and traffic allocation technique that guarantees transfer completion before deadlines for admitted requests. It assigns each transfer a single path to avoid packet reordering. Through simulations, we show that DCRoute is at least 200 times faster than other traffic allocation techniques based on linear programming (LP) while admitting almost the same amount of traffic to the system., Comment: 23rd IEEE International Conference on High Performance Computing (HiPC)

Using multiple datacenters allows for higher availability, load balancing and reduced latency to customers of cloud services. To distribute multiple copies of data, cloud providers depend on inter-datacenter WANs that ought to be used efficiently considering their limited capacity and the ever-increasing data demands. In this paper, we focus on applications that transfer objects from one datacenter to several datacenters over dedicated inter-datacenter networks. We present DCCast, a centralized Point to Multi-Point (P2MP) algorithm that uses forwarding trees to efficiently deliver an object from a source datacenter to required destination datacenters. With low computational overhead, DCCast selects forwarding trees that minimize bandwidth usage and balance load across all links. With simulation experiments on Google's GScale network, we show that DCCast can reduce total bandwidth usage and tail Transfer Completion Times (TCT) by up to $50\%$ compared to delivering the same objects via independent point-to-point (P2P) transfers., Comment: 9th USENIX Workshop on Hot Topics in Cloud Computing, https://www.usenix.org/conference/hotcloud17/program/presentation/noormohammadpour

Datacenters are the main infrastructure on top of which cloud computing services are offered. Such infrastructure may be shared by a large number of tenants and applications generating a spectrum of datacenter traffic. Delay sensitive applications and applications with specific Service Level Agreements (SLAs), generate deadline constrained flows, while other applications initiate flows that are desired to be delivered as early as possible. As a result, datacenter traffic is a mix of two types of flows: deadline and regular. There are several scheduling policies for either traffic type with focus on minimizing completion times or deadline miss rate. In this report, we apply several scheduling policies to mix traffic scenario while varying the ratio of regular to deadline traffic. We consider FCFS (First Come First Serve), SRPT (Shortest Remaining Processing Time) and Fair Sharing as deadline agnostic approaches and a combination of Earliest Deadline First (EDF) with either FCFS or SRPT as deadline-aware schemes. In addition, for the latter, we consider both cases of prioritizing deadline traffic (Deadline First) and prioritizing regular traffic (Deadline Last). We study both light-tailed and heavy-tailed flow size distributions and measure mean, median and tail flow completion times (FCT) for regular flows along with Deadline Miss Rate (DMR) and average lateness for deadline flows. We also consider two operation regimes of lightly-loaded (low utilization) and heavily-loaded (high utilization). We find that performance of deadline-aware schemes is highly dependent on fraction of deadline traffic. With light-tailed flow sizes, we find that FCFS performs better in terms of tail times and average lateness while SRPT performs better in average times and deadline miss rate. For heavy-tailed flow sizes, except for tail times, SRPT performs better in all other metrics., Comment: Technical Report

Large cloud companies manage dozens of datacenters across the globe connected using dedicated inter-datacenter networks. An important application of these networks is data replication which is done for purposes such as increased resiliency via making backup copies, getting data closer to users for reduced delay and WAN bandwidth usage, and global load balancing. These replications usually lead to network transfers with deadlines that determine the time prior to which all datacenters should have a copy of the data. Inter-datacenter networks have limited capacity and need be utilized efficiently to maximize performance. In this report, we focus on applications that transfer multiple copies of objects from one datacenter to several datacenters given deadline constraints. Existing solutions are either deadline agnostic, or only consider point-to-point transfers. We propose DDCCast, a simple yet effective deadline aware point to multipoint technique based on DCCast and using ALAP traffic allocation. DDCCast performs careful admission control using temporal planning, uses rate-allocation and rate-limiting to avoid congestion and sends traffic over forwarding trees that are carefully selected to reduce bandwidth usage and maximize deadline meet rate. We perform experiments confirming DDCCast's potential to reduce total bandwidth usage by up to $45\%$ while admitting up to $25\%$ more traffic into the network compared to existing solutions that guarantee deadlines., Comment: Technical Report