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.
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 …
With the advent of software-defined networking, network configuration through programmable interfaces becomes practical, leading to various on-demand opportunities for network routing update in multi-tenant datacenters, where tenants have diverse requirements on network routings such as short latency, low path inflation, large bandwidth, high reliability, etc. Conventional solutions that rely on topology search coupled with an objective function https:// www.overleaf.com/project/5beb742041ab9c0e3caec84f to find desired routings have at least two shortcomings: (i) they run into scalability issu…
To ensure high availability, datacenter networks must rely on local fast rerouting mechanisms that allow routers to quickly react to link failures, in a fully decentralized manner. However, configuring these mechanisms to provide a high resilience against multiple failures while avoiding congestion along failover routes is algorithmically challenging, as the rerouting rules can only depend on local failure information and must be defined ahead of time. This paper presents a randomized local fast rerouting algorithm for Clos networks, the predominant datacenter topologies. Given a graph $G=(V,E…
Datacenter networks routinely support the data transfers of distributed computing frameworks in the form of coflows, i.e., sets of concurrent flows related to a common task. The vast majority of the literature has focused on the problem of scheduling coflows for completion time minimization, i.e., to maximize the average rate at which coflows are dispatched in the network fabric. Modern applications, though, may generate coflows dedicated to online services and mission-critical computing tasks which have to comply with specific completion deadlines. In this paper, we introduce $\mathtt{DCoflow…
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 al…
Datacenter applications frequently cause incast congestion, which degrades both flow completion times of short flows and throughput of long flows. Without isolating incast, existing congestion control schemes (e.g., DCTCP) rely on existing ECN signal to react to general congestion, and they lose performance due to their slow, cautious, and inaccurate reaction to incast. We propose to isolate incast using Explicit Incast Notifications (EIN) that are generated by switches, similar to ECN. Our incast detection is fast and accurate. Further, we present our congestion control scheme, called Pulser,…
As applications become more distributed to improve user experience and offer higher availability, businesses rely on geographically dispersed datacenters that host such applications more than ever. Dedicated inter-datacenter networks have been built that provide high visibility into the network status and flexible control over traffic forwarding to offer quality communication across the instances of applications hosted on many datacenters. These networks are relatively small, with tens to hundreds of nodes and are managed by the same organization that operates the datacenters which make centra…
As link speeds increase in datacenter networks, existing congestion control algorithms become less effective in providing fast convergence. TCP-based algorithms that probe for bandwidth take a long time to reach the fair-share and lead to long flow completion times. An ideal congestion control algorithms for datacenter must provide 1) zero data loss, 2) fast convergence, and 3) low buffer occupancy. However, these requirements present conflicting goals. For fast convergence,flows must ramp up quickly, but this risks packet losses and large queues. Thus, even the state-of-the-art algorithms, su…
To reduce cost, datacenter network operators are exploring blocking network designs. An example of such a design is a "spine-free" form of a Fat-Tree, in which pods directly connect to each other, rather than via spine blocks. To maintain application-perceived performance in the face of dynamic workloads, these new designs must be able to reconfigure routing and the inter-pod topology. Gemini is a system designed to achieve these goals on commodity hardware while reconfiguring the network infrequently, rendering these blocking designs practical enough for deployment in the near future. The key…
Datacenter applications demand both low latency and high throughput; while interactive applications (e.g., Web Search) demand low tail latency for their short messages due to their partition-aggregate software architecture, many data-intensive applications (e.g., Map-Reduce) require high throughput for long flows as they move vast amounts of data across the network. Recent proposals improve latency of short flows and throughput of long flows by addressing the shortcomings of existing packet scheduling and congestion control algorithms, respectively. We make the key observation that long tails …
Increasingly stringent throughput and latency requirements in datacenter networks demand fast and accurate congestion control. We observe that the reaction time and accuracy of existing datacenter congestion control schemes are inherently limited. They either rely only on explicit feedback about the network state (e.g., queue lengths in DCTCP) or only on variations of state (e.g., RTT gradient in TIMELY). To overcome these limitations, we propose a novel congestion control algorithm, PowerTCP, which achieves much more fine-grained congestion control by adapting to the bandwidth-window product …
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 foc…
We propose Kevin, a novel demand-aware reconfigurable rack-to-rack datacenter network realized with a simple and efficient control plane. In particular, Kevin makes effective use of the network capacity by supporting integrated and multi-hop routing as well as work-conserving scheduling. To this end, Kevin relies on local greedy routing with small forwarding tables which require local updates only during topological reconfigurations, making this approach ideal for dynamic networks. Specifically, Kevin is based on a de Bruijn topology (using a small number of optical circuit switches) in which …
Long tail latency of short flows (or messages) greatly affects user-facing applications in datacenters. Prior solutions to the problem introduce significant implementation complexities, such as global state monitoring, complex network control, or non-trivial switch modifications. While promising superior performance, they are hard to implement in practice. This paper presents CloudBurst, a simple, effective yet readily deployable solution achieving similar or even better results without introducing the above complexities. At its core, CloudBurst explores forward error correction (FEC) over mul…
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…
Kubernetes is the leading platform for orchestrating containerized applications. In this paper, we extend Kubernetes networking to make use of SRv6, a feature-rich overlay networking mechanism. Integration with SRv6 can be very beneficial when Kubernetes is used in large-scale and distributed multi-datacenter scenarios. We have focused on the Calico CNI plugin, one of the most used Kubernetes networking plugins. In particular, we consider Calico-VPP, a version of the Calico plugin based on the VPP (Vector Packet Processing) data plane, which provides support for SRv6 operations with very high …
Network virtualization and SDN-based routing allow carriers to flexibly configure their networks in response to demand and unexpected network disruptions. However, cellular networks, by nature, pose some unique challenges because of user mobility and control/data plane partitioning, which calls for new architectures and provisioning paradigms. In this paper, we address the latter part by devising algorithms that can provision the data plane to create a distributed Mobile Edge Cloud (MEC), which provides opportunities for lower latencies and increased resilience (through placement of network fu…
Recent work has shown that expander-based data center topologies are robust and can yield superior performance over Clos topologies. However, to achieve these benefits, previous proposals use routing and transport schemes that impede quick industry adoption. In this paper, we examine if expanders can be effective for the technology and environments practical in today's data centers, including the use of traditional protocols, at both small and large scale while complying with common practices such as over-subscription. We study bandwidth, latency and burst tolerance of topologies, highlighting…
Conventional wisdom for minimizing the average flow completion time (AFCT) in the datacenter network (DCN), where flow sizes are highly variable, would suggest scheduling every individual flow. However, we show that considering scheduling delay (including scheduler's computational and communication delays), serving most of the flows without any scheduling and only in first-come-first-served (FCFS) manner significantly improves their performance even when it is compared to the shortest remaining processing time (SRPT)-known as optimum algorithm when scheduling delay is zero. To do so, we only r…
Datacenter networks and services are at risk in the face of disasters. Existing fault-tolerant storage services cannot even achieve a nil recovery point objective (RPO) as client-generated data may get lost before the termination of their migration across geo-replicated datacenters. SDN has proved instrumental in exploiting application-level information to optimise the routing of information. In this paper, we propose Software Defined Edge (SDE) or the implementation of SDN at the network edge to achieve nil RPO. We illustrate our proposal with a fault-tolerant key-value store that experimenta…
With the rapid growth of different massive applications and parallel flow requests in Data Center Networks (DCNs), today's providers are confronting challenges in flow forwarding decisions. Since Software Defined Networking (SDN) provides fine granular control, it can be intelligently programmed to distinguish between flow requirements. The present article proposes a knapsack model in which the link bandwidth and incoming flows are modeled as a knapsack capacity and items, respectively. Furthermore, each flow consists of two size and value aspects, acquired through flow size extraction and the…
The interconnect is one of the most critical components in large scale computing systems, and its impact on the performance of applications is going to increase with the system size. In this paper, we will describe Slingshot, an interconnection network for large scale computing systems. Slingshot is based on high-radix switches, which allow building exascale and hyperscale datacenters networks with at most three switch-to-switch hops. Moreover, Slingshot provides efficient adaptive routing and congestion control algorithms, and highly tunable traffic classes. Slingshot uses an optimized Ethern…
The SRv6 architecture (Segment Routing based on IPv6 data plane) is a promising solution to support services like Traffic Engineering, Service Function Chaining and Virtual Private Networks in IPv6 backbones and datacenters. The SRv6 architecture has interesting scalability properties as it reduces the amount of state information that needs to be configured in the nodes to support the network services. In this paper, we describe the advantages of complementing the SRv6 technology with an SDN based approach in backbone networks. We discuss the architecture of a SRv6 enabled network based on Lin…
Segment Routing over IPv6 (SRv6 in short) is a networking solution for IP backbones and datacenters, which has been recently adopted in several of large scale network deployments. The SRv6 research, standardization and implementation activities are going on at a remarkable pace. In particular, a number of Internet Drafts have been submitted related to the Performance Monitoring (PM) of flows in an SRv6 network. In this paper we discuss the proposed PM approaches, considering both data plane and control plane aspects and focusing on loss monitoring. Then we describe the implementation of a per-…
In distributed computing frameworks like MapReduce, Spark, and Dyrad, a coflow is a set of flows transferring data between two stages of a job. The job cannot start its next stage unless all flows in the coflow finish. To improve the execution performance of such a job, it is crucial to reduce the completion time of a coflow which can contribute more than 50% of the job completion time. While several schedulers have been proposed, we observe that routing, as a factor greatly impacting the Coflow Completion Time (CCT), has not been well considered. In this paper, we focus on the coflow scheduli…
We study network coding gaps for the problem of makespan minimization of multiple unicasts. In this problem distinct packets at different nodes in a network need to be delivered to a destination specific to each packet, as fast as possible. The network coding gap specifies how much coding packets together in a network can help compared to the more natural approach of routing. While makespan minimization using routing has been intensely studied for the multiple unicasts problem, no bounds on network coding gaps for this problem are known. We develop new techniques which allow us to upper bound …
Datacenters need networks that support both low-latency and high-bandwidth packet delivery to meet the stringent requirements of modern applications. We present Opera, a dynamic network that delivers latency-sensitive traffic quickly by relying on multi-hop forwarding in the same way as expander-graph-based approaches, but provides near-optimal bandwidth for bulk flows through direct forwarding over time-varying source-to-destination circuits. The key to Opera's design is the rapid and deterministic reconfiguration of the network, piece-by-piece, such that at any moment in time the network imp…
New optical technologies offer the ability to reconfigure network topologies dynamically, rather than setting them once and for all. This is true in both optical wide area networks (optical WANs) and in datacenters, despite the many differences between these two settings. Because of these new technologies, there has been a surge of both practical and theoretical research on algorithms to take advantage of them. In particular, Jia et al. [INFOCOM '17] designed online scheduling algorithms for dynamically reconfigurable topologies for both the makespan and sum of completion times objectives. In …
People desire to be connected, no matter where they are. Recently, providing Internet access to on-board passengers has received a lot of attention from both industry and academia. However, in order to guarantee an acceptable Quality of Service (QoS) for the passenger services with low incurred cost, the path to route the services, as well as the datacenter (DC) to deploy the services should be carefully determined. This problem is challenging, due to different types of Air-to-Ground (A2G) connections, i.e., satellites and Direct-Air-to-Ground (DA2G) links. These A2G connection types differ in…
Oblivious routing has a long history in both the theory and practice of networking. In this work we initiate the formal study of oblivious routing in the context of reconfigurable networks, a new architecture that has recently come to the fore in datacenter networking. These networks allow a rapidly changing bounded-degree pattern of interconnections between nodes, but the network topology and the selection of routing paths must both be oblivious to the traffic demand matrix. Our focus is on the trade-off between maximizing throughput and minimizing latency in these networks. For every constan…
We present Contra, a system for performance-aware routing that can adapt to traffic changes at hardware speeds. While existing work has developed point solutions for performance-aware routing on a fixed topology (e.g., a Fattree) with a fixed routing policy (e.g., use least utilized paths), Contra can be configured to operate seamlessly over any network topology and a wide variety of sophisticated routing policies. Users of Contra write network-wide policies that rank network paths given their current performance. A compiler then analyzes such policies in conjunction with the network topology …
Cooperative ad-hoc UAV networks have been turning into the primary solution set for situations where establishing a communication infrastructure is not feasible. Search-and-rescue after a disaster and intelligence, surveillance, and reconnaissance (ISR) are two examples where the UAV nodes need to send their collected data cooperatively into a central decision maker unit. Recently proposed SDN-based solutions show incredible performance in managing different aspects of such networks. Alas, the routing problem for the highly dynamic UAV networks has not been addressed adequately. An optimal, re…
GraphCC: A Practical Graph Learning-based Approach to Congestion Control in Datacenters
Barcelona Neural Networking Center, Universitat Politècnica de Catalunya（加泰罗尼亚理工大学巴塞罗那神经网络中心）；Telefonica Research（西班牙电信研究中心）；Huawei Technologies Co., Ltd.（华为技术有限公司）
Cooperative UAV networks are becoming increasingly popular in military and civilian applications. Alas, the typical ad-hoc routing protocols, which aim at finding the shortest path, lead to significant performance degradation because of the 3-dimension highly-dynamic nature of UAV networks and the uneven distribution of nodes across the network. This paper proposes OPAR, an optimized predictive and adaptive routing protocol, to face this challenging problem. We model the routing problem with linear programming (LP), where the goal is to maximize network performance, considering the path lifeti…
This paper optimizes the scheduling and routing of the co-flows of MapReduce shuffling phase in state-of-the-art and proposed Passive Optical Networking (PON)-based Data Centre Network (DCN) architectures. A time-slotted Mixed Integer Linear Programming (MILP) model is developed and used for the optimization with the objective of minimizing either the total energy consumption or the completion time. The DCN architectures include four state-of-the-art electronic switching architectures which are spine-leaf, Fat-tree, BCube, and DCell data centres. The proposed PON-based DCN architectures includ…
