The state-of-the-art topologies of datacenter networks are fixed, based on electrical switching technology, and by now, we understand their throughput and cost well. For the past years, researchers have been developing novel optical switching technologies that enable the emergence of reconfigurable datacenter networks (RDCNs) that support dynamic psychical topologies. The art of network design of dynamic topologies, i.e., 'Topology Engineering,' is still in its infancy. Different designs offer distinct advantages, such as faster switch reconfiguration times or demand-aware topologies, and to date, it is yet unclear what design maximizes the throughput.
This paper aims to improve our analytical understanding and formally studies the throughput of reconfigurable networks by presenting a general and unifying model for dynamic networks and their topology and traffic engineering. We use our model to study demand-oblivious and demand-aware systems and prove new upper bounds for the throughput of a system as a function of its topology and traffic schedules.
Next, we offer a novel system design that combines both demand-oblivious and demand-aware schedules, and we prove its throughput supremacy under a large family of demand matrices. We evaluate our design numerically for sparse and dense traffic and show that our approach can outperform other designs by up to 25% using common network parameters.
The performance of large-scale computing systems often critically depends on high-performance communication networks. Dynamically reconfigurable topologies, e.g., based on optical circuit switches, are emerging as an innovative new technology to deal with the explosive growth of datacenter traffic. Specifically, \emph{periodic} reconfigurable datacenter networks (RDCNs) such as RotorNet (SIGCOMM 2017), Opera (NSDI 2020) and Sirius (SIGCOMM 2020) have been shown to provide high throughput, by emulating a \emph{complete graph} through fast periodic circuit switch scheduling. However, to achieve …
State-of-the-art topologies for datacenters (DC) and high-performance computing (HPC) networks are demand-oblivious and static. Therefore, such network topologies are optimized for the worst-case traffic scenarios and can't take advantage of changing demand patterns when such exist. However, recent optical switching technologies enable the concept of dynamically reconfiguring circuit-switched topologies in real-time. This capability opens the door for the design of self-adjusting networks: networks with demand-aware and dynamic topologies in which links between nodes can be established and re-…
Reconfigurable optical topologies are emerging as a promising technology to improve the efficiency of datacenter networks. This paper considers the problem of scheduling opportunistic links in such reconfigurable datacenters. We study the online setting and aim to minimize flow completion times. The problem is a two-tier generalization of classic switch scheduling problems. We present a stable-matching algorithm which is $2\cdot (2/\varepsilon+1)$-competitive against an optimal offline algorithm, in a resource augmentation model: the online algorithm runs $2+\varepsilon$ times faster. Our algo…
This paper initiates the study of online algorithms for the maximum weight $b$-matching problem, a generalization of maximum weight matching where each node has at most $b \geq 1$ adjacent matching edges. The problem is motivated by emerging optical technologies which allow to enhance datacenter networks with reconfigurable matchings, providing direct connectivity between frequently communicating racks. These additional links may improve network performance, by leveraging spatial and temporal structure in the workload. We show that the underlying algorithmic problem features an intriguing conn…
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 …
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…
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…
This paper presents a performance analysis of the design space of optical datacenter networks, including both demand-oblivious (static or dynamic) and demand-aware networks. We formally show that the number of specific optical switch types which should be used in an optimized datacenter network, depends on the traffic pattern, and in particular, the flow size distribution.
Reconfigurable optical topologies promise to improve the performance in datacenters by dynamically optimizing the physical network in a demand-aware manner. State-of-the-art optical technologies allow to establish and update direct connectivity (in the form of edge-disjoint matchings) between top-of-rack switches within microseconds or less. However, to fully exploit temporal structure in the demand, such fine-grained reconfigurations also require fast algorithms for optimizing the interconnecting matchings. Motivated by the desire to offload a maximum amount of demand to the reconfigurable ne…
Applications running in geographically distributed setting are becoming prevalent. Large-scale online services often share or replicate their data into multiple data centers (DCs) in different geographic regions. Driven by the data communication need of these applications, inter-datacenter network (IDN) is getting increasingly important. However, we find congestion control for inter-datacenter networks quite challenging. Firstly, the inter-datacenter communication involves both data center networks (DCNs) and wide-area networks (WANs) connecting multiple data centers. Such a network environmen…
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…
Today's cloud networks are shared among many tenants. Bandwidth guarantees and work conservation are two key properties to ensure predictable performance for tenant applications and high network utilization for providers. Despite significant efforts, very little prior work can really achieve both properties simultaneously even some of them claimed so. In this paper, we present QShare, an in-network based solution to achieve bandwidth guarantees and work conservation simultaneously. QShare leverages weighted fair queuing on commodity switches to slice network bandwidth for tenants, and solves t…
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…
The University of Texas at Austin（德克萨斯大学奥斯汀分校）；Georgia Institute of Technology（佐治亚理工学院）；Meta
RDMA over Converged Ethernet (RoCE) has gained significant attraction for datacenter networks due to its compatibility with conventional Ethernet-based fabric. However, the RDMA protocol is efficient only on (nearly) lossless networks, emphasizing the vital role of congestion control on RoCE networks. Unfortunately, the native RoCE congestion control scheme, based on Priority Flow Control (PFC), suffers from many drawbacks such as unfairness, head-of-line-blocking, and deadlock. Therefore, in recent years many schemes have been proposed to provide additional congestion control for RoCE network…
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…
Optical data center network architectures are becoming attractive because of their low energy consumption, large bandwidth, and low cabling complexity. In\cite{Xu1605:PODCA}, an AWGR-based passive optical data center architecture (PODCA) is presented. Compared with other optical data center architectures, e.g., DOS \cite{ye2010scalable}, Proteus \cite{singla2010proteus}, and Petabit \cite{xia2010petabit}, PODCA can save up to 90$\%$ on power consumption and 88$\%$ in cost. Also, average latency can be low as 9 $μ$s at close to 100$\%$ throughput. However, PODCA is not reconfigurable and cannot…
Massive data centers are at the heart of the Internet. The rapid growth of Internet traffic and the abundance of rich data-driven applications have raised the need for enormous network bandwidth. Towards meeting this growing traffic demand, optical interconnects have gained significant attention, as they can provide high throughput, low latency, and scalability. In particular, optical Wavelength Division Multiplexing (WDM) provides the possibility to build data centers comprising of millions of servers, while providing hundreds of terabits per second bandwidth. In this paper, we propose a WDM-…
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 …
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 …
Modern network applications demand low-latency traffic engineering in the presence of network failure while preserving the quality of service constraints like delay and capacity. Fast Re-Route (FRR) mechanisms are widely used for traffic re-routing purposes in failure scenarios. Control plane FRR typically computes the backup forwarding rules to detour the traffic in the data plane when the failure occurs. This mechanism could be computed in the data plane with the emergence of programmable data planes. In this paper, we propose a system (called TEL) that contains two FRR mechanisms, namely, T…
Many optical circuit switched data center networks (DCN) have been proposed in the past to attain higher capacity and topology reconfigurability, though commercial adoption of these architectures have been minimal. One major challenge these architectures face is the difficulty of handling uncertain traffic demands using commercial optical circuit switches (OCS) with high switching latency. Prior works have generally focused on developing fast-switching OCS prototypes to quickly react to traffic changes through frequent reconfigurations. This approach, however, adds tremendous complexity to the…
Recent networking research has identified that data-driven congestion control (CC) can be more efficient than traditional CC in TCP. Deep reinforcement learning (RL), in particular, has the potential to learn optimal network policies. However, RL suffers from instability and over-fitting, deficiencies which so far render it unacceptable for use in datacenter networks. In this paper, we analyze the requirements for RL to succeed in the datacenter context. We present a new emulator, Iroko, which we developed to support different network topologies, congestion control algorithms, and deployment s…
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 …
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…
