An official website of the United States government
An optical circuit-switched network core has the potential to overcome the inherent challenges of a conventional electrical packet-switched core of today's compute clusters. As optical circuit switches (OCS) directly handle the photon beams without any optical-electrical-optical (O/E/O) conversion and packet processing, OCS-based network cores have the following desirable properties: a) agnostic to data-rate, b) negligible/zero power consumption, c) no need of transceivers, d) negligible forwarding latency, and e) no need for frequent upgrade. Unfortunately, OCS can only provide point-to-point (unicast) circuits. They do not have built-in support for one-to-many (multicast) communication, yet multicast is fundamental to a plethora of data-intensive applications running on compute clusters nowadays. In this paper, we propose Shufflecast, a novel optical network architecture for next-generation compute clusters that can support high-performance multicast satisfying all the properties of an OCS-based network core. Shufflecast leverages small fanout, inexpensive, passive optical splitters to connect the Top-of-rack (ToR) switch ports, ensuring data-rate agnostic, low-power, physical-layer multicast. We thoroughly analyze Shufflecast's highly scalable data plane, light-weight control plane, and graceful failure handling. Further, we implement a complete prototype of Shufflecast in our testbed and extensively evaluate the network. Shufflecast is more power-efficient than the state-of-the-art multicast mechanisms. Also, Shufflecast is more cost-efficient than a conventional packet-switched network. By adding Shufflecast alongside an OCS-based unicast network, an all-optical network core with the aforementioned desirable properties supporting both unicast and multicast can be realized.
more »
« less
When Creek Meets River: Exploiting High-Bandwidth Circuit Switch in Scheduling Multicast Data
Data multicast is an important data traffic pattern in today’s data center running big data oriented applications. The physical layer multicast capability enabled by the emerging technologies used to build circuit switches exhibits huge benefit in transferring multicast data. This paper tackles the problem of scheduling multicast data transfer in high-bandwidth circuit switch. The scheduler aims at minimizing the average demand completion time to deliver the most benefit to the applications. Our algorithm exhibits up to 13.4 improvement comparing with the state-of-the-art solution.
more »
« less
- Award ID(s):
- 1718980
- PAR ID:
- 10058539
- Date Published:
- Journal Name:
- 2017 International Workshop on Networking BigData Oriented Systems (NetBOS)
- Page Range / eLocation ID:
- 1 to 6
- Format(s):
- Medium: X
- Sponsoring Org:
- National Science Foundation
More Like this
-
-
Emerging distributed cloud architectures, e.g., fog and mobile edge computing, are playing an increasingly impor-tant role in the efficient delivery of real-time stream-processing applications (also referred to as augmented information services), such as industrial automation and metaverse experiences (e.g., extended reality, immersive gaming). While such applications require processed streams to be shared and simultaneously consumed by multiple users/devices, existing technologies lack efficient mechanisms to deal with their inherent multicast na-ture, leading to unnecessary traffic redundancy and network congestion. In this paper, we establish a unified framework for distributed cloud network control with generalized (mixed-cast) traffic flows that allows optimizing the distributed execution of the required packet processing, forwarding, and replication operations. We first characterize the enlarged multicast network stability region under the new control framework (with respect to its unicast counterpart). We then design a novel queuing system that allows scheduling data packets according to their current destination sets, and leverage Lyapunov drift-plus-penalty con-trol theory to develop the first fully decentralized, throughput-and cost-optimal algorithm for multicast flow control. Numerical experiments validate analytical results and demonstrate the performance gain of the proposed design over existing network control policies.more » « less
-
WiFi multicast to very large groups has gained attention as a solution for multimedia delivery in crowded areas. Yet, most recently proposed schemes do not provide performance guarantees and none have been tested at scale. To address the issue of providing high multicast throughput with performance guarantees, we present the design and experimental evaluation of the Multicast Dynamic Rate Adaptation (MuDRA) algorithm. MuDRA balances fast adaptation to channel conditions and stability, which is essential for multimedia applications. MuDRA relies on feedback from some nodes collected via a light-weight protocol and dynamically adjusts the rate adaptation response time. Our experimental evaluation of MuDRA on the ORBIT testbed with over 150 nodes shows that MuDRA outperforms other schemes and supports high throughput multicast flows to hundreds of receivers while meeting quality requirements. MuDRA can support multiple high quality video streams, where 90% of the nodes report excellent or very good video quality.more » « less
-
Interference alignment (IA) is widely regarded as a promising interference management technique for wireless networks and its potential is most profound in interference-intensive environments. This motivates us to study IA for multicast communications in multi-hop MIMO networks, which are rich in interference by nature. We develop a set of linear constraints that can characterize a feasible design space of IA for multicast communications. The set of linear constraints constitutes a simple mathematical model of IA that allows us to conduct cross-layer multicast throughput optimization in multi-hop MIMO networks, but without getting involved into the onerous signal design at the physical layer. Based on the mathematical model of IA, we formulate a multicast throughput maximization problem and develop an approximation solution that can achieve (1−ϵ)-optimality. Simulation results show that the use of IA can significantly increase the multicast throughput in multi-hop MIMO networks and the throughput gain increases with the volume of multicast traffic and the number of antennas.more » « less
-
null (Ed.)A continuing trend in many scientific disciplines is the growth in the volume of data collected by scientific instruments and the desire to rapidly and efficiently distribute this data to the scientific community. Transferring these large data sets to a geographically distributed research community consumes significant network bandwidth. As both the data volume and number of subscribers grows, reliable network multicast is a promising approach to reduce the rate of growth of the bandwidth needed to support efficient data distribution. In prior work, we identified a need for reliable network multicast: scientists engaged in atmospheric research subscribing to meteorological file-streams. Specifically, the University Cooperation Atmospheric Research (UCAR) uses the Local Data Manager (LDM) to disseminate data. This work describes a trial deployment of a multicast-enabled LDM, in which eight university campuses are connected via corresponding regional Research-and-Education Networks (RENs) and Internet2. Using this deployment, we evaluated the new version of LDM, LDM7, which uses network multicast with a reliable transport protocol, and leverages Layer-2 (L2) multipoint Virtual LAN (VLANIMPLS). A performance monitoring system was deployed to collect real-time performance of LDM7, which showed that our proof-of-concept prototype worked significantly better than the current production LDM, LDM6, in two ways: (i) LDM7 can distribute file streams faster than LDM6. With six subscribers, an almost 22-fold improvement was observed with LDM7 at 100 Mbps. And (ii) to achieve a similar performance, LDM7 significantly reduces the need for bandwidth, which reduced the bandwidth requirement by about 90% over LDM6 to achieve 20 Mbps average throughput across four subscribers.more » « less
- Free Publicly Accessible Full Text
-
Accepted Manuscript1.0
- Conference Paper:
- https://doi.org/10.1109/ICNP.2017.8117591
