XFabric: A Reconfigurable In-Rack Network for Rack-Scale Computers
نویسندگان
چکیده
Rack-scale computers are dense clusters with hundreds of micro-servers per rack. Designed for data center workloads, they can have significant power, cost and performance benefits over current racks. The rack network can be distributed, with small packet switches embedded on each processor as part of a system-on-chip (SoC) design. Ingress/egress traffic is forwarded by SoCs that have direct uplinks to the data center. Such fabrics are not fully provisioned and the chosen topology and uplink placement impacts performance for different workloads. XFabric is a rack-scale network that reconfigures the topology and uplink placement using a circuit-switched physical layer over which SoCs perform packet switching. To satisfy tight power and space requirements in the rack, XFabric does not use a single large circuit switch, instead relying on a set of independent smaller circuit switches. This introduces partial reconfigurability, as some ports in the rack cannot be connected by a circuit. XFabric optimizes the physical topology and manages uplinks, efficiently coping with partial reconfigurability. It significantly outperforms static topologies and has a performance similar to fully reconfigurable fabrics. We demonstrate the benefits of XFabric using flow-based simulations and a prototype built with electrical crosspoint switch ASICs.
منابع مشابه
Towards Reconfigurable Rack-Scale Networking
Datacenters have traditionally been designed and deployed as a collection of server racks, where each rack consists of approximately 42 units of servers connected to one or two edge switches. In this model, computation is generally localized within a single server, and the edge switches provide 10 or 40 Gbps of non-blocking bandwidth between servers in the same rack. Although the traditional mo...
متن کاملR2C2: A Network Stack for Rack-scale Computers – Public Review
For modern Internet data centers, a key challenge to meeting the immense compute, storage, and networking needs of next-generation applications is the ability of the underlying infrastructure to scale. An important new trend in this direction is the introduction of socalled “rack scale” computers, which are large numbers of tightly integrated systems-on-chip (SoC) processors, interconnected wit...
متن کاملRethinking the Network Stack for Rack-scale Computers
The rack is increasingly replacing individual servers as the basic building block of modern data centers. Future rack-scale computers will comprise a large number of tightly integrated systems-on-chip, interconnected by a switch-less internal fabric. This design enables thousands of cores per rack and provides high bandwidth for rack-scale applications. Most of the benefits promised by these ne...
متن کاملRetrieval–travel-time model for free-fall-flow-rack automated storage and retrieval system
Automated storage and retrieval systems (AS/RSs) are material handling systems that are frequently used in manufacturing and distribution centers. The modelling of the retrieval–travel time of an AS/RS (expected product delivery time) is practically important, because it allows us to evaluate and improve the system throughput. The free-fall-flow-rack AS/RS has emerged as a new technology for dr...
متن کاملQuery processing for datacenter-scale computers
Quickly exploring massive datasets for insights requires an efficient data processing platform. Parallel database management systems were originally designed to scale only to a handful of nodes, where each node keeps recent (“hot”) data in memory and has directlyattached hard disk storage for infrequently accessed (“cold”) data. To keep pace with the growing data volumes, the research focus has...
متن کامل