A load-balanced switch with an arbitrary number of linecards

Abstract

The load-balanced switch architecture is a promising way to scale router capacity. It requires no centralized sched-uler, requires no memory operating faster than the line-rate, and can be built using a fixed, optical mesh. In a recent paper we explained how to prevent packet mis-sequencing and provide 100% throughput for all traffic patterns, and described the design of a 100Tb/s router using technology available within three years. But there is one major problem with the load-balanced switch that makes the basic mesh architecture impractical: Because the optical mesh must be uniform, the switch does not work when one or more linecards is missing or has failed. Instead we can use a passive optical switch architecture with MEMS switches that are reconfigured only when linecards are added and deleted, allowing the router to function when any subset of linecards is present and working. In this paper we derive an expression for the number of MEMS switches that are needed, and describe an algorithm to configure them. We prove that the algorithm will always find a correct configuration in polynomial time, and show examples of its running time. I. BACKGROUND Our goal is to identify router architectures with predictable throughput and scalable capacity. At the same time, we would like to identify architectures in which optical technology (for example optical switches and wavelength division multiplex-ing) can be used inside the router to increase capacity by reducing power consumption. In a previous paper [1] we explained how to build a 100Tb/s Internet router with a single-rack switch fabric built from essentially zero-power passive optics, but without sacrificing throughput guarantees. Compared to routers available today, this is approximately 40 times more switching capacity than can be put in a single rack, with throughput guarantees that no commercial router can match today. The key to the scalabil-ity is the use of the load-balanced switch, first described by C-S. Chang et al. in [2]. In [1] we extended the basic architecture so that it has provably 100% throughput for any traffic pattern, and doesn't mis-sequence packets. It is scalable, has no central scheduler, is amenable to optics, and can simplify the switch fabric by replacing a frequently scheduled and re-configured switch with a single, fixed, passive mesh of WDM channels. Linecard Linecard Linecard 1 2 3 4 Fig. 1. Load-balanced router architecture A load-balanced router based on an optical mesh is shown in Figure 1. Figure 1(a) shows the basic mesh architecture with N = 4 linecards interconnected by 2N 2 links. Each linecard in the first stage is connected to each linecard in the center stage by a channel at rate R/N , where R is the linerate and N is the number of linecards. Likewise, each linecard in the center stage is connected to each linecard in the final stage by a channel at rate R/N. Essentially, the architecture consists of a single stage of buffers sandwiched by two identical stages of switching. The buffer at each center stage linecard input...

Configuring a load-balanced switch in hardware

“…Although the configuration algorithm is described fully in [2] (and we assume the reader is familiar with both references [1], [2]), we give a brief reminder of the algorithm here.…”

“…As explained in [2], there are G groups; group i contains L i linecards, and the total number of linecards is:…”

“…An algorithm for constructing the schedule was proposed in [2]. The algorithm constructs three consecutive schedules.…”

“…Unfortunately, as mentioned in [2], the number of linecards present can keep on changing as more and more linecards are added as the network grows or linecards are removed as they fail. The load-balanced switch works by uniformly spreading packets over all linecards, and therefore needs to be aware of which linecards are present and which are not.…”

“…In [1] we described a hybrid electro-optical architecture that solves this problem, and will operate with any subset of linecards. [2] describes an algorithm to configure the switch fabric, and proves that it will always find a valid configuration in polynomial time.…”