Search for: All records

Scale-out datacenter network fabrics enable network operators to translate improved link and switch speeds directly into end-host throughput. Unfortunately, limits in the underlying CMOS packet switch chip manufacturing roadmap mean that NICs, links, and switches are not getting faster fast enough to meet demand. As a result, operators have introduced alternative, parallel fabric designs in the core of the network that deliver N-times the bandwidth by simply forwarding traffic over any of N parallel network fabrics. In this work, we consider extending this parallel network idea all the way to the end host. Our initial impressions found that direct application of existing path selection and forwarding techniques resulted in poor performance. Instead, we show that appropriate path selection and forwarding protocols can not only improve the performance of existing, homogeneous parallel fabrics, but enable the development of heterogeneous parallel network fabrics that can deliver even higher bandwidth, lower latency, and improved resiliency than traditional designs constructed from the same constituent components. 

Recent proposals for reconfigurable data center networks have shown that providing multiple time-varying paths can improve network capacity and lower physical latency. However, existing TCP variants are ill-suited to utilize available capacity because their congestion control cannot react quickly enough to drastic variations in bandwidth and latency. We present Time-division TCP (TDTCP), a new TCP variant designed for reconfigurable data center networks. TDTCP recognizes that communication in these fabrics happens over a set of paths, each having its own physical characteristics and cross traffic. TDTCP multiplexes each connection across multiple independent congestion states---one for each distinct path---while managing connection-wide tasks in a shared fashion. It leverages network support to receive timely notification of path changes and promptly matches its local view to the current path. We implement TDTCP in the Linux kernel. Results on an emulated network show that TDTCP improves throughput over both traditional TCP variants, such as DCTCP and CUBIC, and multipath TCP by 24--41% without requiring significant in-network buffering to hide path variations. 

Passive remote memory remains the holy grail of disaggregation. Most existing systems for disaggregated memory either use remote memory simply as a backing store, or design special-purpose data structures that require some amount of processing co-resident with the remote memory to manage and apply updates. The few proposals for truly passive remote memory perform well only with read-mostly workloads, rapidly deteriorating in the face of even low levels of write contention. We propose to leverage in-network devices (specifically, a programmable top-of-rack switch) to serialize remote memory accesses and resolve any write conflicts in flight. Our prototype is able to completely avoid write contention in the recently published Clover disaggregated key/value store, delivering a performance boost of almost 50% on our testbed under a mixed read/write workload. 

Multiple vendors have recently released SmartNICs that provide both special-purpose accelerators and programmable processing cores that allow increasingly sophisticated packet processing tasks to be offloaded from general-purpose CPUs. Indeed, leading data-center operators have designed and deployed SmartNICs at scale to support both network virtualization and application-specific tasks. Unfortunately, cloud providers have not yet opened up the full power of these devices to tenants, as current runtimes do not provide adequate isolation between individual applications running on the SmartNICs themselves. We introduce FairNIC, a system to provide performance isolation between tenants utilizing the full capabilities of a commodity SoC SmartNIC. We implement FairNIC on Cavium LiquidIO 2360s and show that we are able to isolate not only typical packet processing, but also prevent MIPS-core cache pollution and fairly share access to fixed-function hardware accelerators. We use FairNIC to implement NIC-accelerated OVS and key/value store applications and show that they both can cohabitate on a single NIC using the same port, where the performance of each is unimpacted by other tenants. We argue that our results demonstrate the feasibility of sharing SmartNICs among virtual tenants, and motivate the development of appropriate security isolation mechanisms. 

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. Unlike prior approaches, Opera requires no separate electrical network and no active circuit scheduling. 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 implements an expander graph, yet, integrated across time, the network provides bandwidth-efficient single-hop paths between all racks. We show that Opera supports low-latency traffic with flow completion times comparable to cost-equivalent static topologies, while delivering up to 4x the bandwidth for all-to-all traffic and supporting up to 60% higher load for published datacenter workloads.