Recently, there is an increasing interest in building data-center applications with RDMA
because of its low-latency, high-throughput, and low-CPU-utilization benefits. However …

This paper describes the design and implementation of HERD, a key-value system designed
to make the best use of an RDMA network. Unlike prior RDMA-based key-value systems …

Remote Direct Memory Access (RDMA) plays a key role in supporting performance-hungry
datacenter applications. However, existing RDMA technologies are ill-suited to multi-tenant …

Researchers have long predicted the demise of the operating system [21, 26, 41]. As
datacenter servers increasingly incorporate I/O devices that let applications bypass the OS …

The unrelenting growth of the memory needs of emerging datacenter applications, along
with ever increasing cost and volatility of DRAM prices, has led to DRAM being a major …

Memory is the most contended and least elastic resource in datacenter servers today.
Applications can use only local memory—which may be scarce—even though memory …

RDMA-capable networks are gaining traction with datacenter deployments due to their high
throughput, low latency, CPU efficiency, and advanced features, such as remote memory …

It is commonly believed that datacenter networking software must sacrifice generality to
attain high performance. The popularity of specialized distributed systems designed …

Resource-disaggregated architectures have risen in popularity for large datacenters.
However, prior disaggregation systems are designed for native applications; in addition, all …

Managing data and computation is at the heart of datacenter computing. Manual
management of data can lead to data loss, wasteful consumption of storage, and laborious …