Modern RDMA hardware offers the potential for exceptional performance, but design
choices including which RDMA operations to use and how to use them significantly affect …

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 …

MICA is a scalable in-memory key-value store that handles 65.6 to 76.9 million key-value
operations per second using a single general-purpose multi-core system. MICA is over 4 …

Distributed applications use replication, implemented by protocols like Paxos, to ensure data
availability and transparently mask server failures. This paper presents a new approach to …

The recent surge of network I/O performance has put enormous pressure on memory and
software I/O processing sub systems. We argue that the primary reason for high memory and …

We present Grappa, a modern take on software distributed shared memory (DSM) for in-
memory data-intensive applications. Grappa enables users to program a cluster as if it were …

As the main gateway for network traffic to a server, the network interface card (NIC) is an
ideal place to incorporate diverse network functionality, such as traffic control, protocol …

Network middleboxes must offer high availability, with automatic failover when a device fails.
Achieving high availability is challenging because failover must correctly restore lost state …

Emerging datacenter applications operate on vast datasets that are kept in DRAM to
minimize latency. The large number of servers needed to accommodate this massive …

As datacenter network speeds rise, an increasing fraction of server CPU cycles is consumed
by TCP packet processing, in particular for remote procedure calls (RPCs). To free server …