We propose a new paradigm for network file system design: serverless n
etwork file systems. While traditional network file systems rely on a
central server machine, a serverless system utilizes workstations coop
erating as peers to provide all file system services. Any machine in t
he system can store, cache, or control any block of data. Our approach
uses this location independence, in combination with fast local area
networks, to provide better performance and scalability than tradition
al file systems. Furthermore, because any machine in the system can as
sume the responsibilities of a failed component, our serverless design
also provides high availability via redundant data storage. To demons
trate our approach, we have implemented a prototype serverless network
file system called xFS. Preliminary performance measurements suggest
that our architecture achieves its goal of scalability. For instance,i
n a 32-node xFS system with 32 active clients, each client receives ne
arly as much read or write throughput as it would see if it were the o
nly active client.