Serverless computing is a new pay-per-use cloud service paradigm that automates resource
scaling for stateless functions and can potentially facilitate bursty machine learning serving …

The exponential growth of digital information is imposing increasing scale and efficiency
demands on modern storage infrastructures. As infrastructure complexity increases, so does …

Remote access to NVMe Flash enables flexible scaling and high utilization of Flash capacity
and IOPS within a datacenter. However, existing systems for remote Flash access either …

Achieving predictable performance is critical for many distributed applications, yet difficult to
achieve due to many factors that skew the tail of the latency distribution even in well …

Datacenter operations today provide a plethora of new queueing and scheduling problems.
The notion of a “job” has become more general and multi-dimensional. The ways in which …

Tail latency is of great importance in user-facing web services. However, maintaining low tail
latency is challenging, because a single request to a web application server results in …

With the increasing popularity of disaggregated storage and microservice architectures, high
fan-out and fan-in Remote Procedure Calls (RPCs) now generate most of the traffic in …

Organizations often build separate training and inference clusters for deep learning, and use
separate schedulers to manage them. This leads to problems for both: inference clusters …

The performance characteristics of modern non-volatile storage devices have led to storage
becoming a shared, rack-scale resource. System designers have an imperative to rethink …

Distributed file systems often exhibit high tail latencies, especially in large-scale datacenters
and in the presence of competing (and possibly higher priority) workloads. This paper …