systems

The Case for Programmable Object Storage Systems

As applications scale to new levels and migrate into cloud environments, there has been a significant departure from the exclusive reliance on the POSIX file I/O interface. However in doing so, application often discover a lack of services, forcing …

A Framework for an In-depth Comparison of Scale-up and Scale-out

When data grows too large, we scale to larger systems, either by scaling out or up. It is understood that scale-out and scale-up have different complexities and bottlenecks but a thorough comparison of the two architectures is challenging because of …

High Performance & Low Latency in Solid-State Drives Through Redundancy

Solid-state drives are becoming increasingly popular in enterprise storage systems, playing the role of large caches and permanent storage. Although SSDs provide faster random access than hard-drives, their performance under read/write workloads is …

In-Vivo Storage System Development

The emergence of high-performance open-source storage systems is allowing application and middleware developers to consider non-standard storage system interfaces. In contrast to the practice of virtually always designing for file-like byte-stream …

In-Vivo Storage System Development

The emergence of high-performance open-source storage systems is allowing application and middleware developers to consider non-standard storage system interfaces. In contrast to the common practice of translating all I/O access onto the POSIX file …

Modeling a Leadership-scale Storage System

Exascale supercomputers will have the potential for billion-way parallelism. While physical implementations of these systems are currently not available, HPC system designers can develop models of exascale systems to evaluate system design points. …

An Integrated Model for Performance Management in a Distributed System

Real-time systems are growing in size and complexity and must often manage multiple competing tasks in environments where CPU is not the only limited shared resource. Memory, network, and other devices may also be shared and system-wide performance …

Virtualizing Disk Performance

Large- and small-scale storage systems frequently serve a mixture of workloads, an increasing number of which require some form of performance guarantee. Providing guaranteed disk performance---the equivalent of a ``virtual disk''---is challenging …

Efficient Guaranteed Disk Request Scheduling with Fahrrad

Guaranteed I/O performance is needed for a variety of applications ranging from real-time data collection to desktop multimedia to large-scale scientific simulations. Reservations on throughput, the standard measure of disk performance, fail to …

RADOS: A Fast, Scalable, and Reliable Storage Service for Petabyte-scale Storage Clusters

Brick and object-based storage architectures have emerged as a means of improving the scalability of storage clusters. However, existing systems continue to treat storage nodes as passive devices, despite their ability to exhibit significant …