Michael P. Mesnier

Object-based storage

Storage technology has enjoyed considerable growth since the first disk drive was introduced nearly 50 years ago, in part facilitated by the slow and steady evolution of storage interfaces (SCSI and ATA/IDE). The stability of these interfaces has allowed continual advances in both storage devices and applications, without frequent changes to the standards. However, the interface ultimately determines the functionality supported by the devices, and current interfaces are holding system designers back. Storage technology has progressed to the point that a change in the device interface is needed. Object-based storage is an emerging standard designed to address this problem. In this article we describe object-based storage, stressing how it improves data sharing, security, and device intelligence. We also discuss some industry applications of object-based storage and academic research using objects as a foundation for building even more intelligent storage systems.

Modeling the relative fitness of storage

Relative fitness is a new black-box approach to modeling the performance of storage devices. In contrast with an absolute model that predicts the performance of a workload on a given storage device, a relative fitness model predicts performance differences between a pair of devices. There are two primary advantages to this approach. First, because are lative fitness model is constructed for a device pair, the application-device feedback of a closed workload can be captured (e.g., how the I/O arrival rate changes as the workload moves from device A to device B). Second, a relative fitness model allows performance and resource utilization to be used in place of workload characteristics. This is beneficial when workload characteristics are difficult to obtain or concisely express (e.g., rather than describe the spatio-temporal characteristics of a workload, one could use the observed cache behavior of device A to help predict the performance of B.n This paper describes the steps necessary to build a relative fitness model, with an approach that is general enough to be used with any black-box modeling technique. We compare relative fitness models and absolute models across a variety of workloads and storage devices. On average, relative fitness models predict bandwidth and throughput within 10-20% and can reduce prediction error by as much as a factor of two when compared to absolute models.

File classification in self-* storage systems

To tune and manage themselves, file and storage systems must understand key properties (e.g., access pattern, lifetime, size) of their various files. This paper describes how systems can automatically learn to classify the properties of files (e.g., read-only access pattern, short-lived, small in size) and predict the properties of new files, as they are created, by exploiting the strong associations between a files properties and the names and attributes assigned to it. These associations exist, strongly but differently, in each of four real NFS environments studied. Decision tree classifiers can automatically identify and model such associations, providing prediction accuracies that often exceed 90%. Such predictions can be used to select storage policies (e.g., disk allocation schemes and replication factors) for individual files. Further, changes in associations can expose information about applications, helping autonomic system components distinguish growth from fundamental change.

Relative fitness models for storage

Relative fitness is a new black-box approach to modeling storage devices. Whereas conventional black-box models train to predict a devices performance given device-independent workload characteristics, relative fitness models learn to predict the changes in performance between specific devices. There are two advantages. First, unlike conventional modeling, relative fitness does not depend entirely on workload characteristics; performance and resource utilization (e.g., cache usage) can also be used to describe a workload. This is beneficial when workload characteristics are difficult to express (e.g., temporal locality). Second, because relative fitness models are constructed for each pair of devices, changes in workload characteristics (e.g., I/O inter-arrival delay) can be modeled. Therefore, unlike a conventional model, a relative fitness model can be used by applications with a closed I/O arrival process. In this article, we present relative fitness as an evolution of the conventional model and share some early results.

Relative fitness modeling

Relative fitness is a new approach to modeling the performance of storage devices (e.g., disks and RAID arrays). In contrast to a conventional model, which predicts the performance of an applications I/O on a given device, a relative fitness model predicts performance differences between devices. The result is significantly more accurate predictions.