| | |
Summary: Context-Aware Prefetching at the Storage Server
Gokul Soundararajan, Madalin Mihailescu
, and Cristiana Amza
Department of Electrical and Computer Engineering
Department of Computer Science
University of Toronto
Abstract
In many of today's applications, access to storage con-
stitutes the major cost of processing a user request.
Data prefetching has been used to alleviate the stor-
age access latency. Under current prefetching tech-
niques, the storage system prefetches a batch of blocks
upon detecting an access pattern. However, the high
level of concurrency in today's applications typically
leads to interleaved block accesses, which makes detect-
ing an access pattern a very challenging problem. To-
wards this, we propose and evaluate QuickMine, a novel,
lightweight and minimally intrusive method for context-
aware prefetching. Under QuickMine, we capture ap-
plication contexts, such as a transaction or query, and
|
