Original paper
ARC: a self-tuning, low overhead replacement cache
Pages: 115 - 130
Published: Mar 31, 2003
Abstract
We consider the problem of cache management in a demand paging scenario with uniform page sizes. We propose a new cache management policy, namely, Adaptive Replacement Cache (ARC), that has several advantages.
In response to evolving and changing access patterns, ARC dynamically, adaptively, and continually balances between the recency and frequency components in an online and selftuning fashion. The policy ARC uses a learning rule to...
Figures & Tables
Fig. 1. Algorithm for the cache replacement policy DBL that manages pages in cac...
Fig. 2. General structure of the cache replacement policy DBL. The cache is part...
Fig. 3. General structure of a generic cache replacement policy . The lists and ...
Fig. 4. Algorithm for Adaptive Replacement Cache. This algorithm is completely s...
Fig. 5. A plot of hit ratios (in percentages) achieved by ARC and LRU. Both the ...
Fig. 6. A plot of hit ratios (in percentages) achieved by ARC and LRU. Both the ...
Fig. 7. A plot of the adaptation parameter (the target size for list ) versus th...
TABLE I. A comparison of computational overhead of various cache algorithms on a...
Paper Details
Title
ARC: a self-tuning, low overhead replacement cache
Published Date
Mar 31, 2003
Pages
115 - 130
TrendsPro
You’ll need to upgrade your plan to Pro
Looking to understand a paper’s academic impact over time?
- Scinapse’s Citation Trends graph enables the impact assessment of papers in adjacent fields.
- Assess paper quality within the same journal or volume, irrespective of the year or field, and track the changes in the attention a paper received over time.
Citation AnalysisPro
You’ll need to upgrade your plan to Pro
Looking to understand the true influence of a researcher’s work across journals & affiliations?
- Scinapse’s Top 10 Citation Journals & Affiliations graph reveals the quality and authenticity of citations received by a paper.
- Discover whether citations have been inflated due to self-citations, or if citations include institutional bias.