Dynamic Performance Profiling of Cloud Caches
- Submitting institution
-
The University of Surrey
- Unit of assessment
- 11 - Computer Science and Informatics
- Output identifier
- 9027032_4
- Type
- E - Conference contribution
- DOI
-
10.1145/2670979.2671007
- Title of conference / published proceedings
- Proceedings of the ACM Symposium on Cloud Computing - SOCC '14
- First page
- 0
- Volume
- 0
- Issue
- 0
- ISSN
- -
- Open access status
- -
- Month of publication
- -
- Year of publication
- 2014
- URL
-
-
- Supplementary information
-
-
- Request cross-referral to
- -
- Output has been delayed by COVID-19
- No
- COVID-19 affected output statement
- -
- Forensic science
- No
- Criminology
- No
- Interdisciplinary
- No
- Number of additional authors
-
-
- Research group(s)
-
-
- Citation count
- -
- Proposed double-weighted
- No
- Reserve for an output with double weighting
- No
- Additional information
- We propose two novel algorithms for estimating space utility of cloud-based data caches. The approximation error is formally proven to be bounded, and the implementation is shown to be efficient through extensive empirical studies. This work has been highly impactful in both academia and industry. It led to extensive follow up work by groups at MIT, CMU, Stanford, and UPenn among others; it contributed to the technology being developed at Microsoft as well as several startup companies, such as Datos IO, and CloudPhysics Inc who have developed a technology based on our algorithms (Waldspurger et al USENIX FAST’15).
- Author contribution statement
- -
- Non-English
- No
- English abstract
- -