Home > Search Results: Tucci, Michele
Search:
Search Tips :: Advanced Search
Search collections:
Sort by: Display results: Output format:
National Repository of Grey Literature 1 records found  Search took 0.00 seconds. 
Asynchronous Duet Benchmarking
 Drozdík, Tomáš ; Horký, Vojtěch (advisor) ; Tucci, Michele (referee)
Accurate regression detection in volatile environments such as the pub- lic cloud is difficult. Cloud offers an accessible and scalable infrastructure to run benchmarks, but the traditional benchmarking methods often fail to predict regressions reliably. Duet method acknowledges the variability and runs the workloads in parallel, assuming similar outside impact symmetry. This thesis examines a duet variant that does not synchronize harness iter- ations which enables broader use of this method. The asynchronous duet method can detect 1 − 5% slowdowns for most of the tested benchmarks in volatile environments while reducing the overall costs by up to 50%. Mea- surements were obtained by a benchmark automation tool for running and processing benchmarks from multiple suites. This tool can run benchmarks with sequential and both duet methods utilizing containers for portability. 1
Detailed record

Interested in being notified about new results for this query?
Subscribe to the RSS feed.
Digital Repository :: Search :: Submit :: Personalize :: Help
Powered by Invenio v1.1.2
Maintained by admin.invenio@techlib.cz
This site is also available in the following languages:
Česky  English