Matches in SemOpenAlex for { <https://semopenalex.org/work/W2018338013> ?p ?o ?g. }
Showing items 1 to 84 of
84
with 100 items per page.
- W2018338013 abstract "Past work has shown that disk prefetching can be an effective technique for improving the performance of disk bound workloads. However, the performance gains are highly dependent on selecting a prefetch size that is appropriate for a specific system and workload. Using a prefetch size that is too small can lead to poor overall disk throughput, whereas prefetch sizes that are too large can lead to data being evicted before it can be used by a subsequent request.This paper looks at disk prefetch sizing for HTTP video streaming servers, such as those used by Apple, Adobe, Netflix, YouTube and Microsoft. We evaluate various representative streaming video workloads and show that the prefetch size that produces the best throughput can vary from 2 MB to 12 MB, and can depend on workload and system characteristics such as video bitrate, hard drive specifications, and memory capacity. A good choice of prefetch size can result in substantial performance gains, for example up to 3 times higher throughput than when using a prefetch size that is too large. We also find that application-level prefetching using the best prefetch size can provide up to 4 times higher throughput. In order to take full advantage of disk prefetching without extensive workload specific experimentation, we introduce an adaptive algorithm that dynamically selects an appropriate prefetch size. Most importantly, our results show our adaptive algorithm selects prefetch sizes that provide performance rivaling the best sizes determined through manual tuning, which requires extensive testing over different possible sizes." @default.
- W2018338013 created "2016-06-24" @default.
- W2018338013 creator A5008426366 @default.
- W2018338013 creator A5010499533 @default.
- W2018338013 creator A5014429043 @default.
- W2018338013 creator A5022075167 @default.
- W2018338013 creator A5028554006 @default.
- W2018338013 creator A5086491717 @default.
- W2018338013 date "2014-06-30" @default.
- W2018338013 modified "2023-10-16" @default.
- W2018338013 title "Automated Control of Aggressive Prefetching for HTTP Streaming Video Servers" @default.
- W2018338013 cites W1488805037 @default.
- W2018338013 cites W1963903779 @default.
- W2018338013 cites W1963957215 @default.
- W2018338013 cites W1970541850 @default.
- W2018338013 cites W1986697120 @default.
- W2018338013 cites W2031623767 @default.
- W2018338013 cites W2037270109 @default.
- W2018338013 cites W2046111861 @default.
- W2018338013 cites W2061442141 @default.
- W2018338013 cites W2073807738 @default.
- W2018338013 cites W2079352634 @default.
- W2018338013 cites W2104674076 @default.
- W2018338013 cites W2108863067 @default.
- W2018338013 cites W2109850171 @default.
- W2018338013 cites W2110054703 @default.
- W2018338013 cites W2112053513 @default.
- W2018338013 cites W2126022651 @default.
- W2018338013 cites W2137935742 @default.
- W2018338013 cites W2141676084 @default.
- W2018338013 cites W2142660124 @default.
- W2018338013 cites W2149273293 @default.
- W2018338013 cites W2150864656 @default.
- W2018338013 cites W2158354536 @default.
- W2018338013 cites W2160179738 @default.
- W2018338013 cites W2163227950 @default.
- W2018338013 cites W2170327727 @default.
- W2018338013 cites W4252120627 @default.
- W2018338013 doi "https://doi.org/10.1145/2611354.2611371" @default.
- W2018338013 hasPublicationYear "2014" @default.
- W2018338013 type Work @default.
- W2018338013 sameAs 2018338013 @default.
- W2018338013 citedByCount "6" @default.
- W2018338013 countsByYear W20183380132016 @default.
- W2018338013 countsByYear W20183380132017 @default.
- W2018338013 countsByYear W20183380132018 @default.
- W2018338013 countsByYear W20183380132019 @default.
- W2018338013 countsByYear W20183380132020 @default.
- W2018338013 crossrefType "proceedings-article" @default.
- W2018338013 hasAuthorship W2018338013A5008426366 @default.
- W2018338013 hasAuthorship W2018338013A5010499533 @default.
- W2018338013 hasAuthorship W2018338013A5014429043 @default.
- W2018338013 hasAuthorship W2018338013A5022075167 @default.
- W2018338013 hasAuthorship W2018338013A5028554006 @default.
- W2018338013 hasAuthorship W2018338013A5086491717 @default.
- W2018338013 hasConcept C111919701 @default.
- W2018338013 hasConcept C2986160907 @default.
- W2018338013 hasConcept C31258907 @default.
- W2018338013 hasConcept C41008148 @default.
- W2018338013 hasConcept C79403827 @default.
- W2018338013 hasConcept C93996380 @default.
- W2018338013 hasConceptScore W2018338013C111919701 @default.
- W2018338013 hasConceptScore W2018338013C2986160907 @default.
- W2018338013 hasConceptScore W2018338013C31258907 @default.
- W2018338013 hasConceptScore W2018338013C41008148 @default.
- W2018338013 hasConceptScore W2018338013C79403827 @default.
- W2018338013 hasConceptScore W2018338013C93996380 @default.
- W2018338013 hasLocation W20183380131 @default.
- W2018338013 hasOpenAccess W2018338013 @default.
- W2018338013 hasPrimaryLocation W20183380131 @default.
- W2018338013 hasRelatedWork W1492749630 @default.
- W2018338013 hasRelatedWork W1540348153 @default.
- W2018338013 hasRelatedWork W1749978345 @default.
- W2018338013 hasRelatedWork W2001930165 @default.
- W2018338013 hasRelatedWork W2023912929 @default.
- W2018338013 hasRelatedWork W2371023786 @default.
- W2018338013 hasRelatedWork W2374646538 @default.
- W2018338013 hasRelatedWork W2378526263 @default.
- W2018338013 hasRelatedWork W2618258202 @default.
- W2018338013 hasRelatedWork W3164102603 @default.
- W2018338013 isParatext "false" @default.
- W2018338013 isRetracted "false" @default.
- W2018338013 magId "2018338013" @default.
- W2018338013 workType "article" @default.