Filters








3,408 Hits in 4.5 sec

New Results on Web Caching with Request Reordering

Susanne Albers
2009 Algorithmica  
We study web caching with request reordering. The goal is to maintain a cache of web documents so that a sequence of requests can be served at low cost.  ...  The algorithms are based on a general technique that reduces web caching with request reordering to a problem of computing batched service schedules.  ...  We remark that in the Fault Model, our results also improve upon the best approximation guarantees known for web caching without request reordering.  ... 
doi:10.1007/s00453-008-9276-x fatcat:44io6orxzrb2fgdbt3lmhh4eke

New results on web caching with request reordering

Susanne Albers
2004 Proceedings of the sixteenth annual ACM symposium on Parallelism in algorithms and architectures - SPAA '04  
We study web caching with request reordering. The goal is to maintain a cache of web documents so that a sequence of requests can be served at low cost.  ...  The algorithms are based on a general technique that reduces web caching with request reordering to a problem of computing batched service schedules.  ...  We remark that in the Fault Model, our results also improve upon the best approximation guarantees known for web caching without request reordering.  ... 
doi:10.1145/1007912.1007925 dblp:conf/spaa/Albers04 fatcat:xfit3722hjcara6qa2sr6gu63y

Combining request scheduling with web caching

Tomás Feder, Rajeev Motwani, Rina Panigrahy, Steve Seiden, Rob van Stee, An Zhu
2004 Theoretical Computer Science  
Then we give tight bounds on competitive ratios for the online case. For caches of size k, we obtain bounds of k + O(1) for deterministic algorithms and (log k) for randomized algorithms.  ...  We extend the classic paging model by allowing reordering of requests under the constraint that a request is delayed by no longer than a predetermined number of time steps.  ...  Introduction Current web caching algorithms serve requests in the order of arrival, despite the fact that web requests are essentially independent and better hit rates may be achieved by reordering the  ... 
doi:10.1016/j.tcs.2004.05.016 fatcat:xoudpryvfbcm7mmi6qphmxt4um

Exploiting the non-determinism and asynchrony of set iterators to reduce aggregate file I/O latency

David C. Steere
1997 ACM SIGOPS Operating Systems Review  
This paper presents this abstraction and describes an implementation of it that runs on local and distributed file systems, as well as the World Wide Web.  ...  Dynamic sets demonstrate substantial performance gains -up to 50% savings in runtime for search on NFS, and up to 90% reduction in I/O latency for Web searches.  ...  Studies of cache performance on the World Wide Web (Web) bear this out: Web proxy caches get low hit rates (30-40%) even with unlimited size and large user populations [11, 3, 9] .  ... 
doi:10.1145/269005.266705 fatcat:cgi2gkcx5rcfpaklnjmoa6smhq

Exploiting the non-determinism and asynchrony of set iterators to reduce aggregate file I/O latency

David C. Steere
1997 Proceedings of the sixteenth ACM symposium on Operating systems principles - SOSP '97  
This paper presents this abstraction and describes an implementation of it that runs on local and distributed file systems, as well as the World Wide Web.  ...  Dynamic sets demonstrate substantial performance gains -up to 50% savings in runtime for search on NFS, and up to 90% reduction in I/O latency for Web searches.  ...  Studies of cache performance on the World Wide Web (Web) bear this out: Web proxy caches get low hit rates (30-40%) even with unlimited size and large user populations [11, 3, 9] .  ... 
doi:10.1145/268998.266705 dblp:conf/sosp/Steere97 fatcat:nnwtipnjy5czvmss7lbdwhiway

File grouping for scientific data management

Shyamala Doraimani, Adriana Iamnitchi
2008 Proceedings of the 17th international symposium on High performance distributed computing - HPDC '08  
recommended; that job reordering with respect to data availability has significant impact on throughput; and finally, that a relatively short history of traces is a good predictor for filecule grouping  ...  Our experimental results provide lessons for workload modeling and suggest design guidelines for data management in dataintensive resource-sharing environments.  ...  The Greedy Request Value (GRV) algorithm combines cache replacement with job scheduling with the purpose of taking advantage of current cache content by reordering jobs such that the jobs with most data  ... 
doi:10.1145/1383422.1383429 dblp:conf/hpdc/DoraimaniI08 fatcat:xvspqs5ijzdf3k3enwomsjnifu

Clearing the clouds

Michael Ferdman, Babak Falsafi, Almutaz Adileh, Onur Kocberber, Stavros Volos, Mohammad Alisafaee, Djordje Jevdjic, Cansu Kaynak, Adrian Daniel Popescu, Anastasia Ailamaki
2012 SIGARCH Computer Architecture News  
considerably exceed the capacity of on-chip caches.  ...  Processor real-estate and power are misspent on large last-level caches that do not contribute to improved scale-out workload performance.  ...  We thank the DSLab for their assistance with Cloud9, Emre Özer and Rustam Miftakhutdinov for their feedback and suggestions, and Aamer Jaleel and Carole Jean-Wu for their assistance with understanding  ... 
doi:10.1145/2189750.2150982 fatcat:26l7woyutjhodbffqiidze5i2e

A simulation study of update techniques for cyclic data broadcast

Sven Buchholz, Alexander Schill, Thomas Ziegert
2001 Proceedings of the 4th ACM international workshop on Modeling, analysis and simulation of wireless and mobile systems - MSWIM '01  
That means that the objects in the new cycle are reordered based on their last broadcast time.  ...  Updates result from a decision of the carousel manager that a requested object is more broadcast-worthy than one or several other objects, respectively, that need to be replaced to insert the requested  ... 
doi:10.1145/381591.381629 dblp:conf/mswim/BuchholzSZ01 fatcat:g75c3mxabnbn7mmw6jbye4l7tu

Clearing the clouds

Michael Ferdman, Babak Falsafi, Almutaz Adileh, Onur Kocberber, Stavros Volos, Mohammad Alisafaee, Djordje Jevdjic, Cansu Kaynak, Adrian Daniel Popescu, Anastasia Ailamaki
2012 Proceedings of the seventeenth international conference on Architectural Support for Programming Languages and Operating Systems - ASPLOS '12  
considerably exceed the capacity of on-chip caches.  ...  Processor real-estate and power are misspent on large last-level caches that do not contribute to improved scale-out workload performance.  ...  We thank the DSLab for their assistance with Cloud9, Emre Özer and Rustam Miftakhutdinov for their feedback and suggestions, and Aamer Jaleel and Carole Jean-Wu for their assistance with understanding  ... 
doi:10.1145/2150976.2150982 dblp:conf/asplos/FerdmanAKVAJKPAF12 fatcat:z37fymq7dzgzxhnrwjudviuzwi

Hyperbolic Caching: Flexible Caching for Web Applications

Aaron Blankstein, Siddhartha Sen, Michael J. Freedman
2017 USENIX Annual Technical Conference  
Today's web applications rely heavily on caching to reduce latency and backend load, using services like Redis or Memcached that employ inflexible caching algorithms.  ...  Inspired by Redis's use of random sampling for eviction (in lieu of a data structure) and recent theoretical justification for this approach, we design a new caching algorithm for web applications called  ...  We thank Siddhartha Jayanti for his assistance with theoretical analyses. Muthu Muthukrishnan coined the name "hyperbolic caching". Finally, we thank our shepherd, Rachit Agarwal.  ... 
dblp:conf/usenix/BlanksteinSF17 fatcat:eznte5th4rh5nd6a4s5t4ab2na

Document Compaction for Efficient Query Biased Snippet Generation [chapter]

Yohannes Tsegay, Simon J. Puglisi, Andrew Turpin, Justin Zobel
2009 Lecture Notes in Computer Science  
Current web search engines return query-biased snippets for each document they list in a result set.  ...  For efficiency, search engines operating on large collections need to cache snippets for common queries, and to cache documents to allow fast generation of snippets for uncached queries.  ...  To compare our results with Turpin et al.'s work, we conduct our analysis on the wt100g collection.  ... 
doi:10.1007/978-3-642-00958-7_45 fatcat:l57ewhdi3vfbfkrhokfg3jcn3m

Exploiting Internal Parallelism of Flash-based SSDs

Seon-yeong Park, Euiseong Seo, Ji-Yong Shin, Seungryoul Maeng, Joonwon Lee
2010 IEEE computer architecture letters  
Simulation results with real workloads have shown that the suggested schemes improve the performance of the SSDs by up to 15% without any additional hardware support.  ...  In order to improve performance further by utilizing the parallelism, this paper suggests request rescheduling and dynamic write request mapping.  ...  Results The effectiveness of the suggested request rescheduling schemes are evaluated with synthetic workloads.  ... 
doi:10.1109/l-ca.2010.3 fatcat:pv6bwn3fwfbuxjka2xfd7l7mhq

Quantifying the Mismatch between Emerging Scale-Out Applications and Modern Processors

Michael Ferdman, Babak Falsafi, Almutaz Adileh, Onur Kocberber, Stavros Volos, Mohammad Alisafaee, Djordje Jevdjic, Cansu Kaynak, Adrian Daniel Popescu, Anastasia Ailamaki
2012 ACM Transactions on Computer Systems  
We use performance counters on modern servers to study scale-out workloads, finding that today's predominant processor microarchitecture is inefficient for running these workloads.  ...  We thank the DSLab for their assistance with Cloud9, EmreÖzer and Rustam Miftakhutdinov for their feedback and suggestions, and Aamer Jaleel and Carole Jean-Wu for their assistance with understanding the  ...  APPENDIX A Comment: We multiply the number of LLC misses per cycle with the number of bytes fetched (64 bytes) and the frequency of the processor in Hertz.  ... 
doi:10.1145/2382553.2382557 fatcat:huy2nlmwibftnbrk32z77noowq

What TCP/IP protocol headers can tell us about the web

F. Donelson Smith, Félix Hernández Campos, Kevin Jeffay, David Ott
2001 Proceedings of the 2001 ACM SIGMETRICS international conference on Measurement and modeling of computer systems - SIGMETRICS '01  
We report the results of a large-scale empirical study of web traffic.  ...  the effects of HTTP protocol improvement, notably persistent connections (e.g., about 50% of web objects are now transferred on persistent connections), and (3) new characterizations of web usage and content  ...  While one motivation for our measurements was to provide the modeling foundation for generating synthetic web traffic, another motivation was to provide new results on the effects recent versions of the  ... 
doi:10.1145/378420.378789 dblp:conf/sigmetrics/SmithCJO01 fatcat:gefr3afwmfea3fcpuhgmfhxaue

What TCP/IP protocol headers can tell us about the web

F. Donelson Smith, Félix Hernández Campos, Kevin Jeffay, David Ott
2001 Performance Evaluation Review  
We report the results of a large-scale empirical study of web traffic.  ...  the effects of HTTP protocol improvement, notably persistent connections (e.g., about 50% of web objects are now transferred on persistent connections), and (3) new characterizations of web usage and content  ...  While one motivation for our measurements was to provide the modeling foundation for generating synthetic web traffic, another motivation was to provide new results on the effects recent versions of the  ... 
doi:10.1145/384268.378789 fatcat:4ne6x4vpijalzj5yrucmrr22ba
« Previous Showing results 1 — 15 out of 3,408 results