Filters








1,046 Hits in 6.2 sec

Workload Characterization and Performance Implications of Large-Scale Blog Servers

Myeongjae Jeon, Youngjae Kim, Jeaho Hwang, Joonwon Lee, Euiseong Seo
2012 ACM Transactions on the Web  
However, there has been a lack of research on the workload characterization of servers running SNS applications such as blog services.  ...  To fill this void, we empirically characterized real-world Web server logs collected from one of the largest South Korean blog hosting sites for 12 consecutive days.  ...  Performance comparison for different data placement schemes. Workload Characterization and Performance Implications of Large-Scale Blog Servers 16:21 Table IX.  ... 
doi:10.1145/2382616.2382619 fatcat:j4yj3tqqyvgsdiyruhgydoxp6e

Measurement, Modeling, and Analysis of a Large-scale Blog Sever Workload

Myeongjae Jeon, Jeaho Hwang, Youngjae Kim, Jae-Wan Jang, Joonwon Lee, Euiseong Seo
2010 2010 IEEE Second International Conference on Social Computing  
Thus, in this paper, we characterize the system workload of the largest blog hosting servers in South Korea, Tistory 1 .  ...  Understanding workload characteristics is important for optimizing and improving the performance of current systems and software based on observed trends.  ...  Tistory is one of the most popular large-scale blog servers in South Korea.  ... 
doi:10.1109/socialcom.2010.88 dblp:conf/socialcom/JeonHKJLS10 fatcat:7tfse6amyzgcjn2vwahtdw3ema

Microarchitectural implications of event-driven server-side web applications

Yuhao Zhu, Daniel Richins, Matthew Halpern, Vijay Janapa Reddi
2015 Proceedings of the 48th International Symposium on Microarchitecture - MICRO-48  
First, unlike traditional server-workloads such as CloudSuite and BigDataBench that are based on the conventional threadbased execution model, event-driven applications are heavily single-threaded, and  ...  The front-end inefficiencies stem from the unique combination of limited intra-event code reuse and large inter-event reuse distance.  ...  Any opinions expressed in this material are those of the authors and do not necessarily reflect the views of the sponsors.  ... 
doi:10.1145/2830772.2830792 dblp:conf/micro/ZhuRHR15 fatcat:2sgy5uiisvfgvoymunks5gnlla

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.  ...  In this work, we identify the key microarchitectural needs of scale-out workloads, calling for a change in the trajectory of server processors that would lead to improved computational density and power  ...  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

Benchmarking cloud serving systems with YCSB

Brian F. Cooper, Adam Silberstein, Erwin Tam, Raghu Ramakrishnan, Russell Sears
2010 Proceedings of the 1st ACM symposium on Cloud computing - SoCC '10  
While the use of MapReduce systems (such as Hadoop) for large scale data analysis has been widely recognized and studied, we have recently seen an explosion in the number of systems developed for cloud  ...  between systems and the workloads for which they are suited.  ...  ACKNOWLEDGEMENTS We would like to thank the system developers who helped us tune the various systems: Jonathan Ellis from Cassandra, Ryan Rawson and Michael Stack from HBase, and the Sherpa Engineering  ... 
doi:10.1145/1807128.1807152 dblp:conf/cloud/CooperSTRS10 fatcat:v5evtaffjfhy3kkycuobp66g3y

Characterizing Network Traffic in a Cluster-based, Multi-tier Data Center

Deniz Ersoz, Mazin S. Yousif, Chita R. Das
2007 27th International Conference on Distributed Computing Systems (ICDCS '07)  
In view of this, there has been a significant amount of work to characterize the workloads of Web-based services.  ...  However, all of the previous studies focus on a high level view of these servers, and analyze request-based or session-based characteristics of the workloads.  ...  Therefore, most of the data centers consist of several tiers of servers in order to simplify the design and monitoring of large-scale systems ( Figure 1 ).  ... 
doi:10.1109/icdcs.2007.90 dblp:conf/icdcs/ErsozYD07 fatcat:avra7b4iznawnilax42lpldluq

Perseus: Characterizing Performance and Cost of Multi-Tenant Serving for CNN Models [article]

Matthew LeMay and Shijian Li and Tian Guo
2020 arXiv   pre-print
In this paper, we present Perseus, a measurement framework that provides the basis for understanding the performance and cost trade-offs of multi-tenant model serving.  ...  However, GPUs can be orders of magnitude more expensive than traditional Central Processing Unit (CPU) servers.  ...  ACKNOWLEDGMENT The authors would like to thank National Science Foundation grants #1755659 and #1815619, and Google Cloud Platform Research credits.  ... 
arXiv:1912.02322v2 fatcat:f3tvqccovje4xnjz5bjzj7eiwy

Studying hardware and software trade-offs for a real-life web 2.0 workload

Stijn Polfliet, Frederick Ryckbosch, Lieven Eeckhout
2012 Proceedings of the third joint WOSP/SIPEW international conference on Performance Engineering - ICPE '12  
Designing data centers for Web 2.0 social networking applications is a major challenge because of the large number of users, the large scale of the data centers, the distributed application base, and the  ...  We consider the Netlog workload, a popular and commercially deployed social networking site with a large user base, and we explore hardware trade-offs in terms of core count, clock frequency, traditional  ...  Additional support is provided by the FWO projects G.0255.08, and G.0179.10, the UGent-BOF projects 01J14407 and 01Z04109, and the European Research Council under the European Community's Seventh Framework  ... 
doi:10.1145/2188286.2188316 dblp:conf/wosp/PolflietRE12 fatcat:guyhdxumsfb3ppotkykhtlcaly

Workload characterization of a location-based social network

Theo Lins, Adriano C. M. Pereira, Fabrício Benevenuto
2014 Social Network Analysis and Mining  
This article aims at characterizing and modeling the patterns of requests that reach a server of a location-based social network.  ...  Providers of this kind of services need to deal with different challenges that could benefit of such understanding, such as content storage, performance and scalability of servers, personalization and  ...  Acknowledgments This research has been supported by CAPES, CNPq, and Fapemig. The authors also would like to thank Apontador Inc. for the data provided.  ... 
doi:10.1007/s13278-014-0209-1 fatcat:xobzicbdvbampefpmtgnlhwanm

Workload generation for YouTube

Abdolreza Abhari, Mojgan Soraya
2009 Multimedia tools and applications  
This paper introduces a workload characterization study of the most popular short video sharing service of Web 2.0, YouTube.  ...  Workload simulators are required for evaluating the methods addressing the problems of high bandwidth usage and scalability of Web 2.0 sites such as YouTube.  ...  Acknowledgements We would like to thank the anonymous reviewers of this paper for their suggestions. References  ... 
doi:10.1007/s11042-009-0309-5 fatcat:5y7fncv32zcn5osuq6sfocsrjy

Track globally, deliver locally

Salvatore Scellato, Cecilia Mascolo, Mirco Musolesi, Jon Crowcroft
2011 Proceedings of the 20th international conference on World wide web - WWW '11  
Our performance evaluation shows that we are able to improve cache hits with respect to cache policies without geographic and social information.  ...  More and more, the diffusion of this content happens on online social networks such as Facebook and Twitter, where social cascades can be observed when users increasingly repost links they have received  ...  Acknowledgments The authors would like to thank Paolo Costa for many insightful discussions on this topic and the members of the Ne-tOS research group of the Computer Laboratory at the University of Cambridge  ... 
doi:10.1145/1963405.1963471 dblp:conf/www/ScellatoMMC11 fatcat:bmh6rcln4nfpzn74hj6y2leoqi

On Energy Security of Server Systems

Zhenyu Wu, Mengjun Xie, Haining Wang
2012 IEEE Transactions on Dependable and Secure Computing  
However, the security perspective of server power management has not yet been studied. In this paper, we investigate energy attacks, a new type of malicious exploits on server systems.  ...  Numerous techniques have been proposed and developed to optimize server power consumption and achieve energy proportional computing.  ...  ACKNOWLEDGMENTS The authors would like to thank the anonymous reviewers for their detailed and insightful comments, which have helped to greatly improve the quality of the paper.  ... 
doi:10.1109/tdsc.2012.70 fatcat:crus6l3rzrhkfelr7b5kzc3mce

Injecting realistic burstiness to a traditional client-server benchmark

Ningfang Mi, Giuliano Casale, Ludmila Cherkasova, Evgenia Smirni
2009 Proceedings of the 6th international conference on Autonomic computing - ICAC '09  
client-server system performance under reproducible bursty workloads.  ...  The design of autonomic systems often relies on representative benchmarks for evaluating system performance and scalability.  ...  Our thesis is that, because of its tremendous performance implications, burstiness must be accounted in capacity planning and must be incorporated into benchmarking of client-server systems.  ... 
doi:10.1145/1555228.1555267 dblp:conf/icac/MiCCS09 fatcat:d5ptmugvszdvlkhqfkgt6kf5za

Youtube traffic characterization

Phillipa Gill, Martin Arlitt, Zongpeng Li, Anirban Mahanti
2007 Proceedings of the 7th ACM SIGCOMM conference on Internet measurement - IMC '07  
In the paper we examine usage patterns, file properties, popularity and referencing characteristics, and transfer behaviors of YouTube, and compare them to traditional Web and media streaming workload  ...  We conclude the paper with a discussion of the implications of the observed characteristics.  ...  This work was supported by the Informatics Circle of Excellence (iCORE) in the Province of Alberta and the Natural Sciences and Engineering Research Council (NSERC) of Canada.  ... 
doi:10.1145/1298306.1298310 dblp:conf/imc/GillALM07 fatcat:rxduc6muozbhndx7st3on7wzwm

Sizing multi-tier systems with temporal dependence: benchmarks and analytic models

Ningfang Mi, Giuliano Casale, Ludmila Cherkasova, Evgenia Smirni
2010 Journal of Internet Services and Applications  
and non-bursty workloads.  ...  This approach enables a better understanding of system performance degradation due to burstiness and makes a strong case for the usefulness of the proposed benchmark enhancement for capacity planning of  ...  For effective capacity planning under bursty workload conditions, capturing this time-varying bottleneck switch in multi-tier systems and its performance implications becomes highly critical.  ... 
doi:10.1007/s13174-010-0012-9 fatcat:3do7ch5blbcapcrlfhtel2s3hu
« Previous Showing results 1 — 15 out of 1,046 results