231 Hits in 2.2 sec


Brandon Schlinker, Radhika Niranjan Mysore, Sean Smith, Jeffrey C. Mogul, Amin Vahdat, Minlan Yu, Ethan Katz-Bassett, Michael Rubin
2015 Proceedings of the 2015 ACM Conference on Special Interest Group on Data Communication - SIGCOMM '15  
We present Condor, our approach to enabling a rapid, efficient design cycle.  ...  Condor then uses constraint-based synthesis to rapidly generate candidate topologies, which can be analyzed against multiple criteria.  ...  In Condor, architects express topology designs through a declarative language, which drives a constraintbased generation system.  ... 
doi:10.1145/2785956.2787476 dblp:conf/sigcomm/SchlinkerMSMVYK15 fatcat:nvvyjsvbkneljc7ue73dmqr5xq

A Fuzzy-Logic Based Coordinated Scheduling Technique for Inter-grid Architectures [chapter]

Abdulrahman Azab, Hein Meling, Reggie Davidrajuh
2014 Lecture Notes in Computer Science  
The proposed technique is tested through simulating its implementation on 512 interconnected Condor pools.  ...  Compared to existing techniques, our results show that the proposed technique is better at maintaining the overall throughput and load balancing with increasing number of interconnected grids.  ...  The proposed technique is tested through simulating its implementation on 512 interconnected Condor pools.  ... 
doi:10.1007/978-3-662-43352-2_14 fatcat:j2ps7rrx7nakldi3xhjdcxzd6e

Lark: Bringing Network Awareness to High Throughput Computing

Zhe Zhang, Brian Bockelman, Dale W. Carder, Todd Tannenbaum
2015 2015 15th IEEE/ACM International Symposium on Cluster, Cloud and Grid Computing  
We also extended the job agent, condor starter, so that it can manage and configure the job's network environment.  ...  It provides the users with better predictability of their job execution and the administrators more flexibility in network resource consumption policies.  ...  If the declarative ClassAd-based matching is insufficient for the final network configuration, the condor starter can invoke an arbitrary script.  ... 
doi:10.1109/ccgrid.2015.116 dblp:conf/ccgrid/ZhangBCT15 fatcat:dg32sfvulvg5thmjfiklaabjlq


William C. Benton, Robert H. Rati, Erik J. Erlandson
2011 State of the Practice Reports on - SC '11  
Wallaby offers several notable advantages over similar systems: it lets administrators write declarative specifications of user-visible functionality on groups of nodes instead of low-level configuration  ...  In this paper, we present Wallaby, an open-source, scalable configuration service for compute resources managed by the Condor high-throughput computing system.  ...  Unlike Wallaby, it can manage several different system components (not merely Condor), but its model is, perhaps necessarily, more complex and less declarative.  ... 
doi:10.1145/2063348.2063362 dblp:conf/sc/BentonRE11 fatcat:r3f6w6ntvjgejmzjm4skbkxibu

Efficiency on the Use of Radiation and Corn Yield under Three Densities of Sowing

A. Morales-Ruiz, J. M. Loeza-Corte, E. Díaz-López, E. J. Morales-Rosales, O. Franco-Mora, M. D. Mariezcurrena-Berasaín, G. Estrada-Campuzano
2016 International Journal of Agronomy  
," and "H-50"), were sown at densities of 6.9, 7.8, and 8.9 plants m−2, under a split plot design, within a factorial arrangement of treatments during three years (2008, 2009, and 2010).  ...  Aiming to evaluate sowing densities and efficiency of radiation use, six corn genotypes, three from open pollination ("Amarillo Almoloya," "Cacahuacintle," and "Jiquipilco") and three hybrids ("Z-60," "Condor  ...  Data analysis was under a factorial design on split plots.  ... 
doi:10.1155/2016/6959708 fatcat:endvy7b3h5dhdcexu2iz6qpcwi

A better way to negotiate for testbed resources

Qin Yin, Timothy Roscoe
2011 Proceedings of the Second Asia-Pacific Workshop on Systems - APSys '11  
Testbed designers have moved to a query-based model: clients provide a declarative description of their desired resources, and the provider allocate specific resources to meet the request.  ...  Our simple first experiments suggest that the late-binding of resources enabled by representing resource reservation as constraints achieves better network resource utilization compared to the fixed assignment  ...  Faced with these trends designers of testbed platforms have moved to a query-based model for resource request: clients supply a declarative description of resources they want, and the provider allocates  ... 
doi:10.1145/2103799.2103822 dblp:conf/apsys/YinR11 fatcat:uqlt2v3u7bbcbp4e3ugiuch3bm

An Information Brokering Service Provider (IBSP) for Virtual Clusters [chapter]

Roberto Podesta', Victor Iniesta, Ala Rezmerita, Franck Cappello
2009 Lecture Notes in Computer Science  
Its pluggable and flexible design is based on a decentralized architecture where each of the cooperating nodes is composed by a resource interface exposing the brokering service, and a portion of a distributed  ...  Declarative programming allows specifying the plug-ins to be loaded to support specific platforms. Plug-ins are deployed even at run-time through a descriptor Java properties file.  ...  The Activity Context allows a smart event routing through declarative programming and a JNDI registry thus enabling the connection between asynchronous network events sources and Java components.  ... 
doi:10.1007/978-3-642-05148-7_13 fatcat:nuinrqnwgjawxhh3gxin4ngjwu

Managing clusters of geographically distributed high-performance computers

Matthias Brune, Jörn Gehring, Axel Keller, Alexander Reinefeld
1999 Concurrency Practice and Experience  
In the DECLARATION section, the nodes are declared with their corresponding attributes. The notion of a 'node' in a graph is recursive.  ...  Communication interfaces (sockets) are declared by the keyword PORT.  ... 
doi:10.1002/(sici)1096-9128(19991225)11:15<887::aid-cpe459>;2-j fatcat:alw4hnhpbbhotnhjzmbniztkoq

Autonomic QoS in ASSIST grid-aware components

M. Aldinucci, M. Danelutto, M. Vanneschi
2006 14th Euromicro International Conference on Parallel, Distributed, and Network-Based Processing (PDP'06)  
The topology declaration specializes the behavior of the Virtual Processes as farm (topology none), or SMPD (topology array).  ...  In particular, the pattern, frequency, and cost of communications among VPs can be derived from parmod declaration. They depend from parmod topology, data types and distribution.  ... 
doi:10.1109/pdp.2006.25 dblp:conf/pdp/AldinucciDV06 fatcat:ehqfjif6vfcmxbowbssf3ydauq

Specifying resources and services in metacomputing environments

Matthias Brune, Jörn Gehring, Axel Keller, Burkhard Monien, Friedhelm Ramme, Alexander Reinefeld
1998 Parallel Computing  
Its textual counterpart gives service providers the necessary¯exibility to specify topology and properties of the available system and software resources.  ...  The DECLARATION section declares all nodes with corresponding attributes. The notion of a`node' in a dependency graph is recursive.  ...  Communication interfaces (i.e. sockets) are declared by the keyword PORT.  ... 
doi:10.1016/s0167-8191(98)00076-3 fatcat:ljvmcmgxcbfk3nukr3asazuy44

A taxonomy and survey on autonomic management of applications in grid computing environments

Mustafizur Rahman, Rajiv Ranjan, Rajkumar Buyya, Boualem Benatallah
2011 Concurrency and Computation  
The vision of AC is to apply the principles of self-regulation and complexity hiding for designing complex computerbased systems.  ...  The above requirements indicate that Grid programming and runtime systems must be able to support the following behaviors: (1) ability to handle the spike in demand across the organization through dynamic  ...  Although these TMs work in a distributed fashion, they communicate with each other through the tuple space that is designed based on a client-server-based centralized technology.  ... 
doi:10.1002/cpe.1734 fatcat:rgaqyybmmvdufphqfcr47ymhoe

Labs of the World, Unite!!!

Walfredo Cirne, Francisco Brasileiro, Nazareno Andrade, Lauro B. Costa, Alisson Andrade, Reynaldo Novaes, Miranda Mowbray
2006 Journal of Grid Computing  
This paper describes OurGrid, a system designed to fill this gap.  ...  If a Condor application accesses the same small file many times, OurGrid is likely to do better.  ...  If an OurGrid application transfers a large file but only uses part of it, performance would be better with Condor.  ... 
doi:10.1007/s10723-006-9040-x fatcat:5obhbrrzr5h5xam3m2ircsj3ky

Evaluating Scalability and Efficiency of the Resource and Job Management System on Large HPC Clusters [chapter]

Yiannis Georgiou, Matthieu Hautreux
2013 Lecture Notes in Computer Science  
BULL and CEA-DAM have been collaborating for the design, construction or installation of 2 petascale cluster systems deployed in Europe.  ...  The goal of this paper is to evaluate SLURM's scalability and jobs placement efficiency in terms of network topology upon large HPC clusters.  ...  The fine topology configuration provides even better results for the lineboard level with more than 90% of right placement.  ... 
doi:10.1007/978-3-642-35867-8_8 fatcat:uxn44icqy5h6dn57wirycsumtq

Pilot-Data: An Abstraction for Distributed Data [article]

Andre Luckow, Mark Santcroos, Ashley Zebrowski, Shantenu Jha
2013 arXiv   pre-print
In this paper, we discuss the design and implementation of the Pilot-Data prototype, demonstrate its use by data-intensive applications on multiple production distributed cyberinfrastructure and illustrate  ...  Any discussion of relevant related work has to be focussed by design and limited by necessity.  ...  We use a simple model for describing resource affinities: Data centers and machines are organized in a logical topology tree (similar to the tree spawned by an DNS topology).  ... 
arXiv:1301.6228v3 fatcat:6snjgnxbgjf6hikhtck6jloyxm

PlanetLab application management using plush

Jeannie Albrecht, Christopher Tuttle, Alex C. Snoeren, Amin Vahdat
2006 ACM SIGOPS Operating Systems Review  
Most tools were developed specifically to deploy and manage a particular service or application on a single platform and were not designed to be general enough to support different environments.  ...  We then discuss initial experiences and lessons learned during the development and PlanetLab deployment of Plush, a tool designed to manage applications running over large-scale distributed systems.  ...  The initial design of Plush uses a star topology (as opposed to, say, a mesh) for communication, so every host running the application connects directly to the controller 2 .  ... 
doi:10.1145/1113361.1113370 fatcat:o7ms23lxpzcflgnu3ltuifejti
« Previous Showing results 1 — 15 out of 231 results