1,154,447 Hits in 8.5 sec

Towards highly available and scalable high performance clusters

Azzedine Boukerche, Raed A. Al-Shaikh, Mirela Sechi Moretti Annoni Notare
2007 Journal of computer and system sciences (Print)  
However, one of the challenges in a clustered environment is to keep system failure to the minimum and to achieve the highest possible level of system availability.  ...  In particular, we explore the hardware and the management layers of the HA-HPC cluster design, as well as a more focused study on the parallel-applications layer (i.e. FT-MPI implementations).  ...  Finally, we put together a small-scale fault tolerant HPC cluster using HA-OSCAR and different MPI implementations, to study the behavior of such a system.  ... 
doi:10.1016/j.jcss.2007.02.011 fatcat:hn4fmdzymncpjobzfekbos3pbi

Replication-Based Highly Available Metadata Management for Cluster File Systems

Zhuan Chen, Jin Xiong, Dan Meng
2010 2010 IEEE International Conference on Cluster Computing  
To guarantee both availability and efficiency, we propose a mechanism for building highly available metadata servers based on replication, which integrates Paxos algorithm effectively into metadata service  ...  In cluster file systems, the metadata management is critical to the whole system. Past researches mainly focus on journaling which alone is not enough to provide high-available metadata service.  ...  Within the file system, a set of highly available metadata servers is a critical component for building robust cluster file system.  ... 
doi:10.1109/cluster.2010.34 dblp:conf/cluster/ChenXM10 fatcat:2q64rf5uwrcshkhznj3jmit5li

Highly available transactions

Peter Bailis, Aaron Davidson, Alan Fekete, Ali Ghodsi, Joseph M. Hellerstein, Ion Stoica
2013 Proceedings of the VLDB Endowment  
We introduce a taxonomy of highly available systems and analyze existing ACID isolation and distributed data consistency guarantees to identify which can and cannot be achieved in HAT systems.  ...  This unifies the literature on weak transactional isolation, replica consistency, and highly available systems.  ...  Read your writes is not achievable in a highly available system.  ... 
doi:10.14778/2732232.2732237 fatcat:qxl5a3pbije3vojlqapz45iere

An evaluation framework for highly available and scalable SIP server clusters

Jong Yul Kim, Gregory W. Bond, Eric Cheung, Thomas M. Smith, Henning Schulzrinne
2011 Proceedings of the 5th International Conference on Principles, Systems and Applications of IP Telecommunications - IPTcomm '11  
SIP server clusters provide scalability and high availability for SIP applications.  ...  There are a number of clustering solutions available to address these requirements, but due to significant differences in architecture and the lack of common terminology, the solutions are difficult to  ...  SIP server vendors offer highly available SIP server cluster solutions.  ... 
doi:10.1145/2124436.2124438 fatcat:md2i7vtfczdazfgnwwycnknp74

Evaluation of highly available and fault-tolerant middleware clustered architectures using RabbitMQ

Maciej Rostański, Krzysztof Grochla, Aleksander Seman
2014 Proceedings of the 2014 Federated Conference on Computer Science and Information Systems  
The paper presents a performance evaluation of message broker system, Rabbit MQ in high availability -enabling and redundant configurations.  ...  The scalability and high availability design issues are discussed.  ...  For this study, HAproxy was chosen as a load balancer between clients and cluster nodes. III.  ... 
doi:10.15439/2014f48 dblp:conf/fedcsis/RostanskiGS14 fatcat:ls2kelijdjh6tjem4ihld73vty

Towards building a highly-available cluster based model for high performance computing

A. Boukerche, R. Al-Shaikh, M.S.M. Notare
2006 Proceedings 20th IEEE International Parallel & Distributed Processing Symposium  
One of the challenges in a clustered environment is to keep system failure to the minimum level and while achieving the highest possible level of system availability.  ...  In recent years, we have witnessed a growing interest in high performance computing (HPC) using a cluster of workstations.  ...  Finally, we have presented a smallscale fault tolerant HPC cluster using HA-OSCAR and different MPI implementations, to study the behavior of such a system.  ... 
doi:10.1109/ipdps.2006.1639633 dblp:conf/ipps/BoukerchetAN06 fatcat:mveoejclzrc7vixxgko4ew3rye

Manageability, availability, and performance in porcupine: a highly scalable, cluster-based mail service

Yasushi Saito, Brian N. Bershad, Henry M. Levy
2000 ACM Transactions on Computer Systems  
The goal of Porcupine is to provide a highly available and scalable electronic mail service using a large cluster of commodity PCs.  ...  Key to the system's manageability, availability, and performance is that sessions, data, and underlying services are distributed homogeneously and dynamically across nodes in a cluster.  ...  Introduction The growth of the Internet has led to the need for highly scalable and highly available services. This paper describes the Porcupine scalable electronic mail service.  ... 
doi:10.1145/354871.354875 fatcat:ckbbccvahbgu7clc2cf2xzkyyi

A Distributed and Cooperative NameNode Cluster for a Highly-Available Hadoop Distributed File System

Yonghwan KIM, Tadashi ARARAGI, Junya NAKAMURA, Toshimitsu MASUZAWA
2015 IEICE transactions on information and systems  
It may also lose the advantage of using commodity hardware since the two NameNodes have to share a highly reliable sophisticated storage.  ...  However, HDFS requires a single master node, called a NameNode, to manage the entire namespace (or all the i-nodes) of a file system.  ...  ZooKeeper ZooKeeper [8] is a small cluster that provides highly reliable distributed coordination. All servers in Zookeeper are synchronized, and one of them behaves as a leader (Fig. 2 ).  ... 
doi:10.1587/transinf.2014edp7258 fatcat:4ur7tbfypbgatmmsyotxqoh42a

Modelling-based experiment retrieval: a case study with gene expression clustering

Paul Blomstedt, Ritabrata Dutta, Sohan Seth, Alvis Brazma, Samuel Kaski
2016 Bioinformatics  
Availability: The method can be implemented using standard clustering algorithms and normalized information distance, available in many statistical software packages.  ...  The method is highly scalable and straightforward to apply to construct a general-purpose gene expression experiment retrieval method.  ...  The computational simplicity makes the method highly scalable and easy to apply in a black-box manner, as a general-purpose retrieval scheme.  ... 
doi:10.1093/bioinformatics/btv762 pmid:26740526 fatcat:zscvacmfsnebbhiiix7oxshaau

Highly Available Queue-oriented Speculative Transaction Processing [article]

Thamir M. Qadah, Mohammad Sadoghi
2021 arXiv   pre-print
This paper proposes a generic framework to model the replication process in deterministic transaction processing systems and use it to study three cases.  ...  However, the problem of ensuring high availability in deterministic distributed transaction processing systems has received less attention from the research community, and this aspect has not been analyzed  ...  The Zookeeper cluster is a highly available system, and it does not constitute a single point of failure because it uses its internal replication and consensus protocols to ensure correct fail-over.  ... 
arXiv:2107.11378v1 fatcat:dt7zrynjpndhdbiiqqhnaag6p4

Propagation and Decay of Injected One-Off Delays on Clusters: A Case Study [article]

Ayesha Afzal, Georg Hager, Gerhard Wellein
2019 arXiv   pre-print
Despite numerous efforts to quantify, categorize, and reduce such effects, a comprehensive quantitative understanding of their performance impact is not available, especially for long delays that have  ...  We analyze the dependence of the propagation speed of idle waves emanating from injected delays with respect to the execution and communication properties of the application, study how such delays decay  ...  along an ordered set of processes is a good starting point for studying propagation phenomena.  ... 
arXiv:1905.10603v3 fatcat:p4jbdraivnakhio6qrn4fzldoi

Highly available systems for database applications

Won Kim
1984 ACM Computing Surveys  
This paper presents a survey and analysis of representat~%e architectures and techniques that have been developed for constructing highly available systems for database applications.  ...  It then proposes a design of a distributed software subsystem that can serve as a unified framework for constructing database application systems that meet various requirements for high availability.  ...  Finally, a technical editor did a superb job of shaping the paper into publishable form.  ... 
doi:10.1145/861.866 fatcat:x3v4qxcsmrc3rog2f4uv7ybut4

Comdb2 bloomberg's highly available relational database system

Alex Scotti, Fabio Angius, Lingzhi Deng, Mark Hannum, Michael Ponomarenko, Dorin Hogea, Akshat Sikarwar, Mohit Khullar, Adi Zaimi, James Leddy, Rivers Zhang
2016 Proceedings of the VLDB Endowment  
Comdb2 is a distributed database system designed for geographical replication and high availability.  ...  Moreover, the system allows for rich stored procedures using a dialect of Lua. Comdb2 implements a serializable system in which reads from any node always return current values.  ...  High Availability SQL Comdb2 provides a highly available experience to application programs similar to [9] 2 .  ... 
doi:10.14778/3007263.3007275 fatcat:umo7iflt45fo5ki4wpescgcl4e

Toward highly-available WSNs for assisted living

Safwan Al-Omari, Weisong Shi
2007 Proceedings of the 1st ACM SIGMOBILE international workshop on Systems and networking support for healthcare and assisted living environments - HealthNet '07  
Motivated by the fact that sensor nodes are resource-constrained and error-prone on one hand, and mission urgency on the other hand, we argue that high availability is a vital requirement that viable WSNs  ...  We develop analytical models of the WSN availability in terms of the availability of the underlying sensor nodes.  ...  The no scheduling scheme We simply model the availability of the cluster as a classical κ-out-of-m system.  ... 
doi:10.1145/1248054.1248063 dblp:conf/mobisys/Al-OmariS07 fatcat:r2eiihwar5e4jegkgslz2kui3e

Critical Success Factors and Cluster Evolution: A Case Study of the Linköping ICT Cluster Lifecycle

Sam Tavassoli, Dimitrios Tsagdis
2014 Environment and planning A  
The main findings comprise a stage-specific group of CSFs whose importance varies across the cluster's lifecycle stages with different patterns.  ...  The lifecycle of the Linköping ICT cluster is delineated and its stages segmented.  ...  critical case study).  ... 
doi:10.1068/a46258 fatcat:4stfdh4xl5bepikn7d2grnnueq
« Previous Showing results 1 — 15 out of 1,154,447 results