@article{LiangLiuLiuetal.2015,
  author    = {Liang, Feng and Liu, Yunzhen and Liu, Hai and Ma, Shilong and Schnor, Bettina},
  title     = {A Parallel Job Execution Time Estimation Approach Based on User Submission Patterns within Computational Grids},
  series = {International journal of parallel programming},
  volume    = {43},
  journal   = {International journal of parallel programming},
  number    = {3},
  publisher = {Springer},
  address   = {New York},
  issn      = {0885-7458},
  doi       = {10.1007/s10766-013-0294-1},
  pages     = {440 -- 454},
  year      = {2015},
  abstract  = {Scheduling performance in computational grid can potentially benefit a lot from accurate execution time estimation for parallel jobs. Most existing approaches for the parallel job execution time estimation, however, require ample past job traces and the explicit correlations between the job execution time and the outer layout parameters such as the consumed processor numbers, the user-estimated execution time and the job ID, which are hard to obtain or reveal. This paper presents and evaluates a novel execution time estimation approach for parallel jobs, the user-behavior clustering for execution time estimation, which can give more accurate execution time estimation for parallel jobs through exploring the job similarity and revealing the user submission patterns. Experiment results show that compared to the state-of-art algorithms, our approach can improve the accuracy of the job execution time estimation up to 5.6 \%, meanwhile the time that our approach spends on calculation can be reduced up to 3.8 \%.},
  language  = {en}
}
@article{JungKiertscherMenskietal.2015,
  author    = {Jung, J{\"o}rg and Kiertscher, Simon and Menski, Sebastian and Schnor, Bettina},
  title     = {Self-Adapting Load Balancing for DNS},
  series = {Journal of networks},
  volume    = {10},
  journal   = {Journal of networks},
  number    = {4},
  publisher = {Kluwer Academic Publishers},
  address   = {Oulu},
  doi       = {10.1109/SPECTS.2014.6879994},
  pages     = {222 -- 231},
  year      = {2015},
  abstract  = {The Domain Name System belongs to the core services of the Internet infrastructure. Hence, DNS availability and performance is essential for the operation of the Internet and replication as well as load balancing are used for the root and top level name servers. This paper proposes an architecture for credit based server load balancing (SLB) for DNS. Compared to traditional load balancing algorithms like round robin or least connection, the benefit of credit based SLB is that the load balancer can adapt more easily to heterogeneous load requests and back end server capacities. The challenge of this approach is the definition of a suited credit metric. While this was done before for TCP based services like HTTP, the problem was not solved for UDP based services like DNS. In the following an approach is presented to define credits also for UDP based services. This UDP/DNS approach is implemented within the credit based SLB implementation salbnet. The presented measurements confirm the benefit of the self-adapting credit based SLB approach. In our experiments, the mean (first) response time dropped significantly compared to weighted round robin (WRR) (from over 4 ms to about 0.6 ms for dynamic pressure relieve (DPR)).},
  language  = {en}
}
@article{LuckowSchnor2008,
  author    = {Luckow, Andr{\´e} and Schnor, Bettina},
  title     = {Migol : a fault-tolerant service framework for MPI applications in the grid},
  doi       = {10.1016/j.future.2007.03.007},
  year      = {2008},
  abstract  = {Especially for sciences the provision of massive parallel CPU capacity is one of the most attractive features of a grid. A major challenge in a distributed, inherently dynamic grid is fault tolerance. The more resources and components involved, the more complicated and error-prone becomes the system. In a grid with potentially thousands of machines connected to each other the reliability of individual resources cannot be guaranteed.The benefit of the grid is that in case of a failure ail application may be migrated and restarted from a checkpoint file on another site. This approach requires a service infrastructure which handles the necessary activities transparently. In this article, we present Migol, a fault-tolerant and self-healing grid middleware for MPI applications. Migol is based on open standards and extends the services of the Globus toolkit to support the fault tolerance of grid applications.Further, the Migol framework itself is designed with special focus on fault tolerance. For example, Migol eplicates ritical services and uses a ring-based replication protocol to achieve data consistency. (c) 2007 Elsevier B.V. All rights reserved.},
  language  = {en}
}
@article{LuckowJhaKimetal.2009,
  author    = {Luckow, Andre and Jha, Shantenu and Kim, Joohyun and Merzky, Andre and Schnor, Bettina},
  title     = {Adaptive distributed replica-exchange simulations},
  issn      = {1364-503X},
  doi       = {10.1098/rsta.2009.0051},
  year      = {2009},
  abstract  = {Owing to the loose coupling between replicas, the replica-exchange (RE) class of algorithms should be able to benefit greatly from using as many resources as available. However, the ability to effectively use multiple distributed resources to reduce the time to completion remains a challenge at many levels. Additionally, an implementation of a pleasingly distributed algorithm such as replica-exchange, which is independent of infrastructural details, does not exist. This paper proposes an extensible and scalable framework based on Simple API for Grid Applications that provides a general-purpose, opportunistic mechanism to effectively use multiple resources in an infrastructure-independent way. By analysing the requirements of the RE algorithm and the challenges of implementing it on real production systems, we propose a new abstraction (BIGJOB), which forms the basis of the adaptive redistribution and effective scheduling of replicas.},
  language  = {en}
}
@article{KiertscherZinkeSchnor2013,
  author    = {Kiertscher, Simon and Zinke, J{\"o}rg and Schnor, Bettina},
  title     = {CHERUB power consumption aware cluster resource management},
  series = {Cluster computing : the journal of networks, software tools and applications},
  volume    = {16},
  journal   = {Cluster computing : the journal of networks, software tools and applications},
  number    = {1},
  publisher = {Springer},
  address   = {New York},
  issn      = {1386-7857},
  doi       = {10.1007/s10586-011-0176-5},
  pages     = {55 -- 63},
  year      = {2013},
  abstract  = {This paper presents an evaluation of ACPI energy saving modes, and deduces the design and implementation of an energy saving daemon for clusters called cherub. The design of the cherub daemon is modular and extensible. Since the only requirement is a central approach for resource management, cherub is suited for Server Load Balancing (SLB) clusters managed by dispatchers like Linux Virtual Server (LVS), as well as for High Performance Computing (HPC) clusters. Our experimental results show that cherub's scheduling algorithm works well, i.e. it will save energy, if possible, and avoids state-flapping.},
  language  = {en}
}