BCFG: A Con.guration Management Tool for Heterogeneous Environments
نویسندگان
چکیده
Since clusters were first introduced[5], node counts have increased rapidly. Currently, a variety of clusters with more than one thousand nodes are listed on the TOP500 list. In the next three years, clusters with more than four thousand nodes are expected. Cluster management functionality has lagged behind all areas of system software. In order to effectively manage the clusters of today and tomorrow, the basic cluster management software model must change. Current techniques focus on the management of single nodes, as opposed to complete cluster configurations. This approach typically leads to automatic management of compute nodes, while using ad-hoc techniques to manage service nodes. Configuration management is the process where software configurations on clients are installed, updated and verified. Scalability in this context applies not only to node count, but also to numbers of administrators and discrete configurations. Another important area is that of cluster-aware configuration description languages. We believe these concerns will impact large cluster operations greatly if not addressed. To address these issues, we have begun development of BCFG, a symbolic configuration management tools for heterogeneous clusters. It uses a multi-tiered configuration description, allowing high levels of reuse among differing configurations. BCFG is intended as a vehicle for research into system management problems, and experimentation with new techniques. This effort was also motivated by our experiences on Chiba City[2], our testbed cluster. Testbed users can specify the software configuration for nodes; this allows the automatic replacement of any portion of the default cluster OS. Chiba City’s configuration management requirements are complex, due to this testbed usage model. However, we feel that these problems translate to large scale computational clusters as well; as the size of these clusters grows, the numbers of discreet configurations employed will grow as well.
منابع مشابه
BCFG: A Configuration Management Tool for Heterogeneous Environments
Since clusters were first introduced[5], node counts have increased rapidly. Currently, a variety of clusters with more than one thousand nodes are listed on the TOP500 list. In the next three years, clusters with more than four thousand nodes are expected. Cluster management functionality has lagged behind all areas of system software. In order to effectively manage the clusters of today and t...
متن کاملAdaptive Dynamic Data Placement Algorithm for Hadoop in Heterogeneous Environments
Hadoop MapReduce framework is an important distributed processing model for large-scale data intensive applications. The current Hadoop and the existing Hadoop distributed file system’s rack-aware data placement strategy in MapReduce in the homogeneous Hadoop cluster assume that each node in a cluster has the same computing capacity and a same workload is assigned to each node. Default Hadoop d...
متن کاملIncremental Data Migration in Multi-database Systems Using ETL Algorithm
Nowadays Information is becoming an increasingly valuable corporate asset, the demand for a right tool to store, manage, and move this information in a cost efficient and reliable manner do arises. As part of an Information Lifecycle Management (ILM) best-practices strategy, the organizations require innovative solutions for migrating data among heterogeneous database systems and environments. ...
متن کاملMonitoring and managing heterogeneous middleware
The development and deployment of distributed applications still represents a major problem of computer science due to the complex and heterogeneous architectures of modern computing systems. The goal of this thesis is to improve the development and deployment of distributed applications by enhancing the on-line tool support for heterogeneous middleware environments. Our approach to reach this ...
متن کاملPerformance Management Tool for Interoperable Environments
Next generation computing architectures will consist of a combination of heterogeneous hardware and software platforms, automatically and transparently interoperating. this interconnectivity can be achieved through middleware. Middleware systems, the adhesive binding components in distributed environments, are rapidly evolving into more flexible, robust and usable systems. Nevertheless, tools t...
متن کامل