Loading...
Please wait, while we are loading the content...
Similar Documents
Improved Fault Tolerant Job Scheduler for Optimal Resource Utilization in Computational Grid
| Content Provider | Semantic Scholar |
|---|---|
| Copyright Year | 2012 |
| Abstract | Grid computing provides the ability to access, utilize and control a variety of underutilized heterogeneous resources distributed across multiple administrative domains while it is an error prone environment. The failure of resources affects job execution during runtime. We propose a new strategy named Improved Fault Tolerant Job Scheduler (IFTJS) for Optimal Resource Utilization in Computational Grid which effectively schedules grid jobs tolerating faults gracefully and executes more jobs successfully within the specified deadline. This system maintains the history of fault occurrence of resources with respect to Processor, Memory and Bandwidth. The usage of this information causes the reduction of selecting chances of the resources which have more failure probability and hence improves the resource utilization. Also, the system guarantees the efficient job execution using Reduced Recovery Time (RRT) strategy. Whenever the scheduler has jobs to schedule, the Improved Fault Tolerant (IFT) algorithm finds the optimal resources based on their failure rate. The resources with lowest failure rate will have highest priority for scheduling. The job manager can monitor the execution of job and return the results to the user after successful completion. If failure occurs it reexecutes the job with the same resource using the last saved state when the Failure Rate of the resource is lesser than the optimal value or with the backup resources when it exceeds an optimal value with the last saved state using RRT strategy. Otherwise it reschedules the failed job with the next available optimal resource using the last saved state. Hence the recovery time is getting reduced. Approach is effective in the sense that the resource manager detects the occurrence of resource failures and the job manager guarantees that the submitted jobs executed with optimal resources with the specified deadline. |
| File Format | PDF HTM / HTML |
| Alternate Webpage(s) | http://research.ijcaonline.org/volume48/number22/pxc3880552.pdf |
| Language | English |
| Access Restriction | Open |
| Subject Keyword | Algorithm Backup Cognitive dimensions of notations Computation (action) Execution Failure rate Fault tolerance Fault-tolerant computer system Genetic Heterogeneity Grid computing Heart failure Job Syndrome Job scheduler Job stream Mike Lesser Name Occupations Optimization problem Renal Replacement Therapy Resource identifier:URI:Pt:Clinical document:Nom Salt-Tolerant Plants Schedule (document type) Scheduling (computing) Scheduling - HL7 Publishing Domain Transcutaneous electrical nerve stimulation |
| Content Type | Text |
| Resource Type | Article |
