Abstract | ||
---|---|---|
In the Big Data era, the gap between the storage performance and an application's I/O requirement is increasing. I/O congestion caused by concurrent storage accesses from multiple applications is inevitable and severely harms the performance. Conventional approaches either focus on optimizing an application's access pattern individually or handle I/O requests on a low-level storage layer without any knowledge from the upper-level applications. In this paper, we present a novel I/O-aware bandwidth allocation framework to coordinate ongoing I/O requests on petascale computing systems. The motivation behind this innovation is that the resource management system has a holistic view of both the system state and jobs' activities and can dynamically control the jobs' status or allocate resource on the fly during their execution. We treat a job's I/O requests as periodical sub-jobs within its lifecycle and transform the I/O congestion issue into a classical scheduling problem. Based on this model, we propose a bandwidth management mechanism as an extension to the existing scheduling system. We design several bandwidth allocation policies with different optimization objectives either on user-oriented metrics or system performance. We conduct extensive trace-based simulations using real job traces and I/O traces from a production IBM Blue Gene/Q system at Argonne National Laboratory. Experimental results demonstrate that our new design can improve job performance by more than 30%, as well as increasing system performance. |
Year | DOI | Venue |
---|---|---|
2016 | 10.1016/j.parco.2016.05.005 | Parallel Computing |
Keywords | Field | DocType |
Job scheduling,Resource management,I/O congestion,Resource allocation | Job shop scheduling,Computer science,Bandwidth allocation,Parallel computing,Input/output,Resource Management System,Resource allocation,Job scheduler,Petascale computing,Bandwidth management | Journal |
Volume | Issue | ISSN |
58 | C | 0167-8191 |
Citations | PageRank | References |
2 | 0.36 | 22 |
Authors | ||
7 |
Name | Order | Citations | PageRank |
---|---|---|---|
Zhou Zhou | 1 | 85 | 6.02 |
Xu Yang | 2 | 87 | 6.95 |
Dongfang Zhao | 3 | 362 | 26.49 |
Paul Rich | 4 | 50 | 8.21 |
Wei Tang | 5 | 152 | 10.65 |
Jia Wang | 6 | 148 | 12.47 |
Zhiling Lan | 7 | 818 | 54.25 |