Abstract | ||
---|---|---|
Distributed metadata management, administrating the distribution of metadata nodes on different metadata servers (MDS's), can substantially improve overall performance of large-scale distributed storage systems if well designed. A major difficulty confronting many metadata management schemes is the trade-off between two conflicting aspects: system load balance and metadata locality preservation. It becomes even more challenging as file access pattern inevitably varies with time. However, existing works dynamically reallocate nodes to different servers adopting history-based coarse-grained methods, failing to make timely and efficient update on distribution of nodes. In this paper, we propose an adaptive fine-grained metadata management scheme, AdaM, leveraging Deep Reinforcement Learning, to address the trade-off dilemma against time-varying access pattern. At each time step, AdaM collects environmental "states" including access pattern, the structure of namespace tree and current distribution of nodes on MDS's. Then an actor-critic network is trained to reallocate hot metadata nodes to different servers according to the observed "states". Adaptive to varying access pattern, AdaM can automatically migrate hot metadata nodes among servers to keep load balancing while maintaining metadata locality. We test AdaM on real-world data traces. Experimental results demonstrate the superiority of our proposed method over other schemes.
|
Year | DOI | Keywords |
---|---|---|
2019 | 10.1145/3337821.3337822 | deep reinforcement learning, distributed file system, metadata management |
Field | DocType | ISSN |
Computer science,Metadata management,Distributed computing | Conference | 978-1-4503-6295-5 |
ISBN | Citations | PageRank |
978-1-4503-6295-5 | 1 | 0.34 |
References | Authors | |
0 | 4 |
Name | Order | Citations | PageRank |
---|---|---|---|
Shiyi Cao | 1 | 1 | 0.34 |
Yuanning Gao | 2 | 4 | 2.73 |
Xiaofeng Gao | 3 | 713 | 98.58 |
guihai chen | 4 | 3537 | 317.28 |