I/O-Performance Prediction Method for Mission-critical Grid-batch Processing
Autor: | Ken Naono, Tomohiro Hanai, Toshihiko Kashiyama, Yoshio Suzuki |
---|---|
Rok vydání: | 2011 |
Předmět: |
Input/output
Concurrent I/O streams Computer science Grid-batch Mission critical Real-time computing I/O performance prediction Distributed file system Function (mathematics) Grid Metadata management Batch processing Performance prediction General Earth and Planetary Sciences Distributed File System Throughput (business) Algorithm General Environmental Science |
Zdroj: | ICCS |
ISSN: | 1877-0509 |
Popis: | Aiming to solve the performance-degradation problem when multiple computing nodes are in use in mission-critical batch systems (so-called “grid-batch” systems), a new performance-prediction method that focuses on metadata management for file input/output (I/O) control and performance degradation in case of concurrent I/O streams is proposed. To enhance the accuracy of the prediction, this I/O-performance prediction method models metadata management time as a function of number of files and models performance degradation as a probabilistic function of sequential I/O throughput and random I/O throughput. According to an evaluation of the proposed method, the difference between actual and estimated execution time is 14.0%. In contrast, as for the storage/network-based conventional method, the difference is 36.5%. These results demonstrate that the target prediction error, namely, within 20%, was accomplished with the proposed method, which can therefore be considered effective in predicting the performance of grid-batch systems. |
Databáze: | OpenAIRE |
Externí odkaz: |