Abstract | ||
---|---|---|
It is known that I/O system rather than CPU and memory is the performance killer of many of the newly emerged data intensive applications. Evaluating and understanding I/O system performance has become a timely issue facing the high performance computing community. Conventional I/O performance metrics, such as Input/Output Operations Per Second (IOPS), bandwidth, response time, etc., are effective for traditional I/O environments. However, as I/O systems become more and more complex, existing I/O metrics become less and less able to catch the characteristic of I/O systems performance. In this study, we reveal the limitations of existing metrics, and introduce a novel I/O metric, Blocks Per Second (BPS), to measure the performance of the I/O systems. A unique merit of BPS is that it provides an overall I/O system performance, not the file system performance or disk performance. This is very important; since with concurrency and optimization at the I/O stacks, file system performance and disk performance no long represent the data access performance. In fact, they are often misleading. A methodology is designed to measure BPS, and experiments are conducted with various I/O access patterns and storage configurations. Experimental results show that BPS is significantly more appropriate than existing metrics in I/O performance evaluation. |
Year | DOI | Venue |
---|---|---|
2013 | 10.1109/IPDPSW.2013.64 | IPDPS Workshops |
Keywords | Field | DocType |
i/o system,bps,o environment,i/o access patterns,o system,o access pattern,concurrency control,o stack,o systems performance,i/o metrics,parallel i/o system,software metrics,software performance evaluation,input-output programs,o performance evaluation,o system performance,concurrency,i/o performance evaluation,i/o storage configurations,o performance metrics,o metrics,performance metric,disk performance,blocks per second,i/o metric,optimization,system performance,correlation,bandwidth | File system,Supercomputer,Concurrency control,IOPS,Computer science,Performance metric,Parallel computing,Response time,Input/output,Software metric,Computer engineering | Conference |
ISBN | Citations | PageRank |
978-0-7695-4979-8 | 0 | 0.34 |
References | Authors | |
8 | 3 |
Name | Order | Citations | PageRank |
---|---|---|---|
Shuibing He | 1 | 109 | 20.45 |
Xian-he Sun | 2 | 1987 | 182.64 |
Yanlong Yin | 3 | 134 | 8.93 |