Loading...
Please wait, while we are loading the content...
Similar Documents
Improving File System Performance via Predictive Caching Improving File System Performance via Predictive Caching
| Content Provider | Semantic Scholar |
|---|---|
| Author | Appletongri, Randy |
| Copyright Year | 1995 |
| Abstract | Despite impressive advances in le system throughput resulting from technologies such as high-bandwidth networks and disk arrays, le system latency has improved little and in several cases has become worse. Consequently, le system I/O remains one of the major bottlenecks to operating system performance Ous90]. This paper investigates an automated predictive approach that improves le cache performance, utilizes increased device bandwidth, and reduces le system latency. Automatic Prefetching uses past le accesses to predict future le system requests. The objective is to eeectively masking access latencies. In short, we want to transform the le cache from a repository of recently accessed data into a staging area for data about to be accessed. We have designed and implemented a system to measure the performance beneets of automatic prefetching. Our current results show that prefetching results in over 60% improvement in le system performance compared to LRU, especially for smaller caches. Alternatively, prefetching can reduce cache size by up to 50%. |
| File Format | PDF HTM / HTML |
| Alternate Webpage(s) | http://euclid.acs.nmu.edu/~randy/Research/iopads.ps |
| Language | English |
| Access Restriction | Open |
| Content Type | Text |
| Resource Type | Article |
