{"title":"多媒体存储系统的缓冲区替换算法","authors":"Banu Özden, R. Rastogi, A. Silberschatz","doi":"10.1109/MMCS.1996.534971","DOIUrl":null,"url":null,"abstract":"In a disk-based storage system, a buffer cache is used to reduce the number of disk I/Os. The buffer manager is responsible for buffer replacement to free memory in order to accommodate new data blocks from the disk. An optimal buffer replacement algorithm is one which yields the lowest number of cache misses and, as a result, the lowest number of disk I/Os. In general, optimal buffer replacement algorithms require future knowledge, and therefore cannot be realized. Thus, most storage systems use approximation algorithms such as the least-recently-used (LRU) and most-recently-used (MRU) buffer replacement algorithms. In this paper, we show that both of these algorithms yield poor performance when they are used in storage systems that provide support for continuous media data. We present two new buffer replacement algorithms-BASIC and DISTANCE-which reduce the cache misses by up to 30% as compared to LRU and MRU. Furthermore, in the simulation experiments we conducted, our new algorithms resulted in at most a 9.7% increase in cache misses as compared to the optimal algorithm when the videos are sufficiently long (i.e. longer than 30 minutes). Moreover, we show that the DISTANCE scheme incurs an overhead which is comparable to those of the LRU and MRU schemes. Our conclusion is that DISTANCE is a very suitable candidate for a buffer replacement scheme in storage systems that deal with continuous media data.","PeriodicalId":371043,"journal":{"name":"Proceedings of the Third IEEE International Conference on Multimedia Computing and Systems","volume":"18 3 1","pages":"0"},"PeriodicalIF":0.0000,"publicationDate":"1996-06-17","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":"92","resultStr":"{\"title\":\"Buffer replacement algorithms for multimedia storage systems\",\"authors\":\"Banu Özden, R. Rastogi, A. Silberschatz\",\"doi\":\"10.1109/MMCS.1996.534971\",\"DOIUrl\":null,\"url\":null,\"abstract\":\"In a disk-based storage system, a buffer cache is used to reduce the number of disk I/Os. The buffer manager is responsible for buffer replacement to free memory in order to accommodate new data blocks from the disk. An optimal buffer replacement algorithm is one which yields the lowest number of cache misses and, as a result, the lowest number of disk I/Os. In general, optimal buffer replacement algorithms require future knowledge, and therefore cannot be realized. Thus, most storage systems use approximation algorithms such as the least-recently-used (LRU) and most-recently-used (MRU) buffer replacement algorithms. In this paper, we show that both of these algorithms yield poor performance when they are used in storage systems that provide support for continuous media data. We present two new buffer replacement algorithms-BASIC and DISTANCE-which reduce the cache misses by up to 30% as compared to LRU and MRU. Furthermore, in the simulation experiments we conducted, our new algorithms resulted in at most a 9.7% increase in cache misses as compared to the optimal algorithm when the videos are sufficiently long (i.e. longer than 30 minutes). Moreover, we show that the DISTANCE scheme incurs an overhead which is comparable to those of the LRU and MRU schemes. Our conclusion is that DISTANCE is a very suitable candidate for a buffer replacement scheme in storage systems that deal with continuous media data.\",\"PeriodicalId\":371043,\"journal\":{\"name\":\"Proceedings of the Third IEEE International Conference on Multimedia Computing and Systems\",\"volume\":\"18 3 1\",\"pages\":\"0\"},\"PeriodicalIF\":0.0000,\"publicationDate\":\"1996-06-17\",\"publicationTypes\":\"Journal Article\",\"fieldsOfStudy\":null,\"isOpenAccess\":false,\"openAccessPdf\":\"\",\"citationCount\":\"92\",\"resultStr\":null,\"platform\":\"Semanticscholar\",\"paperid\":null,\"PeriodicalName\":\"Proceedings of the Third IEEE International Conference on Multimedia Computing and Systems\",\"FirstCategoryId\":\"1085\",\"ListUrlMain\":\"https://doi.org/10.1109/MMCS.1996.534971\",\"RegionNum\":0,\"RegionCategory\":null,\"ArticlePicture\":[],\"TitleCN\":null,\"AbstractTextCN\":null,\"PMCID\":null,\"EPubDate\":\"\",\"PubModel\":\"\",\"JCR\":\"\",\"JCRName\":\"\",\"Score\":null,\"Total\":0}","platform":"Semanticscholar","paperid":null,"PeriodicalName":"Proceedings of the Third IEEE International Conference on Multimedia Computing and Systems","FirstCategoryId":"1085","ListUrlMain":"https://doi.org/10.1109/MMCS.1996.534971","RegionNum":0,"RegionCategory":null,"ArticlePicture":[],"TitleCN":null,"AbstractTextCN":null,"PMCID":null,"EPubDate":"","PubModel":"","JCR":"","JCRName":"","Score":null,"Total":0}
Buffer replacement algorithms for multimedia storage systems
In a disk-based storage system, a buffer cache is used to reduce the number of disk I/Os. The buffer manager is responsible for buffer replacement to free memory in order to accommodate new data blocks from the disk. An optimal buffer replacement algorithm is one which yields the lowest number of cache misses and, as a result, the lowest number of disk I/Os. In general, optimal buffer replacement algorithms require future knowledge, and therefore cannot be realized. Thus, most storage systems use approximation algorithms such as the least-recently-used (LRU) and most-recently-used (MRU) buffer replacement algorithms. In this paper, we show that both of these algorithms yield poor performance when they are used in storage systems that provide support for continuous media data. We present two new buffer replacement algorithms-BASIC and DISTANCE-which reduce the cache misses by up to 30% as compared to LRU and MRU. Furthermore, in the simulation experiments we conducted, our new algorithms resulted in at most a 9.7% increase in cache misses as compared to the optimal algorithm when the videos are sufficiently long (i.e. longer than 30 minutes). Moreover, we show that the DISTANCE scheme incurs an overhead which is comparable to those of the LRU and MRU schemes. Our conclusion is that DISTANCE is a very suitable candidate for a buffer replacement scheme in storage systems that deal with continuous media data.