T. Cortes and J. Labarta. Extending Heterogeneity to RAID level 5. In Proceedings of the USENIX Annual Technical Conference, 2001.  Home/Search   Document Details and Download   Summary   Related Articles   Check

....efficiently. For example, virtually all data has to be replaced to fully integrate a new disk into an existing RAID array. The RAID levels also do not allow to support non uniform disks. Even though there are some efforts under way to expand the RAID levels to handle non uniform disks efficiently [16, 4, 3], a general solution has yet to be found. In addition to (re )distributing data among disks according to their capabilities, it is also important to be able to determine the disk storing a particular data item in a fast and compact way to ensure that a high load of data requests can be handled ....

T. Cortes and J. Labarta. Extending heterogeneity to RAID level 5. In USENIX 2001.

....heterogeneity in the disk subsystem; in particular, a new disk or ERAID segment may have different performance characteristics than the other disks of the system. In such a case, traditional striping and RAID schemes do not work well, as they all assume that disks run at identical rates [4, 10]. Traditionally, the presence of multiple disks is hidden by the storage layer from the file system. Thus, current systems must handle any disk performance heterogeneity in the storage layer the file system does not have enough information to do so itself. The research community has proposed ....

....is hidden by the storage layer from the file system. Thus, current systems must handle any disk performance heterogeneity in the storage layer the file system does not have enough information to do so itself. The research community has proposed schemes to deal with static disk heterogeneity [3, 10, 32, 52], though many of these solutions require careful tuning by an administrator. As Van Jacobsen notes, Experience shows that anything that needs to be configured will be misconfigured [18] Further complicating the issue is that the delivered performance of a device could change over time. Such ....

T. Cortes and J. Labarta. Extending Heterogeneity to RAID level 5. In Proceedings of the 2001.

....are as effective, yet simpler, than proposals in those research areas. Our study is set in the context of a network attached disk system. Network attached disks are an increasingly important storage paradigm, and present clients with both static and dynamic forms of performance heterogeneity [5, 6, 13]. However, the algorithms we develop are general and can be applied across a broader range of storage devices. Our main results are as follows. We show storageaware caching is significantly more performance robust than cost oblivious caching and as robust as a leading web caching algorithm. Since ....

T. Cortes and J. Labarta. Extending Heterogeneity to RAID level 5. In Proceedings of the 2001.

....are as effective, yet simpler, than proposals in those research areas. Our study is set in the context of a network attached disk system. Network attached disks are an increasingly important storage paradigm, and present clients with both static and dynamic forms of performance heterogeneity [5, 6, 13]. However, the algorithms we develop are general and can be applied across a broader range of storage devices. Our main results are as follows. We show storageaware caching is significantly more performance robust than cost oblivious caching and as robust as a leading web caching algorithm. Since ....

T. Cortes and J. Labarta. Extending Heterogeneity to RAID level 5. In Usenix

No context found.

T. Cortes and J. Labarta. Extending Heterogeneity to RAID level 5. In Proceedings of the USENIX Annual Technical Conference, 2001.

Online articles have much greater impact   More about CiteSeer.IST   Add search form to your site   Submit documents   Feedback  

CiteSeer.IST - Copyright Penn State and NEC