公开(公告)号：US20090037662A1

公开(公告)日：2009-02-05

申请号：US11830124

申请日：2007-07-30

申请人： Lee Charles La Frese ,  Joshua Douglas Martin ,  Justin Thomas Miller ,  Vernon Walter Miller ,  James Russell Thompson ,  Yan Xu ,  Olga Yiparaki

发明人： Lee Charles La Frese ,  Joshua Douglas Martin ,  Justin Thomas Miller ,  Vernon Walter Miller ,  James Russell Thompson ,  Yan Xu ,  Olga Yiparaki

IPC分类号： G06F12/08

CPC分类号： G06F12/0888

摘要： A mechanism for selectively disabling and enabling read caching based on past performance of the cache and current read/write requests. The system improves overall performance by using an autonomic algorithm to disable read caching for regions of backend disk storage (i.e., the backstore) that have had historically low cache hit ratios. The result is that more cache becomes available for workloads with larger hit ratios, and less time and machine cycles are spent searching the cache for data that is unlikely to be there.

摘要翻译： 一种基于过去高速缓存和当前读/写请求的性能来选择性地禁用和启用读缓存的机制。 该系统通过使用自动算法来禁用具有历史上低的缓存命中率的后端磁盘存储（即，后台）的区域的读取缓存来提高整体性能。 结果是更多的缓存可用于具有较大命中率的工作负载，并且花费更少的时间和机器周期来搜索缓存中不太可能存在的数据。

公开(公告)号：US08874854B2

公开(公告)日：2014-10-28

申请号：US11830124

申请日：2007-07-30

申请人： Lee Charles La Frese ,  Joshua Douglas Martin ,  Justin Thomson Miller ,  Vernon Walter Miller ,  James Russell Thompson ,  Yan Xu ,  Olga Yiparaki

发明人： Lee Charles La Frese ,  Joshua Douglas Martin ,  Justin Thomson Miller ,  Vernon Walter Miller ,  James Russell Thompson ,  Yan Xu ,  Olga Yiparaki

IPC分类号： G06F12/00 ,  G06F12/08

CPC分类号： G06F12/0888

摘要： A mechanism for selectively disabling and enabling read caching based on past performance of the cache and current read/write requests. The system improves overall performance by using an autonomic algorithm to disable read caching for regions of backend disk storage (i.e., the backstore) that have had historically low cache hit ratios. The result is that more cache becomes available for workloads with larger hit ratios, and less time and machine cycles are spent searching the cache for data that is unlikely to be there.

摘要翻译： 一种基于过去高速缓存和当前读/写请求的性能来选择性地禁用和启用读缓存的机制。 该系统通过使用自动算法来禁用具有历史上低的缓存命中率的后端磁盘存储（即，后台）的区域的读取缓存来提高整体性能。 结果是更多的缓存可用于具有较大命中率的工作负载，并且花费更少的时间和机器周期来搜索缓存中不太可能存在的数据。

公开(公告)号：US08055868B2

公开(公告)日：2011-11-08

申请号：US12182059

申请日：2008-07-29

申请人： Lee Charles La Frese ,  Christopher Michael Sansone ,  Dana Fairbairn Scott ,  Olga Yiparaki ,  Yan Xu

发明人： Lee Charles La Frese ,  Christopher Michael Sansone ,  Dana Fairbairn Scott ,  Olga Yiparaki ,  Yan Xu

IPC分类号： G06F12/00

CPC分类号： G06F3/065 ,  G06F3/0608 ,  G06F3/061 ,  G06F3/0644 ,  G06F3/0686 ,  G06F3/0689

摘要： A method to store point-in-time data, comprising establishing a block size, providing source data storage comprising (S) blocks, and target data storage comprising (T) blocks. The method configures (B) source storage segments and (B) target storage segments, and receives updated point-in-time data for original point-in-time data written to an (i)th source storage segment. The method then determines if a (j)th target storage segment comprises available storage capacity to store the original point-in-time data. If a (j)th target storage segment comprises available storage capacity to store the original point-in-time data, the method writes the original point-in-time data to that (j)th target storage segment.

摘要翻译： 一种存储时间点数据的方法，包括建立块大小，提供包括（S）块的源数据存储器和包括（T）块的目标数据存储器。 该方法配置（B）源存储段和（B）目标存储段，并且接收更新的写入第（i）个源存储段的原始时间点数据。 该方法然后确定第（j）目标存储段是否包括存储原始时间点数据的可用存储容量。 如果第（j）目标存储段包括存储原始时间点数据的可用存储容量，则该方法将原始时间点数据写入到第（j）个目标存储段。

公开(公告)号：US08244868B2

公开(公告)日：2012-08-14

申请号：US12054025

申请日：2008-03-24

申请人： Lee Charles La Frese ,  Brian Jay Smith

发明人： Lee Charles La Frese ,  Brian Jay Smith

IPC分类号： G06F15/173

CPC分类号： G06F9/505 ,  G06F2209/5019

摘要： A method, apparatus, and computer program product for thin-provisioning of storage in a storage system by an adviser is provided. A workload profile of the storage is created from performance data. The workload profile includes a measurement of changed data per a predetermined time and resource utilization data over a period of time. A capacity estimate is derived from the measurement of changed data per a predetermined time. A placement estimate is derived from the resource utilization data obtained over a period of time. A target capacity is recommended to a user based on the capacity estimate. A placement location is recommended to a user based on the placement estimate. A predicted resource utilization is provided to the user based on the capacity estimate or the placement estimate.

摘要翻译： 提供了一种用于由顾问对存储系统中的存储进行精简配置的方法，装置和计算机程序产品。 从性能数据创建存储的工作负载配置文件。 工作负载简档包括在一段时间内每个预定时间的改变的数据的测量和资源利用数据。 容量估计是从每个预定时间的改变数据的测量得出的。 从一段时间内获得的资源利用率数据导出布局估计。 基于容量估计，向用户推荐目标容量。 根据展示位置估算值向用户推荐展示位置。 基于容量估计或放置估计，向用户提供预测的资源利用。