发明名称 |
Capacity forecasting for a deduplicating storage system |
摘要 |
A system for managing a storage system comprises a processor and a memory. The processor is configured to receive storage system information from a deduplicating storage system. The processor is further configured to determine a capacity forecast based at least in part on the storage system information. The processor is further configured to provide a compression forecast. The memory is coupled to the processor and configured to provide the processor with instructions. |
申请公布号 |
US9558200(B2) |
申请公布日期 |
2017.01.31 |
申请号 |
US201414267675 |
申请日期 |
2014.05.01 |
申请人 |
EMC IP Holding Company LLC |
发明人 |
Chamness Mark |
分类号 |
G06F17/30;G06F3/06;G06F11/30;G06F11/34 |
主分类号 |
G06F17/30 |
代理机构 |
Blakely, Sokoloff, Taylor & Zafman LLP |
代理人 |
Blakely, Sokoloff, Taylor & Zafman LLP |
主权项 |
1. A system for managing a storage system, comprising:
a memory storing instructions; and a processor coupled to the memory to execute the instructions from the memory, the processor being configured to: receive storage system information from a deduplicating storage system that comprises one or more storage units; in response to the storage system information satisfying generation criteria including the deduplicating storage system capacity being above a threshold, determine a storage capacity forecast using a regression analysis based at least in part on fitting a predictive model to historical data of storage capacity usage included in the storage system information, wherein the regression analysis includes selecting, from a plurality of regressions, a best fitting regression based on an R-squared value to forecast a capacity threshold date for each of the storage units, wherein the capacity threshold date forecasts a date the storage unit reaches a total storage capacity threshold; wherein the historical data of storage capacity usage includes data corresponding to total storage capacity used on particular days of a week, and the predictive model includes a first predictive model for a first day of the week and a second predictive model, different from the first predictive model, for a second day of the week; and in response to the storage capacity forecast satisfying a preset capacity criteria, manage files stored on at least one of the one or more storage units based at least in part on one or more file management policies and a ranked list the one or more storage units, wherein the ranked list is ranked according to the forecasted capacity threshold date of the storage unit. |
地址 |
Hopkinton MA US |