Using data characteristics to optimize grouping of similar data for garbage collection

Abstract

A plurality of characteristics associated with a plurality of erase blocks are received from two or more of a plurality of storage devices. A garbage collection process is performed by grouping valid data from the plurality of erase blocks based on a similarity of the plurality of characteristics between the valid data and storing the grouped valid data at another erase block at the plurality of storage devices.

What is claimed is: 
     
         1 . A system comprising:
 a plurality of storage devices; and   a storage controller operatively coupled to the plurality of storage devices, the storage controller comprising a processing device, the processing device to:
 receive, from two or more of the plurality of storage devices, a plurality of characteristics associated with a plurality of erase blocks of the plurality of storage devices; and 
 perform a garbage collection process by grouping valid data from the plurality of erase blocks based on a similarity of the plurality of characteristics between the valid data and storing the grouped valid data at another erase block of the plurality of storage devices. 
   
     
     
         2 . The system of  claim 1 , wherein the plurality of storage devices comprise a plurality of direct-mapped solid-state storage devices. 
     
     
         3 . The system of  claim 1 , wherein the garbage collection process is performed based on a capacity of the plurality of storage devices being used for storage. 
     
     
         4 . The system of  claim 1 , wherein the processing device is further to:
 determine an expected longevity associated with each of the valid data based on the plurality of characteristics, wherein the valid data is grouped based on a similarity of the expected longevity between the valid data.   
     
     
         5 . The system of  claim 1 , wherein the plurality of characteristics comprise an age associated with each of the valid data. 
     
     
         6 . The system of  claim 1 , wherein the plurality of characteristics comprise a type of data associated with each of the valid data. 
     
     
         7 . The system of  claim 1 , wherein the plurality of characteristics specifies a deduplication importance associated with each valid data, the deduplication importance corresponding to a number of times that a respective valid data was associated with a deduplication operation. 
     
     
         8 . A method comprising:
 receiving, from two or more of a plurality of storage devices, a plurality of characteristics associated with a plurality of erase blocks of the plurality of storage devices; and   performing, by a processing device, a garbage collection process by grouping valid data from the plurality of erase blocks based on a similarity of the plurality of characteristics between the valid data and storing the grouped valid data at another erase block of the plurality of storage devices.   
     
     
         9 . The method of  claim 8 , wherein the plurality of storage devices comprise a plurality of direct-mapped solid-state storage devices. 
     
     
         10 . The method of  claim 8 , wherein the garbage collection process is performed based on a capacity of the plurality of storage devices being used for storage. 
     
     
         11 . The method of  claim 8 , further comprising:
 determining an expected longevity associated with each of the valid data based on the plurality of characteristics, wherein the valid data is grouped based on a similarity of the expected longevity between the valid data.   
     
     
         12 . The method of  claim 8 , wherein the plurality of characteristics comprise an age associated with the valid data. 
     
     
         13 . The method of  claim 8 , wherein the plurality of characteristics comprise a type of data associated with the valid data. 
     
     
         14 . The method of  claim 8 , wherein the plurality of characteristics specifies a deduplication importance associated with the valid data, the deduplication importance corresponding to a number of times that the valid data was associated with a deduplication operation. 
     
     
         15 . A non-transitory computer readable storage medium storing instructions, which when executed, cause a processing device to:
 receive, from two or more of a plurality of storage devices, a plurality of characteristics associated with a plurality of erase blocks of the plurality of storage devices; and   perform, by the processing device, a garbage collection process by grouping valid data from the plurality of erase blocks based on a similarity of the plurality of characteristics between the valid data and storing the grouped valid data at another erase block of the plurality of storage devices.   
     
     
         16 . The non-transitory computer readable storage medium of  claim 15 , wherein the plurality of storage devices comprise a plurality of direct-mapped solid-state storage devices. 
     
     
         17 . The non-transitory computer readable storage medium of  claim 15 , wherein the garbage collection process is performed based on a capacity of the plurality of storage devices being used for storage. 
     
     
         18 . The non-transitory computer readable storage medium of  claim 15 , wherein the processing device is further to:
 determine an expected longevity associated with each of the valid data based on the plurality of characteristics, wherein the valid data is grouped based on a similarity of the expected longevity between the valid data.   
     
     
         19 . The non-transitory computer readable storage medium of  claim 15 , wherein the plurality of characteristics comprise an age associated with the valid data. 
     
     
         20 . The non-transitory computer readable storage medium of  claim 15 , wherein the plurality of characteristics comprise a type of data associated with the valid data.