Apparatus and method for meeting performance metrics for users in file systems

Abstract

A data block storage management capability is presented. A file system includes a plurality of data blocks which are managed using a first storage service and a second storage service, where the first storage service has a lower storage cost and a higher input-output cost than the second storage service. The data blocks stored using the second storage service have associated therewith respective expected storage durations indicative of respective lengths of time for which the data blocks are to be stored using the second storage service (which may be the same or different across the ones of the data blocks stored using the second storage service). The expected storage durations of the data blocks are modified based on a comparison of an expected hit rate of the second storage service and a current hit rate of the second storage service or current hit rates of the data blocks.

What is claimed is: 
     
         1 . An apparatus, comprising:
 a processor and a memory communicatively connected to the processor, the processor configured to:
 determine, for a data block stored using a first storage service and stored using a second storage service, an expected storage duration (T) for storage of the data block using the second storage service, wherein the first storage service has a lower storage cost than the second storage service and a higher input-output cost than the second storage service; and 
 determine, based on the expected storage duration (T) for the data block and a storage duration control parameter associated with the data block, whether to evict the data block from the second storage service. 
   
     
     
         2 . The apparatus of  claim 1 , wherein, to determine whether to evict the data block from the second storage service, the processor is configured to:
 compute a storage duration based on the expected storage duration (T) for the data block and the storage duration control parameter associated with the data block; and   determine, based on the storage duration, whether to evict the data block from the second storage service.   
     
     
         3 . The apparatus of  claim 2 , wherein the processor is configured to compute the storage duration using ((1+storage duration control parameter)×T). 
     
     
         4 . The apparatus of  claim 3 , wherein the expected storage duration (T) for the data block is based on a mean inter-arrival time for the data block or an average first-hit time interval for the data block. 
     
     
         5 . The apparatus of  claim 1 , wherein the expected storage duration (T) for the data block is based on data block access statistics for the data block. 
     
     
         6 . The apparatus of  claim 1 , wherein the expected storage duration (T) for the data block is based on a mean inter-arrival time for the data block. 
     
     
         7 . The apparatus of  claim 6 , wherein the processor is configured to:
 evict the data block from the second storage service based on a determination that the data block has been accessed more than once and based on a determination that a time since a last access to the data block is greater than a storage duration, wherein the storage duration is computed based on the expected storage duration (T) for the data block and the storage duration control parameter associated with the data block.   
     
     
         8 . The apparatus of  claim 1 , wherein the expected storage duration (T) for the data block is based on an average first-hit time interval for the data block. 
     
     
         9 . The apparatus of  claim 8 , wherein the processor is configured to:
 evict the data block from the second storage service based on a determination that the data block has not been accessed more than once and based on a determination that a time since a last access to the data block is greater than a storage duration, wherein the storage duration is computed based on the expected storage duration (T) for the data block and the storage duration control parameter associated with the data block.   
     
     
         10 . A method, comprising:
 using a processor and a memory for:
 determining, for a data block stored using a first storage service and stored using a second storage service, an expected storage duration (T) for storage of the data block using the second storage service, wherein the first storage service has a lower storage cost than the second storage service and a higher input-output cost than the second storage service; and 
 determining, based on the expected storage duration (T) for the data block and a storage duration control parameter associated with the data block, whether to evict the data block from the second storage service. 
   
     
     
         11 . An apparatus, comprising:
 a processor and a memory communicatively connected to the processor, the processor configured to:
 obtain, for a data block stored using a first storage service and stored using a second storage service, data block access statistics associated with storage of the data block using the second storage service, wherein the first storage service has a lower storage cost than the second storage service and a higher input-output cost than the second storage service; and 
 determine, based on the data block access statistics for the data block and a storage duration control parameter associated with the data block, whether to evict the data block from the second storage service. 
   
     
     
         12 . The apparatus of  claim 11 , wherein the processor is configured to:
 determine, based on the data block access statistics for the data block, an expected storage duration (T) for the data block; and   determine, based on the expected storage duration (T) for the data block and the storage duration control parameter associated with the data block, whether to evict the data block from the second storage service.   
     
     
         13 . The apparatus of  claim 12 , wherein, to determine whether to evict the data block from the second storage service, the processor is configured to:
 compute a storage duration based on the expected storage duration (T) for the data block and the storage duration control parameter associated with the data block; and   determine, based on the storage duration, whether to evict the data block from the second storage service   
     
     
         14 . The apparatus of  claim 13 , wherein the processor is configured to compute the storage duration using ((1+storage duration control parameter)×T). 
     
     
         15 . The apparatus of  claim 11 , wherein the processor is configured to:
 determine, based on the data block access statistics for the data block, a mean inter-arrival time for the data block; and   determine, based on the mean inter-arrival time for the data block and the storage duration control parameter associated with the data block, whether to evict the data block from the second storage service.   
     
     
         16 . The apparatus of  claim 15 , wherein the processor is configured to:
 evict the data block from the second storage service based on a determination that the data block has been accessed more than once and based on a determination that a time since a last access to the data block is greater than a storage duration, wherein the storage duration is computed based on the mean inter-arrival time for the data block and the storage duration control parameter associated with the data block.   
     
     
         17 . The apparatus of  claim 16 , wherein the processor is configured to:
 compute the storage duration using ((1+storage duration control parameter)×mean inter-arrival-time).   
     
     
         18 . The apparatus of  claim 11 , wherein the processor is configured to:
 determine, based on the data block access statistics for the data block, an average first-hit time interval for the data block; and   determine, based on the average first-hit time interval for the data block and the storage duration control parameter associated with the data block, whether to evict the data block from the second storage service.   
     
     
         19 . The apparatus of  claim 18 , wherein the processor is configured to:
 evict the data block from the second storage service based on a determination that the data block has not been accessed more than once and based on a determination that a time since a last access to the data block is greater than a storage duration, wherein the storage duration is computed based on the average first-hit time interval for the data block and the storage duration control parameter associated with the data block.   
     
     
         20 . The apparatus of  claim 19 , wherein the processor is configured to:
 compute the storage duration using ((1+storage duration control parameter)×average first-hit time interval).