Hybrid memory system

Abstract

An example apparatus comprises a hybrid memory system to couple to a host and a controller coupled to the hybrid memory system. The controller may be configured to cause data associated with a virtual memory location of the host to be selectively transferred to the hybrid memory system responsive to a determination that a main memory of the host experiences threshold amount of resource utilization.

What is claimed is: 
     
         1 . An apparatus, comprising:
 a first memory resource coupled to a controller; and   a second memory resource coupled to the controller, wherein the controller is to:
 allocate a portion of the first memory resource or the second memory resource that is configured to exhibit a lower access latency than the other of the first memory resource or the second memory resource for use as a swap space for the apparatus; 
 assign a sensitivity to a command corresponding to performance of a swap operation, the command being associated with a memory external to the apparatus, wherein the command corresponds to a file system write having a determinable write pattern associated therewith, and wherein the sensitivity is based on a write latency associated with execution of the command; and 
 cause data to be transferred to the portion of the first memory resource or the second memory resource that is allocated as the swap space for the apparatus based, at least in part, on the assigned sensitivity or the command corresponding to the particular type of file system write having the determinable write pattern associated therewith, or both. 
   
     
     
         2 . The apparatus of  claim 1 , wherein the swap space for the apparatus comprises a particular logical block address range of the first memory resource or the second memory resource. 
     
     
         3 . The apparatus of  claim 1 , wherein the swap space for the apparatus comprises one or more pages of memory of the first memory resource or the second memory resource. 
     
     
         4 . The apparatus of  claim 1 , wherein the controller is configured to cause an anonymous page to be transferred to the swap space as part of causing the data to be transferred to the portion of the first memory resource or the second memory resource that is allocated as the swap space for the apparatus. 
     
     
         5 . The apparatus of  claim 1 , wherein the memory external to the apparatus comprises 
       a main memory of a host that is couplable to the controller. 
     
     
         6 . The apparatus of  claim 1 , wherein the controller is further to cause data to be transferred to the portion of the first memory resource or the second memory resource that is allocated as the swap space for the apparatus responsive to a determination that a memory external to the apparatus experiences a threshold amount of resource utilization. 
     
     
         7 . The apparatus of  claim 1 , wherein the data includes data corresponding to a process working set of data. 
     
     
         8 . A system, comprising:
 a first non-volatile memory (NVM) resource;   a second NVM resource; and   a controller coupled to the first NVM resource and the second NVM resource, the controller to:
 allocate a portion of the first NVM resource or the second NVM resource that is configured to exhibit a higher endurance than the other of the first NVM resource or the second NVM resource for use as a swap space for the system; 
 assign a sensitivity to a command corresponding to performance of a swap operation, the command being associated with a memory external to the apparatus, wherein the command corresponds to a file system write having a determinable write pattern associated therewith; and 
 cause data to be transferred to the portion of the first NVM resource or the second NVM resource that is allocated as the swap space for the system based, at least in part, on the assigned sensitivity or the command corresponding to the particular type of file system write having the determinable write pattern associated therewith, or both. 
   
     
     
         9 . The system of  claim 8 , wherein the controller is further to allocate the portion of the first NVM resource or the second NVM resource that is configured to exhibit a lower access latency 
       than the other of the first NVM resource or the second NVM resource for use as the swap space for the system. 
     
     
         10 . The system of  claim 8 , wherein the sensitivity is based on a write latency associated with execution of the command. 
     
     
         11 . The system of  claim 8 , wherein the data corresponds to a process working set of data accessed by a virtual memory page associated with a component external to the first NVM resource, the second NVM resource, and the controller. 
     
     
         12 . The system of  claim 11 , wherein the controller is to cause the data to be transferred to the portion of the first NVM resource or the second NVM resource that is allocated as the swap space for the system in response to a determination that an amount of memory corresponding to the process working set has exceeded a threshold memory consumption value. 
     
     
         13 . The system of  claim 8 , wherein the controller is to cause an anonymous page to be transferred to the swap space as part of causing the data to be transferred to the portion of the first memory resource or the second memory resource that is allocated as the swap space for the system. 
     
     
         14 . The system of  claim 8 , wherein the memory external to the apparatus comprises 
       a main memory of a host that is couplable to the system. 
     
     
         15 . The system of  claim 8 , wherein the controller is further to cause the data to be transferred to the portion of the first memory resource or the second memory resource that is allocated as the swap space for the apparatus responsive to a determination that a memory external to the system experiences a threshold amount of resource utilization. 
     
     
         16 . A method, comprising:
 allocating a portion of a first memory resource or a second memory resource that is configured to exhibit a lower access latency or a higher endurance, or both, than the other of the first memory resource or the second memory resource for use as a swap space for a computing system;   assigning a sensitivity to a command corresponding to performance of a swap operation invoking the swap space, wherein the command corresponds to a file system write having a determinable write pattern associated therewith, and wherein the sensitivity is based on a write latency associated with execution of the command; and   causing, as part of performance of the swap operation, data to be transferred to the portion of the first memory resource or the second memory resource that is allocated as the swap space for the computing system based, at least in part, on the assigned sensitivity or the command corresponding to the particular type of file system write having the determinable write pattern associated therewith, or both.   
     
     
         17 . The method of  claim 16 , further comprising causing an anonymous page of data to be transferred to the swap space as part of causing the data to be transferred to the portion of the first memory resource or the second memory resource that is allocated as the swap space for the computing system. 
     
     
         18 . The method of  claim 17 , wherein the anonymous page of data includes data corresponding to a process working set of data. 
     
     
         19 . The method of  claim 16 , wherein allocating the portion of the first memory resource or the second memory resource for use as the swap space for the computing system further comprises allocating a logical block address range of the first memory resource or the second memory resource to store the data. 
     
     
         20 . The method of  claim 16 , wherein allocating the portion of the first memory resource or the second memory resource for use as the swap space for the computing system further comprises allocating one or more pages of memory of the first memory resource or the second memory resource to store the data.