Method and system for memory allocation in a disaggregated memory architecture

Abstract

Embodiments of the present invention disclose a method, computer program product, and system for allocating memory. A computer receives a request for memory to be allocated to a computer node and determines if the allocation request needs to be carried out on a cluster level, a server rack level, or on a server level. The computer retrieves a memory policy associated with the determined level the allocation request needs to be carried out on from a memory policy database and determines how much available memory may be allocated and if there enough available memory to meet the request. The computer reallocates the available memory to address the received the received request based on the retrieved memory policy.

What is claimed is: 
     
         1 . A method for allocating memory in a server farm, wherein the server farm comprises a plurality of server racks, wherein each server rack comprises a plurality server levels, the method comprising:
 receiving and storing, by a computer, a memory policy allocation rule from an administrator, wherein the memory policy allocation rule is based on thresholds, priority, and granularity;   receiving, by the computer, an allocation request for memory allocation on a server level to a computer node;   determining, by the computer, a current allocation of memory for the server level for a plurality of memory extension cards;   determining, by the computer, the amount of memory requested in the allocation request;   determining, by the computer, an amount of available memory is not enough to fill the amount of the memory for the allocation request, in response to determination the amount of available memory is not enough, determining, by the computer, currently allocated memory that can be reassigned to fill the memory request; and   reallocating, by the computer, the available memory and the allocated memory that can be reassigned to an address of the received allocation request based on the received memory policy, when there is enough of the available memory to meet the allocation request.