Managing memory system quality of service (QoS)
A memory request manager in a memory system registers a tenant for access to a plurality of memory devices, registers one or more service level agreement (SLA) requirements for the tenant for access to the plurality of memory devices, monitors usage of the plurality of memory devices by tenants, receives a memory request from the tenant to access a selected one of the plurality of memory devices, and allows the access when usage of the plurality of memory devices meets the one or more SLA requirements for the tenant.
1 . An apparatus comprising:
processing circuitry coupled to memory circuitry, the memory circuitry to:
register one or more tenants, via one or more computing devices associated with the one or more tenants, seeking access to one or more memory devices, wherein the one or more tenants are registered based on one or more service level agreements (SLAs), wherein a tenant is registered based on and associated with a SLA that is specific to and customized for the tenant based on access patterns or usage history associated with the tenant;
monitor the tenants and maintain balance in usage associated with the one or more memory devices based, at least in part, on an access level associated with the tenant; and
in response to a request from the tenant, via a computing device associated with the tenant, to access a selected one of the one or more memory devices, allow or disallow the request to access based on ensuring the SLA that is specific to and customized for the tenant is not violated and that the balance in the usage of the one or more memory devices is continuously maintained.
2 . The apparatus of claim 1 , wherein the request includes an address, the address comprising an identifier (ID) of the tenant and a physical address of a memory device of the one or more memory devices, wherein the tenant ID includes a globally unique ID across a cloud computing environment.
3 . The apparatus of claim 1 , wherein the memory circuitry comprises:
tenant registrar circuitry to receive a register tenant command, to store tenant information relating to the tenant, the tenant information including the tenant ID, to receive a register SLA command, and to store one or more SLA requirements associated with the tenant;
tenant resource monitor circuitry to monitor usage of the one or more memory devices by the tenants based at least in part on a successful completion of received requests; and
enforcer circuitry to allow or disallow the access, wherein the processing circuitry comprises at least one of application processing circuitry or graphics processing circuitry.
4 . A method comprising:
registering one or more tenants, by a computing device via one or more computing devices coupled to the computing device and associated with the one or more tenants, seeking access to one or more memory devices, wherein the one or more tenants are registered based on one or more service level agreements (SLAs), wherein a tenant is registered based on and associated with a SLA that is specific to and customized for the tenant based on access patterns or usage history associated with the tenant;
monitoring the tenants and maintain balance in usage associated with the one or more memory devices based, at least in part, on an access level associated with the tenant;
in response to a request from the tenant, via a computing device associated with the tenant, to access a selected one of the one or more memory devices, allowing or disallowing the request to access based on ensuring the SLA that is specific to and customized for the tenant is not violated and that the balance in the usage of the one or more memory devices is continuously maintained.
5 . The method of claim 4 , wherein the request includes an address, the address comprising an identifier (ID) of the tenant and a physical address of a memory device of the one or more memory devices, wherein the tenant ID includes a globally unique ID across a cloud computing environment.
6 . The method of claim 4 , further comprising:
receiving a register tenant command, to store tenant information relating to the tenant, the tenant information including the tenant ID, to receive a register SLA command, and to store one or more SLA requirements associated with the tenant;
monitoring usage of the one or more memory devices by the tenants based at least in part on a successful completion of received requests; and
allowing or disallowing the access, wherein the computing device comprises processing circuitry coupled to memory circuitry, the processing circuitry comprising at least one of application processing circuitry or graphics processing circuitry.
7 . At least one non-transitory computer-readable medium having stored thereon instructions which, when executed, cause a computing device to facilitate operations comprising:
register one or more tenants, via one or more computing devices coupled to the computing device and associated with the one or more tenants, seeking access to one or more memory devices, wherein the one or more tenants are registered based on one or more service level agreements (SLAs), wherein a tenant is registered based on and associated with a SLA that is specific to and customized for the tenant based on access patterns or usage history associated with the tenant device;
monitor the tenants and maintain balance in usage associated with the one or more memory devices based, at least in part, on an access level associated with the tenant;
in response to a request from the tenant to access a selected one of the one or more memory devices, allowing or disallowing the request to access based on ensuring the SLA that is specific to and customized for the tenant is not violated and that the balance in the usage of the one or more memory devices is continuously maintained.
8 . The at least one non-transitory computer-readable medium of claim 7 , wherein the request includes an address, the address comprising an identifier (ID) of the tenant and a physical address of a memory device of the one or more memory devices, wherein the tenant ID includes a globally unique ID across a cloud computing environment.
9 . The non-transitory computer-readable medium of claim 7 , wherein the operations further comprise:
receiving a register tenant command, to store tenant information relating to the tenant, the tenant information including the tenant ID, to receive a register SLA command, and to store one or more SLA requirements associated with the tenant;
monitoring usage of the one or more memory devices by the tenants based at least in part on a successful completion of received requests; and
allowing or disallowing the access, wherein the computing device comprises processing circuitry coupled to memory circuitry, the processing circuitry comprising at least one of application processing circuitry or graphics processing circuitry.