US 8,028,017 B2 · Virtual controllers with a large data center

Abstract

Disclosed are a method, a system and a computer program product for dynamically allocating and/or de-allocating resources and/or partitions that provide I/O and/or active storage access services in a supercomputing system. The supercomputing system can include multiple compute nodes, high performance computing (HPC) switches coupled to the compute nodes, and active non-volatile storage devices coupled to the compute nodes. Each of the compute nodes can be configured to communicate with another compute node through at least one of the HPC switches. In one or more embodiments, each of at least two compute nodes includes a storage controller and is configured to dynamically allocate and de-allocate a storage controller partition to provide storage services to the supercomputing system, and each of at least two compute nodes includes an I/O controller and is configured to dynamically allocate and de-allocate an I/O controller partition to provide I/O services to the supercomputing system.

Claims17

Dependent claims

A supercomputing system, comprising:

a plurality of compute nodes;
a plurality of high performance computing (HPC) switches coupled to the plurality of compute nodes;
and
a plurality of active non-volatile storage devices coupled to the plurality of compute nodes;
wherein each of the plurality of compute nodes is configured to communicate with another compute node of the plurality of compute nodes through at least one of the plurality of HPC switches;
wherein each of at least first and second compute nodes of the plurality of compute nodes includes a plurality of processors operable to perform computation operations for the supercomputing system;
and
wherein a resource of a processor among the plurality of processors in the first compute node is dynamically allocated as a storage controller that stores data to and reads data from the plurality of active non-volatile storage devices on behalf of others of the plurality of compute nodes in provision of a storage service and is thereafter deallocated from the storage service and utilized to perform computation operations for the supercomputing system.

5 more elements

A method for operating a supercomputing system including a plurality of compute nodes, the method comprising:

in a first compute node among the plurality of compute nodes, allocating a resource of the first compute node to a storage service, wherein the first compute node includes a plurality of processors operable to perform computation operations for the supercomputing system and wherein the allocating includes allocating as a storage controller of the storage service a resource of a processor among the plurality of processors;
others of the plurality of compute nodes of the supercomputing system transmitting data to the first compute node for storage by the storage service;
the first compute node storing the data received from others of the plurality of compute nodes in active storage in provision of the storage service, wherein the storing in the active storage is controlled by the storage controller implemented by the resource of the processor;
and
thereafter, de-allocating from the storage service the resource of the processor on the first compute node allocated as the storage controller for the storage service.

2 more elements

Dependencies are inferred from the claim text.

Virtual controllers with a large data center

Life of this patent

Virtual controllers with a large data center

Life of this patent

Abstract

Claims17