Array-based computations on a storage device

• US 9,509,773 B2
• Filed: 09/10/2014
• Issued: 11/29/2016
• Est. Priority Date: 09/10/2014
• Status: Active Grant

• Current Assignee: Futurewei Technologies Incorporated (Huawei Investment & Holding Co., Ltd.)
• Original Assignee: Futurewei Technologies Incorporated (Huawei Investment & Holding Co., Ltd.)
• Inventors: Chadha, Vineet, Palani, Gopinath, Shi, Guangyu
• Primary Examiner(s): Tran, Jimmy H
• Application Number:
  US14/482,352
• Publication Number:
  US 20160072885A1
• Time in Patent Office: 811 Days
• US Class Current: 1/1
• CPC Class Codes: G06F 16/10 File systems; File servers
• CPC Class Codes: G06F 16/13 File access structures, e.g. distributed indices arrangements of input from, or output to, record carriers G06F3/06
• CPC Class Codes: G06F 16/1827 Management specifically adapted to NAS management of storage area networks [SAN] G06F3/067
• CPC Class Codes: G06F 3/0665 at area level, e.g. provisioning of virtual or logical volumes
• CPC Class Codes: G06F 3/0689 Disk arrays, e.g. RAID, JBOD
• CPC Class Codes: H04L 67/1097 for distributed storage of data in networks, e.g. transport arrangements for network file system [NFS], storage area networks [SAN] or network attached storage [NAS]

Abstract

An instruction from an application server to perform a computation is received at a network-attached storage (NAS) device. The computation uses arrays of data that are stored by the NAS device as inputs. The instruction includes remote procedure calls that identify operations that are included in the computation, including a first remote procedure call that will cause the NAS device to perform a read operation on a first file containing an array of data to be used as an input for the computation, and a second remote procedure call that will cause the NAS device to perform an array operation using the array of data. The operations are executed on the NAS device to produce a result that is stored in a second file in a location in a file system managed by the NAS device and accessible to the application server.

Claims

1. A method performed by a network-attached storage (NAS) device comprising a processor and memory, the method executed by the processor and comprising:

receiving, at the NAS device, an instruction from an application server that causes the NAS device to perform a computation that uses arrays of data that are stored by the NAS device as inputs, the instruction comprising a plurality of remote procedure calls that identify operations that are included in the computation, the remote procedure calls comprising a first remote procedure call operable for causing the NAS device to perform a read operation on a first file stored by the NAS device and containing an array of data to be used as an input for the computation, the remote procedure calls further comprising a second remote procedure call operable for causing the NAS device to perform an array operation using the array of data from the first file;

executing the read operation and the array operation on the NAS device to produce a result; and

storing the result in a second file in a location in a file system managed by the NAS device and accessible to the application server.

2. The method of claim 1, wherein the array operation is selected from the group consisting of:

add the array of data and another array of data;

multiply the array of data by another array of data;

invert the array of data; and

transpose the array of data.

3. The method of claim 1, wherein each remote procedure call in the plurality of remote procedure calls is associated with a single one of the operations.

4. The method of claim 1, further comprising performing the operations on the NAS device using a plurality of virtual machines that are executed on the NAS device, each virtual machine in the plurality of virtual machines configured to perform a single operation.

5. The method of claim 1, further comprising the NAS device sending the result to the application server.

6. The method of claim 1, further comprising the NAS device sending, to the application server, information comprising a fully qualified name for the second file.

7. The method of claim 1, wherein the remote procedure calls include information comprising a fully qualified name for the second file.

8. The method of claim 1, wherein the remote procedure calls are included in a data-sharing and file-sharing protocol selected from the group consisting of:

Network File System; and

Common Internet File System.

9. The method of claim 1, wherein the remote procedure calls are selected from the group consisting of a first remote procedure call that identifies data to be read and an operation to be performed;

a second remote procedure call that identifies a fully qualified file name for data to be read; and

a third remote procedure call that identifies data to be read, an operation to be performed, and a fully qualified file name for a computation result.

10. The method of claim 1, further comprising sending information to the application server indicating a status of the computation.

11. A network-attached storage (NAS) device, comprising:

a processor, and

memory coupled to the processor and having stored therein instructions that, if executed by the NAS, cause the NAS device to perform a method comprising;

receiving, at the NAS device, an Instruction from an application server that causes the NAS device to perform a computation that uses arrays of data that are stored by the NAS device as inputs, the instruction comprising a sequence of remote procedure calls that identify operations that are included in the computation, the operations comprising a read operation on a first file in a file system managed by the NAS device, the first file containing an array of data, the operations further comprising an array operation that uses the array of data from the first file;

in response to the remote procedure calls in the instruction, performing the operations including the read operation and the array operation using virtual machines that are executed on the NAS device, the virtual machines comprising a first virtual machine configured to perform the read operation and a second virtual machine configured to perform the array operation, wherein said performing produces a result; and

storing the result in a second file in a location in the file system that is accessible to the application server.

12. The NAS device of claim 11, wherein the remote procedure calls are selected from the group consisting of:

array_compute, which identifies data to be read and an operation to be performed;

array_from, which identifies a fully qualified file name for data to be read; and

array_compute_save, which identifies data to be read, an operation to be performed, and a fully qualified file name for a computation result.

13. The NAS device of claim 11, wherein the method further comprises the NAS device sending, to the application server, information comprising a fully qualified name for the second file.

14. The NAS device of claim 11, wherein the remote procedure calls include information comprising a fully qualified name for the second file.

15. The NAS device of claim 11, wherein the method further comprises the NAS device sending information to the application server indicating the computation is completed.

16. A non-transitory computer-readable storage medium having computer-executable instructions that, when executed, cause an application server to perform a method, the method comprising:

identifying a computation to be performed on an array of data stored by a network-attached storage (NAS) device, the computation comprising an array operation to be performed on the array of data, the computation further comprising a read operation to be performed on a first file stored by the NAS device and containing the array of data;

generating an instruction for the computation, the instruction comprising a plurality of remote procedure calls that identify operations that are included in the computation, the remote procedure calls comprising a first remote procedure call operable for causing the NAS device to perform the read operation on the first file, the remote procedure calls further comprising a second remote procedure call operable for causing the NAS device to perform the array operation on the array of data read from the first file;

sending the instruction to the NAS device; and

subsequent to execution of the operations by the NAS device, accessing a result of the computation.

17. The computer-readable storage medium of claim 16, wherein the method further comprises receiving the result at the application server from the NAS device.

18. The computer-readable storage medium of claim 16, wherein the method further comprises receiving, from the NAS device, information indicating a location in a file system managed by the NAS device of a second file that contains the result.

19. The computer-readable storage medium of claim 16, wherein the remote procedure calls include information comprising a fully qualified file name for a second file that contains the result.

20. The computer-readable storage medium of claim 16, wherein the remote procedure calls are selected from the group consisting of:

array_compute, which identifies data to be read and an operation to be performed;

array_from, which identifies a fully qualified file name for data to be read; and

array_compute_save, which identifies data to be read, an operation to be performed, and a fully qualified file name for a computation result.