Framework for QoS in embedded computer infrastructure

• US 9,906,466 B2
• Filed: 06/15/2015
• Issued: 02/27/2018
• Est. Priority Date: 06/15/2015
• Status: Expired due to Fees

• Current Assignee: International Business Machines Corporation
• Original Assignee: International Business Machines Corporation
• Inventors: Eda, Sasikanth, Hildebrand, Dean, Patil, Sandeep R., Owen, William W.
• Primary Examiner(s): Serrao, Ranodhi
• Assistant Examiner(s): FIORILLO, JAMES N
• Application Number:
  US14/739,158
• Publication Number:
  US 20160366068A1
• Time in Patent Office: 988 Days
• Field of Search: 709220, 709221, 709223, 709226
• CPC Class Codes: H04L 47/805 QOS or priority aware
• CPC Class Codes: H04L 47/821 Prioritising resource allocation or reservation requests
• CPC Class Codes: H04L 47/823 Prediction of resource usage
• CPC Class Codes: H04L 47/83 based on usage prediction
• CPC Class Codes: H04L 67/10 in which an application is distributed across nodes in the network software deployment G06F8/60; multiprogramming arrangements G06F9/46

Abstract

Various embodiments providing a framework for Quality of Service (QoS) within and between globally distributed computing components by a processor. At least one resource required for a computing process is estimated by examining information associated with a resource template. A storlet is allocated as the at least one resource at a storage node, thereby offloading computing elements to at least one storage unit. The allocated storlet performs the computing process according to constraints delineated by the resource template.

Claims

1. A method providing a framework for Quality of Service (QoS) within and between globally distributed computing components by a processor, the method comprising:

identifying a QoS for a particular user by comparing identification information with information in a predefined table;

defining a resource template for the user based on the identified QoS, the resource template specifying computing resources required for a computing process uploaded by the user to an object store;

appending information, including header and metadata information associated with the computing process, to the resource template;

estimating at least one resource required for the computing process by examining information associated with the resource template and executing the computing process from within a sandboxed environment in the object store to gauge resource utilization prior to accepting the computing process for general deployment, wherein the computing process is accepted for general deployment when the resource utilization aligns with constraints delineated by the resource template, and

upon accepting the computing process for general deployment;

allocating a storlet as the at least one resource at a storage node, the storlet comprising embedded compute functionality within the object store and thereby offloading computing elements to at least one storage unit;

wherein the allocated storlet performs the computing process according to the constraints delineated by the resource template to efficiently manage and bound the computing resources between multiple tenants of the object store.

2. The method of claim 1, further including examining the resource template, including the appended information, as defined for the user, wherein:

if the estimated at least one resource required for the computing process exceeds the delineated constraints of the resource template, returning an incompatibility, and

if the estimated at least one resource required for the computing process does not exceed the delineated constraints of the resource template, allowing the storlet to proceed to perform the computing process.

3. The method of claim 1, further including monitoring the storlet to determine a utilization of the at least one resource as the computing process is performed.

4. The method of claim 1, wherein performing, by the allocated storlet, the computing process according to constraints delineated by the resource template further includes limiting an access of the computing process to an embedded computing infrastructure associated with the storlet.

5. The method of claim 1, wherein performing, by the allocated storlet, the computing process according to constraints delineated by the resource template further includes selecting a storage media determined to appropriately correspond to the resource template for the computing process.

6. The method of claim 1, wherein performing, by the allocated storlet, the computing process according to constraints delineated by the resource template further includes limiting an access of the computing process to at least one client.

7. A system providing a framework for Quality of Service (QoS) within and between globally distributed computing components, comprising:

a processor, coupled to a memory which stores computer readable program instructions that when executed by the processor;

identifies a QoS for a particular user by comparing identification information with information in a predefined table,

defines a resource template for the user based on the identified QoS, the resource template specifying computing resources required for a computing process uploaded by the user to an object store,

appends information, including header and metadata information associated with the computing process, to the resource template,

estimates at least one resource required for Hall the computing process by examining information associated with Hall the resource template and executing the computing process from within a sandboxed environment in the object store to gauge resource utilization prior to accepting the computing process for general deployment, wherein the computing process is accepted for general deployment when the resource utilization aligns with constraints delineated by the resource template, and

upon accepting the computing process for general deployment;

allocates a storlet as the at least one resource at a storage node, the storlet comprising embedded compute functionality within the object store and thereby offloading computing elements to at least one storage unit;

wherein the allocated storlet performs the computing process according to the constraints delineated by the resource template to efficiently manage and bound the computing resources between multiple tenants of the object store.

8. The system of claim 7, wherein the processor examines the resource template, including the appended information, as defined for the user, wherein:

if the estimated at least one resource required for the computing process exceeds the delineated constraints of the resource template, the processor returns an incompatibility, and

if the estimated at least one resource required for the computing process does not exceed the delineated constraints of the resource template, the processor allows the storlet to proceed to perform the computing process.

9. The system of claim 7, wherein the processor monitors the storlet to determine a utilization of the at least one resource as the computing process is performed.

10. The system of claim 7, wherein the processor, pursuant to performing, by the allocated storlet the computing process according to constraints delineated by the resource template, limits an access of the computing process to an embedded computing infrastructure associated with the storlet.

11. The system of claim 7, wherein the processor, pursuant to performing, by the allocated storlet the computing process according to constraints delineated by the resource template, selects a storage media determined to appropriately correspond to the resource template for the computing process.

12. The system of claim 7, wherein the processor, pursuant to performing, by the allocated storlet the computing process according to constraints delineated by the resource template, limits an access of the computing process to at least one client.

13. A computer program product providing a framework for Quality of Service (QoS) within and between globally distributed computing components by a processor, the computer program product comprising a non-transitory computer-readable storage medium having computer-readable program code portions stored therein, the computer-readable program code portions comprising:

an executable portion that identifies a QoS for a particular user by comparing identification information with information in a predefined table;

an executable portion that defines a resource template for the user based on the identified QoS, the resource template specifying computing resources required for a computing process uploaded by the user to an object store;

an executable portion that appends information, including header and metadata information associated with the computing process, to the resource template;

an executable portion that estimates at least one resource required for the computing process by examining information associated with the resource template and executing the computing process from within a sandboxed environment in the object store to gauge resource utilization prior to accepting the computing process for general deployment, wherein the computing process is accepted for general deployment when the resource utilization aligns with constraints delineated by the resource template, and upon accepting the computing process for general deployment;

an executable portion that allocates a storlet as the at least one resource at a storage node, the storlet comprising embedded compute functionality within the object store and thereby offloading computing elements to at least one storage unit;

wherein the allocated storlet performs the computing process according to the constraints delineated by the resource template to efficiently manage and bound the computing resources between multiple tenants of the object store.

14. The computer program product of claim 13, further including an executable portion that examines the resource template, including the appended information, as defined for the user, wherein:

if the estimated at least one resource required for the computing process exceeds the delineated constraints of the resource template, an incompatibility is returned, and

if the estimated at least one resource required for the computing process does not exceed the delineated constraints of the resource template, the storlet is allowed to proceed to perform the computing process.

15. The computer program product of claim 13, further including an executable portion that monitors the storlet to determine a utilization of the at least one resource as the computing process is performed.

16. The computer program product of claim 13, further including an executable portion that, pursuant to performing, by the allocated storlet the computing process according to constraints delineated by the resource template, limits an access of the computing process to an embedded computing infrastructure associated with the storlet.

17. The computer program product of claim 13, further including an executable portion that, pursuant to performing, by the allocated storlet the computing process according to constraints delineated by the resource template, selects a storage media determined to appropriately correspond to the resource template for the computing process.

18. The computer program product of claim 13 further including an executable portion that, pursuant to performing, by the allocated storlet the computing process according to constraints delineated by the resource template, limits an access of the computing process to at least one client.