DATA STORAGE RESOURCE ALLOCATION USING CATEGORY BLACKLISTING WHEN DATA MANAGEMENT REQUESTS FAIL

• US 20170160970A1
• Filed: 02/21/2017
• Published: 06/08/2017
• Est. Priority Date: 06/19/2008
• Status: Abandoned Application

• Current Assignee: CommVault Systems Incorporated
• Original Assignee: CommVault Systems Incorporated
• Inventors: Gokhale, Parag, Kottomtharayil, Rajiv, Karandikar, Amey Vijaykumar, Wang, Yu
• Application Number:
  US15/438,347
• Publication Number:
  US 20170160970A1
• Time in Patent Office: Days
• CPC Class Codes: G06F 11/0727 in a storage system, e.g. in a DASD or network based storage system drivers for digital recording or reproducing units G06F3/06; circuits for error detection or correction within digital recording or reproducing units G11B20/18; 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], H04L67/1097
• CPC Class Codes: G06F 11/0793 Remedial or corrective actions recovery from an exception in an instruction pipeline G06F9/3861; by retry G06F11/1402; for recovering from a failure of a protocol instance or entity H04L69/40
• CPC Class Codes: G06F 11/1458 Management of the backup or restore process
• CPC Class Codes: G06F 16/22 Indexing; Data structures therefor; Storage structures
• CPC Class Codes: G06F 16/2365 Ensuring data consistency and integrity
• CPC Class Codes: G06F 16/285 Clustering or classification
• CPC Class Codes: G06F 3/0605 by facilitating the interaction with a user or administrator
• CPC Class Codes: G06F 3/0622 in relation to access
• CPC Class Codes: G06F 3/0631 by allocating resources to storage systems
• CPC Class Codes: G06F 3/0659 Command handling arrangements, e.g. command buffers, queues, command scheduling
• CPC Class Codes: G06F 3/067 Distributed or networked storage systems, e.g. storage area networks [SAN], network attached storage [NAS]
• CPC Class Codes: G06F 9/4818 Priority circuits therefor
• CPC Class Codes: G06F 9/4881 Scheduling strategies for dispatcher, e.g. round robin, multi-level priority queues
• CPC Class Codes: G06F 9/5011 the resources being hardware resources other than CPUs, Servers and Terminals
• CPC Class Codes: G06F 9/5016 the resource being the memory
• CPC Class Codes: H04L 47/805 QOS or priority aware
• CPC Class Codes: H04L 63/101 Access control lists [ACL]

Abstract

A resource allocation system begins with an ordered plan for matching requests to resources that is sorted by priority. The resource allocation system optimizes the plan by determining those requests in the plan that will fail if performed. The resource allocation system removes or defers the determined requests. In addition, when a request that is performed fails, the resource allocation system may remove requests that require similar resources from the plan. Moreover, when resources are released by a request, the resource allocation system may place the resources in a temporary holding area until the resource allocation returns to the top of the ordered plan so that lower priority requests that are lower in the plan do not take resources that are needed by waiting higher priority requests higher in the plan.

Claims

1. A computer-readable medium encoded with instructions for controlling a computer system to perform a set of data management requests, by a method comprising:

receiving a list of data management requests to be performed by a data management system,

wherein each data management request is to perform at least one data management operation requesting data management resources;

attempting to perform a first data management request from the list of data management requests by assigning the first data management request to one or more data management resources; and

if the first data management request fails, then;

identifying at least one data management resource at least partially responsible for the failure,

determining a category associated with the at least one data management resource at least partially responsible for the failure, wherein each data management resource is associated with a category,

identifying other data management requests in the list of data management requests that request data management resources having the same category as the category associated with the at least one data management resource at least partially responsible for the failure, and

updating the received list of data management requests to indicate that the data management system is not to perform the identified other data management requests.

2. The computer-readable medium of claim 1 wherein a category is created for each data management resource, common to some of the data management requests in the list, that is likely to be critical to the performance of a given data management request.

3. The computer-readable medium of claim 1 wherein the identifying of the other data management requests in the list comprises determining that a threshold is passed by a likeness factor among data management requests requesting similar data management resources.

4. The computer-readable medium of claim 1 wherein identifying other data management requests in the list comprises determining whether the first data management request failed because of a data management resource that is common among the data management requests in the list, and when the first data management request fails because of a common data management resource, identifying other data management requests in the list requesting data management resources having the same category as the common data management resource.

5. The computer-readable medium of claim 1 wherein identifying other data management requests in the list comprises determining whether the first data management request failed because of a data management resource that is unique among the data management requests in the list, and when the first data management request fails because of a unique data management resource, then not identifying certain data management requests in the list requesting data management resources having the same category as the unique resource.

6. A method comprising:

receiving a list of data management requests to be performed by a data management system,

wherein each data management request is to perform at least one data management operation requesting data management resources, and

wherein each data management request is associated with a category;

attempting to perform a first data management request from the list of data management requests by assigning the data management request to one or more data management resources; and

if the first data management request fails, then;

identifying at least one data management resource that is at least partially responsible for the failure,

identifying other data management requests in the list of data management requests having the same category as the first data management request, and

removing the identified other data management requests from the received list of data management requests to be performed by the data management system.

7. The method of claim 6 wherein the removing the identified other data management requests from the received list occurs without attempting to perform any of the identified other data management requests after the first data management request fails.

8. The method of claim 6 wherein a category is created for each data management resource that is determined to be common among a plurality of data management requests in the list and that is likely to be critical to the performance of a given data management request.

9. The method of claim 6 wherein the identifying of the other data management requests comprises determining that a threshold is passed by a likeness factor among the other data management requests, based on the other data management requests requesting similar data management resources.

10. The method of claim 6 wherein the identifying of the other data management requests is based on determining that a threshold is passed by a likeness factor among the other data management requests, wherein the likeness factor considers commonality of a subset of data management resources requested by each respective data management request in the list.

11. The method of claim 6 wherein the identifying of the other data management requests comprises determining whether the first data management request failed because of a data management resource that is common among the other data management requests, and when the first data management request fails because of a common data management resource, identifying the other data management requests having the same category as the first data management request.

12. The method of claim 6 wherein when the first data management request failed because of a data management resource that is common among the other data management requests, identifying the other data management requests having the same category as the first data management request.

13. The method of claim 6 wherein the identifying of the other data management requests comprises determining whether the first data management request failed because of a data management resource that is unique to the first data management request, and when the first data management request fails because of a unique resource, then declining to identify certain data management requests in the list of data management requests that have the same category as the first data management request and do not request the unique data management resource.

14. The method of claim 6 wherein when the first data management request failed because of a data management resource that is unique to the first data management request, declining to identify certain data management requests in the list of data management requests that have the same category as the first data management request and do not request the unique data management resource.

15. The method of claim 6 wherein when the first data management request failed because of a resource that is unique to the first data management request, declining to remove the identified other data management requests from the received list of data management requests to be performed by the data management system even though the identified other data management requests have the same category as the failed first data management request.

16. The method of claim 6 wherein the category is associated with a storage policy.

17. A data management system comprising:

resources for performing data storage requests;

a server;

wherein the server comprises one or more storage policies, and

further comprises a queue of data storage requests to be performed in the data management system,

wherein each data storage request in the queue is associated with one of the one or more storage policies,

wherein a respective associated storage policy comprises criteria for performing the data storage request, and

wherein each data storage request in the queue requires resources for performing the respective data storage request; and

wherein the server is configured to;

classify each data storage request in the queue into one of a plurality of categories,

attempt to perform a first data storage request according to a respective associated storage policy, and

if the attempted first data storage request fails, remove from the queue, without attempting to perform, other data storage requests classified into the same category as the attempted first data storage request.

18. The data management system of claim 17 wherein a given data storage request is classified into a given category based on at least one of (a) resources required by the given data storage request, and (b) rules from the respective storage policy associated with the given data storage request.

19. The data management system of claim 17 wherein two or more data storage requests in the queue are classified into the same category if they require one or more resources in common.

20. The data management system of claim 17 wherein two or more data storage requests in the queue are classified into different categories if a likeness factor that considers which resources the two or more data storage requests have in common fails to pass a threshold.