MANAGING PERFORMANCE WITHIN AN ENTERPRISE OBJECT STORE FILE SYSTEM

• US 20120254269A1
• Filed: 05/05/2011
• Published: 10/04/2012
• Est. Priority Date: 04/04/2011
• Status: Active Grant

• Current Assignee: Veritas Technologies, LLC (Whitehouse Group Ltd.)
• Original Assignee: Symantec Corporation (NortonLifeLock Inc.)
• Inventors: Carmichael, John Albert
• Granted Patent: US 8,751,449 B2
• Time in Patent Office: Days
• US Class Current: 707/827
• 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 16/134 Distributed indices
• CPC Class Codes: G06F 16/178 Techniques for file synchronisation in file systems
• CPC Class Codes: H04L 43/0876 Network utilisation, e.g. volume of load or congestion level

Abstract

A file system is disclosed that includes an application wide name space instantiated in a global index (Gindex) that is used for accessing objects related to an application. Summary workload statistics are monitored and calculated via a calibrated hierarchical service level agreement (SLA) in a method of operation that includes: establishing a tenant wide name space used for accessing objects of an application stored in physical file systems across one or more appliances, each defining a storage cluster, in association with a tenant logically spanning across the appliances; and monitoring a performance statistic for the application across the tenant.

Claims

1. A non-transitory computer-readable storage medium having computer executable instructions for causing a computer system to perform a method for accessing a file system, comprising:

establishing a tenant wide name space used for accessing objects of an application stored in physical file systems across one or more appliances, each defining a storage cluster, in association with a tenant logically spanning across said appliances; and

monitoring a performance statistic for said application across said tenant.

2. The computer-readable storage medium of claim 1, wherein said monitoring a performance statistic in said method comprises:

monitoring a load for said application across said tenant.

3. The computer-readable storage medium of claim 1, wherein said monitoring a performance statistic in said method comprises:

monitoring a saturation for said application across said tenant.

4. The computer-readable storage medium of claim 1, wherein said monitoring a performance statistic in said method comprises:

monitoring a performance statistic for said application across an appliance of said tenant.

5. The computer-readable storage medium of claim 4, wherein said monitoring a performance statistic in said method comprises:

monitoring a performance statistic for said application across a bucket set of said appliance.

6. The computer-readable storage medium of claim 1, wherein said method further comprises:

providing a user interface illustrating said performance statistic.

7. The computer-readable storage medium of claim 1, wherein said rebalancing operations comprises:

adjusting a read mixture between an appliance and one or more appliance replicas associated with said appliance; and

adjusting a write mixture between bucket sets of an appliance or bucket sets across said tenant.

8. A non-transitory computer-readable storage medium having computer executable instructions for causing a computer system to perform a method for monitoring performance, comprising:

establishing a tenant wide name space used for accessing objects of an application stored in physical file systems across one or more appliances, each defining a storage cluster, in association with a tenant logically spanning across said appliances;

monitoring a performance statistic for said application across said tenant; and

rebalancing operations performed by said application in said tenant wide name space in response to said performance statistic.

9. The computer-readable storage medium of claim 8, wherein said rebalancing operations in said method comprises:

adjusting a read mixture between an appliance and one or more appliance replicas associated with said appliance.

10. The computer-readable storage medium of claim 8, wherein said rebalancing operations in said method comprises:

adjusting a write mixture between bucket sets of an appliance or bucket sets across said tenant.

11. The computer-readable storage medium of claim 8, wherein said rebalancing operations in said method comprises:

allocating a new object to a higher performing bucket set of an appliance associated with said tenant.

12. The computer-readable storage medium of claim 8, wherein said rebalancing operations in said method comprises:

creating a new bucket set from reserve file systems located on an appliance; and

allocating a new object to said bucket set.

13. The computer-readable storage medium of claim 8, wherein said monitoring a performance in said method comprises:

monitoring a load for said application across said tenant; and

monitoring a saturation for said application across said tenant.

14. A non-transitory computer-readable storage medium having computer executable instructions for causing a computer system to perform a method for mobile storage, comprising:

in a first data center, establishing one or more appliances, each defining a storage cluster;

establishing one or more tenants spanning across said one or more appliances in said data center, wherein an application stores objects in file systems associated with said appliances and said tenants;

establishing one or more directories of said file systems;

storing said directories in a first directory file system in association with said application;

replicating said directories to a second directory file system in a second data center; and

providing directory look-up in said directories at said second data center.

15. The non-transitory computer-readable storage medium of claim 14, wherein said method further comprises:

providing a path name to an object in said directories; and

accessing said object via said path name in a corresponding directory look-up operation.

16. The non-transitory computer-readable storage medium of claim 15, wherein said method further comprises:

receiving at said second data center a directory look-up request for an object stored at said first data center;

accessing said object at said first data center;

replicating said object at said first data center to said second data center; and

providing said object in response to said directory look-up request.

17. The non-transitory computer-readable storage medium of claim 14, wherein said method further comprises:

storing objects in said file systems that are separate from said directory file system.

18. The non-transitory computer-readable storage medium of claim 14, wherein said method further comprises:

replicating an object stored in said first data center to a file system in said second data center; and

receiving a directory look-up request for said object at said second data center; and

accessing said object at said second data center.

19. The non-transitory computer-readable storage medium of claim 14, wherein said method further comprises:

storing a new object at said second data center;

incorporating directory information for said new object into said directory file system located in said second data center;

replicating said directory information into said directory file system located in said first data center;

providing directory look-up for said new object in said directory file systems located in said first and second data centers.

20. The non-transitory computer-readable storage medium of claim 14, wherein said method further comprises:

establishing a name space associated with said directories;

storing said name space in said first directory file system in association with said application;

replicating said name space to said second directory file system in said second data center; and

providing directory look-up in said name space at said second data center.