Storage system deduplication with service level agreements

• US 10,127,235 B2
• Filed: 03/06/2013
• Issued: 11/13/2018
• Est. Priority Date: 03/06/2013
• Status: Active Grant

• Current Assignee: Quest Software, Inc.
• Original Assignee: Quest Software, Inc.
• Inventors: Rao, Goutham, Bolla, Ratna Manoj, Jayaraman, Vinod
• Primary Examiner(s): Fan, Shiow-Jy
• Application Number:
  US13/786,759
• Publication Number:
  US 20140258244A1
• Time in Patent Office: 2,078 Days
• CPC Class Codes: G06F 16/122 using management policies backup systems G06F11/1446; file migration policies for HSM systems G06F16/185
• CPC Class Codes: G06F 16/1724 Details of de-fragmentation performed by the file system saving storage space on storage systems G06F3/0608; management of blocks in storage devices G06F3/064
• CPC Class Codes: G06F 16/1752 based on file chunks

Abstract

Mechanisms are provided for adjusting a configuration of data stored in a storage system. According to various embodiments, a storage module may be configured to store a configuration of data. A processor may be configured to identify an estimated performance level for the storage system based on a configuration of data stored on the storage system. The processor may also be configured to transmit an instruction to adjust the configuration of data on the storage system to meet the service level objective when the estimated performance level fails to meet a service level objective for the storage system.

Claims

1. A method comprising:

determining a service characteristic of a storage system by reading or writing test data on the storage system and measuring a performance metric associated with the reading or writing;

via a processor at the storage system that includes memory and a communications interface, identifying an estimated performance level for data access on the storage system over a network through the communications interface, wherein the estimated performance level is determined based on a comparison of stored on the storage system with the service characteristic, the data stored on the storage system being at least partially deduplicated;

determining via the processor whether the estimated performance level meets a service level objective for the storage system, wherein the estimated performance level corresponds to a data access throughput level that measures a rate at which the data may be stored to or retrieved from the storage system, and wherein the rate is determined at least in part by identifying a degree of data contiguity of the data stored on the storage system; and

adjusting the data on the storage system to meet the service level objective when the estimated performance level fails to meet the service level objective for the storage system, wherein adjusting the data on the storage system involves moving one or more data segments to create a contiguous block of data, and wherein an arrangement of the data is adjusted based on a balance of an impact of deduplication on an amount of storage space used by the data with an impact of data contiguity on the estimated performance level, wherein adjusting the data on the storage system comprises performing one or more data deduplication operations on one or more of data segments to meet the service level objective so that the estimated performance level reaches a threshold objective level.

2. The method recited in claim 1, wherein the estimated performance level corresponds to a data readback throughput level that measures a rate at which the data may be retrieved from the storage system.

3. The method recited in claim 1, wherein the degree of data contiguity indicates a degree to which a plurality of related data segments are stored in contiguous blocks of memory on the storage system.

4. The method recited in claim 1, wherein the service characteristic comprises a functional relationship between two or more measurable quantities associated with accessing the storage system.

5. The method recited in claim 1, wherein adjusting the arrangement of the data segments on the storage system comprises performing one or more data defragmentation operations on the one or more data segments.

6. The method recited in claim 1, wherein the storage system comprises one or more magnetic disk drives, each magnetic disk drive including one or more magnetic disks.

7. A system comprising:

a storage module configured to store an arrangement of a plurality of data segments; and

a processor configured to;

determine a service characteristic of the storage module by reading or writing test data on the storage module and measuring a performance metric associated with the reading or writing,

identify an estimated performance level for data access on the storage system over a network through the a communications interface, wherein the estimated performance level is determined based a comparison of a plurality of data segments stored on the storage module with the service characteristic, the plurality of data segments being at least partially deduplicated,

determine whether the estimated performance level meets a service level objective for the storage system, wherein the estimated performance level corresponds to a data access throughput level that measures a rate at which the data may be stored to or retrieved from the storage system, and wherein the rate is determined at least in part by identifying a degree of data contiguity of the data stored on the storage system, and

transmit an instruction to adjust the arrangement of the plurality of data segments on the storage system to meet the service level objective when the estimated performance level fails to meet the service level objective for the storage system, wherein adjusting the arrangement of the plurality of data segments on the storage system involves moving one or more of the data segments to create a contiguous block of data, and wherein the arrangement of the plurality of data segments is adjusted based on a balance of an impact of deduplication on an amount of storage space used by the data segments with an impact of data contiguity on the estimated performance level, wherein adjusting the data on the storage system comprises performing one or more data deduplication operations on one or more of data segments to meet the service level objective so that the estimated performance level reaches a threshold objective level.

8. The system recited in claim 7, wherein the estimated performance level corresponds to a data readback throughput level that measures a rate at which the data may be retrieved from the storage module.

9. The system recited in claim 7, wherein the degree of data contiguity indicates a degree to which a plurality of related data segments are stored in contiguous blocks of memory on the storage module.

10. The system recited in claim 7, wherein the service characteristic comprises a functional relationship between two or more measurable quantities associated with accessing the storage module.

11. One or more computer readable media having instructions stored thereon for performing a method, the method comprising:

determining a service characteristic of a storage system by reading or writing test data on the storage system and measuring a performance metric associated with the reading or writing;

via a processor at the storage system that includes memory and a communications interface, identifying an estimated performance level for data access on the storage system over a network through the communications interface, wherein the estimated performance level is determined based on a comparison of a plurality of data segments stored on the storage system with the service characteristic, the plurality of data segments being at least partially deduplicated;

determining via the processor whether the estimated performance level meets a service level objective for the storage system, wherein the estimated performance level corresponds to a data access throughput level that measures a rate at which the data may be stored to or retrieved from the storage system, and wherein the rate is determined at least in part by identifying a degree of data contiguity of the data stored on the storage system; and

adjusting an arrangement of the plurality of data segments on the storage system to meet the service level objective when the estimated performance level fails to meet the service level objective for the storage system, wherein adjusting the arrangement of the plurality of data segments on the storage system involves moving one or more of the data segments to create a contiguous block of data, and wherein the arrangement of the plurality of data segments is adjusted based on a balance of an impact of deduplication on an amount of storage space used by the data segments with an impact of data contiguity on the estimated performance level, wherein adjusting the data on the storage system comprises performing one or more data deduplication operations on one or more of data segments to meet the service level objective so that the estimated performance level reaches a threshold objective level.