Systems, methods and devices for performing efficient patrol read operations in a storage system

• US 10,001,947 B1
• Filed: 05/02/2016
• Issued: 06/19/2018
• Est. Priority Date: 05/08/2015
• Status: Active Grant

• Current Assignee: AmZetta Technologies, LLC (American Megatrends International, LLC)
• Original Assignee: American Megatrends Incorporated
• Inventors: Chatterjee, Paresh, Ranganathan, Loganathan, Mallavaram, Venugopalreddy, Gopalakrishnan, Sankarji
• Primary Examiner(s): Torres, Joseph D
• Application Number:
  US15/143,851
• Time in Patent Office: 778 Days
• CPC Class Codes: G06F 11/1076 Parity data used in redundant arrays of independent storages, e.g. in RAID systems
• CPC Class Codes: G06F 3/0619 in relation to data integrity, e.g. data losses, bit errors
• CPC Class Codes: G06F 3/0631 by allocating resources to storage systems
• CPC Class Codes: G06F 3/0653 Monitoring storage devices or systems
• CPC Class Codes: G06F 3/0689 Disk arrays, e.g. RAID, JBOD
• CPC Class Codes: G11C 2029/0409 Online test
• CPC Class Codes: G11C 29/52 Protection of memory contents; Detection of errors in memory contents

Abstract

An example computer-implemented method for performing efficient patrol read operations in a storage system including a plurality of disks organized in a RAID array can include determining an I/O load on the storage system, identifying at least one portion of an available storage capacity containing valid data and reading the portion of the available storage capacity containing the valid data. Optionally, the portion of the available storage capacity containing the valid data is the only portion read during the patrol read operations. The method can also include determining whether a medium error exists in the portion of the available storage capacity containing the valid data. If a medium error exists, the method can include fixing the medium error. Additionally, the above operations can optionally be performed only when the I/O load on the storage system is less than a predetermined threshold.

Claims

1. A computer-implemented method for performing efficient patrol read operations in a storage system including a plurality of disks organized in a RAID array, the method comprising:

determining an input/output (“

I/O”

) load on the storage system;

identifying at least one portion of an available storage capacity of the storage system containing valid data by querying a distributed volume management layer to request one or more allocated provisions containing valid data;

reading the portion of the available storage capacity of the storage system containing the valid data;

determining whether a medium error exists in the portion of the available storage capacity of the storage system containing the valid data; and

if a medium error exists, fixing the medium error, wherein reading the portion of the available storage capacity of the storage system containing the valid data, determining whether a medium error exists in the portion of the available storage capacity of the storage system containing the valid data and fixing the medium error are performed only when the I/O load on the storage system is less than a predetermined threshold.

2. The computer-implemented method of claim 1, wherein identifying at least one portion of an available storage capacity of the storage system containing valid data further comprises receiving mapping information corresponding to one or more allocated portions of the available storage capacity.

3. The computer-implemented method of claim 2, wherein the mapping information identifies at least one RAID stripe storing written data.

4. The computer-implemented method of claim 3, wherein the mapping information comprises a RAID stripe bitmap.

5. The computer-implemented method of claim 1, wherein reading the portion of the available storage capacity of the storage system containing the valid data further comprises:

issuing a READ VERIFY small-computer systems interface (“

SCSI”

) command to the storage system; and

receiving an acknowledgement to the READ VERIFY SCSI command from the storage system.

6. The computer-implemented method of claim 1, wherein fixing the medium error further comprises, if the medium error exists in a parity chunk of a RAID stripe, reading a data chunk of the RAID stripe, computing the parity chunk of the RAID stripe, and writing the parity chunk of the RAID stripe.

7. The computer-implemented method of claim 1, wherein fixing the medium error further comprises, if the medium error exists in a data chunk of a RAID stripe, reading one or more data chunks and a parity chunk of the RAID stripe containing the medium error.

8. The computer-implemented method of claim 1, further comprising wherein dynamically controlling a rate or speed of the patrol read operations based on the I/O load on the storage system.

9. The computer-implemented method of claim 8, wherein determining an I/O load on the storage system further comprises using information lifecycle management (“

ILM”

) statistics for the storage system.

10. A non-transitory computer-readable recording medium having computer-executable instructions stored thereon for performing efficient patrol read operations in a storage system including a plurality of disks organized in a RAID array that, when executed by a storage server computer, cause the storage server computer to:

determine an input/output (“

I/O”

) load on the storage system;

identify at least one portion of an available storage capacity of the storage system containing valid data by querying a distributed volume management layer to request one or more allocated provisions containing valid data;

read the portion of the available storage capacity of the storage system containing the valid data;

determine whether a medium error exists in the portion of the available storage capacity of the storage system containing the valid data; and

if a medium error exists, fix the medium error, wherein reading the portion of the available storage capacity of the storage system containing the valid data, determining whether a medium error exists in the portion of the available storage capacity of the storage system containing the valid data and fixing the medium error are performed only when the I/O load on the storage system is less than a predetermined threshold.

11. The non-transitory computer-readable recording medium of claim 10, wherein identifying at least one portion of an available storage capacity of the storage system containing valid data further comprises receiving mapping information corresponding to one or more allocated portions of the available storage capacity.

12. The non-transitory computer-readable recording medium of claim 11, wherein the mapping information identifies at least one RAID stripe storing written data.

13. The non-transitory computer-readable recording medium of claim 12, wherein the mapping information comprises a RAID stripe bitmap.

14. The non-transitory computer-readable recording medium of claim 10, wherein reading the portion of the available storage capacity of the storage system containing the valid data further comprises:

issuing a READ VERIFY small-computer systems interface (“

SCSI”

) command to the storage system; and

receiving an acknowledgement to the READ VERIFY SCSI command from the storage system.

15. The non-transitory computer-readable recording medium of claim 10, wherein fixing the medium error further comprises, if the medium error exists in a parity chunk of a RAID stripe, reading a data chunk of the RAID stripe, computing the parity chunk of the RAID stripe, and writing the parity chunk of the RAID stripe.

16. The non-transitory computer-readable recording medium of claim 10, wherein fixing the medium error further comprises, if the medium error exists in a data chunk of a RAID stripe, reading one or more data chunks and a parity chunk of the RAID stripe containing the medium error.

17. The non-transitory computer-readable recording medium of claim 10, having further computer-executable instructions stored thereon that, when executed by the storage server computer, cause the storage server computer to dynamically control a rate or speed of the patrol read operations based on the I/O load on the storage system.

18. A storage server computer for performing efficient patrol read operations in a storage system, the storage system including a plurality of disks organized in a RAID array, the storage server computer comprising:

a processing unit; and

a memory operably coupled to the processing unit, the memory having computer-executable instructions stored thereon that, when executed by the processing unit, cause the storage server computer to;

determine an input/output (“

I/O”

) load on the storage system;

identify at least one portion of an available storage capacity of the storage system containing valid data by querying a distributed volume management layer to request one or more allocated provisions containing valid data;

read the portion of the available storage capacity of the storage system containing the valid data;

determine whether a medium error exists in the portion of the available storage capacity of the storage system containing the valid data; and

if a medium error exists, fix the medium error, wherein reading the portion of the available storage capacity of the storage system containing the valid data, determining whether a medium error exists in the portion of the available storage capacity of the storage system containing the valid data and fixing the medium error are performed only when the I/O load on the storage system is less than a predetermined threshold.

19. The storage server computer of claim 18, wherein identifying at least one portion of an available storage capacity of the storage system containing valid data further comprises receiving mapping information corresponding to one or more allocated portions of the available storage capacity.

20. The storage server computer of claim 19, wherein the mapping information identifies at least one RAID stripe storing written data.