Enhanced FSCK Mechanism for Improved Consistency in Case of Erasure Coded Object Storage Architecture Built Using Clustered File System

Patent metadata

Field	Value
Publication number	US-2018293265-A1
Application number	US-201715481044-A
Country	US
Kind code	A1
Filing date	Apr 6, 2017
Priority date	Apr 6, 2017
Publication date	Oct 11, 2018
Grant date	—

Abstract

A mechanism is provided in a data processing system comprising at least one processor and at least one memory, the at least one memory comprising instructions which are executed by the at least one processor and configure the processor to implement a file system consistency check utility on an erasure coded object storage architecture. Responsive to the file system consistency check utility determining a directory entry does not exist for a given file inode, the mechanism determines whether the given file is part of an erasure code schema of an object storage architecture. Responsive to the file system consistency check utility determining the given file/fragment is part of the erasure code schema, the mechanism determines a container (parent directory) for the given erasure code fragment, wherein the given fragment is a given error code fragment of an object, based on other erasure code fragments corresponding to the object and their placement schematics in the erasure code schema. Responsive to the file system consistency check utility determining the directory, the mechanism updates the directory entry with details of the given error code fragment.

First claim

What is claimed is:

1 . A method, in a data processing system comprising at least one processor and at least one memory, the at least one memory comprising instructions which are executed by the at least one processor and configure the processor to implement a file system consistency check utility on an erasure coded object storage architecture, the method comprising:
responsive to the file system consistency check utility determining a directory entry does not exist for a given file, determining whether the given file is part of an erasure code schema of an object storage architecture; responsive to the file system consistency check utility determining the given file is part of the erasure code schema, determining a directory for the given file, wherein the given file is a given error code fragment of an object, based on other erasure code fragments corresponding to the object and their placement schematics in the erasure code schema; and responsive to the file system consistency check utility determining the directory, updating a directory entry for the directory with details of the given error code fragment.

2 . The method of claim 1 , wherein determining whether the given file is part of the erasure code schema comprises obtaining the error code schema from a proxy layer configuration of the object storage architecture.

3 . The method of claim 1 , wherein the details of the given error code fragment comprise an error code fragment name and an error code fragment inode identifier.

4 . The method of claim 1 , further comprising:
responsive to the file system consistency check utility determining the given file is not part of the erasure code schema, placing the given file in a “lost+found” directory.

5 . The method of claim 1 , further comprising:
responsive to the file system consistency check utility determining a directory does exist for the given file, correcting metadata of an inode of the given file.

6 . The method of claim 1 , further comprising:
determining locations of a plurality of error code fragments of the object; gathering all inodes corresponding to the plurality of error code fragments including the given error code fragment; and passing the inodes to the file system consistency check utility.

7 . The method of claim 1 , further comprising:
responsive to determining that a workload of a namespace associated with a given file system is online cloud storage, collecting a snapshot of the given file system; executing the file system consistency check utility on the snapshot of the given file system; responsive to determining that original inodes of the given file system have changed, collecting inodes with corruptions, counting a number of corruptions, and responsive to the number of corruptions exceeding a threshold, taking the given file system offline and performing, by the file system consistency check utility, inode metadata corrections on the inodes with corruptions.

8 . The method of claim 7 , further comprising:
responsive to determining that the original inodes of the given file system have not changed, applying fixes to the original inodes based on a relationship between the original inodes and inodes in the snapshot data.

9 . The method of claim 7 , further comprising:
responsive to determining that the workload of the namespace associated with the given file system is not online cloud storage, taking the given file system offline and executing the file system consistency check utility on the given file system offline.

10 . The method of claim 7 , further comprising:
responsive to the number of corruptions not exceeding a threshold, prompting a user to indicate whether to take the file system offline to perform metadata corrections.

11 . A computer program product comprising a computer readable storage medium having a computer readable program stored therein, wherein the computer readable program, when executed on a computing device, causes the computing device to implement a file system consistency check utility on an erasure coded object storage architecture, wherein the computer readable program causes the computing device to:
responsive to the file system consistency check utility determining a directory does not exist for a given file, determine whether the given file is part of an erasure code schema of an object storage architecture; responsive to the file system consistency check utility determining the given file is part of the erasure code schema, determine a directory for the given file, wherein the given file is a given error code fragment of an object, based on other erasure code fragments corresponding to the object and their placement schematics in the erasure code schema; and responsive to the file system consistency check utility determining the directory, update a directory entry for the directory with details of the given error code fragment.

12 . The computer program product of claim 11 , wherein determining whether the given file is part of the erasure code schema comprises obtaining the error code schema from a proxy layer configuration of the object storage architecture.

13 . The computer program product of claim 11 , wherein the details of the given error code fragment comprise an error code fragment name and an error code fragment inode identifier.

14 . The computer program product of claim 11 , wherein the computer readable program further causes the computing device to:
responsive to the file system consistency check utility determining the given file is not part of the erasure code schema, place the given file in a “lost+found” directory.

15 . The computer program product of claim 11 , wherein the computer readable program further causes the computing device to:
responsive to the file system consistency check utility determining a directory does exist for the given file, correct metadata of an inode of the given file.

16 . The computer program product of claim 11 , wherein the computer readable program further causes the computing device to:
determine locations of a plurality of error code fragments of the object; gather all inodes corresponding to the plurality of error code fragments including the given error code fragment; and pass the inodes to the file system consistency check utility.

17 . The computer program product of claim 11 , wherein the computer readable program further causes the computing device to:
responsive to determining that a workload of a namespace associated with a given file system is online cloud storage, collect a snapshot of the given file system; execute the file system consistency check utility on the snapshot of the given file system; responsive to determining that original inodes of the given file system have changed, collect inodes with corruptions, count a number of corruptions, and responsive to the number of corruptions exceeding a threshold, take the given file system offline and perform, by the file system consistency check utility, inode metadata corrections on the inodes with corruptions.

18 . The computer program product of claim 17 , wherein the computer readable program further causes the computing device to:
responsive to determining that the original inodes of the given file system have not changed, apply fixes to the original inodes based on a relationship between the original inodes and inodes in the snapshot data.

19 . The computer program product of claim 17 , wherein the computer readable program further causes the computing device to:
responsive to determining

Assignees

• IBM

Inventors

• Eda Sasikanth
• Ghuge Deepak R
• Pancha Huzefa H
• Patil Sandeep R

Classifications

• G06F16/2365 Primary

  Ensuring data consistency and integrity · CPC title

• G06F16/162

  Delete operations (erasing in storage systems G06F3/0652) · CPC title

• G06F17/30144

  Physics · mapped topic

• G06F17/30371 Primary

  Physics · mapped topic

• G06F17/3007

  Physics · mapped topic