Deleting a file from a distributed filesystem

• US 9,678,968 B1
• Filed: 02/15/2013
• Issued: 06/13/2017
• Est. Priority Date: 05/03/2010
• Status: Active Grant

• Current Assignee: Panzura, Inc.
• Original Assignee: Panzura, Inc.
• Inventors: Chou, Randy Yen-pang, Davis, Andrew P., Taylor, John Richard
• Primary Examiner(s): Rahman, Sm
• Application Number:
  US13/769,194
• Time in Patent Office: 1,579 Days
• Field of Search: 709219
• CPC Class Codes: G06F 11/1435 using file system or storage system metadata
• CPC Class Codes: G06F 11/2089 Redundant storage control functionality
• CPC Class Codes: G06F 11/2094 Redundant storage or storage space G06F11/2056 takes precedence
• CPC Class Codes: G06F 16/128 Details of file system snapshots on the file-level, e.g. snapshot creation, administration, deletion use of snapshots for error detection or correction G06F11/14, G06F11/16
• CPC Class Codes: G06F 16/162 Delete operations erasing in storage systems G06F3/0652
• CPC Class Codes: G06F 16/1827 Management specifically adapted to NAS management of storage area networks [SAN] G06F3/067
• CPC Class Codes: G06F 16/27 Replication, distribution or synchronisation of data between databases or within a distributed database system; Distributed database system architectures therefor
• CPC Class Codes: G06F 2201/85 Active fault masking without idle spares active fault masking without idle spare hardware where processing functionality is redundant G06F11/2035
• CPC Class Codes: G06F 3/0608 Saving storage space on storage systems
• CPC Class Codes: G06F 3/061 Improving I/O performance
• CPC Class Codes: G06F 3/0652 Erasing, e.g. deleting, data cleaning, moving of data to a wastebasket
• CPC Class Codes: G06F 3/067 Distributed or networked storage systems, e.g. storage area networks [SAN], network attached storage [NAS]

Abstract

The disclosed embodiments disclose techniques for deleting a file from a distributed filesystem. Two or more cloud controllers collectively manage distributed filesystem data that is stored in one or more cloud storage systems; the cloud controllers store metadata for the distributed filesystem, and cache and ensure data consistency for the data stored in the cloud storage systems. During operation, a cloud controller receives a request from a client to delete a file from the distributed filesystem. The cloud controller updates a user view of the distributed filesystem to present the appearance of the target file being deleted to the client, and then initiates a background deletion operation to delete the target file without negatively affecting the performance of the other users of the distributed filesystem.

Claims

1. A computer-implemented method for deleting a file from a distributed filesystem, the method comprising:

collectively managing the data of the distributed filesystem using two or more cloud controllers, wherein the cloud controllers store metadata for the distributed filesystem;

collectively presenting a unified namespace for the distributed filesystem to the clients of the distributed filesystem via the two or more cloud controllers, wherein the clients access the distributed filesystem via the cloud controllers, wherein the file data for the distributed filesystem is stored in the cloud storage system, wherein each cloud controller caches a subset of the file data from the remote cloud storage system that is being actively accessed by that cloud controller'"'"'s respective clients, wherein new file data received by each cloud controller from its clients is written to the remote cloud storage system via the receiving cloud controller;

maintaining at each cloud controller a copy of the metadata for the files stored in the distributed filesystem, wherein changes to the metadata for the distributed filesystem are synchronized across the cloud controllers, wherein synchronizing metadata includes synchronizing deduplication information across the cloud controllers, wherein each cloud controller maintains a deduplication table that tracks deduplicated data for the distributed filesystem;

receiving at a cloud controller a request from a client to delete a target file in the distributed filesystem;

updating a user view of the distributed filesystem to present an appearance of the target file being deleted to clients of the cloud controller;

notifying the set of cloud controllers of the pending delete of the target file via an incremental metadata snapshot, wherein upon receiving the incremental metadata snapshot the other cloud controllers in the set of cloud controllers also present an appearance of the target file being deleted to their clients to ensure that the delete operation is consistent across the distributed filesystem; and

initiating a background deletion operation across the cloud controllers to delete the target file without negatively affecting the performance of other users of the distributed filesystem, wherein the background deletion operation comprises using the incremental metadata snapshot to update the deduplication tables across the set of cloud controllers to reflect deduplication updates for the deletion of the target file.

2. The computer-implemented method of claim 1, wherein collectively managing the data of the distributed filesystem comprises:

upon receiving in a cloud controller new data from a client, sending from the cloud controller the incremental metadata snapshot for the new data, wherein the incremental metadata snapshot is received by the other cloud controllers of the distributed filesystem;

storing the data for the distributed filesystem in one or more cloud storage systems, wherein the cloud controllers cache and ensure data consistency for data stored in the cloud storage systems; and

sending an incremental data snapshot containing the new data from the cloud controller to a cloud storage system.

3. The computer-implemented method of claim 2,

wherein the cloud controller maintains a snapshot hierarchy that comprises a set of file metadata that tracks the set of data that is currently stored in the distributed filesystem;

wherein the snapshot directory also includes samples over time of the metadata tree for the distributed filesystem that indicate how the metadata for the distributed filesystem has changed historically;

wherein an overlay for the snapshot directory maintains the user view of the distributed filesystem by tracking a portion of the distributed filesystem that is actively visible to the client; and

wherein the user view of the filesystem might not include all of the data that is currently stored in the distributed filesystem.

4. The computer-implemented method of claim 3, wherein presenting the appearance of the target file being deleted to the client comprises:

removing a link from the overlay to the metadata for the target file in the snapshot hierarchy, thereby making the target file no longer visible to the client but not actually deleting any data associated with the target file; and

generating the incremental metadata snapshot that reflects the change to the overlay to the other cloud controllers of the distributed filesystem to make the target file invisible to other clients of the distributed filesystem.

5. The computer-implemented method of claim 4, wherein initiating the background deletion operation comprises:

traversing the target file'"'"'s metadata in the snapshot hierarchy to retrieve a deduplication hash value from the metadata for each of the one or more data blocks of the target file; and

adding each retrieved deduplication hash value to a deduplication update list to decrement the reference count for each data block in the target file.

6. The computer-implemented method of claim 5, where initiating the background deletion operation further comprises:

subsequent to retrieving the deduplication hash values for all of the data blocks of the target file, removing the metadata for the target file from the snapshot hierarchy; and

generating a third incremental metadata snapshot that notifies the other cloud controllers of the distributed filesystem that the metadata for the target file has been deleted from the snapshot hierarchy.

7. The computer-implemented method of claim 6, where adding retrieved deduplication hash values to the deduplication update list further comprises using the deduplication update list to update the deduplication table, which tracks the reference counts for each data block stored in the distributed filesystem.

8. The computer-implemented method of claim 7, wherein updating the deduplication table further comprises determining whether the updated reference count for a given data block is zero, and if so:

updating a tracking structure for a cloud file containing the given data block to indicate that the given data block is no longer referenced;

using the tracking structure for the cloud file to determine whether all of the data blocks in the cloud file are no longer referenced, and if so, adding the cloud file to a list of cloud files to be deleted.

9. The computer-implemented method of claim 8, where the method further comprises determining whether an unreferenced data block from the target file is currently being cached by the cloud controller, and if so, deleting the unreferenced data block from the cache of the cloud controller.

10. The computer-implemented method of claim 8, where the method further comprises sending the identifier for a cloud file to be deleted to the cloud storage system in a delete request.

11. The computer-implemented method of claim 10, wherein the operations of traversing the metadata of the target file to add retrieved deduplication hash values to the deduplication update list, updating the deduplication table, determining cloud files to be deleted, and deleting cloud files execute as low-priority asynchronous background jobs to ensure that delete operations do not adversely affect the performance of other users of the distributed filesystem.

12. The computer-implemented method of claim 11, wherein one or more actions for the background deletion operation are delayed by the cloud controller to ensure that the delete request was not erroneous.

13. The computer-implemented method of claim 12, wherein a locality policy for the cloud controller:

specifies a delay for the background deletion operation;

specifies that a notification be sent to alert at least one cloud controller or client of a pending delete; and

specifies that a moderation request be sent to a user of the distributed filesystem prior to performing the background deletion operation.

14. A non-transitory computer-readable storage medium storing instructions that when executed by a computer cause the computer to perform a method for deleting a file from a distributed filesystem, the method comprising:

collectively managing the data of the distributed filesystem using two or more cloud controllers, wherein the cloud controllers store metadata for the distributed filesystem;

collectively presenting a unified namespace for the distributed filesystem to the clients of the distributed filesystem via the two or more cloud controllers, wherein the clients access the distributed filesystem via the cloud controllers, wherein the file data for the distributed filesystem is stored in the cloud storage system, wherein each cloud controller caches a subset of the file data from the remote cloud storage system that is being actively accessed by that cloud controller'"'"'s respective clients, wherein new file data received by each cloud controller from its clients is written to the remote cloud storage system via the receiving cloud controller;

maintaining at each cloud controller a copy of the metadata for the files stored in the distributed filesystem, wherein changes to the metadata for the distributed filesystem are synchronized across the cloud controllers, wherein synchronizing metadata includes synchronizing deduplication information across the cloud controllers, wherein each cloud controller maintains a deduplication table that tracks deduplicated data for the distributed filesystem;

receiving at a cloud controller a request from a client to delete a target file in the distributed filesystem;

updating a user view of the distributed filesystem to present an appearance of the target file being deleted to clients of the cloud controller;

notifying the set of cloud controllers of the pending delete of the target file via an incremental metadata snapshot, wherein upon receiving the incremental metadata snapshot the other cloud controllers in the set of cloud controllers also present an appearance of the target file being deleted to their clients to ensure that the delete operation is consistent across the distributed filesystem; and

initiating a background deletion operation across the cloud controllers to delete the target file without negatively affecting the performance of other users of the distributed filesystem, wherein the background deletion operation comprises using the incremental metadata snapshot to update the deduplication tables across the set of cloud controllers to reflect deduplication updates for the deletion of the target file.

15. The non-transitory computer-readable storage medium of claim 14, wherein collectively managing the data of the distributed filesystem comprises:

upon receiving in a cloud controller new data from a client, sending from the cloud controller the incremental metadata snapshot for the new data, wherein the incremental metadata snapshot is received by the other cloud controllers of the distributed filesystem;

storing the data for the distributed filesystem in one or more cloud storage systems, wherein the cloud controllers cache and ensure data consistency for data stored in the cloud storage systems; and

sending an incremental data snapshot containing the new data from the cloud controller to a cloud storage system.

16. The non-transitory computer-readable storage medium of claim 15,

wherein the cloud controller maintains a snapshot hierarchy that comprises a set of file metadata that tracks the set of data that is currently stored in the distributed filesystem;

wherein the snapshot directory also includes samples over time of the metadata tree for the distributed filesystem that indicate how the metadata for the distributed filesystem has changed historically;

wherein an overlay for the snapshot directory maintains the user view of the distributed filesystem by tracking a portion of the distributed filesystem that is actively visible to the client; and

wherein the user view of the filesystem might not include all of the data that is currently stored in the distributed filesystem.

17. The non-transitory computer-readable storage medium of claim 16, wherein presenting the appearance of the target file being deleted to the client comprises:

removing a link from the overlay to the metadata for the target file in the snapshot hierarchy, thereby making the target file no longer visible to the client but not actually deleting any data associated with the target file; and

generating the incremental metadata snapshot that reflects the change to the overlay to the other cloud controllers of the distributed filesystem to make the target file invisible to other clients of the distributed filesystem.

18. The non-transitory computer-readable storage medium of claim 17, wherein initiating the background deletion operation comprises:

traversing the target file'"'"'s metadata in the snapshot hierarchy to retrieve a deduplication hash value from the metadata for each of the one or more data blocks of the target file; and

adding each retrieved deduplication hash value to a deduplication update list to decrement the reference count for each data block in the target file.

19. The non-transitory computer-readable storage medium of claim 18, where initiating the background deletion operation further comprises:

subsequent to retrieving the deduplication hash values for all of the data blocks of the target file, removing the metadata for the target file from the snapshot hierarchy; and

generating a third incremental metadata snapshot that notifies the other cloud controllers of the distributed filesystem that the metadata for the target file has been deleted from the snapshot hierarchy.

20. A cloud controller that deletes a file from a distributed filesystem, comprising:

a processor;

a storage mechanism that stores metadata for the distributed filesystem; and

a storage management mechanism;

wherein two or more cloud controllers collectively manage the data of the distributed filesystem, wherein collectively managing the data of the distributed filesystem comprises;

collectively presenting a unified namespace for the distributed filesystem to the clients of the distributed filesystem via the two or more cloud controllers, wherein the clients access the distributed filesystem via the cloud controllers, wherein the file data for the distributed filesystem is stored in the cloud storage system, wherein each cloud controller caches a subset of the file data from the remote cloud storage system that is being actively accessed by that cloud controller'"'"'s respective clients, wherein new file data received by each cloud controller from its clients is written to the remote cloud storage system via the receiving cloud controller; and

maintaining at each cloud controller a copy of the metadata for the files stored in the distributed filesystem, wherein changes to the metadata for the distributed filesystem are synchronized across the cloud controllers, wherein synchronizing metadata includes synchronizing deduplication information across the cloud controllers, wherein each cloud controller maintains a deduplication table that tracks deduplicated data for the distributed filesystem;

wherein the cloud controller is configured to receive a request from a client to delete a target file in the distributed filesystem;

wherein the storage management mechanism is configured to update a user view of the distributed filesystem to present an appearance of the target file being deleted to clients of the cloud controller;

wherein the storage management mechanism is configured to notify the set of cloud controllers of the pending delete of the target file via an incremental metadata snapshot, wherein upon receiving the incremental metadata snapshot the other cloud controllers in the set of cloud controllers also present an appearance of the target file being deleted to their clients to ensure that the delete operation is consistent across the distributed filesystem; and

wherein the storage management mechanism is further configured to initiate a background deletion operation across the cloud controllers to delete the target file without negatively affecting the performance of other users of the distributed filesystem, wherein the background deletion operation comprises using the incremental metadata snapshot to update the deduplication tables across the set of cloud controllers to reflect deduplication updates for the deletion of the target file.