Deleting content in a distributed computing environment

• US 8,775,373 B1
• Filed: 05/21/2009
• Issued: 07/08/2014
• Est. Priority Date: 05/21/2008
• Status: Active Grant

• Current Assignee: Qualcomm, Inc.
• Original Assignee: TransLattice, Inc.
• Inventors: Ross, Robert F., Caudill, Harrison B.
• Primary Examiner(s): Shmatov, Alexey
• Assistant Examiner(s): PARK, GRACE A
• Application Number:
  US12/454,851
• Time in Patent Office: 1,874 Days
• Field of Search: 707/612
• US Class Current: 707/612
• CPC Class Codes: G06F 16/162 Delete operations erasing in storage systems G06F3/0652
• CPC Class Codes: G06F 16/2272 Management thereof
• CPC Class Codes: G06F 16/2282 Tablespace storage structures; Management thereof
• CPC Class Codes: G06F 9/5083 Techniques for rebalancing the load in a distributed system
• CPC Class Codes: H04L 41/30 Decision processes by autonomous network management units using voting and bidding
• CPC Class Codes: H04L 67/1001 for accessing one among a plurality of replicated servers
• CPC Class Codes: H04L 67/1008 based on parameters of servers, e.g. available memory or workload monitoring of computer activity G06F11/30
• CPC Class Codes: H04L 67/1034 Reaction to server failures by a load balancer
• CPC Class Codes: H04L 67/1095 Replication or mirroring of data, e.g. scheduling or transport for data synchronisation between network nodes
• CPC Class Codes: H04L 67/1097 for distributed storage of data in networks, e.g. transport arrangements for network file system [NFS], storage area networks [SAN] or network attached storage [NAS]

Abstract

Deleting content is disclosed. A delete request is received for a file that is distributed with a plurality of nodes. The file is replaced with a first delete token. A determination is made as to whether all nodes in the plurality of nodes have replaced their respective copies of the file with first delete tokens. The file is deleted.

Claims

1. A method for deleting content comprising:

receiving at a first node a delete request for a file, a primary copy of which is stored on each of at least a subset of a plurality of nodes, wherein at least one other node of the plurality of nodes has received the delete request for the file;

replacing the file at the first node with a first delete token, the first delete token comprising data identifying one or more nodes comprising the plurality of nodes on which a primary copy of the file is stored;

determining at a second node of the plurality of nodes that the second node does not have a record of the file;

in response at least in part to a determination by the second node that at least some other nodes in the plurality of nodes have replaced their respective copies of the file with first delete tokens, adding a first delete token for the file in records associated with the second node;

determining, based at least in part on the first node receiving successful responses from all other nodes in the plurality of nodes in response to the request, that all other nodes in the plurality of nodes have replaced their respective copies of the file with first delete tokens;

in response at least in part to the determination that all other nodes in the plurality of nodes have replaced their respective copies of the file with first delete tokens;

causing an entry associated with the file to be removed from a distributed index by the first node; and

replacing the first delete token at the first node with a second delete token;

determining by the first node that at least some other nodes in the plurality of nodes have replaced their respective first delete tokens with second delete tokens;

in response to the determination by the first node that at least some other nodes in the plurality of nodes have replaced their respective first delete tokens with second delete tokens, removing the second delete token from the first node;

determining by the second node that at least some other nodes in the plurality of nodes have replaced their respective first delete tokens with second delete tokens; and

in response to the determination by the second node that at least some other nodes in the plurality of nodes have replaced their respective first delete tokens with second delete tokens, not adding a second delete token for the file in the records associated with the second node.

2. The method of claim 1, wherein the first delete token includes a list of the other nodes in the plurality of nodes, wherein the list of other nodes is usable to find all other nodes in the plurality of nodes that should also have first delete tokens.

3. The method of claim 1, wherein the delete request is generated by a user.

4. The method of claim 1, wherein the delete request is generated by an application.

5. The method of claim 1, in response to the delete request for the file, further comprising disabling a cached copy of the file at the first node.

6. The method of claim 5, wherein the primary copy of the file is different from the cached copy of the file.

7. The method of claim 1, wherein portions of the distributed index are stored by at least a subset of the plurality of nodes and wherein causing the entry associated with the file to be removed from the distributed index by the first node includes:

determining at the first node whether the first node stores a portion of the distributed index that includes the entry associated with the file;

in the event that the first node does store the portion of the distributed index that includes the entry associated with the file, removing the entry associated with the file from the portion of the distributed index at the first node; and

in the event that the first node does not store the portion of the distributed index that includes the entry associated with the file, sending a request from the first node to another node that does store the portion of the distributed index to remove the entry associated with the file from the portion of the distributed index.

8. A system for deleting content, comprising:

a processor configured to;

receive at a first node a delete request for a file, a primary copy of which is stored on each of at least a subset of a plurality of nodes, wherein at least one other node of the plurality of nodes has received the delete request for the file;

replace the file at the first node with a first delete token, the first delete token comprising data identifying one or more nodes comprising the plurality of nodes on which a primary copy of the file is stored;

determine at a second node of the plurality of nodes that the second node does not have a record of the file;

in response at least in part to a determination by the second node that at least some other nodes in the plurality of nodes have replaced their respective copies of the file with first delete tokens, add a first delete token for the file in records associated with the second node;

determine, based at least in part on the first node receiving successful responses from all other nodes in the plurality of nodes in response to the request, that all other nodes in the plurality of nodes have replaced their respective copies of the file with first delete tokens;

in response at least in part to the determination that all other nodes in the plurality of nodes have replaced their respective copies of the file with first delete tokens;

cause an entry associated with the file to be removed from a distributed index by the first node; and

replace the first delete token at the first node with a second delete token;

determine by the first node that at least some other nodes in the plurality of nodes have replaced their respective first delete tokens with second delete tokens;

in response to the determination by the first node that at least some other nodes in the plurality of nodes have replaced their respective first delete tokens with second delete tokens, remove the second delete token from the first node;

determine by the second node that at least some other nodes in the plurality of nodes have replaced their respective first delete tokens with second delete tokens; and

in response to the determination by the second node that at least some other nodes in the plurality of nodes have replaced their respective first delete tokens with second delete tokens, do not add a second delete token for the file in the records associated with the second node; and

a memory coupled to the processor and configured to provide the processor with instructions.

9. The system of claim 8, wherein the first delete token includes a list of the other nodes in the plurality of nodes, wherein the list of other nodes is usable to find all other nodes in the plurality of nodes that should also have first delete tokens.

10. The system of claim 8, wherein the delete request is generated by a user.

11. The system of claim 8, wherein the delete request is generated by an application.

12. The system of claim 8, in response to the delete request for the file, wherein the processor is further configured to disable a cached copy of the file at the first node.

13. The system of claim 12, wherein the primary copy of the file is different from the cached copy of the file.

14. The system of claim 8, wherein portions of the distributed index are stored by at least a subset of the plurality of nodes and wherein causing the entry associated with the file to be removed from the distributed index by the first node includes the processor being configured to:

determine at the first node whether the first node stores a portion of the distributed index that includes the entry associated with the file;

in the event that the first node does store the portion of the distributed index that includes the entry associated with the file, remove the entry associated with the file from the portion of the distributed index at the first node; and

in the event that the first node does not store the portion of the distributed index that includes the entry associated with the file, send a request from the first node to another node that does store the portion of the distributed index to remove the entry associated with the file from the portion of the distributed index.

15. A computer program product for deleting content, the computer program product being embodied in a non-transitory computer readable storage medium and comprising computer instructions for:

receiving at a first node a delete request for a file, a primary copy of which is stored on each of at least a subset of a plurality of nodes, wherein at least one other node of the plurality of nodes has received the delete request for the file;

replacing the file at the first node with a first delete token, the first delete token comprising data identifying one or more nodes comprising the plurality of nodes on which a primary copy of the file is stored;

determining at a second node of the plurality of nodes that the second node does not have a record of the file;

in response at least in part to a determination by the second node that at least some other nodes in the plurality of nodes have replaced their respective copies of the file with first delete tokens, adding a first delete token for the file in records associated with the second node;

determining, based at least in part on the first node receiving successful responses from all other nodes in the plurality of nodes in response to the request, that all other nodes in the plurality of nodes have replaced their respective copies of the file with first delete tokens;

in response at least in part to the determination that all other nodes in the plurality of nodes have replaced their respective copies of the file with first delete tokens;

causing an entry associated with the file to be removed from a distributed index by the first node; and

replacing the first delete token at the first node with a second delete token;

determining by the first node that at least some other nodes in the plurality of nodes have replaced their respective first delete tokens with second delete tokens;

in response to the determination by the first node that at least some other nodes in the plurality of nodes have replaced their respective first delete tokens with second delete tokens, removing the second delete token from the first node;

determining by the second node that at least some other nodes in the plurality of nodes have replaced their respective first delete tokens with second delete tokens; and

in response to the determination by the second node that at least some other nodes in the plurality of nodes have replaced their respective first delete tokens with second delete tokens, not adding a second delete token for the file in the records associated with the second node.

16. The computer program product of claim 15, wherein the first delete token includes a list of the other nodes in the plurality of nodes, wherein the list of other nodes is usable to find all other nodes in the plurality of nodes that should also have first delete tokens.

17. The computer program product of claim 15, wherein the delete request is generated by a user.

18. The computer program product of claim 15, wherein the delete request is generated by an application.

19. The computer program product of claim 15, in response to the delete request for the file, further comprising disabling a cached copy of the file at the first node.

20. The computer program product of claim 19, wherein the primary copy of the file is different from the cached copy of the file.

21. The computer program product of claim 15, wherein portions of the distributed index are stored by at least a subset of the plurality of nodes and wherein causing the entry associated with the file to be removed from the distributed index by the first node includes:

determining at the first node whether the first node stores a portion of the distributed index that includes the entry associated with the file;

in the event that the first node does store the portion of the distributed index that includes the entry associated with the file, removing the entry associated with the file from the portion of the distributed index at the first node; and

in the event that the first node does not store the portion of the distributed index that includes the entry associated with the file, sending a request from the first node to another node that does store the portion of the distributed index to remove the entry associated with the file from the portion of the distributed index.