Storing files in a parallel computing system based on user or application specification
View Patent ↗Techniques are provided for storing files in a parallel computing system based on a user-specification. A plurality of files generated by a distributed application in a parallel computing system are stored by obtaining a specification from the distributed application indicating how the plurality of files should be stored; and storing one or more of the plurality of files in one or more storage nodes of a multi-tier storage system based on the specification. The plurality of files comprise a plurality of complete files and/or a plurality of sub-files. The specification can optionally be processed by a daemon executing on one or more nodes in a multi-tier storage system. The specification indicates how the plurality of files should be stored, for example, identifying one or more storage nodes where the plurality of files should be stored.
1. A method for storing at least one sub-file created by a distributed source application and sent by said distributed source application to a parallel computing system for storage, wherein said at least one sub-file comprises a portion of a larger file, said method comprising the steps of:
obtaining a specification from said distributed source application indicating how said at least one sub-file should be stored in said parallel computing system;
processing said specification prior to storage of said at least one sub-file to determine a placement for storing said at least one sub-file within said parallel computing system; and
storing said at least one sub-file in one or more storage nodes of a multi-tier storage system within said parallel computing system based on said placement determined from said specification.
2. The method of claim 1 , wherein said specification identifies one or more of said storage nodes where said at least one sub-file should be stored.
3. The method of claim 2 , wherein said specification indicates a replica quantity for said at least one sub-file.
4. The method of claim 2 , wherein said specification identifies one or more tiers in said multi-tier storage system for storing said at least one sub-file.
5. The method of claim 1 , wherein said specification indicates whether said at least one sub-file is compressible.
6. The method of claim 1 , wherein said specification indicates whether said at least one sub-file will be re-read.
7. The method of claim 1 , wherein said specification identifies one or more additional files that are similar to said at least one sub-file.
8. The method of claim 1 , wherein said method is implemented by a daemon executing on one or more nodes in a multi-tier storage system.
9. The method of claim 1 , further comprising the step of deleting said at least one sub-file based on said specification.
10. The method of claim 1 , further comprising the step of returning a list of said storage nodes where said at least one sub-file is stored.
11. The method of claim 1 , wherein said specification implements one or more of a policy and a schedule.
12. A computer program product comprising a tangible processor-readable recordable storage memory having encoded therein executable code of one or more software programs, wherein the one or more software programs when executed by a processor implement the steps of the method of claim 1 .
13. An apparatus for storing at least one sub-file created by a distributed source application and sent by said distributed source application to a parallel computing system for storage, wherein said at least one sub-file comprises a portion of a larger file, comprising:
a memory; and
at least one hardware device operatively coupled to the memory and configured to:
obtain a specification from said distributed source application indicating how said at least one sub-file should be stored in said parallel computing system;
process said specification prior to storage of said at least one sub-file to determine a placement for storing said at least one sub-file within said parallel computing system; and
store said at least one sub-file in one or more storage nodes of a multi-tier storage system within said parallel computing system based on said placement determined from said specification.
14. The apparatus of claim 13 , wherein said specification comprises one or more of (i) an identification of one or more of said storage nodes where said at least one sub-file should be stored; (ii) a replica quantity for said at least one sub-file; and (iii) an identification of one or more tiers in said multi-tier storage system for storing said at least one sub-file.
15. The apparatus of claim 13 , wherein said specification comprises one or more of: (i) an indication of whether said at least one sub-file is compressible; (ii) an indication of whether said at least one sub-file will be re-read; and (iii) an indication of one or more additional files that are similar to said at least one sub-file.
16. The apparatus of claim 13 , wherein said at least one hardware device comprises a daemon executing on one or more nodes in a multi-tier storage system.
17. The apparatus of claim 13 , wherein said at least one hardware device is further configured to delete said at least one sub-file based on said specification.
18. The apparatus of claim 13 , wherein said at least one hardware device is further configured to return a list of said storage nodes where said at least one sub-file is stored.
19. A data storage system for storing at least one sub-file created by a distributed source application and sent by said distributed source application to a parallel computing system for storage, wherein said at least one sub-file comprises a portion of a larger file, comprising:
a processing device configured to obtain a specification from said distributed source application indicating how said at least one sub-file should be stored in said parallel computing system; and to process said specification prior to storage of said at least one sub-file to determine a placement for storing said at least one sub-file within said parallel computing system; and store said at least one sub-file in one or more storage nodes of a multi-tier storage system within said parallel computing system based on said placement determined from said specification.
20. The data storage system of claim 19 , wherein said specification comprises one or more of (i) an identification of one or more of said storage nodes where said at least one sub-file should be stored; (ii) a replica quantity for said at least one sub-file; and (iii) an identification of one or more tiers in said multi-tier storage system for storing said at least one sub-file.
21. The data storage system of claim 19 , wherein said specification comprises one or more of: (i) an indication of whether said at least one sub-file is compressible; (ii) an indication of whether said at least one sub-file will be re-read; and (iii) an indication of one or more additional files that are similar to said at least one sub-file plurality of files.
22. The data storage system of claim 19 , wherein said processing unit comprises a daemon executing on one or more nodes in a multi-tier storage system.
23. The data storage system of claim 19 , wherein said processing unit is further configured to delete said at least one sub-file based on said specification.
24. The data storage system of claim 19 , wherein said processing unit is further configured to return a list of said storage nodes where said at least one sub-file is stored.