An apparatus includes a computing node and a metadata server. The computing node may transmit a request to open a file to the metadata server, which may provide a corresponding file identifier to the computing node. The computing node may use the file identifier to directly access the storage storin
An apparatus includes a computing node and a metadata server. The computing node may transmit a request to open a file to the metadata server, which may provide a corresponding file identifier to the computing node. The computing node may use the file identifier to directly access the storage storing the file. In one embodiment, the storage may be an object-based storage. The storage may receive the file identifier with an access command and may perform the mapping from file identifier to storage blocks internally. Thus, accesses to the storage may be performed on an arbitrary boundary within the file. In other words, the entire block including the data needed by the computing node may not be transferred to the computing node. Instead, the storage may select the data requested from the file (e.g. via an offset and a number of bytes or some similar mechanism) and return that data to the computing node.
대표청구항▼
1. An apparatus comprising:a computing node configured to generate a request to open a file, wherein said computing node is configured not to cache data from said file; a storage; and a metadata server coupled to receive said request, wherein said metadata server is configured to provide at least a
1. An apparatus comprising:a computing node configured to generate a request to open a file, wherein said computing node is configured not to cache data from said file; a storage; and a metadata server coupled to receive said request, wherein said metadata server is configured to provide at least a first file identifier corresponding to said file responsive to said request, said first file identifier identifying at least a portion of said file within said storage, and wherein said metadata server is further configured to provide a device identifier identifying said storage on an interconnect to which at least said computing node and said storage are coupled; wherein said computing node is coupled to receive said first file identifier and said device identifier for directly accessing said storage on said interconnect, and wherein said computing node is configured to transmit an access command to said storage to close said file, and wherein said storage is configured to transmit an indication to said metadata server including said first file identifier to inform said metadata server of said file being closed. 2. The apparatus as recited in claim 1 wherein said metadata server is configured to assign an access key to said request.3. The apparatus as recited in claim 2 wherein said computing node is coupled to receive said access key, and wherein said computing node is configured to transmit said access key with an access command to said storage.4. The apparatus as recited in claim 3 wherein said storage is coupled to receive said access key from said metadata server, and wherein said storage is configured to validate said access key from said computing node.5. The apparatus as recited in claim 1 wherein said request includes a file name of said file.6. The apparatus as recited in claim 5 wherein said metadata server includes a directory, and wherein said directory maps said file name to said first file identifier.7. The apparatus as recited in claim 1 wherein said computing node is configured to transmit an access command to said storage to access one or more bytes, and wherein a number of said one or more bytes affected by said access command is not equal to a block size of said storage.8. The apparatus as recited in claim 1 further comprising said interconnect, wherein said computing node, said metadata server, and said storage are each coupled directly to said interconnect.9. The apparatus as recited in claim 8 wherein said computing node is configured to transmit said request to said metadata server through said interconnect, and wherein said computing node is configured to receive said first file identifier and said device identifier from said metadata server through said interconnect.10. A method comprising:generating a request to open a file from a computing node; providing at least a first file identifier corresponding to said file from a metadata server responsive to said request, said first file identifier corresponding to said file and identifying said file within a storage storing at least a portion of said file; providing a device identifier identifying said storage on an interconnect to which at least said computing node and said storage are coupled, the providing responsive to said request; directly accessing said storage from said computing node on said interconnect responsive to said first file identifier and said device identifier, wherein said computing node is configured not to cache data from said file; said computing node transmitting an access command to said storage to close said file; and said storage transmitting an indication to said metadata server including said first file identifier to inform said metadata server of said file being closed. 11. The method as recited in claim 10 further comprising assigning an access key to said computing node responsive to said generating said request.12. The method as recited in claim 11 further comprising transmitting said access key from said computing node to said storage with an access command for said storage.13. The method as recited in claim 12 further comprising: receiving said access key from said metadata server into said storage; receiving said access key from said computing node into said storage; and validating said access key from said computing node using said access key from said metadata server.14. The method as recited in claim 10 wherein said directly accessing comprises generating an access command for one or more bytes and transmitting said access command to said storage, wherein a number of said one or more bytes does not equal a block size of said storage.15. The apparatus as recited in claim 1 wherein said interconnect comprises one or more devices configured to route communications on said interconnect, and wherein said one or more devices are configured to use said device identifier to route communications from said computing node to said storage.16. The apparatus as recited in claim 1 wherein said storage is configured to detect direct accesses by said computing node to said storage on said interconnect using said device identifier.17. The method as recited in claim 10 wherein said interconnect comprises one or more devices configured to route communications on said interconnect, and wherein the method further comprises said one or more devices using said device identifier to route communications from said computing node to said storage.18. The method as recited in claim 10 further comprising said storage detecting direct accesses by said computing node to said storage on said interconnect using said device identifier.19. The apparatus as recited in claim 1 wherein said storage is an object-based storage.20. An apparatus comprising:a computing node configured to generate a request to open a file, wherein said computing node is configured not to cache data from said file; a storage; and a metadata server coupled to receive said request, wherein said metadata server is configured to provide, responsive to said request: (i) at least a first file identifier corresponding to said file, wherein said first file identifier identifies at least a portion of said file within said storage; (ii) a device identifier identifying said storage on an interconnect to which at least said computing node and said storage are coupled; and (iii) an access key assigned by said metadata server to said computing node for said file; wherein said metadata server is further configured to provide said access key to both said storage and said computing node; and wherein said computing node is coupled to receive said first file identifier, said access key, and said device identifier for directly accessing said storage on said interconnect, and wherein said computing node is configured to transmit an access command to said storage to access said file, and wherein said access command includes said first file identifier, said device identifier, and said access key, and wherein said storage is configured to verify access by said computing node to said file using said access key. 21. The apparatus as recited in claim 20 wherein said access key is encrypted.22. The apparatus as recited in claim 20 wherein said access key includes one or more permissions for said computing node for accessing said file.23. The apparatus as recited in claim 20 wherein said access command accesses one or more bytes on said storage, and wherein a number of said one or more bytes affected by said access command is not equal to a block size of said storage.24. The apparatus as recited in claim 20 further comprising said interconnect, wherein said computing node, said metadata server, and said storage are each coupled directly to said interconnect.25. The apparatus as recited in claim 24 wherein said computing node is configured to transmit said request to said metadata server through said interconnect, and wherein said computing node is configured to receive said first file identifier, said device identifier, and said access key from said metadata server through said interconnect.26. The apparatus as recited in claim 20 wherein said storage is an object-based storage.
연구과제 타임라인
LOADING...
LOADING...
LOADING...
LOADING...
LOADING...
이 특허에 인용된 특허 (25)
Kumar, Subbarao Ravi, Caching pattern and method for caching in an object-oriented programming environment.
Senator Steven T. ; Fuller Billy J., Computer system method and apparatus providing for various versions of a file without requiring data copy or log operati.
Ali Seifu ; Burket Thomas G. ; Hu Tawei ; Kozina Gerald Edward ; Lee Thomas S., Distributed storage management system having a cache server and method therefor.
Napolitano Richard ; Silverman Herbert W. ; Juzsczak Chester ; Panner Bryan K. ; Franklin Chris ; Noya Eric S. ; Hoskins Timothy Lee ; Luke Stanley ; Shaughnessy Paul Richard ; McLeod Alexander C. ; , File array storage architecture having file system distributed across a data processing platform.
Uresh K. Vahalia ; Xiaoye Jiang ; Jeffrey Jon Darcy ; Boris Zuckerman ; Ronald Curtis Searls, File manager providing distributed locking and metadata management for shared data access by clients relinquishing locks after time period expiration.
Xiaoye Jiang ; Uresh K. Vahalia ; Uday Gupta ; Percy Tzelnic, File server system using connection-oriented protocol and sharing data sets among data movers.
Xu Yikang ; Vahalia Uresh K. ; Jiang Xiaoye ; Gupta Uday ; Tzelnic Percy, File server system using file system storage, data movers, and an exchange of meta data among data movers for file locking and direct access to shared file systems.
Steven R. Soltis ; Matthew T. O'Keefe ; Thomas M. Ruwart ; Gerald A. Houlder ; James A. Coomes ; Michael H. Miller ; Edward A. Soltis ; Raymond W. Gilson ; Kenneth W. Preslan, Global file system and data storage device locks.
Irwin ; Jr. Basil L. (Longmont CO) Kitts David L. (Fraser CO) Ruff Craig R. (Boulder CO) Sloan John L. (Arvada CO), Mass storage system for file-systems.
Laura Margaret Bostian ; John Lee Brooks ; William James Schoen ; Jimmy Paul Strickland ; Walter James Kincaid, Read/write data sharing of DASD data, including byte file system data, in a cluster of multiple data processing systems.
Loaiza Juan R. ; Macnaughton Neil ; Bamford Roger J. ; Bridge William H. ; Klots Boris, Sharing, updating data blocks among multiple nodes in a distributed system.
Madhav Mutalik ; John Deshayes ; Ananthan Pillai ; Ajay Shekhar ; Benoit J. Merlet ; Faith M. Senie, System and method for backing up data stored in multiple mirrors on a mass storage subsystem under control of a backup server.
Kisley, Richard V.; Knight, Philip D., Distributed file serving architecture system with metadata storage virtualization and data access at the data server connection speed.
Kisley, Richard V.; Knight, Philip D., Distributed file serving architecture system with metadata storage virtualization and data access at the data server connection speed.
Kisley, Richard Victor; Knight, Philip Douglas, Distributed file serving architecture system with metadata storage virtualization and data access at the data server connection speed.
Kisley, Richard Victor; Knight, Philip Douglas, Distributed file serving architecture with metadata storage and data access at the data server connection speed.
Vainstein, Klimenty; Nath, Satyajit; Ouye, Michael Michio, Method and apparatus for transitioning between states of security policies used to secure electronic documents.
Vainstein, Klimenty; Nath, Satyajit; Ouye, Michael Michio, Method and apparatus for transitioning between states of security policies used to secure electronic documents.
Huang, Weiqing; Supramaniam, Senthilvasan; Vainstein, Klimenty, Method and system for implementing changes to security policies in a distributed security system.
Huang, Weiqing; Supramaniam, Senthilvasan; Vainstein, Klimenty, Method and system for implementing changes to security policies in a distributed security system.
Coates, Joshua L.; Bozeman, Patrick E.; Landrum, Alfred Gary; Mattis, Peter D.; Nalam, Naveen; Roselli, Drew S., Methods and apparatus for load balancing storage nodes in a distributed storage area network system.
Coates,Joshua L.; Bozeman,Patrick E.; Gautier,Taylor, Methods and apparatus for off loading content servers through direct file transfer from a storage center to an end-user.
Garcia, Denis Jacques Paul; Ouye, Michael Michio; Rossmann, Alain; Crocker, Steven Toye; Gilbertson, Eric; Huang, Weiqing; Humpich, Serge; Vainstein, Klimenty; Ryan, Nicholas Michael, Methods and systems for providing access control to secured data.
Garcia, Denis Jacques Paul; Ouye, Michael Michio; Rossmann, Alain; Crocker, Steven Toye; Gilbertson, Eric; Huang, Weiqing; Humpich, Serge; Vainstein, Klimenty; Ryan, Nicholas Michael, Methods and systems for providing access control to secured data.
Garcia, Denis Jacques Paul; Ouye, Michael Michio; Rossmann, Alain; Crocker, Steven Toye; Gilbertson, Eric; Huang, Weiqing; Humpich, Serge; Vainstein, Klimenty; Ryan, Nicholas Michael, Methods and systems for providing access control to secured data.
Garcia, Denis Jacques Paul; Ouye, Michael Michio; Rossmann, Alain; Crocker, Steven Toye; Gilbertson, Eric; Huang, Weiqing; Humpich, Serge; Vainstein, Klimenty; Ryan, Nicholas Michael, Methods and systems for providing access control to secured data.
Kazar, Michael; Jernigan, IV, Richard P.; Sanzi, Jr., Richard N., Storage system architecture for striping data container content across volumes of a cluster.
Corbett, Peter F.; Jernigan, IV, Richard P.; Vully, Vani; Ramani, Balaji; Simharajan, Srishylam; Eisler, Michael; Kazar, Michael, System and method for addressing data containers using data set identifiers.
Eisler, Michael; Nydick, Daniel S.; Corbett, Peter F.; Kazar, Michael; Wagner, J. Christopher, System and method for enabling a data container to appear in a plurality of locations in a super-namespace.
Kazar, Michael; Jernigan, IV, Richard P.; Sanzi, Jr., Richard N.; Hyer, Jr., Robert Wyckoff, System and method for multi-tiered meta-data caching and distribution in a clustered computer environment.
Hyer, Jr., Robert Wyckoff; Derr, Todd; Edwards, John K., System and method for performing distributed consistency verification of a clustered file system.
Jiang, Tianyu; Jernigan, IV, Richard P.; Hamilton, Eric, System and method for providing space availability notification in a distributed striped volume set.
Jiang, Tianyu; Jernigan, IV, Richard P.; Hamilton, Eric, System and method for providing space availability notification in a distributed striped volume set.
※ AI-Helper는 부적절한 답변을 할 수 있습니다.