File replication in a distributed segmented file system
View Patent ↗A system includes storage configured to store file system entities, including directories and files, residing in segments of a distributed, segmented single file system, file servers configured to implement the single file system with separate ones of the file servers controlling metadata of separate ones of the segments, and a controller configured to control storage of files in the file system such that for a master file stored in a first segment, a first replica of the master file will be stored in a second segment that is physically separate from the first segment, the controller being further configured to control storage of directories in the file system such that a single directory will include identifiers for the master file and the first replica.
1. A system comprising:
storage configured to store file system entities, including directories and files, residing in segments of a distributed, segmented single file system;
file servers comprising at least one processor configured to implement the single file system with separate ones of the file servers controlling metadata of separate ones of the segments of the file system entities; and
a controller configured to control storage of files in the file system such that for a master file stored in a first segment, a first replica of the master file is stored in a second segment that is physically separate from the first segment, the controller being further configured to control storage of directories in the file system such that a single directory entry includes a first identifier pointing to the master file and a second identifier pointing to the first replica, wherein the controller controls storage of replica such that no replica of the master file is stored in the same segment as the master file.
2. The system of claim 1 wherein the controller is further configured such that a second replica of the master file is made and the single directory entry further includes a third identifier pointing to the second replica.
3. The system of claim 2 wherein the single directory entry includes identifiers pointing to all replicas of the master file.
4. The system of claim 1 wherein the first replica is a synchronous replica.
5. The system of claim 1 wherein the controller is further configured such that second and third replicas of the master file are made, wherein the second replica is a synchronous replica and the third replica is an asynchronous replica.
6. The system of claim 1 wherein the controller is configured to store the master file and the first replica based upon a non-hierarchical allocation policy.
7. The system of claim 1 wherein the controller is configured to reproduce an inaccessible segment using replicas in other segments of file system entities in the inaccessible segment.
8. The system of claim 1 wherein the controller is configured to determine frequently-accessed files and to make replicas of the frequently-accessed files.
9. A computer method comprising:
storing file system entities in segments of a distributed, segmented single file system, the file system entities including directories and files;
controlling metadata of the segments with file servers comprising at least one processor configured to implement the single file system, with separate ones of the file servers controlling separate ones of the segments of the file system entities;
storing using a controller configured to control storage of files and storage of directories in the file system a first replica of a master file stored in a first segment, the first replica being stored in a second segment that is physically separate from the first segment; and
storing with the controller a single directory entry including a first identifier pointing to the master file and a second identifier pointing to the first replica, wherein the controller controls storage of replica such that no replica of the master file is stored in the same segment as the master file.
10. The computer method of claim 9 further comprising:
storing a second replica of the master file; and
including a third identifier pointing to the second replica in the single directory entry.
11. The computer method of claim 10 further comprising including identifiers pointing to all replicas of the master file in the single directory entry.
12. The computer method of claim 9 wherein the first replica is a synchronous replica.
13. The computer method of claim 9 further comprising making second and third replicas of the master file, wherein the second replica is a synchronous replica and the third replica is an asynchronous replica.
14. The computer method of claim 9 further comprising storing the master file and the first replica based upon a non-hierarchical allocation policy.
15. The computer method of claim 9 further comprising producing an inaccessible segment using replicas in other segments of file system entities in the inaccessible segment.
16. The computer method of claim 9 further comprising:
determining frequently-accessed files; and
making replicas of the frequently-accessed files.