Pro-active self-healing in a distributed file system
AssigneeRed Hat, Inc.
InventorsPranith Kumar Karampuri, Anand Vishweswaran Avati, Vijay Bellur
Life of this patent
Estimating the term…
Abstract
A first server identifies a second server connecting to a cluster of servers in a file system. The first server examines a file in a replication directory hierarchy in the second server. The file has not been accessed by a client application. The first server determines, prior to the file being accessed by the client application that the file on the second server has stale data and overwrites the stale data in the file on the second server with current data.
Claims17
A method comprising:
- locating, by the processing device of a first server, an image file in a replication directory hierarchy in a second server;
- determining, prior to a first request to access the image file by a client application after the second server is coupled to a cluster of servers in a file system, that a first region of the image file comprises stale data indicating at least a portion of data is out of date;
- acquiring, by the processing device, a partial lock on the first region of the image file while write access is provided on a second region of the image file not comprising the stale data;
- and
- updating the stale data with current data.
A non-transitory computer-readable medium having instructions encoded thereon that, when executed by a processing device, cause the processing device to:
- locate, by the processing device, an image file in a replication directory hierarchy in a server;
- determine, prior to a first request to access the image file by a client application after the server is coupled to a cluster of servers in a first system, that a first region of the image file comprises stale data indicating at least a portion of data is out of date;
- acquire a partial lock on the first region of the image file while write access is provided on a second region of the image file not comprising the stale data;
- and
- update the stale data in the image file with current data.
A system comprising:
- a memory;
- and
- a processing device operatively coupled to the memory, the processing device to:
- locate an image file in a replication directory hierarchy in a server;
- determine, prior to a first request to access the image file by a client application after the server is coupled to a cluster of servers in a file system, that a first region of the image file comprises stale data indicating at least a portion of data is out of date;
- acquire a partial lock on the first region of the image file while write access is provided on a second region of the image file not comprising the stale data;
- and
- update the stale data with current data.
Dependencies are inferred from the claim text.