Back to results
US 11,385,980 B2Granted
Methods and systems for rapid failure recovery for a distributed storage system
AssigneeWeka.IO Ltd.
InventorsMaor Ben Dayan, Omri Palmon, Liran Zvibel
Life of this patent
Estimating the term…
Abstract
Methods and systems are provided for rapid failure recovery for a distributed storage system for failures by one or more nodes.
Claims20
A method for recovering from a server failure, comprising:
- determining that a first server is inaccessible;
- performing a degraded mode read when a read request is directed to the inaccessible first server;
- redirecting a write request to another server when the write request is directed to the inaccessible first server;
- determining whether a wait time has elapsed since the determination of the first server to be inaccessible, wherein the wait time starts when the first server is determined to be inaccessible;
- after the wait time has elapsed, rebuilding data blocks that are in the inaccessible first server, wherein before rebuilding:
- each of the data blocks in the inaccessible first server is associated with a particular stripe of a first plurality of stripes,
- each stripe of the first plurality of stripes spans a different set of servers, and
- each different set of servers comprises at least two servers;
- selecting a second server to replace the inaccessible first server;
- and
- storing the rebuilt data blocks in the second server, wherein after rebuilding:
- each stripe of a second plurality of stripes comprises at least one data block in the second server,
- each stripe of the second plurality of stripes spans a different set of servers, and
- each different set of servers comprises at least two servers.
11 more elements
A system comprising a plurality of storage devices controlled by a plurality of servers, comprising:
- one or more processors configured to determine that a first server is inaccessible, wherein:
- each of the data blocks in the inaccessible first server is associated with a particular stripe of a plurality of stripes,
- each stripe of the plurality of stripes spans a different set of servers, and
- each different set of servers comprises at least two servers;
- and
- when the first server is determined to be inaccessible:
- the one or more processors are configured to:
- set the system to a degraded mode read for a read request to the first server;
- set the system to redirect a write request to the first server to other servers;
- determine whether a wait time has elapsed since determination of the first server to be inaccessible;
- and
- when the wait time is determined to have elapsed:
- the one or more processors are configured to:
- rebuild data blocks that are in the first server;
- determine a second server to replace the first server;
- and
- store the rebuilt data blocks in the second server.
14 more elements
Dependencies are inferred from the claim text.