US 9,286,175 B2 · System and method of write hole protection for a multiple-node storage cluster

Abstract

The disclosure is directed to preserving data consistency in a multiple-node data storage system. According to various embodiments, a write log is maintained including log entries for data transfer requests being served by a respective node of the multiple-node data storage system. Rather than maintaining a full write journal of data and parity associated with each data transfer request, the log entries only need to identify portions of the virtual volume being updated according to the data transfer requests served by each node. When a first node fails, a second node takes over administration of a virtual volume for the failed node. Upon taking over for the first (failed) node, the second node resolves any inconsistencies between data and parity in portions of the virtual volume identified the respective log entries. Accordingly, write holes are prevented without substantially increasing memory usage or system complexity.

Claims20

Dependent claims

A system for preserving data consistency, comprising:

a controller for at least one node of a plurality of nodes in communication with a storage cluster, the controller being configured to:
receive a data transfer request including a request to store at least one data segment and at least one parity segment to a virtual volume defined by at least a portion of the storage cluster;
store a log entry identifying a portion of the virtual volume associated with the data transfer request in a write log;
complete the data transfer request after the log entry has been stored in the write log;
and
resolve an inconsistency between at least one data segment and at least one parity segment stored on the virtual volume by a failed node of the plurality of nodes, wherein the at least one data segment and the at least one parity segment stored by the failed node are associated with at least one log entry stored in the write log prior to failure of the failed node, and wherein resolving the inconsistency includes recalculating and overwriting parity in the at least one parity segment without comparing the at least one data segment and the at least one parity segment stored by the failed node.

3 more elements

A method of preserving data consistency, comprising:

receiving a data transfer request for at least one node of a plurality of nodes in communication with a storage cluster, wherein the data transfer request includes a request to store at least one data segment and at least one parity segment to a virtual volume defined by at least a portion of the storage cluster;
storing a log entry identifying a portion of the virtual volume associated with the data transfer request in a write log;
completing the data transfer request after the log entry has been stored in the write log;
and
resolving an inconsistency between at least one data segment and at least one parity segment stored on the virtual volume by a failed node of the plurality of nodes, wherein the at least one data segment and the at least one parity segment stored by the failed node are associated with at least one log entry stored in the write log prior to failure of the failed node, and wherein resolving the inconsistency includes recalculating and overwriting parity in the at least one parity segment without comparing the at least one data segment and the at least one parity segment stored by the failed node.

2 more elements

Dependencies are inferred from the claim text.

System and method of write hole protection for a multiple-node storage cluster

Life of this patent

System and method of write hole protection for a multiple-node storage cluster

Life of this patent

Abstract

Claims20