Methods and systems for storing information that facilitates the reconstruction of at least some of the contents of a storage unit on a storage system

Abstract

The failure of a storage unit in a storage array of a storage system may render the storage unit unresponsive to any requests. Any writes to the storage system that occur during the failure of the storage unit will not be reflected on the failed unit, rendering some of the failed unit's data stale. Assuming the failed unit's data is not corrupted but is just stale, a partial rebuild may be performed on the failed unit, selectively reconstructing only data that is needed to replace the stale data. Described herein are techniques for storing information that identifies the data that needs to be rebuilt. When the storage unit fails, the segment identifier associated with the last data segment written to the storage system may be stored. Upon the storage unit recovering, the storage system can rebuild only those data segments whose identifier is greater than the stored segment identifier.

Description

RELATED APPLICATIONS[0001]This application is a Continuation of U.S. application Ser. No. 14 / 446,191 filed on Jul. 29, 2014, incorporated herein by reference.FIELD OF THE INVENTION[0002]The present invention relates to methods and systems for reconstructing at least some of the contents of a storage unit following the failure of the storage unit, and more particularly relates to efficiently storing information that facilitates such reconstruction process.BACKGROUND[0003]In a storage system with a plurality of storage units, data is often stored in a redundant manner. When one or more of the storage units experiences a failure and its associated data is lost, data redundancy allows the data of the failed storage units to be recovered from the operational storage units (assuming there is sufficient redundancy). While it is certainly beneficial that data on a failed storage unit can be recovered, there are certain costs (and concerns) associated with the data recovery process.[0004]Fir...

AI Technical Summary

Benefits of technology

The patent describes a method for rebuilding data on a failed storage unit in a log structured file system. The system uses a persistent storage to store information about the failed unit and the data segments that were written to it. When the unit is recovered, the system can refer to the persistent storage to rebuild only the data segments that were written before the failure. This helps to minimize the amount of data that needs to be rewritten and reduces the time needed for the rebuilding process. The system can also use a segment map to associate segment identifiers with stripe numbers, which helps to determine which data to rebuild on the failed unit. Overall, this method improves the efficiency and speed of rebuilding data on a failed storage unit in a log structured file system.

Problems solved by technology

While it is certainly beneficial that data on a failed storage unit can be recovered, there are certain costs (and concerns) associated with the data recovery process.

First, data recovery consumes resources of the storage system that would otherwise be available to process read and / or write requests of a host.

Such reads and processing of a data recovery process may increase the time it takes for a storage system to respond to read and write requests from a host.

Second, the longer the data recovery process takes, the longer the storage system operates in a degraded mode of operation.

Further, a reduced level of data redundancy makes the storage system more vulnerable to permanent data loss.

Such approach, of course, is not always possible.

In other words, a failure of a storage unit may render the storage unit unresponsive to any read or write requests, but its data is left intact.

Upon recovery of the failed storage unit, the problem is that any writes to the storage system that occurred during the failure of the storage unit will not be reflected on the failed storage unit, rendering some of its data “stale”.

While a partial rebuild is preferable to a full rebuild (reducing the amount of time that the system is in a degraded mode of operation and reducing the processing of the storage system), a tradeoff is that the storage system is required to keep track of which data needs to be rebuilt, which takes additional resources as compared to a full rebuild process.

Images