COMBINED ASYNCHRONOUS AND SYNCHRONOUS FOUNTAIN CODE STORAGE IN AN OBJECT STORE

摘要

Example apparatus and methods produce a set of rateless erasure codes (e.g., fountain codes) for a file stored in a primary data store (e.g., hard drive) or in an archive system. The archive system may store the file in a redundant array of independent disks (RAID). A first subset of the rateless erasure codes are stored in an object storage using a synchronous protocol. A second subset of rateless erasure codes are stored in the object storage using an asynchronous protocol. The object storage system may inform the archive system when desired redundancy has been achieved or when desired redundancy has been lost. The archive system may buffer rateless erasure codes before providing the codes to the object storage to improve performance. A failure in the archive system or object storage system may be mitigated by retaining the file in the primary data store until the desired redundancy is achieved.

主权项

1. A method performed in a computer storage device that provides an object store, the method comprising:
receiving a request to increase the redundancy of data stored in a first data store, where the first data store is not located in the computer storage device; receiving the data in a second data store in the computer storage device; producing a plurality of erasure codes from the data; selecting a first subset of erasure codes from the plurality of erasure codes, where the first subset provides a first degree of redundancy for the data; selecting a second subset of erasure codes from the plurality of erasure codes, where the second subset includes the erasure codes in the plurality of erasure codes that are not in the first subset of erasure codes, where the plurality of erasure codes provides a second, greater degree of redundancy for the data; storing the first subset of erasure codes in the object store using a synchronous approach; upon determining that the first subset of erasure codes has been stored in the object store, sending a first signal to the first data store indicating that the first degree of redundancy has been achieved; storing the second subset of erasure codes in the object store using an asynchronous approach; and upon determining that the entire plurality of erasure codes has been stored in the object store, sending a second signal to the first data store indicating that the second degree of redundancy has been achieved.