Abstract: A disclosed method is performed at a fault-tolerant object-based storage system including M data storage entities, each is configured to store data on an object-basis. The method includes obtaining a request to store N copies of a data object and in response, storing the N copies of the data object across the M data storage entities, where the N copies are distributed across the M data storage entities. The method additionally includes generating a first parity object for a first subset of M copies of the N copies of the data object, where the first parity object is stored on a first parity storage entity separate from the M data storage entities. The method also includes generating a manifest linking the first parity object with one or more other subsets of M copies of the N copies of the data object.

Abstract: Various implementations of hard disk track management method, device, and system disclosed herein enable improvements of file system write bandwidth. In various implementations, a method is performed at a disk storage including a file controller controlling a disk drive with a disk platter that is divided into multiple regions including a fast region. In various implementations, the method includes receiving a write request associated with data to be written to the disk drive and in response, determining a disk utilization of the disk drive. In various implementations, the method further includes placing the disk drive in a surge mode to write the data to the fast region upon determining that the disk utilization is above a first threshold, and placing the disk drive in a non-surge mode to write the data to other regions of the multiple regions upon determining that the disk utilization is below a second threshold.

Abstract: Various implementations disclosed herein provide fault-tolerant enterprise object storage system that can store small objects. In various implementations, the fault-tolerant enterprise object storage system writes a small object into an aggregate object that is distributed across a plurality of storage entities. In some implementations, the small object is at least an order of magnitude smaller than the aggregate object, and the small object is within the same order of magnitude of a block unit addressable within each of the storage entities. In some implementations, based on the small object, the storage system updates the parity data associated with the aggregate object in response to writing the small object into the aggregate object. In various implementations, the storage system updates a processed data end offset indicator that indicates that the parity data for the aggregate object includes valid data up to and including the small object.

Abstract: A disclosed method is performed at a fault-tolerant object-based storage system including M data storage entities, each is configured to store data on an object-basis. The method includes obtaining a request to store N copies of a data object and in response, storing the N copies of the data object across the M data storage entities, where the N copies are distributed across the M data storage entities. The method additionally includes generating a first parity object for a first subset of M copies of the N copies of the data object, where the first parity object is stored on a first parity storage entity separate from the M data storage entities. The method also includes generating a manifest linking the first parity object with one or more other subsets of M copies of the N copies of the data object.

Abstract: Various implementations of hard disk track management method, device, and system disclosed herein enable improvements of file system write bandwidth. In various implementations, a method is performed at a disk storage including a file controller controlling a disk drive with a disk platter that is divided into multiple regions including a fast region. In various implementations, the method includes receiving a write request associated with data to be written to the disk drive and in response, determining a disk utilization of the disk drive. In various implementations, the method further includes placing the disk drive in a surge mode to write the data to the fast region upon determining that the disk utilization is above a first threshold, and placing the disk drive in a non-surge mode to write the data to other regions of the multiple regions upon determining that the disk utilization is below a second threshold.

Abstract: A disclosed method is performed at a fault-tolerant object-based storage system configured to synthesize parity data in order to protect stored data from loss, the fault-tolerant object storage system including a plurality of storage entities each configured to store data on an object-basis. The method includes determining a first parity value for a first data block set of one or more data block sets, wherein the first data block set comprises one or more respective data blocks, each respective data block associated with a respective storage entity of the plurality of storage entities. The method further includes generating a first compressed parity indicator for the first data block set, corresponding to the first parity value, and storing the first compressed parity indicator in a stripe of parity data in place of the first parity value within a first block set comprising the first data block set.

Abstract: In some implementations, a method includes, at a latency reduction system configured to reduce latency in writing data to one or more storage entities that are each configured to store data on an object-basis, receiving a scheduling request associated with a write operation. The method also includes determining a wait period for the write operation, where the wait period is less than or equal to the difference between a client-defined operation threshold and an operation completion time of the write operation and determining an operation start time for the write operation, based in part on the wait period.

Abstract: In some implementations, a method includes, at a latency reduction system configured to reduce latency in writing data to one or more storage entities that are each configured to store data on an object-basis, receiving a scheduling request associated with a write operation. The method also includes determining a wait period for the write operation, where the wait period is less than or equal to the difference between a client-defined operation threshold and an operation completion time of the write operation and determining an operation start time for the write operation, based in part on the wait period.

Abstract: Various implementations disclosed herein enable writing a number of copies of object data or parity data associated with a data segment to a storage system. For example, in various implementations, a method of writing a number of copies of object data or parity data associated with a data segment is performed by a first storage entity of the storage system. In various implementations, the first storage entity includes a non-transitory computer readable storage medium and one or more processors. In various implementations, the method includes obtaining a data segment from an ingest entity in response to a request to write a number of copies of object data or parity data, determining whether the request is to write object data or parity data, and in response to determining that the request is to write object data, writing the number of copies of object data according to a shared resource utilization threshold.

Abstract: In some implementations, a method includes, at a latency reduction system configured to reduce latency in writing data to one or more storage entities that are each configured to store data on an object-basis, receiving a scheduling request associated with a write operation. The method also includes determining a wait period for the write operation, where the wait period is less than or equal to the difference between a client-defined operation threshold and an operation completion time of the write operation and determining an operation start time for the write operation, based in part on the wait period.

Abstract: Various implementations disclosed herein provide fault-tolerant enterprise object storage system that can store small objects. In various implementations, the fault-tolerant enterprise object storage system writes a small object into an aggregate object that is distributed across a plurality of storage entities. In some implementations, the small object is at least an order of magnitude smaller than the aggregate object, and the small object is within the same order of magnitude of a block unit addressable within each of the storage entities. In some implementations, based on the small object, the storage system updates the parity data associated with the aggregate object in response to writing the small object into the aggregate object. In various implementations, the storage system updates a processed data end offset indicator that indicates that the parity data for the aggregate object includes valid data up to and including the small object.

Abstract: In some implementations, a method includes, at a latency reduction system configured to reduce latency in writing data to one or more storage entities that are each configured to store data on an object-basis, receiving a scheduling request associated with a write operation. The method also includes determining a wait period for the write operation, where the wait period is less than or equal to the difference between a client-defined operation threshold and an operation completion time of the write operation and determining an operation start time for the write operation, based in part on the wait period.

Abstract: A disclosed method is performed at a fault-tolerant object-based storage system configured to synthesize parity data in order to protect stored data from loss, the fault-tolerant object storage system including a plurality of storage entities each configured to store data on an object-basis. The method includes determining a first parity value for a first data block set of one or more data block sets, wherein the first data block set comprises one or more respective data blocks, each respective data block associated with a respective storage entity of the plurality of storage entities. The method further includes generating a first compressed parity indicator for the first data block set, corresponding to the first parity value, and storing the first compressed parity indicator in a stripe of parity data in place of the first parity value within a first block set comprising the first data block set.