Western Digital Technologies, Inc.

Hgst Netherlands, B.v.

Amplidata N.v.

Carl Rene D'Halluin

Thomas Demoor

Koen De Keyser

Frederik Jacqueline Luc De Schrijver

Bastiaan Stougie

Tomy Ammuthan Cheru

Joris Custers

Jochen Maes

Frederik De Schrijver

Ameet Pyati

Romain Raymond Agnes Slootmaekers

Ruben De Zaeytijd

Nicolas Maria Sylvain Trangez

Jan Doms

Souvik Roy

Wim De Waegeneer

Lien Joke Boelaert

Nina Tang

Michael Heyvaert

Nicolas Trangez

Example distributed storage systems, replication managers, and methods provide replication barriers for dependent data transfers between data stores. An object data store may include a barrier object and be configured to identify dependencies between a dependency set of data objects and the barrier object. When replicating data objects to another data store, the dependency set of data objects may be transferred first, delaying the transfer of the barrier object while the dependency set is being transferred.

Replication barriers for dependent data transfers between data stores

Example distributed storage systems, delete managers, and methods provide for managing dependent delete operations among data stores. Dependent data operation entries and corresponding dependency sets may be identified in an operations log. Dependent data operations may be identified in each shard and data operation entries. A delete process for the data objects in the dependency set may be delayed until the delete process for the dependent data object completes.

Managing dependent delete operations among data stores

Example storage systems and methods provide data storage management using a key data store with progress values. A key data store includes a set of key data entries that each include a key value associated with a storage operation and a timestamp corresponding to a creation time of the key data entry. Storage management processes are executed on the set of key data entries and progress values for the storage management processes are tracked using the timestamps of the key data entries to manage the relative progress of the storage management processes.

Key value store using progress verification

Example distributed storage systems, replication managers, and methods provide barriers for dependent data operations among sharded data stores. Shard operation logs may be associated with different shards and storage nodes. Dependent data operations may be identified in each shard and data operation entries corresponding to dependency sets for those dependent data operations may be determined. Log-based operations may be executed by delaying execution of the dependent data operations in all shards until the dependency set data operations in all shards are completed.

Barriers for dependent operations among sharded data stores

A system, method and apparatus for storing metadata in a metadata store in a robust and efficient manner including receiving a request from a client to perform a data transaction, updating a key-value pair in a metadata store based on the request, entering the data transaction in a transaction log, updating a read cache with the key-value pair, and replicating the last transaction log entry in at least one other storage node in the metadata store.

Database read cache optimization

A system, method and apparatus for storing metadata in a metadata store in a robust and efficient manner including receiving a request from a client to perform a data transaction, updating a key-value pair in a metadata store based on the request, entering the data transaction in a transaction log, replicating the last transaction log entry in at least one other storage node in the metadata store and, in response to a threshold event, migrating a first portion of the transaction log from the a data storage medium to a second data storage medium of each of the plurality of data storage nodes.

Database transaction log migration

Example storage systems and methods provide data storage management using change values in a key data store. A key data store includes a set of key data entries that each include a key value associated with a storage operation, a precondition value, and a postcondition value. A storage parameter is calculated using the precondition value and the postcondition value for each key data entry the set of key data entries. The calculated storage parameter may be reported to manage storage configuration and operations in the storage system.

Key value store using change values for data properties

Example distributed storage systems, replication state engines, and methods manage replication state for guaranteed replication between data stores. An object data store may store data objects that have been determined for deletion and rendered inaccessible to a client application. A replication state may be queried for deleted data objects and, if the replication state indicates that replication to another object data store is incomplete, physical deletion may be delayed until the replication state indicates that replication is complete and the data object may be physically deleted.

Managing replication state for deleted objects

A novel distributed data storage system is disclosed. In an example method, a first plurality of key entries is stored in a first key data store at a first location and a second plurality of key entries is stored in a second key data at a second location. A key entry in comprises a corresponding key having an object identifier, an inverse timestamp, and a source identifier. The method further replicates a set of the first key entries to the second key data store. The method further inserts each first key entry from the set of the first key entries into the second key data store based on the object identifier, the inverse timestamp, and the source identifier of the first key included in that first key entry, the first key entries and the second key entries being interwoven to form a plurality of interwoven ordered key entries.

Conflict resolution and garbage collection in distributed databases

In an example embodiment, a method comprises determining that a multipart upload request to upload a data object in separate object parts has been received by an object storage service; generating temporary keys for the separate object parts of the data object; storing the temporary keys in a temporary key data store; generating, based on the temporary keys, a multipart key entry for the data object, the multipart key entry comprising a multipart key that contains an object identifier identifying the data object and an inverse timestamp; and inserting the multipart key entry in a persistent key data store storing an ordered set of key entries in a position determined by the object identifier and the inverse timestamp.

Key data store garbage collection and multipart object management

Example object storage systems, bookkeeping engines, and methods provide quota-based access control for control entities, such as accounts, users, and buckets. An object data store is configured to enable control entities to access data objects associated with each control entity. Quota thresholds and usage values are determined for control entities and used to determine a quota status. Quota status is used to determine data object access response based on the requesting control entities.

Object storage system with access control quota status check

Example object storage systems, meta object generators, and methods provide versioned meta objects for internal operational data that may be replicated between data object stores. A meta object may be generated that includes meta object data, such as internal operational data. A meta object identifier may be assigned to the meta object. A first version identifier may be associated with the meta object data and a second version identifier may be associated with a marker for the meta object, where the marker prevents exposure as a user data object.

Object storage system with versioned meta objects

Example storage systems and methods provide data storage management using generation markers in a key data store. A key data store includes a set of key data entries that each include a key value and a property value associated with a storage operation. An active generation of the key data entries include an active generation marker and a base generation does not. A base storage parameter is calculated from a data scan and a current storage parameter is calculated from the base storage parameter and the property values of the active generation of key data entries. The calculated storage parameter may be reported to manage storage configuration and operations in the storage system.

Key value store using generation markers

Example object storage systems, replication managers, and methods provide meta objects for priority replication of configuration data between data object stores. A meta object may be generated that includes configuration data. Data objects are selected for replication from a first replication queue. Meta objects associated with the data objects in the first replication queue are replicated, independent of the first replication queue, between object data stores.

Object storage system with priority meta object replication

In an example embodiment, a method comprises determining an ordered set of key entries; determining a first key entry for a first object in the ordered set of key entries; determining an object storage operation represented by a key of the first key entry; determining the object storage operation represented by the key of the first key entry to comprise a delete operation; and responsive to determining the object storage operation represented by the key of the first key entry to comprise the delete operation, skipping over subsequent key entries associated with the first object in the ordered set of key entries.

Growing community of inventors

Zwijnaarde, Belgium

Carl Rene D'Halluin