Pure Storage, Inc.

Dirk Meister

Subramaniam Periyagaram

Ronald S Karr

Alexei Potashnik

Tejal Joshi Chakeres

Prudhvi Lokireddy

Reese Robertson

Yisha Zhao

David A Grunwald

Cary A Sandvig

Zoheb Shivani

Chu Zhang

Matthew Paul Fay

Dilip Kumar Uppugandla

Chu Zang

Omer Asad

Cheng Chang

An illustrative data storage system is configured to replicate, from a source storage system to a target storage system, a pod that includes a file system constructed of block objects. The pod may be a storage system construct that groups storage entities within a namespace and supports operations on the storage entities as a group. The block objects may store metadata for individual files and directories of the file system and may support random read-write access to blocks of data associated with the files and directories of the file system.

Replicating a file system

Cost considerate placement of data within a pool of storage resources, including: receiving one or more data objects for storage; selecting, based at least upon a storage policy and upon one or more characteristics of storage data, one or more storage classes from among a plurality of storage classes of one or more data storage services, wherein the storage policy specifies parameters for one or more of: storage costs, storage operation response time, data resiliency, or service level agreement specifications; and storing the one or more data objects to the selected one or more storage classes of the one or more data storage services.

Cost considerate placement of data within a pool of storage resources

An illustrative data storage system establishes path sets that represent relationships between service layer entities and storage layer entities associated with service layer entities. The data storage system coordinates, based on the path sets and on operations applied to one or more of the service layer entities, implementation of the operations on the storage layer entities. The path sets may be used to support implementation of snapshots, space accounting, and/or other operations of the data storage system.

Managing directory-tree operations in file storage

Tiering snapshots across different storage tiers, including: creating a snapshot of a dataset, wherein the snapshot includes user data and metadata; offloading the snapshot of the dataset to a first storage level storage system; and migrating, in accordance with a lifecycle policy and via one or more copy offload operations, the snapshot from the first storage level storage system to a second storage level storage system.

Tiering snapshots across different storage tiers

An illustrative system is configured to optimize a transfer of a file system from a source storage system to a target storage system. For example, the system, in association with the transfer, determines that a copy of a collection of blocks containing data of block objects of the file system is already stored at the target storage system. In certain examples, an identifier referencing the collection of blocks is shared by the source and target storage systems and is used to determine that the copy of the collection of blocks containing data of block objects of the file system is already stored at the target storage system. The system uses the copy of the collection of blocks already stored at the target storage system instead of transferring the collection of blocks from the source storage system to the target storage system as part of the transfer.

Optimizing a transfer of a file system

An illustrative data storage system captures snapshots of a data structure based on snapshot creation schedules and sets retention periods for the snapshots based on snapshot retention schedules. The data storage system eradicates snapshots based on expirations of the retention periods. In certain examples, the data storage system determines a rule to use to capture a snapshot based on a state of snapshots within one or more lookback periods and/or based on a set of rules each defining a snapshot capture schedule and a snapshot retention schedule.

Snapshot management in a storage system

An illustrative unified data storage method includes providing, by a data storage system, block containers that represent a linear address space of blocks; and using, by the data storage system, the block containers to store content for a plurality of different data storage services. In certain examples, the different data storage services include at least one of a file storage service, an object storage service, or a database service.

Unified storage on block containers

Cost conscious garbage collection, including: selecting one or more storage classes from among a plurality of storage classes of one or more data storage services for storing one or more data objects; determining, for the one or more data objects stored in the one or more data storage services, an estimated quantity of data eligible for garbage collection; and initiating, after determining that resources for continued storage of the one or more data objects exceed resources for performing garbage collection on the data eligible for garbage collection and based upon an expected cost savings based on storage cost savings from performing garbage collection compared against access cost expenses for performing one or more cloud-based operations to perform the garbage collection, garbage collection on the one or more data objects in the one or more data storage services.

Cost conscious garbage collection

Protecting data stored on a storage system through the use of different storage levels, including: creating a snapshot of a dataset stored on a storage system, wherein the snapshot includes user data and metadata, and wherein the metadata describes the storage layout of the dataset, offloading the snapshot to a first storage level storage system, and migrating, in accordance with a lifecycle policy, the snapshot from the first storage level storage system onto a second storage level storage system.

Metadata-based replication of a dataset

Storage management within a cloud-based data store, including: receiving one or more data objects for storage; selecting, based at least upon a storage policy and upon one or more characteristics of storage data, one or more storage classes from among a plurality of storage classes of one or more data storage services; and storing the one or more data objects to the selected one or more storage classes of the one or more data storage services.

Growing community of inventors

Mountain View, CA, United States of America

Dirk Meister