Oracle International Corporation

Sridhar Valaguru

Unmesh Rathi

Santosh Sugur

Techniques for providing efficient space management in writable snapshots are disclosed. The techniques include dividing available storage in a filesystem into one or more contiguous allocation unit (AU) chunks. Each AU chunk includes a set of contiguous fixed-size AUs, wherein each AU includes a series of contiguous fixed-size blocks. Each AU chunk also includes a set of contiguous AU mappings, wherein each AU mapping represents a different AU. The techniques also include storing, in a first AU mapping, a first snapshot identifier for a snapshot of the filesystem to indicate allocation of a first AU represented by the first AU mapping to the snapshot. The techniques further include allocating a first block in the first AU to the snapshot by incrementing, in the first AU mapping, a reference count that tracks a number of blocks in the first AU that are allocated to the snapshot.

Efficient space management for high performance writable snapshots

The present disclosure describes systems and methods for enhancing the space utilization of storing keys in hierarchical data structures, such as B+Tree leaf blocks, by partially or fully compressing the keys. Partially compressing the keys may include storing certain keys as offsets from a start key. Fully compressing the keys may include setting a 'type' value included in the header of the leaf block to a value indicating that the keys are implicitly represented by an ordinal key index, which defines the ordinal arrangement of keys in the leaf block. Partially or fully compressing keys, according to the implementations described herein, reduces the amount of space needed to store keys in a leaf block of a B+Tree.

Systems and methods for compressing keys in hierarchical data structures

Techniques for providing high-performance writable snapshots in data storage systems are disclosed. The techniques include storing a set of snapshots containing changes to a data set over time in a set of allocation units containing a series of contiguous blocks. A set of metadata blocks in the allocation units is used to track a state of data stored in the series of contiguous blocks. Ownership of the allocation units by the snapshots is also tracked in a set of allocation unit mappings between the allocation units and a set of snapshot identifiers representing the snapshots. The allocation unit mappings and metadata blocks are then used to execute writes to the data set and free blocks in the snapshots.

Growing community of inventors

Sunnyvale, CA, United States of America

Sridhar Valaguru