Hewlett Packard Enterprise Development LP

Hewlett-packard Development Company, L.p.

David Malcolm Falkinder

Richard Phillip Mayo

Peter Thomas Camble

Mark David Lillibridge

Andrew Todd

Kave Eshghi

Alastair Michael Slater

Russell Ian Monk

Ieuan James Henry

Callum Murray

Aman Sahil

Graham Perry

John M Czerkowicz

Example implementations relate to deduplication operations in a storage system. An example includes receiving data units of a backup stream to be stored in a deduplication storage system; performing a first matching operation to match the data units against a first container index of a plurality of container indexes, where the plurality of container indexes comprise metadata indicating storage locations of data units previously stored in the persistent storage; calculating a first ratio indicating the amount of deduplication that occurred during the first matching operation against the first container index; and in response to a determination that the first ratio violates a condition with respect to local ratio history data of the first container index, identifying at least one portion of the backup stream as being potentially affected by a ransomware attack.

Ransomware detection in a deduplication storage system

Example implementations relate to journals for metadata changes. An example includes detecting, by a storage controller of a deduplication storage system, a cloning operation of a manifest range; loading a journal from persistent storage into memory in response to the detected cloning operation, wherein the journal is to store changes to a container index associated with the manifest range, and wherein the container index is not loaded into the memory in response to the detected cloning operation; and updating the journal in the memory to include an indication of changes to metadata of the container index that is not loaded into the memory, wherein the changes to the metadata are associated with the detected cloning operation.

Journals for data cloning operations

Example implementations relate to metadata operations in a storage system. An example includes a machine-readable medium storing instructions that upon execution cause a processor to: receive a data stream to be stored in persistent storage of a deduplication storage system; store data units of the data stream in a container entity group object according to arrival time, where the data units of the container entity group object are referenced by a plurality of container indexes; generate a data index to list each container index that references at least one data unit included in the container entity group object; and in response to a determination that the total size of the container entity group object exceeds the threshold size, transfer the container entity group object from memory to the persistent storage.

Data index for deduplication storage system

Example implementations relate to deduplication operations in a storage system. An example includes, in response to initiation of a new backup process to store a first stream of data, initializing a temporary sparse index to be stored in a memory of a deduplication storage system; identifying a cloned portion of the first data stream; identifying at least one container index associated with the cloned portion of the first data stream; identifying a set of hook points included in the at least one container index; and populating the temporary sparse index with a set of entries, the set of entries mapping the identified set of hook points to the at least one container index.

Temporary sparse index for a deduplication storage system

Example implementations relate to metadata operations in a storage system. An example includes detecting, by a storage controller of a deduplication storage system, a housekeeping operation to perform updates to data of a set of container indexes of stored deduplicated data; in response to a detection of the housekeeping operation, the storage controller identifying, among the set of container indexes, a plurality of container indexes associated with a particular journal group, the particular journal group comprising a plurality of journals to store updates to data of the plurality of container indexes, respectively; and maintaining, by the storage controller, the particular journal group loaded in memory until all of the updates of the housekeeping operation to the plurality of container indexes have been stored in the respective journals of the particular journal group.

Journal groups for metadata housekeeping operation

Example implementations relate to metadata operations in a storage system. An example storage system includes a machine-readable storage storing instructions executable by a processor to determine to generate a synthetic full backup based on data stream representations of a plurality of data streams. The instructions are also executable to, in response to a determination to generate the synthetic full backup, create a logical group including the data stream representations. The instructions are also executable to specify a cache resource allocation for the logical group, and generate the synthetic full backup from data stream representations using an amount of a cache resource limited by the cache resource allocation for the logical group.

Resource allocation for synthetic backups

Examples implementations relate to journals for metadata changes. An example includes detecting, by a storage controller, metadata changes associated with a container index of a deduplication storage system; recording, by the storage controller, the detected metadata changes in a journal associated with the container index, where the journal is included in a journal group comprising a plurality of journals; determining, by the storage controller, whether a filled amount of the journal exceeds a fill threshold; and, in response to a determination that the filled amount of the journal does not exceed the fill threshold, writing the journal group from memory to persistent storage.

Journals to record metadata changes in a storage system

Example implementations relate to storing manifest portions in a metadata cache. An example includes receiving, by a storage controller, a read request associated with a first data unit. In response to receiving the read request, the storage controller stores a manifest portion in a metadata cache, the stored manifest portion comprising a plurality of records, the plurality of records including a first record associated with the first data unit. The storage controller determines storage information of the first data unit using pointer information included in the first record of the stored manifest portion, and replaces the pointer information in the first record with the determined storage information of the first data unit.

Metadata cache for storing manifest portion

Examples may include storage of a small object representation in a deduplication system. Examples may store the small object representation of an object in the deduplication system based on a determination that the object is smaller than a threshold size. In examples, the small object representation may include a direct reference from a top-level data structure to small object metadata in a bottom-level data structure of the small object representation.

Storage of a small object representation in a deduplication system

Example implementations relate to metadata operations in a storage system. An example method includes receiving, from a first stream process, a first write request for a first container index in memory. The method further includes, in response to a receipt of the first write request, sending a first token to the first stream process without writing the first container index to a persistent storage. The method further includes receiving, from a second stream process, a first completion request for the first container index. The method further includes, in response to a receipt of the first completion request, writing the first container index from the memory to the persistent storage.

Writing a container index to persistent storage

Example implementations relate to metadata operations in a storage system. An example includes a storage controller loading a manifest from persistent storage into memory, and loading a first container index from persistent storage into the memory. The first container index is associated with the manifest loaded into the memory. The storage controller determines whether a tracking data structure of the first container index includes an identifier of the manifest. In response to a determination that the tracking data structure of the first container index does not include the identifier of the manifest, the storage controller discards the manifest.

Container index including a tracking data structure

In some examples, in response to an event at the deduplication system, a system accesses item metadata of a backup item that is backed up to a remote object storage system, the item metadata of the backup item including range information indicating a range of identifier values for portion objects of the backup item stored in the remote object storage system. The system issues, based on the range information, requests to obtain respective attribute information of the portion objects of the backup item stored in the remote object storage system. The system determines, based on the attribute information, a name of a given portion object of the backup item already used.

Backup item metadata including range information

In some examples, region cloning may include obtaining a clone request to clone a logical range of a source backup. The clone request may specify the source backup, a logical start offset, and a logical end offset. A source manifest associated with the logical range of the source backup may be determined. A start entry of the source manifest may be identified based on the logical start offset. The start entry may represent a start data chunk. A determination may be made as to whether the logical start offset represents an intermediate position of the start data chunk, and if so, a start partial chunk entry representing a sub-range of the start data chunk may be appended to a destination manifest. A backup of the logical range of the source backup may be generated based on the destination manifest with the appended start partial chunk entry.

Region cloning for deduplication

Examples include the storage of format-aware filter format tracking states. Some examples include storage of a format tracking state for a format aware filter in a backup system in association with a backup object, access of the format tracking state from the backup system in response to detection of a potential continuation of a backup image, and applying the format-aware filter using the accessed format tracking state.

Growing community of inventors

Bristol, United Kingdom

David Malcolm Falkinder