Hewlett Packard Enterprise Development LP

Hewlett-packard Development Company, L.P.

Nebuon, Inc.

Srinivasa D Murthy

Siamak Nazari

Jin Wang

Roopesh Kumar Tamma

Ming Ma

Shankar Iyer

Wei Wang

Feng Zhou

Gilad Sade

Ayman Abouelwafa

Hueichian Huang

Jonathan Stewart

Mark Doherty

Salil Gokhale

Christopher Robert Sutton

Paul Kinnaird

Jianding Luo

Pierre Labat

Jonathan McDowell

Jinyang Li

Ying Fairweather

Storage redundancy may be resynchronized without determining a snapshot difference. A storage component () owning a volume () can maintain current and expected generation numbers () based on modification requests received and modification requests that a backup component () acknowledges completing. The backup () can maintain current and expected generation numbers () based on modification requests received and applied to a backup volume (). If either component () fails and later returns to service, differences between the owner's current and expected generation numbers () and the backup's current and expected generation numbers () indicate which modification requests may have been missed and need to be reconstructed to restore synchronization.

Reestablishing redundancy in redundant storage

A technique includes changing a configuration setting of a virtual volume of data stored in a storage system. The technique includes converting data of the virtual volume in place to reflect the changing of the configuration setting.

Converting virtual volumes in place

Examples include compressed extent versions. Examples may create an empty target virtual volume tree having a tree structure of a source virtual volume tree of a source storage system, the source virtual volume tree comprising source base and source snapshot virtual volumes, each representing respective versions of a plurality of extents, wherein each of the extents corresponds to a different portion of an address space of the source base virtual volume. Examples may include compressed extent collections, each comprising a compressed representation of multiple populated versions of a single extent from the source base and snapshot virtual volumes, the multiple populated versions compressed relative to one another.

Compressed extent versions

Examples include compressed pages having data and compression metadata. Some examples include receiving a write request containing write data, storing the write data in data cache, and applying a page fit process to the write data. In some such examples, a virtual page table entry in a virtual page table may be generated for the processed write data. The virtual page table entry may include a compression index and a page address. An inline compression of the processed write data may be performed to compress and store the processed write data in a compressed page at a location associated with the compression index. In some examples, the compressed page may include a compression metadata having a reference count, a compressed page offset, and a virtual page address.

Compressed pages having data and compression metadata

Methods and systems for collision handling during an asynchronous replication are provided. A system includes a cache memory system comprising a number of cache memory pages. A collision detector detects when a host is attempting to overwrite a cache memory page that has not been completely replicated. A revision page tagger copies the cache memory page to a free page and tags the copied page as protected.

Collision handling during an asynchronous replication

Example implementations relate to determining lengths of acknowledgment delays for input/output (I/O) commands. In example implementations, a length of an acknowledgment delay for a respective I/O command may be based on cache availability, and activity level of a drive at which the respective I/O command is directed, after the respective I/O command has been executed. Acknowledgments for respective I/O commands may be transmitted after respective periods of time equal to respective lengths of acknowledgment delays have elapsed.

Determining lengths of acknowledgment delays for I/O commands

An example storage system may include storage media and a storage controller. The storage controller may be to establish virtual volumes, private data stores, and a deduplication data store, each being a virtual storage space of the storage media, wherein each of the private data stores is associated with one of the virtual volumes and the deduplication data store is shared among the virtual volumes. The storage controller may, in response to receiving input data that is to be stored in a given one of the virtual volumes, determine a signature for the input data and select between storing the input data in the private data store associated with the given one of the virtual volumes and storing the input data in the deduplication data store. The storage controller may select where to store the input data based on whether a metadata storage location addressed by a first portion of the signature includes valid metadata, and, if so: whether the metadata includes a back-pointer to one of the virtual volumes, and whether a second portion of the signature matches a key included in the metadata.

Storage system deduplication

Examples disclosed herein relate to processing transaction logs for storage nodes. Multiple nodes manage transactions for storage units including transaction logs. A node assumes control over a set of storage units and blocks host access requests to the storage units. Transaction logs are processed to determine a subset of the set to perform recovery for. In this example, the subset of storage units are locked. Host access requests are resumed.

Resume host access based on transaction logs

Examples include repair of a volume while the volume is online. In some examples, a request is received to access a compressed page, wherein the compressed page includes compressed data and compression metadata, an error is identified in the compression metadata or the compressed data, and based on the error and the request, repair of the error is handled while the volume is online.

Online volume repair

Example implementations relate to data chunk storage. For example, an implementation includes an apparatus that includes a processor. The processor is to receive a first data chunk from a source device and to generate a first fingerprint of the first data chunk. In response to a determination that the first fingerprint matches a second fingerprint of a second data chunk, the processor is to select a storage pool from a plurality of storage pools at a storage device to store the first data chunk based on the first data chunk and based on the second data chunk. The plurality of storage pools includes a first storage pool associated with first particular data chunks with non-colliding fingerprints and a second storage pool associated with second particular data chunks with colliding fingerprints.

Storage of a data chunk with a colliding fingerprint

Example implementations relate to storage space allocation. For example, an implementation includes an apparatus including a controller. The controller is to receive an allocation request from a host computing device. The controller is also to reserve a portion of storage space in the storage device via a reservation table based on the allocation request. The controller is further to determine a type of the allocation request. The type of the allocation request includes a space-optimized allocation request and a non-space-optimized allocation request. When the type of the allocation request corresponds to the non-space-optimized allocation request, the controller is to commit the portion of storage space via an allocation table. When the type of the allocation request corresponds to the space-optimized allocation request, the controller is to release the portion of storage space via the reservation table.

Storage space allocation

Disclosed herein are a system, non-transitory computer-readable medium, and method for maintaining storage unit transaction logs. Storage unit transaction logs received from controllers are separated.

Separating storage transaction logs

Examples include a device for memory space management. Some examples include receiving, from a host, a space management request that identifies a virtual page address. The virtual page address may be associated with a compressed page that includes a compression metadata having a reference count that indicates a number of virtual pages of data in the compressed page. The virtual page table entry associated with the virtual page address in a virtual page table may be looked up. The virtual page table entry may identify the compressed page. In such examples, the virtual page table entry may be marked as invalid without updating the reference count in the compressed page. A determination may be made as to whether each virtual page table entry that identifies the compressed page is marked invalid. Based on the determination that each virtual page table entry that identifies the compressed page is invalid, a free space bitmap entry for the compressed page may be updated to indicate that the compressed page is free.

Memory space management

In example implementations, unreferenced memory addresses in a segment of a storage volume may be identified. Access to the segment of the storage volume may be controlled by one of a plurality of storage volume controllers (SVCs). The plurality of SVCs may control access to respective segments of the storage volume. Indicators of the identified unreferenced memory addresses may be stored in a volatile memory in the one of the plurality of SVCs. In response to an input/output (I/O) command from a host, data may be written to one of the identified unreferenced memory addresses corresponding to one of the indicators stored in the volatile memory. After the data has been written, the one of the indicators may be deleted from the volatile memory. The one of the identified unreferenced memory addresses may not have been made available to other SVCs after being identified.

Storing indicators of unreferenced memory addresses in volatile memory

Each node in a clustered array is the owner of a set of zero logical disks (LDs). Thinly-provisioned VVs (TPVVs) are partitioned so each is mapped to a group of zero LDs from different sets of zero LDs. When there is a change in ownership, the affected zero LDs are switched one at a time so only a group of the TPVVs is affected each time.

Growing community of inventors

Cupertino, CA, United States of America

Srinivasa D Murthy