International Business Machines Corporation

Netapp, Inc.

Lsi Corporation

Lsi Logic Corporation

Agere Systems Inc.

Brian Dennis McKean

Donald Roman Humlicek

Kevin Lee Kidney

John Edward Archibald, Jr

Noel Simen Otterness

Ross Zwisler

Sandeep Kumar R Ummadi

David L Dreifus

Robert Warren

Joseph G Skazinski

Timothy R Snider

Pradeep Ganesan

Jeremy Pinson

Gregory Friebus

Randall Alan Pare

James Lee Hafner

Bret S Weber

Douglas William Dewey

Mohamad H El-Batal

Wendy Ann Belluomini

Martin Jess

Yanling Qi

Theresa Lynn Segura

Sai Susarla

Somasundaram Krishnasamy

Bhaskar Jayaraman

Ariel Hoffman

Mark Ish

Timothy E Hoglund

Rodney A Dekoning

Arindam Banerjee

James A Lynn

Dennis James Hahn

Mark Nossokoff

Edward Lewis Hauck

Kenneth Michael Harris

Jeffrey S Werning

Dennis Kleppen

Robert Clyde Coulter

John Dietterich

A method, a computing device, and a non-transitory machine-readable medium for modifying cache settings in the array cache are provided. Cache settings are set in an array cache, such that the array cache caches data in an input/output (I/O) stream based on the cache settings. Multiple cache simulators simulate the caching the data from the I/O stream in the array cache using different cache settings in parallel with the array cache. The cache settings in the array cache are replaced with the cache settings from one of the cache simulators based on the determination that the cache simulators increase effectiveness of caching data in the array cache.

Adapting cache processing using phase libraries and real time simulators

A method and system for synchronizing caches after reboot are described. In a cached environment, a host server stores a cache counter associated with the cache, which can be stored in the cache itself or in another permanent storage device. When data blocks are written to the cache, metadata for each data block is also written to the cache. This metadata includes a block counter based on a value of the cache counter. After a number of data operations are performed in the cache, the value of the cache counter is updated. Then, each data block is selectively updated based on a comparison of the value of the cache counter with a value of the block counter in the metadata for the corresponding data block.

System and method for synchronizing caches after reboot

Systems and techniques for performing a data transaction are disclosed that provide data redundancy using two or more cache devices. In some embodiments, a data transaction is received by a storage controller of a storage system from a host system. The storage controller caches data and/or metadata associated with the data transaction to at least two cache devices that are discrete from the storage controller. After caching, the storage controller provides a transaction completion response to the host system from which the transaction was received. In some examples, each of the at least two cache devices includes a storage class memory. In some examples, the storage controller caches metadata to the at least two cache devices and to a controller cache of the storage controller, while data is cached to the at least two cache devices without being cached in the controller cache.

Storage controller caching using symmetric storage class memory devices

A system and method for improving storage system operation is disclosed. A storage system includes a first tier with high-performance redundancy and a second tier with capacity efficient redundancy. The first tier and the second tier are built from the same storage devices in a storage pool so each storage device includes both the first and second tiers. The storage system stores write data initially to the first tier. When demand for the data falls below a threshold, the storage system migrates the write data to the second tier. This is done by changing the mapping of underlying physical locations on the storage devices where the write data is stored so that the underlying physical locations are logically associated with the second tier instead of the first tier. After remapping, the storage system also computes parity information for the migrated write data and stores it in the second tier.

Raid data migration through stripe swapping

A method, a computing device, and a non-transitory machine-readable medium for changing ownership of a storage volume from a first controller to a second controller without flushing data, is provided. In the system, the first controller is associated with a first DRAM cache comprising a primary partition that stores data associated with the first controller and a mirror partition that stores data associated with the second controller. The second controller in the system is associated with a second DRAM cache comprising a primary partition that stores data associated with the second controller and the mirror partition associated with the first controller. Further, the mirror partition in the second DRAM cache stores a copy of a data in the primary partition of the first DRAM cache and the mirror partition in the first DRAM cache stores a copy of a data in the primary partition of the second DRAM cache.

Changing storage volume ownership using cache memory

Systems and techniques are disclosed for the mirroring of cache data from a storage controller to a storage class memory ('SCM') device. The storage controller receives a write request, caches the write data, and mirrors the write data to the SCM device instead of to a cache of another storage controller. The SCM device stores the mirrored data in the SCM device. The storage controller acknowledges the write to the host. If the storage controller later fails, an alternate controller assumes ownership of storage volumes associated with the failed controller. Upon receipt of a new read request to the failed controller, the alternate controller checks the SCM device for a cache hit. If there is, the data is read from the SCM device; otherwise, it is read from the storage volume(s). The read data is cached at the alternate controller and then sent on to the requesting host.

Write mirroring to storage class memory devices

Method and systems for a storage system are provided. Simulated cache blocks of a cache system are tracked using cache metadata while performing a workload having a plurality of storage operations. The cache metadata is segmented, each segment corresponding to a cache size. Predictive statistics are determined for each cache size using a corresponding segment of the cache metadata. The predictive statistics are used to determine an amount of data that is written for each cache size within certain duration. The process then determines if each cache size provides an endurance level after executing a certain number of write operations, where the endurance level indicates a desired life-cycle for each cache size.

Methods and systems for using predictive cache statistics in a storage system

A storage manager can reduce the overhead of parity based fault tolerance by leveraging the access performance of SSDs for the parities. Since reading a parity value can be considered a small read operation, the reading of parity from an SSD is an effectively 'free' operation due to the substantially greater SSD read performance. With reading parity being an effectively free operation, placing parity on SSDs eliminates the parity read operations (in terms of time) from the parity based fault tolerance overhead. A storage manager can selectively place parity on SSDs from HDDs based on a criterion or criteria, which can relate to frequency of access to the data corresponding to the parity. The caching criterion can be defined to ensure the reduced overhead gained by reading parity values from a SSD outweighs any costs (e.g., SSD write endurance).

Solid state device parity caching in a hybrid storage array

A method, apparatus, and system of a priority command queues for low latency solid state drives are disclosed. In one embodiment, a system of a storage system includes a command sorter to determine a target storage device for at least one of a solid state drive (SSD) command and a hard disk drive (HDD) command and to place the command in a SSD ready queue if the SSD command is targeted to a SSD storage device of the storage system and to place the HDD command to a HDD ready queue if the HDD command is targeted to an HDD storage device of the storage system, a SSD ready queue to queue the SSD command targeted to the SSD storage device, and a HDD ready queue to queue the HDD command targeted to the HDD storage device.

Priority command queues for low latency solid state drives

A system and method for performing protected-mode data transactions using an initiator cache is provided. In some embodiments, a protected-mode data transaction is received from an initiator. It is determined that the initiator includes an initiator cache having a cache entry associated with the data transaction. A storage controller of a storage system performs the data transaction in conjunction with a storage device such that the performing of the data transaction is initiated before any writing of the data transaction to a cache of any storage controller of the storage system other than the storage controller based on the determination that the initiator includes the cache entry. In some such embodiments, when it is determined the data transaction failed to complete, a request is provided to the initiator to recreate the transaction from the cache entry in the initiator cache.

Systems and methods for a storage array-managed initiator cache

System and method for dynamic storage tiering are disclosed. A storage hot-spot in a first storage pool is detected. A first point-in-time copy of a virtual volume including the storage hot-spot is created in a second storage pool according to the detecting. Write requests directed to the virtual volume are redirected to the second storage pool. When decreased I/O activity directed to the storage hot-spot in the second storage pool is detected, the point-in-time copy in the second storage pool is reintegrated into at least one of a second point-in-time copy or the virtual volume.

Method and system for dynamic storage tiering using allocate-on-write snapshots

The present invention is a system and method which allows for a VTL system that supports thin provisioning to implicitly unmap unused storage. Such unmap operations may occur even though the VTL system does not receive any explicit unmap requests from its initiators. For example, if a system administrator knows that once a virtual tape drive of the VTL system has been partially overwritten, all previously written data sets on that virtual tape drive will never again be accessed, the system administrator may configure the VTL system so that it unmaps the entire remainder of the virtual tape drive on the first data overwrite.

System and method for providing implicit unmaps in thinly provisioned virtual tape library systems

Growing community of inventors

Longmont, CO, United States of America

Brian Dennis McKean