Western Digital Technologies, Inc.

Hitachi Global Storage Technologies Netherlands B.v.

International Business Machines Corporation

Hgst Netherlands, B.v.

Adam Michael Espeseth

David Robison Hall

Colin Christopher McCambridge

David George Dreyer

Dylan Mark Dewitt

Lee Anton Sendelbach

Michael J Anderson

Trevor James Briggs

Maile Matsui Vasoli

Edward Henry Younk

Robert Anton Steinbach

Zvonimir Z Bandic

David Lee Darrington

Cyril Guyot

Marco Sanvido

Brandon William Schulz

Brent William Jacobs

Yuval Cassuto

Kraig Bottemiller

Christopher David Wiederholt

James R Shipman

James Joseph Mosser

Steven Glenn Smith

Techniques for improved copy on write functionality within an SSD are disclosed. In some embodiments, the techniques may be realized as a method for providing improved copy on write functionality within an SSD including providing, in memory of a device, an indirection data structure. The data structure may include a master entry for cloned data, the master entry having a reference to one or more indexes and a clone entry for the cloned data, the cloned entry having at least one of: a reference to a master index, a reference to a next index, and a value indicating an end of a data structure. The techniques may include traversing, using a computer processor, one or more copies of the cloned data using one or more of the references.

System and method for copy on write on an SSD

A method includes receiving, by a storage device and from a host device, a set of protocol parameters initialized by the host device. The set of protocol parameters are used to facilitate data transfer between the host device and the storage device. The method also includes determining that a threshold value associated with the data transfer between the host device and the storage device has been satisfied. The method further includes, in response to determining that the threshold value has been satisfied, sending, by the storage device and to the host device, the set of protocol parameters that were received from the host device.

Embedding protocol parameters in data streams between host devices and storage devices

A method, apparatus, and system are provided for implementing debug data saving in host memory on a Peripheral Component Interconnect Express (PCIE) solid state drive (SSD). Upon Power Loss Interruption (PLI) event detected in a solid state drive (SSD), the SSD transfers debug data directly to the host system main (DRAM) memory via a Peripheral Component Interconnect Express (PCIE) bus.

Debug data saving in host memory on PCIE solid state drive

A method and apparatus for accessing a storage device is disclosed. More specifically, for load balancing by dynamically transferring memory address range assignments. In one embodiment, a storage device receives, from a host apparatus, an access request directed at two or more storage addresses, assigns, based on a first storage address of the two or more storage addresses, the access request to a first processor of two or more processors of the storage device, obtains a local memory lock based on the first storage address, determines, based on a second storage address of the two or more storage addresses, that the second storage address is assigned to a second processor of the two or more processors, obtains a remote memory lock from the second processor based on the second storage address and processes the access request.

Load balancing by dynamically transferring memory range assignments

An apparatus for implementing an enhanced-write-bandwidth caching stream includes a memory that stores machine instructions and a processor that executes the machine instructions. The apparatus apportions a first address space and a second address space that comprises a logical namespace. The apparatus also subjects the first address space to host-write throttling, and exempts the second address space from host-write throttling. The apparatus further requires that valid data in memory cells corresponding to the second address space be invalidated at an interval not to exceed a number of host writes equaling the capacity of the second address space.

Method for providing nonvolatile storage write bandwidth using a caching namespace

An apparatus for implementing an enhanced-write-bandwidth caching stream includes a memory that stores machine instructions and a processor that executes the machine instructions. The apparatus receives a first host write stream and a second host write stream that comprises latency-sensitive host write requests. The apparatus also subjects the first host write stream to host-write throttling, and exempts the second host write stream from host-write throttling. The apparatus further requires that the second host write stream invalidate logical blocks in an order corresponding to a previous order in which the respective logical blocks were previously programmed.

In general, techniques are described for stream management in storage devices. A storage device comprising a memory device and a processor may be configured to perform the techniques. The processor may detect a stream collision in which a host device writes a first version of a logical block (LB) to a first stream, and writes a second version of the same LB to a second stream. The processors may compare a first blockset sequence number (BSN) associated with a first collection of physical blocks referenced by the first stream to a second BSN associated with a second collection of physical blocks referenced by the second stream. Based on the comparison of the first BSN to the second BSN, the processor may write, to the mem device, the second version of the LB to the first stream.

Stream management for storage devices

Salvaging event trace information in power loss interruption (PLI) scenarios, for use in solid-state drive (SSD) and hard disk drive (HDD) storage devices. If volatile state information that is salvaged after an inadvertent power loss were to include event trace information, then such information can provide a valuable debug resource. Event trace information from volatile memory is copied to a second memory upon a power on which is in response to a PLI event. A corrupt state of context reconstruction data stored on non-volatile memory is detected, and an indication of the corrupt state is set. The event trace information is passed to the host if requested based on the indication.

Salvaging event trace information in power loss interruption scenarios

An abort function for storage devices sets a 'poison bit' flag in the command to be deleted while the command resides on a submission queue prior to being fetched by the SSD controller. In response to the set 'poison bit' flag, a storage device controller aborts execution of the I/O command and returns an abort successful status reply to the completion queue.

Abort function for storage devices by using a poison bit flag wherein a command for indicating which command should be aborted

A method and apparatus are provided for implementing secure erase for solid state drives (SSDs). An encryption key is used to encrypt data being written to SSD. A controller identifies a key storage option, and responsive to the identified key storage option, stores a key for data encryption and decryption. The controller deletes the key within the SSD responsive to the identified key storage option, ensuring that once the key is deleted, the key is not recoverable and data is effectively erased.

Implementing secure erase for solid state drives

Multiple disk access commands such as XOR commands are broken down into their constituent read and write parts and, if in LBA sequence, coalesced into pipes. These XOR read and write commands are then provided to the RPO algorithm of the HDD for scheduling along with data reads and writes. The actual XOR buffer operation is also scheduled by the RPO algorithm, advantageously to occur during a seek for another read or write.

System and method for optimizing random XOR command performance

Commands in a queue in a hard disk drive (HDD) are selected based on a benefit of providing either an optimized throughput or an optimized number of commands per second execution, as opposed to a simple shortest access time first (SATF) selection method.

System and method for selecting command for execution in HDD based on benefit

An RPO algorithm in a HDD coalesces LBA-sequential XOR commands in pipes, and passes the pipes to a lower level execution engine. The execution engine executes XOR reads and write separately to optimize performance using head and/or cylinder skew information to approach the nominal disk data rate.

Growing community of inventors

Rochester, MN, United States of America

Adam Michael Espeseth