Western Digital Technologies, Inc.

Samsung Electronics Co., Ltd.

Sandisk Technologies Inc.

Hitachi Global Storage Technologies Netherlands B.v.

Hgst Netherlands, B.v.

Rajesh Koul

James J Walsh

Rodney Norman Mullendore

Shay Benisty

Daniel Lee Helmick

Martin Aureliano Hassner

Sumanth Jannyavula Venkata

Young Deok Kim

Sridhar Chatradhi

Anthony Edwin Welter

Robert Wayne Moss

Ryan Matthew Schulz

A method may include receiving, at a device, a copy command, wherein the copy command comprises a first indication of a first amount of source data and a second indication of a second amount of source data, determining, based at least in part on the first indication, an amount of destination space, and blocking at least a portion of the amount of destination space. The method may further include reading the first indication, and reading the second indication, wherein the amount of destination space may include at least a first portion of the first amount and at least a second portion of the second amount. The blocking may include blocking the at least the first portion of the first amount and the at least the second portion of the second amount. The method may further include storing the first indication to generate a stored first indication.

Systems, methods, and apparatus for copy destination atomicity in devices

A storage system controller chip includes routing circuitry comprising a host interface for coupling to a host device and an extension interface for coupling to a secondary controller chip. A host controller is coupled to a logical interface of the routing circuitry for receiving a host data access command from the host device via the host interface and logical interface. The routing circuitry transfers the host data access command to the secondary controller chip via the extension interface. The storage system controller chip further includes processor circuitry coupled to the logical interface of the routing circuitry. The processor circuitry receives an indication from the secondary controller chip via the extension interface that execution of the host data access command has been completed by the secondary controller chip and instructs the host controller to notify the host device that execution of the host data access command has been completed.

Extensible storage system and method

A storage system and method for secure host controller memory buffer access are provided. In one embodiment, a storage system is provided comprising a storage area configured to store a database comprising a submission queue and a completion queue dedicated for use by an authorized host, and a controller. The controller is configured to: receive a request to access the storage area; determine whether the request is from the authorized host or from an unauthorized host; in response to determining that the request is from the authorized host, grant the request; and in response to determining that the request is from an unauthorized host, deny the request. Other embodiments are provided.

Storage system and method for secure host controller memory buffer access

Methods, systems, and computer readable media for intelligent fetching of storage device commands from submission queues are disclosed. The controller may implement a hierarchical scheme comprising first-level arbitration(s) between submission queues of each of a plurality of input/output virtualization (IOV) functions, and a second-level arbitration between the respective IOV functions. Alternatively, or in addition, the controller may implement a flat arbitration scheme, which may comprise selecting submission queue(s) from one or more groups, each group comprising submission queues of each of the plurality of IOV functions. In some embodiments, the controller implements a credit-based arbitration scheme. The arbitration scheme(s) may be modified in accordance with command statistics and/or current resource availability.

Systems, methods, and computer-readable media for managing instruction fetch in virtual computing environments

Systems and methods for flexible management of resources in a Non-Volatile Memory Express (NVMe) virtualization environment are disclosed. In NVMe virtualization, the host device operates in the virtual world and the memory device operates in the physical world. In order for the memory device to perform a host access request (which includes the virtual identification), the memory device transforms the virtual identification into a physical identification. Likewise, prior to the memory device sending a memory device access request to the host device, the memory device transforms the physical identification into the virtual identification. There may be multiple physical resources, such as submission queues/completion queues and interrupt vectors. Rather than having separate translation tables for the queues and the interrupt vectors, a single virtual translation table is used to perform the translation from the virtual identification to the queues and the interrupt vectors. In this way, the memory device may perform the virtual translation in a more simplified manner.

System and method for flexible management of resources in an NVMe virtualization

Systems and methods for quality of service (QoS) using adaptive command fetching are disclosed. NVM Express (NVMe) implements a paired submission queue and completion queue mechanism, with host software on the host device placing commands into the submission queue. The memory device processes the commands through various phases including fetching, processing, posting a completion message, and sending an interrupt to the host. NVMe also includes an NVMe virtualization environment, which uses a subsystem with multiple controllers to provide virtual or physical hosts direct I/O access. QoS may be used so that the NVMe processes in the virtualization environment receive sufficient resources. In particular, bandwidth assigned to a submission queue may be considered when processing of commands (such as fetching of commands). In the event that the bandwidth assigned to the submission queue is exceeded, the processing of the commands (such as the fetching of the commands) may be delayed.

System and method for QoS over NVMe virtualization platform using adaptive command fetching

Extensible storage system controller

Approaches for an emergency power off (EPO) power island, for saving critical data to non-volatile memory in the event of an EPO condition, for use in a hard-disk drive (HDD) storage device. The EPO power island includes a controller for detecting an EPO condition. A voltage regulator supplies power from spindle motor back EMF only to the EPO power island and to the non-volatile memory. Thus, the remainder of the hard drive controller (HDC) is isolated from the EPO power island so that it will not corrupt the data as the HDC's power supply is decaying. Using the power provided by the voltage regulator, the EPO power island transfers critical data from a memory internal to the island to a non-volatile memory external to the island, such as to a flash memory chip.

Emergency power off (EPO) island for saving critical data to non-volatile memory

Embodiments of the present invention provide techniques for detecting and correcting encoded data. In one embodiment, a system for detecting and correcting errors in a plurality of data bits comprises a static memory configured to store a plurality of data bits; a systematic encoder configured to convert the plurality of data bits into a codeword; a systematic parity check encoder configured to convert the codeword into a syndrome; and a syndrome decoder configured to evaluate the syndrome based on preset criteria used to determine whether the syndrome corresponds to an uncorrectable error. A binary [16, 8, 5] code is used to encode the plurality of data bits.

Growing community of inventors

San Jose, CA, United States of America

Rajesh Koul