Seagate Technology Incorporated

Benjamin J Scott

Steven Scott Williams

Kyumsung Lee

Stacey Secatch

David W Claude

Stephen H Perlmutter

Robert William Dixon

Ryan James Goss

Marc Timothy Jones

Daniel John Benjamin

Andrew J Louder

Jeff Rogers

Jason Wayne Kinsey

The technology disclosed herein pertains to a system and method for scaling storage using peer-to-peer NVMe communication, the method including selecting one of a plurality of NVMe devices as principal device to control communication with a host via a PCI switch, designating remainder of the plurality of NVMe devices as subordinate devices, and controlling the communication between the host and the subordinate devices using a PCI P2P DMA between the principal device and the subordinate devices.

Scalable storage using NVMe communication

A semiconductor data storage memory can receive data access commands into a queue in a first time sequence that correspond with the transfer of data between a host and portions of the memory. The memory may be divided into separate portions that each have a different owner and the access commands may be issued to each of the respective separate portions. The access commands can subsequently be executed in a different, second time sequence responsive to estimated completion times for each of the access commands based on measured completion times for previously serviced, similar commands to maintain a nominally consistent quality of service level for each of the respective owners.

Deterministic optimization via performance tracking in a data storage system

Apparatus and method for storing data in a non-volatile memory (NVM), such as a flash memory in a solid-state drive (SSD). In some embodiments, a distributed storage space of the NVM is defined to extend across a plural number of regions of the NVM. A non-standard parity data set is provided having a plural number of data elements greater than or equal to the plural number of regions in the storage space. The data set is written by storing a first portion of the data elements and a first parity value to the plural number of regions and a remaining portion of the data elements and a second parity value to a subset of the plural number of regions. The regions can comprise semiconductor dies in a flash memory, and the distributed storage space can be a garbage collection unit formed using one erasure block from each flash die.

Providing additional parity for non-standard sized parity data sets

Apparatus and method for managing entropy in a cryptographic processing system, such as but not limited to a solid-state drive (SSD). In some embodiments, a processing device is operated to transfer data between a host device and a non-volatile memory (NVM). In response to the detection of a power down event associated with the processing device, entropy associated with the power down event is collected and stored in a memory. Upon a subsequent reinitialization of the processing device, the entropy is conditioned and used as an input to a cryptographic function to subsequently transfer data between the host device and the NVM. In some embodiments, the entropy is obtained from the state of a hardware timer that provides a monotonically increasing count for timing control. In other embodiments, the entropy is obtained from a RAID buffer used to store data to a die set of the NVM.

Collection of uncorrelated entropy during a power down sequence

Apparatus and method for managing shared resources in a data storage device such as a solid-state drive (SSD). In some embodiments, a non-volatile memory (NVM) has a population of semiconductor memory dies to which are connected a number of parallel channel. A controller circuit apportions the semiconductor memory dies into a plurality of die sets each configured to store user data blocks associated with a different user during hot data transfers responsive to a sequence of host access commands. A shared resource is available for use by each of the die sets to support background data transfers not associated with the host access commands, such as a RAID buffer. The controller circuit arbitrates the use of the shared resource by each of the die sets in turn to sequentially perform the background data transfers to maintain a selected level of deterministic performance of the hot data transfers.

Arbitrated management of a shared non-volatile memory resource

Apparatus and method for managing metadata in a data storage device such as a solid-state drive (SSD). In some embodiments, a write stream is formed of user data blocks to be sequentially written to a non-volatile memory (NVM). An entry of a reverse directory footer is generated for each user data block in the write stream to describe a physical address in the NVM at which the corresponding user data block is to be stored. The entries are accumulated in a buffer memory until the total count of entries reaches a predetermined threshold and a complete footer data structure is formed. The complete footer data structure is thereafter inserted into the write stream for writing, with the data blocks, to the NVM. The complete footer data structure has an overall size that corresponds to an overall size of each of the user data blocks.

Reverse directory structure in a garbage collection unit (GCU)

A data storage system can connect a plurality of remote hosts to a plurality of die sets resident in a semiconductor memory. Execution of at least one data access command addressed by a remote host of the plurality of remote hosts can occur prior to a power interruption event being detected for at least one die set of the plurality of die sets. User-generated data associated with the at least one data access command may then be flushed to a predetermined location responsive to an available resource budget associated with the power interruption event.

Growing community of inventors

Longmont, CO, United States of America

Benjamin J Scott