Pavilion Data Systems, Inc.

Promise Technology, Inc.

Raghuraman Govindasamy

Kiron Balkrishna Malwankar

Dan M Melnic

Venkeepuram R Satish

Suhas Dantkale

Mohan Babu Rowlands

Muthukumar Ratty

Ganesh Kumar

A storage server includes a first controller, a second controller and physical drives. The first controller receives a request to store data in a virtual block address (VBA) of a virtual drive, determines a physical block address (PBA) of a physical drive on which to store the data, and sends to the physical drive a command to store the data at the PBA. The first controller generates a first metadata update for a first metadata table associated with the virtual drive, wherein the first metadata update indicates a mapping of the VBA to the PBA. The first controller generates a second metadata update for a second metadata table that identifies statuses of PBAs, wherein the second metadata update indicates that the PBA is valid. The first controller writes an entry to a cache in a memory, the entry comprising the first metadata update and the second metadata update.

Low latency metadata log

A processing device receives an input/output (I/O) command generated by a process, the I/O command directed to a virtual storage provided to a host executing the process, wherein the virtual storage comprises a virtual non-volatile memory express (NVMe) drive. The processing device generates a new I/O command based on the received I/O command and encapsulates the new I/O command into a message. The processing device sends the message to at least one of a remote NVMe storage device or a storage server comprising one or more remote NVMe storage devices.

Virtual non-volatile memory express drive

A processing device generates a clone of a first volume of storage, the first volume comprising a plurality of storage blocks, wherein the clone is a second volume that is writable and that references the plurality of storage blocks. The processing device increments a global volume count that represents a number of volumes. For each storage block of the plurality of storage blocks, the processing device postpones an update to metadata of the storage block until an event that causes any volume to stop referencing the storage block, wherein the metadata indicates volumes that reference the storage block.

Writable clones with minimal overhead

A storage server includes an IO controller, a management controller and physical drives. The IO controller generates multiple metadata updates and writes a cache entry that includes the multiple metadata updates to a first cache in memory of the management controller. The IO controller additionally writes a copy of the cache entry to a second cache in a memory of the IO controller and increments a commit pointer in the first and second caches to indicate that the metadata updates are committed.

Recovery mechanism for low latency metadata log

A solid state drive (SSD) comprises a storage area, a network interface controller (NIC) and a storage controller operatively coupled to the storage area. The storage controller comprises a mapping between the storage area and a virtual storage device that is accessible to a remote computing device. The storage controller is configured to receive a message encapsulating an input/output (I/O) command from a remote computing device via the NIC, wherein the I/O command is directed to the virtual storage device. The storage controller is further configured to determine one or more logical addresses of the virtual storage device specified in the I/O command, translate the one or more logical addresses of the virtual storage device into one or more physical addresses of the storage area, and access the one or more physical addresses of the storage area.

Remotely accessible solid state drive

A storage server generates a device tree representing a maximal topology of the storage server, wherein the maximal topology is a maximum number of storage controllers and solid state drives (SSDs) that are supported by the storage server, and wherein a plurality of entries in the device tree contain placeholder information. The storage server discovers one or more SSDs of the storage server and determines drive information for the one or more SSDs that have been discovered. The storage server replaces the placeholder information in one or more of the plurality of entries in the device tree with the drive information for the one or more SSDs.

Storage sever with hot plug and unplug capabilities

A processing device identifies a plurality of solid state storage devices arranged in an array and determines, for at least one solid state storage device of the plurality of solid state storage devices, a first time window during which the at least one solid state storage device is permitted to perform one or more garbage collection operations. The processing device then sends, to the at least one solid state storage device, a message comprising the first time window allocated to the at least one storage device, wherein the at least one solid state storage device is to perform the garbage collection operations during the first time window allocated to the at least one solid state storage device.

Scheduled garbage collection for solid state storage devices

A processing device receives a message encapsulating an input/output (I/O) command from a remote computing device. The processing device identifies one or more physical storage devices to be accessed to satisfy the I/O command. The processing device then sends, to each physical storage device of the one or more physical storage devices, one or more non-volatile memory express (NVMe) commands directed to that physical storage device.

Non-volatile memory express over ethernet

A method of operation of a disk storage system includes: providing a disk storage controller; coupling a first physical disk to the disk storage controller; detecting a failure of the first physical disk; and rebuilding a first logical drive, after replacing the first physical disk, includes: selecting a selected stripe of the first logical drive, reading a selected stripe status of the selected stripe, and marking the selected stripe as on-line in the selected stripe status.

Growing community of inventors

San Jose, CA, United States of America

Raghuraman Govindasamy