A node interconnection apparatus includes a computing node and a resource control node, and a device interconnection interface connecting the two. Each of the computing node and the resource control node includes a processing unit and a storage unit, and the resource control node further includes a resource interface for connecting with a network storage device. The resource control node manages storage resource of the network storage device, and when the computing node needs to start up, the resource control node obtains operating system startup information from the network storage device and provides the information to the computing node. The computing node can start up without the need for storing startup information locally.

Deploying client-specific applications in a storage system utilizing redundant system resources, including: identifying a redundant controller in the storage system, wherein the storage system includes at least a first controller and the redundant controller; and executing one or more applications on the redundant controller, wherein the one or more applications are executed in a container.

A resource management method of a first device, which includes: receiving a request message sent by a second device, where the request message is used to indicate the first device to allocate a memory to the second device, the request message carries a size of the memory. allocating a memory space from a memory of the first device based on the size of the memory carried in the request message; generating a virtual disk based on the memory space; and providing the virtual disk for the second device as a memory of the second device.

The memory includes a first descriptor area and a first data area corresponding to the first OS, and a second descriptor area and a second data area corresponding to the second OS. The second processor stores the first transmission instruction information corresponding to the transmission data stored in the second data area in the second descriptor area and transmits a first update notification of the second descriptor area to the first processor. In response to the first update notification, the first processor reads the first transmission instruction information stored in the second descriptor area and stores the first transmission instruction information in the first descriptor area. The communication circuit controlled by the first processor performs transmission process of transmission data stored in the second data area based on the first transmission instruction information stored in the first descriptor area.

A RAID data storage device direct communication system includes a first RAID data storage device that includes a first RAID data storage device controller having a first RAID data storage device function providing a second RAID data storage device submission queue in a first RAID data storage device memory subsystem, and a second RAID data storage device that includes a second RAID data storage device controller having a second RAID data storage device function providing a second RAID data storage device completion queue in a second RAID data storage device memory subsystem. The second RAID data storage device generates a command, transmits the command directly to first RAID data storage device and in the second RAID data storage device submission queue, and receives a completion message that is associated with the command directly from the first RAID data storage device and in the second RAID data storage device completion queue.

Examples may forward an input/output (IO) request with use of kernel-level instructions. Examples may receive the IO request via a port of a standby controller, generate an alternate version of the IO request using at least kernel-level instructions of the standby controller, and provide the alternate version of the IO request to physical memory of the active controller by providing the alternate version of the IO request to a designated region of physical memory of the standby controller that is mapped to a designated region of the physical memory of the active controller.

Example implementations relate to managing ownership transfer of a file system instance in a virtualized distributed storage system. The virtualized distributed storage system includes a first node having a first virtual controller that acts as an owner of a file system instance in a distributed storage, and a second node having a second virtual controller coupled to the first node over a network. A failure condition associated with a first node is detected. Further, in response to detection of the failure condition, an ownership of the file system instance may be transferred from the first virtual controller to the second virtual controller no later than an IP address switchover of the first virtual controller.

An aspect of performance optimization in a storage system environment includes providing a metadata structure that describes a storage space of a storage system. For each storage object of a plurality of storage objects, an aspect includes monitoring input/output (IO) patterns for IO operations conducted, monitoring deduplication characteristics of the storage object, and configuring local mapping layer parameters. An aspect further includes modifying local object metadata in the metadata structure as a function of the monitoring and the configuring.

Method and apparatus for managing data transfers. In some embodiments, first and second storage devices respectively include first and second controllers, first and second local memories, and first and second non-volatile memories (NVMs). A virtual controller memory buffer (CMB) is formed from a dedicated portion of each of the first and second local memories for control by a host device. The first controller receives a virtual command set from the host device, and extracts a first local command to transfer data between the host device and the first NVM. In some cases, the second controller also receives the virtual command set and concurrently extracts a different, second local command to transfer data between the host device and the second NVM. Alternatively, the first controller may extract and forward the second local command to the second controller. The first and second NVMs may form an NVMe (Non-Volatile Memory Express) namespace.

Embodiments of application provide a node interconnection apparatus, and a method implemented by the node interconnection apparatus. The node interconnection apparatus includes a computing node and a resource control node, and a device interconnection interface connecting the two. Each of the computing node and the resource control node includes a processing unit and a storage unit, and the resource control node further includes a resource interface for connecting with a network storage device. The resource control node manages storage resource of the network storage device, and when the computing node needs started up, the resource control node obtains operating system startup information from the network storage device and provide the information to the computing node. The computing node can start up without the need for storing startup information locally. Therefore, storage resource inside the computing node is saved.