Abstract: Methods and systems for managing data access based threats are disclosed. To manage the data access based threats, a data processing system may include a network interface controller (NIC). The network interface controller may present emulated storages that may be used for data storage. The emulated storage devices may utilize storage resources of storage devices. The NIC may actively screen for access patterns in use of the emulated storage devices that indicate compute complexes may be compromised. When doing so, the processing may be done locally on the NIC.

Abstract: Embodiments of using command tags are described to prevent data corruption in a multi-path network in an NVMe over Fabrics (NVMe-OF) environment. A command tag is incorporated in a written command send from a host for command identification. Once the host detects an issue of a first link between the host and namespace, the host may immediately send, using a second link, a retry of a command that was previously sent by the host to a first controller via the first link. The retry of the command comprises the same command tag which allows the first and second controllers to detect an execution condition of the first write command, and thus avoiding repeat execution of the first write command by the first controller and the second controller. Therefore, data corruption may be addressed efficiently to the root cause.

Abstract: A technique of managing message between chassis includes forming a first message by a computing node in a first chassis. The first message complies with a first communications protocol and provides an instruction directed to a controller in a second chassis to manage one or more hardware functions of the second chassis. The controller operates in accordance with a second communications protocol that is different from the first communications protocol. The technique further includes transmitting both the first message and a set of I/O requests from the first chassis to the second chassis over a communications link configured to carry messages complying with the first communications protocol. The technique further includes converting, in the second chassis, the first message complying with the first communications protocol into a second message complying with the second communications protocol, the second message including the instruction directed to the controller.

Abstract: A technique of managing message between chassis includes forming a first message by a computing node in a first chassis. The first message complies with a first communications protocol and provides an instruction directed to a controller in a second chassis to manage one or more hardware functions of the second chassis. The controller operates in accordance with a second communications protocol that is different from the first communications protocol. The technique further includes transmitting both the first message and a set of I/O requests from the first chassis to the second chassis over a communications link configured to carry messages complying with the first communications protocol. The technique further includes converting, in the second chassis, the first message complying with the first communications protocol into a second message complying with the second communications protocol, the second message including the instruction directed to the controller.

Abstract: An emulated device management system includes a chassis housing a device emulation subsystem coupled to an operating system via operating system physical connection(s) and to a management system via management system physical connection(s). The device emulation subsystem emulates a physical device to provide an emulated device that is presented to the operating system as a local device connected to the operating system physical connection(s), and presented to the management system as a local device connected to the management system physical connection(s).

Abstract: A computing device/DPU log collection system includes a computing device chassis housing a computing device log generation subsystem coupled to a DPU device via physical connection(s). The DPU device emulates a physical storage device to provide an emulated storage device that is presented to the computing device log generation subsystem as a local storage device coupled to the physical connection(s), configures the emulated storage device with a computing device log storage file system, and receives computing device logs from the computing device log generation subsystem via the computing device log storage file system. The DPU device then performs log collection operations that identify a subset of the computing device logs that were received from the computing device log generation subsystem via the computing device log storage file system in the emulated storage device, and transmits the subset of the computing device logs to a log storage system via a network.

Abstract: Techniques provide communication between storage processors (SPs) of a storage array. The techniques involve electrically coupling the SPs with an interconnect of the storage array. The techniques further involve electrically coupling a storage device having dual on-device controllers with the interconnect. The techniques further involve establishing a communications pathway between the SPs through the interconnect and the storage device having the dual on-device controllers while the SPs are electrically coupled with the interconnect and while the storage device is electrically coupled with the interconnect.

Abstract: Embodiments of using command tags are described to prevent data corruption in a multi-path network in an NVMe over Fabrics (NVMe-OF) environment. A command tag is incorporated in a written command send from a host for command identification. Once the host detects an issue of a first link between the host and namespace, the host may immediately send, using a second link, a retry of a command that was previously sent by the host to a first controller via the first link. The retry of the command comprises the same command tag which allows the first and second controllers to detect an execution condition of the first write command, and thus avoiding repeat execution of the first write command by the first controller and the second controller. Therefore, data corruption may be addressed efficiently to the root cause.

Abstract: Techniques provide communication between storage processors (SPs) of a storage array. The techniques involve electrically coupling the SPs with an interconnect of the storage array. The techniques further involve electrically coupling a storage device having dual on-device controllers with the interconnect. The techniques further involve establishing a communications pathway between the SPs through the interconnect and the storage device having the dual on-device controllers while the SPs are electrically coupled with the interconnect and while the storage device is electrically coupled with the interconnect.

Abstract: Methods and systems for managing data access based threats are disclosed. To manage the data access based threats, a data processing system may include a network interface controller (NIC). The network interface controller may present emulated storages that may be used for data storage. The emulated storage devices may utilize storage resources of storage devices. The NIC may actively screen for access patterns in use of the emulated storage devices that indicate compute complexes may be compromised. When doing so, the processing may be done locally on the NIC.

Abstract: Methods and systems for managing data access based threats are disclosed. To manage the data access based threats, a data processing system may include a network interface controller (NIC). The network interface controller may present emulated storages that may be used for data storage. The emulated storage devices may utilize storage resources of storage devices. The NIC may actively screen for access patterns in use of the emulated storage devices that indicate compute complexes may be compromised. When doing so, the processing may be done locally on the NIC.

Abstract: Methods and systems for managing storage of data in a distributed system are disclosed. To manage storage of data in a distributed system, a data processing system may include a network interface controller (NIC). The network interface controller may present emulated storages that may be used for data storage. The emulated storage devices may utilize storage resources of storage devices. The storage devices may be remote to the NIC. To reduce communication bandwidth and/or use of resources of the storage devices, the NIC and/or NICs of other data processing systems may implemented a distributed cache for data stored in the storage devices. The NICs may implement a method of managing the distributed cache to maintain synchronization between the distributed cache and the data stored in the storage devices.

Abstract: Methods and systems for managing storage of data in a distributed system are disclosed. To manage storage of data in a distributed system, a data processing system may include a network interface controller (NIC). The network interface controller may present emulated storages that may be used for data storage. The emulated storage devices may utilize storage resources of storage devices. The storage devices may be remote to the NIC. To reduce communication bandwidth and/or use of resources of the storage devices, the NIC and/or NICs of other data processing systems may implemented a distributed cache for data stored in the storage devices. The NICs may implement a method of managing the distributed cache to maintain synchronization between the distributed cache and the data stored in the storage devices.

Abstract: Methods and systems for managing storage of data in a distributed system is disclosed. To manage storage of data in a distributed system, a data processing system may include a network interface controller (NIC). The NIC may present emulated storages that may be used for data storage. The emulated storage devices may utilize storage resources of storage devices. The NIC and the storage devices may implement a distributed deduplication process. The NIC may segment data into chunks and obtain fingerprints of the chunks. The fingerprints may be provided to the storage which may check the fingerprints against fingerprints of already stored chunks. The storage may request the chunks corresponding to the fingerprints that did not match any fingerprints of the already stored chunks. The NIC may provide only those requested chunks to the storage before discarding all of the chunks.

Abstract: A host can include a programmable network interface card (NIC) or “Smart NIC” which accesses host-local drives hidden from a host processor. One configuration can include a switch with a one logical partition including the NIC as a root complex (RC) and the local drives as end points (EPs), and with another logical partition including the host processor as an RC and the NIC as an EP. A second configuration can include the NIC and switch directly connected to the host processor with an access control component (ACC) configured on switch ports connected to the local drives. A third configuration can include the NIC and local drives directly connected to the host processor with the ACC configured on host processor ports connected to the local drives. The NIC can use a multi-layer driver to communicate with the ACC and local drives hidden behind the ACC.

Abstract: Traditionally, servers are interconnected inside a data center using regular network cards. It is desired that high-available network-attached storage arrays have the feature of non-disruptive upgrade (NDU) for software and firmware, while one or more applications are still running IO. With the emergence of SmartNICs, there are many functions available now to SmartNIC that may enhance server and entire solution capabilities. Since SmartNIC is a new emerging technology, there are no adequate solutions currently for NDU while running I/O. The present patent document discloses embodiments for upgrading the SmartNIC software without disruption to the host applications. A shared namespace may be implemented inside an emulated NVMe/PCIe device, such as a data processing unit (DPU) or infrastructure processing unit (IPU), such that multiple instances may be enabled to run both old and new target emulation SPDK-based software together using multiple paths to achieve SmartNIC storage NDU.

Abstract: Methods and systems for managing storage of data in a distributed system are disclosed. To manage storage of data in a distributed system, a data processing system may include a network interface controller (NIC). The NIC may present emulated storages that may be used for data storage. The emulated storage devices may be implemented with a storage pipeline that uses any number of storage devices that may be local or remote to the data processing system. The computing resources of the data processing system may view the emulated storage as a local device. The NIC may use its storage pipeline to service its own storage needs. By doing so, the NIC may improve the likelihood that its hosted applications have sufficient storage service access.

Abstract: A method, computer program product, and computing system for deploying a storage processor of a storage system as a target of a non-volatile memory express (NVMe) over fabric (NVMe-oF) network. One or more NVMe storage devices coupled to the storage processor may be identified, thus defining one or more local NVMe storage devices. A smart network interface card may be coupled to the NVMe-oF network. The smart network interface card may be provided with access to the one or more local NVMe storage devices via the NVMe-oF network.

Abstract: Methods and systems for managing storage of data in a distributed system are disclosed. To manage storage of data in a distributed system, a data processing system may include a network interface controller (NIC). The network interface controller may present emulated storages that may be used for data storage. The emulated storage devices may utilize storage resources of storage devices. Overtime, the data stored in various data storages may be migrated between the data storages. To migrate the data, the NIC may manage the migration process. To do so, the NIC may obtain various access requests (e.g., writes, reads) and process them in a manner that allows for the migration to be transparent. By doing so, migrations that are transparent to compute resources of data processing systems may be completed.

Abstract: Methods and systems for managing storage of data in a distributed system is disclosed. To manage storage of data in a distributed system, a data processing system may include a network interface controller (NIC). The NIC may present emulated storages that may be used for data storage. The emulated storage devices may utilize storage resources of storage devices. The NIC and the storage devices may implement a distributed deduplication process. The NIC may segment data into chunks and obtain fingerprints of the chunks. The fingerprints may be provided to the storage which may check the fingerprints against fingerprints of already stored chunks. The storage may request the chunks corresponding to the fingerprints that did not match any fingerprints of the already stored chunks. The NIC may provide only those requested chunks to the storage before discarding all of the chunks.