Abstract: Systems, methods, apparatuses, and software for data systems are provided herein. In one example, a data system is presented. The system includes a processing system configured to execute an operating system that comprises a network module for handling data frames directed to a plurality of kernel threads and received over one or more network interfaces of the data system. The network module is configured to establish a plurality of data buffers individually associated with the kernel threads, store associated ones of the data frames for the kernel threads in the data buffers as the data frames are processed through a network stack of the data system, and maintain data exclusivity locks for the plurality of data buffers and individually associate the data exclusivity locks with the kernel threads.

Abstract: Systems, methods, apparatuses, and software for data storage systems are provided herein. In one example, a data storage system is provided that includes processing systems configured to receive storage operations for storage drives coupled over a communication fabric. The data storage system includes a control processor configured to establish a timer synchronization signal and distribute the timer synchronization signal to the processing systems. Each of the processing systems is configured to assign timestamps to received storage operations based on a timestamp counter synchronized among the processing systems using the timer synchronization signal. The processing systems are configured to order committing of the storage operations to the storage drives based at least on the timestamps associated with the storage operations.

Abstract: Systems, methods, apparatuses, and software for data storage systems are provided herein. In one example, a data storage system is provided that includes a processor and a network interface having a tunneled network connection established with another network interface associated with another processor. The processor is configured to receive one or more packets indicating the network interface as a network destination and comprising a storage operation, and inspect at least a storage address included in a header of the one or more packets to determine that the storage operation corresponds to a storage drive managed by the other processor. The processor is configured to establish one or more further packets comprising the storage operation and having a header modified from the one or more packets to indicate a network address of the other network interface, and transfer the one or more further packets for delivery to the other network interface.

Abstract: Systems, methods, apparatuses, and software for data storage systems are provided herein. In one example, a data storage apparatus includes a processor configured to assign service levels in a queue for handling storage operations directed to one or more data storage drives. The processor can pre-allocate resources in the queue for selected ones of the service levels before ones of the storage operations associated with the selected ones of the service levels are received by the processor. The processor receives the storage operations, and based at least on the service levels, services the storage operations from the queue with the one or more data storage drives.

Abstract: Disaggregated computing architectures, platforms, and systems are provided herein. In one example, a method of operating a data system is provided. The method includes initiating an isolation function in a communication fabric to form a peer arrangement between graphics processing units (GPUs) coupled to the communication fabric. The isolation function isolates a first address domain associated with the GPUs from at least a second address domain associated with the host by at least establishing synthetic devices representing the GPUs in the second address domain.

Abstract: Systems, methods, apparatuses, and software for computing systems are provided herein. In one example, a computing system includes a first processor configured to establish a network connection with a target system, and transfer to a second processor information describing the network connection comprising a network address and a network port. The computing system includes the second processor configured to identify when the first processor has failed, and responsively inherit the network connection with the target system based at least on the information describing the network connection and packet sequence information received from the target system to resume packet acknowledge or sequence counts established between the first processor and the target system.

Abstract: Systems, methods, apparatuses, and software for data storage systems are provided herein. In one example, a data storage system is provided that includes storage drives each comprising a PCIe interface, and configured to store data and retrieve the data stored on associated storage media responsive to data transactions received over a switched PCIe fabric. The data storage system includes processors configured to each manage only an associated subset of the storage drives over the switched PCIe fabric. A first processor is configured to identify first data packets received over a network interface associated with the first processor within a network buffer of the first processor as comprising a storage operation associated with at least one of the plurality of storage drives managed by a second processor, and responsively transfer the first data packets into a network buffer of the second processor.

Abstract: Systems, methods, apparatuses, and software for data systems are provided herein. In one example, a data system is presented. The system includes a processing system configured to execute an operating system that comprises a network module for handling data frames directed to a plurality of kernel threads and received over one or more network interfaces of the data system. The network module is configured to establish a plurality of data buffers individually associated with the kernel threads, store associated ones of the data frames for the kernel threads in the data buffers as the data frames are processed through a network stack of the data system, and maintain data exclusivity locks for the plurality of data buffers and individually associate the data exclusivity locks with the kernel threads.

Abstract: Systems, methods, apparatuses, and software for data storage systems are provided herein. In one example, a data storage system is provided that includes at least one storage drive and at least one processing module coupled over a Peripheral Component Interconnect Express (PCIe) fabric. The data storage system includes a first processing module in a first storage assembly configured to receive a storage operation for a storage drive managed by a second processing module in a second storage assembly. The first processing module is configured to identify the second processing module as managing the storage drive associated with the storage operation and responsively transfer the storage operation over a tunneled network connection for handling by the second processing module of the second storage assembly.

Abstract: Systems, methods, apparatuses, and software for data storage systems are provided herein. In one example, a data storage platform includes one or more data storage modules each comprising storage drives coupled over a Peripheral Component Interconnect Express (PCIe) fabric with at least one processing module that receives storage operations directed to the one or more data storage modules over one or more network interfaces. The processing module is configured to assign service levels in a queue to the storage operations that are received over the one or more network interfaces. Based at least on the service levels, the processing module is configured to service the storage operations from the queue with the one or more data storage modules over the PCIe fabric.

Abstract: Systems, methods, apparatuses, and software for data storage systems are provided herein. In one example, a data storage system is provided that includes a first processor configured to establish a network connection with an external system, and receive first storage operations transferred by the external system over the network connection, the first storage operations related to storage and retrieval of data on at least one storage drive. The first processor is configured to transfer information describing the network connection for delivery to at least a second processor. The second processor is configured to identify when the first processor has failed, responsively establish the network connection with the external system based at least on the information describing the network connection, and receive second storage operations transferred by the external system over the network connection.

Abstract: Disaggregated computing architectures, platforms, and systems are provided herein. In one example, a method of operating a data processing system is provided. The method includes communicatively coupling graphics processing units (GPUs) over a Peripheral Component Interconnect Express (PCIe) fabric. The method also includes establishing a peer-to-peer arrangement between the GPUs over the PCIe fabric by at least providing an isolation function in the PCIe fabric configured to isolate a device PCIe address domain associated with the GPUs from at least a local PCIe address domain associated with a host processor that initiates the peer-to-peer arrangement between the GPUs.

Abstract: Disaggregated computing architectures, platforms, and systems are provided herein. In one example, a method of operating a data processing system is provided. The method includes communicatively coupling graphics processing units (GPUs) over a Peripheral Component Interconnect Express (PCIe) fabric. The method also includes establishing a peer-to-peer arrangement between the GPUs over the PCIe fabric by at least providing an isolation function in the PCIe fabric configured to isolate a device PCIe address domain associated with the GPUs from at least a local PCIe address domain associated with a host processor that initiates the peer-to-peer arrangement between the GPUs.

Abstract: Disaggregated computing architectures, platforms, and systems are provided herein. In one example, a data system is provided. The data system includes a first assembly comprising a plurality of modular storage bays populated with one or more graphics processing modules each including a graphics processing unit (GPU), wherein the plurality of modular storage bays each comprise a bay connector that includes a bay Peripheral Component Interconnect Express (PCIe) connection. The first assembly further comprises PCIe switch circuitry configured to communicatively couple the bay PCIe connections to a PCIe fabric over one or more external PCIe links.

Abstract: A connectivity card insertable into a connector of a host system is provided. The connectivity card includes a plurality of Peripheral Component Interconnect Express (PCIe) connectors configured to provide external PCIe ports on the connectivity card, each of the plurality of PCIe connectors capable of carrying PCIe traffic. The connectivity card also includes a PCIe switch circuit configured to communicatively couple the plurality of connectors to a shared connectivity interface carried over a host connector of the connectivity card. The connectivity card further includes control circuitry configured to monitor for connectivity issues that arise with regard to the plurality of PCIe connectors, and responsively mitigate the connectivity issues by at least reconfiguring a communication pathway in the PCIe switch circuit for at least a portion of the PCIe traffic affected by the connectivity issues.

Abstract: Systems, methods, apparatuses, and software for networked data systems are provided herein. In one example, a networked data processing system is presented. The system includes a processing system configured to execute an operating system that comprises a network module for handling data frames received over one or more network interfaces of the networked data processing system, the data frames directed to one or more applications. The network module is configured to establish a plurality of data buffers individually associated with application threads of the one or more applications, store associated ones of the data frames for the application threads in the data buffers as the data frames are processed through a network stack of the networked data processing system, and maintain data exclusivity locks for the plurality of data buffers and individually associate the data exclusivity locks with the application threads.

Abstract: Disaggregated computing architectures, platforms, and systems are provided herein. In one example, a method of operating a disaggregated computing architecture is presented. The method includes, receiving user commands to establish compute units among a plurality of physical computing components, each of the compute units comprising one or more of the plurality of physical computing components selected from among central processing units (CPUs), graphics processing units (GPUs), storage modules, and network interface modules. The method also includes forming the compute units based at least on logical partitioning within a Peripheral Component Interconnect Express (PCIe) fabric communicatively coupling the plurality of physical computing components, wherein each of the compute units have visibility over the PCIe fabric to the one or more of the plurality of physical computing components assigned to the associated compute units using the logical partitioning within the PCIe fabric.

Abstract: Disaggregated computing architectures, platforms, and systems are provided herein. In one example, a method of operating at graphical user interface system to a disaggregated computing platform is provided. The method includes receiving user input for a cluster interface portion to establish compute clusters comprising compute units for executing user software thereon, and receiving further user input to add physical resources into one or more compute units that are coupled over a Peripheral Component Interconnect Express (PCIe) fabric and associate the one or more compute units to associated ones of the compute clusters, the physical resources comprising processing resources, storage resources, and network interface resources. The method also includes presenting indications of the formation of the physical resources into the compute units and the compute units into the compute clusters, and presenting telemetry data related to operation of at least the compute units.

Abstract: Disaggregated computing architectures, platforms, and systems are provided herein. In one example, a method of operating compute units is presented that includes forming compute units among a plurality of physical computing components comprising at least central processing units (CPUs), storage modules, and network interface modules coupled over a Peripheral Component Interconnect Express (PCIe) fabric configured to communicatively couple the plurality of physical computing components and isolate the compute unit in the clustered environment using logical partitioning within the PCIe fabric. The method also includes initiating a software component deployed to at least associated CPUs within the compute units, reporting telemetry to the management processor related to operation of the compute unit, and emulating operation of an Ethernet interface to an operating system of the associated CPU for transfer of communications comprising at least the telemetry to the management processor over the PCIe fabric.

Abstract: Systems, methods, apparatuses, and software for data storage systems are provided herein. In one example, a data storage system is provided that includes storage drives each comprising a PCIe interface, and configured to store data and retrieve the data stored on associated storage media responsive to data transactions received over a switched PCIe fabric. The data storage system includes processors configured to each manage only an associated subset of the storage drives over the switched PCIe fabric. A first processor is configured to identify first data packets received over a network interface associated with the first processor within a network buffer of the first processor as comprising a storage operation associated with at least one of the plurality of storage drives managed by a second processor, and responsively transfer the first data packets into a network buffer of the second processor.