Abstract: Technologies for quality of service (QoS) management include a computing device having a physical storage volume and multiple processor cores. A management thread reads I/O counters that are each associated with a logical volume and a processor core. The logical volumes are backed by the physical storage volume. The management thread configures stop bits as a function of the I/O counters and multiple QoS parameters. Each stop bit is associated with a logical volume and a processor core. The QoS parameters include minimum guaranteed bandwidth and optional maximum allowed bandwidth for each logical volume. A worker thread reads the stop bit associated with a logical volume and a processor core, accesses the logical volume if the stop bit is not set, and updates the I/O counter associated with the logical volume and the processor core in response to accessing the logical volume. Other embodiments are described and claimed.

Abstract: Technologies for quality of service (QoS) management include a computing device having a physical storage volume and multiple processor cores. A management thread reads I/O counters that are each associated with a logical volume and a processor core. The logical volumes are backed by the physical storage volume. The management thread configures stop bits as a function of the I/O counters and multiple QoS parameters. Each stop bit is associated with a logical volume and a processor core. The QoS parameters include minimum guaranteed bandwidth and optional maximum allowed bandwidth for each logical volume. A worker thread reads the stop bit associated with a logical volume and a processor core, accesses the logical volume if the stop bit is not set, and updates the I/O counter associated with the logical volume and the processor core in response to accessing the logical volume. Other embodiments are described and claimed.

Abstract: Method and apparatus for asynchronous discovery of processing and storage nodes coupled via an expander switch in a fabric. In some embodiments, an initiator device operates as a processing node to transfer data to and from a non-volatile memory (NVM) of a target device at a storage node. One of the initiator or target devices is activated prior to the other device. The second activated device broadcasts a discovery command responsive to the activation of the second activated device and prior to receipt of a request for the discovery command from the first activated device. The first activated device processes the discovery command to establish an I/O communication link between the first activated device and the second activated device. The discovery command may include a non-volatile memory express (NVMe) controller list, and the NVM may be arranged as one or more NVMe namespaces.

Abstract: The disclosed technology provides for selection of a subset of available non-volatile memory devices in an array to receive a dirty cache data of a volatile cache responsive to detection of a power failure. In one implementation, the selection of the non-volatile memory devices is based on one or more predictive power parameters usable to estimate a time remaining during which a reserve power supply can support a cache offload to the selected subset of devices.

Abstract: Method and apparatus for asynchronous discovery of processing and storage nodes coupled via an expander switch in a fabric. In some embodiments, an initiator device operates as a processing node to transfer data to and from a non-volatile memory (NVM) of a target device at a storage node. One of the initiator or target devices is activated prior to the other device. The second activated device broadcasts a discovery command responsive to the activation of the second activated device and prior to receipt of a request for the discovery command from the first activated device. The first activated device processes the discovery command to establish an I/O communication link between the first activated device and the second activated device. The discovery command may include a non-volatile memory express (NVMe) controller list, and the NVM may be arranged as one or more NVMe namespaces.

Abstract: The disclosed technology provides for selection of a subset of available non-volatile memory devices in an array to receive a dirty cache data of a volatile cache responsive to detection of a power failure. In one implementation, the selection of the non-volatile memory devices is based on one or more predictive power parameters usable to estimate a time remaining during which a reserve power supply can support a cache offload to the selected subset of devices.

Abstract: A storage controller coupled to a host computer is dynamically configured by a device driver executing in the host computer. The storage controller manages a logical volume for the host using a set of flash-based storage devices arranged as a redundant array of inexpensive disks (RAID). The device driver identifies a RAID type for the logical volume and a queue depth from a stream of I/O commands. For a logical volume in RAID 0, the device driver compares the queue depth to a threshold value and configures the storage controller to process the stream of I/O commands with a first path or an alternative path based on a result of the comparison. For a logical volume in RAID 5, the device driver performs a similar comparison and uses the result to direct the storage controller to use a write back or a write through mode of operation.

Abstract: A storage controller coupled to a host computer is dynamically configured by a device driver executing in the host computer. The storage controller manages a logical volume for the host using a set of flash-based storage devices arranged as a redundant array of inexpensive disks (RAID). The device driver identifies a RAID type for the logical volume and a queue depth from a stream of I/O commands. For a logical volume in RAID 0, the device driver compares the queue depth to a threshold value and configures the storage controller to process the stream of I/O commands with a first path or an alternative path based on a result of the comparison. For a logical volume in RAID 5, the device driver performs a similar comparison and uses the result to direct the storage controller to use a write back or a write through mode of operation.

Abstract: A cache controller implemented in O/S kernel, driver and application levels within a guest virtual machine dynamically allocates a cache store to virtual machines for improved responsiveness to changing demands of virtual machines. A single cache device or a group of cache devices are provisioned as multiple logical devices and exposed to a resource allocator. A core caching algorithm executes in the guest virtual machine. As new virtual machines are added under the management of the virtual machine monitor, existing virtual machines are prompted to relinquish a portion of the cache store allocated for use by the respective existing machines. The relinquished cache is allocated to the new machine. Similarly, if a virtual machine is shutdown or migrated to a new host system, the cache capacity allocated to the virtual machine is redistributed among the remaining virtual machines being managed by the virtual machine monitor.

Abstract: Disclosed is a microprocessor based system with a dynamically selectable Operating System that is capable of providing unique operating systems based upon current hardware states without user intervention. The system will determine the current state of the system and select from a plurality of operating systems the best operating system to load. In normal operating conditions the system will select the most full-featured and robust operating system. If, for example, the system loses alternating-current power, the system will shutdown, reboot, and automatically select an operating system with very limited capabilities and limited power consumption to allow the system to retrieve important data from the cache and store the data to a data storage device.

Abstract: An I/O scheduler and a method for scheduling I/O requests to a solid-state drive (SSD) is disclosed. The I/O scheduler in accordance with the present disclosure bundles the write requests in such a form that the write requests in each bundle goes into one SSD block. Bundling the write requests in accordance with the present disclosure reduces write amplification and increases system performance. The I/O scheduler in accordance with the present disclosure also helps increasing the life of the SSDs.