Abstract: A redundant array of independent drives controller and board controlled cache off-loading during a power failure is described. Methods associated with the use of the redundant array of independent drives controller and board for controlled cache off-loading during a power failure are also described.

Abstract: Systems and methods presented herein provide for resetting a controller in a Single Root Input/Output Virtualization (SR-IOV) architecture. The architecture includes a physical function that periodically issues a heartbeat command to a physical function of an SR-IOV controller, starts a first timer, determines a firmware failure of the controller upon expiration of the first timer, and issues a command to reset the firmware of the controller. The architecture also includes a plurality of a virtual function drivers coupled to a plurality of virtual functions of the controller. Each virtual function driver periodically issues a heartbeat command to its corresponding virtual function, starts a second timer having a duration that is less than a duration of the first timer, determines a firmware failure of the controller upon expiration of the second timer, and pauses input/output operations to its corresponding virtual function until the firmware of the controller is reset.

Abstract: In one embodiment, a Peripheral Component Interconnect Express (PCIe) Input/Output (I/O) device operable to perform Single Root I/O Virtualization (SR-IOV) is provided. The device comprises hardware registers implementing a PCIe configuration space for the device, and firmware implementing one or more SR-IOV virtual functions that each provide a virtual machine access to a subset of PCIe configuration space hardware registers for the device. The device further includes a hardware recovery register directly accessible by each of the virtual machines, and a control unit. The control unit is operable to detect a firmware fault at the I/O device and to update the hardware recovery register with information describing the firmware fault.

Abstract: An apparatus configured to shadow volatile data while minimizing read latency is described. In an implementation, the apparatus includes a memory controller configured to operatively couple to a volatile memory device and a non-volatile memory device. The volatile memory device includes a volatile memory cell and the non-volatile memory device includes a corresponding non-volatile memory cell. The volatile memory device has a first transfer speed and the non-volatile memory device has a second transfer speed. The memory controller is configured to cause storage of data to the volatile memory cell and the non-volatile memory cell and to determine an occurrence of an unanticipated power outage. The memory controller is configured set a read speed to the second transfer speed and to cause replication of the data from the non-volatile memory cell to a corresponding volatile memory cell upon recovery from the unanticipated power outage.

Abstract: Methods and structure for enabling re-training of a DDR memory controller in a storage device without loss of data in the DDR memory devices of the cache memory in response to detecting failure of the memory subsystem during operation of the storage device. In response to detecting a failure of the memory subsystem, the memory controller is reset without resetting the memory devices. The memory controller is then re-trained for operation with the memory device. During the re-training, self-refresh mode of the memory devices is disabled and manual refresh is performed by a processor of the storage device to thereby retain any user data in the memory device.

Abstract: Systems and methods presented herein provide for resetting a controller in a Single Root Input/Output Virtualization (SR-IOV) architecture. The architecture includes a physical function that periodically issues a heartbeat command to a physical function of an SR-IOV controller, starts a first timer, determines a firmware failure of the controller upon expiration of the first timer, and issues a command to reset the firmware of the controller. The architecture also includes a plurality of a virtual function drivers coupled to a plurality of virtual functions of the controller. Each virtual function driver periodically issues a heartbeat command to its corresponding virtual function, starts a second timer having a duration that is less than a duration of the first timer, determines a firmware failure of the controller upon expiration of the second timer, and pauses input/output operations to its corresponding virtual function until the firmware of the controller is reset.

Abstract: In one embodiment, a Peripheral Component Interconnect Express (PCIe) Input/Output (I/O) device operable to perform Single Root I/O Virtualization (SR-IOV) is provided. The device comprises hardware registers implementing a PCIe configuration space for the device, and firmware implementing one or more SR-IOV virtual functions that each provide a virtual machine access to a subset of PCIe configuration space hardware registers for the device. The device further includes a hardware recovery register directly accessible by each of the virtual machines, and a control unit. The control unit is operable to detect a firmware fault at the I/O device and to update the hardware recovery register with information describing the firmware fault.

Abstract: A redundant array of independent drives controller and board controlled cache off-loading during a power failure is described. Methods associated with the use of the redundant array of independent drives controller and board for controlled cache off-loading during a power failure are also described.

Abstract: Methods and structure for enabling re-training of a DDR memory controller in a storage device without loss of data in the DDR memory devices of the cache memory in response to detecting failure of the memory subsystem during operation of the storage device. In response to detecting a failure of the memory subsystem, the memory controller is reset without resetting the memory devices. The memory controller is then re-trained for operation with the memory device. During the re-training, self-refresh mode of the memory devices is disabled and manual refresh is performed by a processor of the storage device to thereby retain any user data in the memory device.

Abstract: Methods and structure for rapid offloading of cached data in a volatile cache memory of a storage controller to a nonvolatile memory. Features and aspects hereof provide an enhanced storage controller having a volatile cache memory and multiple communication channels each coupled with a corresponding nonvolatile memory device. Responsive to detecting an impending loss of power, control logic of the controller copies data from the volatile cache memory to the multiple nonvolatile memories using the multiple communication channels operating substantially in parallel. Using multiple parallel channels and nonvolatile memory substantially temporally overlapping their operations assures that the cached data can be saved to nonvolatile memory before the controller is inoperable due to power loss. A simple “file system” and error detection and correction codes on the nonvolatile memory help assure that the saved data is valid for return to the volatile memory when power is restored to the controller.