Abstract: A method is provided for data storage management in a virtualized information handling system that includes a first and second network storage resource, a hypervisor allowing multiple virtual machines to run on the virtualized information handling system, and a data access agent. The data access agent may intercept a data access request initiated by a virtual machine and intended for the first network storage resource. In response to intercepting the data access request, the data access agent may establish a connection with the first network storage resource, and retrieve from the first network storage resource metadata associated with the data access request. The retrieved metadata may identify a location of the second network storage resource. Additionally, the data access may establish a connection with the second network storage resource using the location of the second network storage resource identified by the retrieved metadata.

Abstract: In accordance with the present disclosure, a system and method for transmitting communications over a transmission medium between a first component and a second component is provided. The system and method may include an information handling system in which a packet is defined. The packet may include at least one header at a specific bit location and a vendor defined header extension, located in a packet payload portion of the packet. The system and method may further include at least one control command defined within the information handling system. The at least one control command may, for example, be used to negotiate the meaning of at least one field in the header. In addition, the at least one control command may be used to handle and recover from errors within communications and to control the flow of communications once transmission has commenced.

Abstract: In accordance with embodiments of the present disclosure, a method may include receiving a read command. The method may also include determining if the read command is a command to read current data or historical data for a given logical address. The method may additionally include reading data stored on a storage resource at a historical physical address defined by a historical data offset associated with the given logical address in response to determining that the read command is a command to read historical data. The method may further include communicating the data stored at the historical physical address as a response to the read command.

Abstract: Systems and methods for performing RAID I/O operations in PCIe-based storage resources are disclosed. In accordance with embodiments of the present disclosure, a method for performing a read operation may be provided. The method may include overlaying memory address space of storage resources of a source logical unit for the read operation onto a destination address. The method may also include determining whether the source logical unit is a RAID0 array. The method may additionally include generating a source address in a receive buffer for each storage resource of the source logical unit if the source logical unit is a RAID0 array. The method may further include storing data received from each storage address of the logical unit at the generated source address of the receive buffer associated with such storage resource.

Abstract: Virtualization of I/O devices to support operation of plural virtual machines on a host information handling system is managed with distributed translation agents that translate addresses generated from I/O devices according to mapping defined by a virtual machine monitor. The translation agents reside in the host I/O subsystem, such as at I/O hubs or at I/O devices. A discovery module discovers and configures plural translation agents to coordinate I/O device communications with translation of physical memory addresses and virtual I/O addresses.

Abstract: Redundant storage of information is provided by distributing storage functions between a RAID controller and switching device. The switching device multi-casts writes to storage devices and to the RAID controller. The RAID controller generates parity for the information and writes the parity to the storage devices in space reserved for parity by the switching device. Information is read from the storage devices through the switching device without action by the RAID controller.

Abstract: A method may include determining based on at least one data scrubbing parameter associated with at least one storage resource that the at least one storage resource is scheduled for a data scrubbing operation. The method may also include cause the at least one storage resource to transition from a low-power mode to a normal-power mode in order to perform a data scrubbing operation in response to a determination that the at least one storage resource is scheduled for a data scrubbing operation. The method may additionally include determining based on the at least one data scrubbing parameter that the data scrubbing operation is scheduled to cease. The method may further comprise causing the at least one storage resource to transition from the normal-power mode to the low-power mode in response to a determination that the data scrubbing operation is scheduled to cease.

Abstract: In accordance with embodiments of the present disclosure, a method may include receiving a read command. The method may also include determining if the read command is a command to read current data or historical data for a given logical address. The method may additionally include reading data stored on a storage resource at a historical physical address defined by a historical data offset associated with the given logical address in response to determining that the read command is a command to read historical data. The method may further include communicating the data stored at the historical physical address as a response to the read command.

Abstract: A method is provided for managing errors in a virtualized information handling system that includes an error detection system and a hypervisor allowing multiple virtual machines to run on the information handling system. The hypervisor may assign at least one memory region to each of multiple virtual machines. The error detection system may detect an error, determine a physical memory address associated with the error, and report that address to the hypervisor. Additionally, the hypervisor may determine whether the memory region assigned to each virtual machine includes the physical memory address associated with the error. The hypervisor may shut down each virtual machine for which a memory region assigned to that virtual machine includes the physical memory address associated with the error, and not shut down each virtual machine for which the memory regions assigned to that virtual machine do not include the physical memory address associated with the error.

Abstract: Redundant storage of information is provided by distributing storage functions between a RAID controller and switching device. The switching device multi-casts writes to storage devices and to the RAID controller. The RAID controller generates parity for the information and writes the parity to the storage devices in space reserved for parity by the switching device. Information is read from the storage devices through the switching device without action by the RAID controller.

Abstract: Systems and methods for performing RAID I/O operations in PCIe-based storage resources are disclosed. In accordance with embodiments of the present disclosure, a method for performing a read operation may be provided. The method may include overlaying memory address space of storage resources of a source logical unit for the read operation onto a destination address. The method may also include determining whether the source logical unit is a RAIDO array. The method may additionally include generating a source address in a receive buffer for each storage resource of the source logical unit if the source logical unit is a RAIDO array. The method may further include storing data received from each storage address of the logical unit at the generated source address of the receive buffer associated with such storage resource.

Abstract: A method is provided for managing errors in a virtualized information handling system that includes an error detection system and a hypervisor allowing multiple virtual machines to run on the information handling system. The hypervisor may assign at least one memory region to each of multiple virtual machines. The error detection system may detect an error, determine a physical memory address associated with the error, and report that address to the hypervisor. Additionally, the hypervisor may determine whether the memory region assigned to each virtual machine includes the physical memory address associated with the error. The hypervisor may shut down each virtual machine for which a memory region assigned to that virtual machine includes the physical memory address associated with the error, and not shut down each virtual machine for which the memory regions assigned to that virtual machine do not include the physical memory address associated with the error.

Abstract: In accordance with the present disclosure, a system and method for transmitting communications over a transmission medium between a first component and a second component is provided. The system and method may include an information handling system in which a packet is defined. The packet may include at least one header at a specific bit location and a vendor defined header extension, located in a packet payload portion of the packet. The system and method may further include at least one control command defined within the information handling system. The at least one control command may, for example, be used to negotiate the meaning of at least one field in the header. In addition, the at least one control command may be used to handle and recover from errors within communications and to control the flow of communications once transmission has commenced.

Abstract: A method is provided for managing errors in a virtualized information handling system that includes an error detection system and a hypervisor allowing multiple virtual machines to run on the information handling system. The hypervisor may assign at least one memory region to each of multiple virtual machines. The error detection system may detect an error, determine a physical memory address associated with the error, and report that address to the hypervisor. Additionally, the hypervisor may determine whether the memory region assigned to each virtual machine includes the physical memory address associated with the error. The hypervisor may shut down each virtual machine for which a memory region assigned to that virtual machine includes the physical memory address associated with the error, and not shut down each virtual machine for which the memory regions assigned to that virtual machine do not include the physical memory address associated with the error.

Abstract: A method is provided for data storage management in a virtualized information handling system that includes a first and second network storage resource, a hypervisor allowing multiple virtual machines to run on the virtualized information handling system, and a data access agent. The data access agent may intercept a data access request initiated by a virtual machine and intended for the first network storage resource. In response to intercepting the data access request, the data access agent may establish a connection with the first network storage resource, and retrieve from the first network storage resource metadata associated with the data access request. The retrieved metadata may identify a location of the second network storage resource. Additionally, the data access may establish a connection with the second network storage resource using the location of the second network storage resource identified by the retrieved metadata.

Abstract: A system and method that allows a plurality of SR-PCIMs to operate within a PCIe fabric. The system and method describe a master SR-PCIM election process and transfer of mastership from a master SR-PCIM to a standby SR-PCIM under certain conditions. The system and method leverage the PCI configuration space and PCI messages so that SR-PCIMs from multiple vendors can potentially interoperate.

Abstract: A method is provided for managing errors in a virtualized information handling system that includes an error detection system and a hypervisor allowing multiple virtual machines to run on the information handling system. The hypervisor may assign at least one memory region to each of multiple virtual machines. The error detection system may detect an error, determine a physical memory address associated with the error, and report that address to the hypervisor. Additionally, the hypervisor may determine whether the memory region assigned to each virtual machine includes the physical memory address associated with the error. The hypervisor may shut down each virtual machine for which a memory region assigned to that virtual machine includes the physical memory address associated with the error, and not shut down each virtual machine for which the memory regions assigned to that virtual machine do not include the physical memory address associated with the error.

Abstract: A system and method that allows a plurality of SR-PCIMs to operate within a PCIe fabric. The system and method describe a master SR-PCIM election process and transfer of mastership from a master SR-PCIM to a standby SR-PCIM under certain conditions. The system and method leverage the PCI configuration space and PCI messages so that SR-PCIMs from multiple vendors can potentially interoperate.

Abstract: Virtualization of I/O devices to support operation of plural virtual machines on a host information handling system is managed with distributed translation agents that translate addresses generated from I/O devices according to mapping defined by a virtual machine monitor. The translation agents reside in the host I/O subsystem, such as at I/O hubs or at I/O devices. A discovery module discovers and configures plural translation agents to coordinate I/O device communications with translation of physical memory addresses and virtual I/O addresses.

Abstract: For backing up of data from a source to a destination, a virtual tape library (VTL) appliance intercepts a message for backing up the data. In response to the intercepted message, the VTL appliance sends a command to initiate the backing up of the data. A network attached storage (NAS) server, which is the source of the data and is coupled to the VTL appliance by a network, receives the command. An agent located in the NAS server is triggered in response to the command to directly transfer the data from the source to the destination. The agent informs the VTL appliance upon completion of the transfer of the data.