Abstract: A baseboard management controller (BMC) of a system can retrieve logged system events from a non-volatile storage of the BMC and receive a command from an administrator device for the BMC to collect system debug information. The BMC can obtain debug information from a component of the system, in response to receiving the command. The BMC can save the debug information to a debug file and send the debug file to the administrator device.

Abstract: Various embodiments of the present technology provide methods for activating a security module of a rack system prior to the loading of an operating system. The security module can be configured to examine server platform security, communicate with an administrator through a baseboard management controller (BMC), certify signatures of firmware pieces on a motherboard of the rack system, exclude malware by isolating unsigned UEFI images, examine a signature list and security key installed on the motherboard, and/or report status of security management to a controller of the rack system (e.g., BMC). When the security module determines that an uncertified firmware or a bootable storage with malware is loaded onto the rack system, the security module can stop process(es) associated with the uncertified firmware and/or the bootable storage, and subsequently send a report the administrator.

Abstract: A method for power management by a rack management controller (RMC) of a server rack includes collecting power consumption data from a first baseboard management controller (BMC) of a first server in the server rack and sending the power consumption data to a management server. The RMC receives power requirements from the management server and determines a power setting based on the power consumption data and the power requirements. The RMC requests the first BMC to limit power consumption of the first server according to the power setting.

Abstract: A system, method and computer-readable storage devices for providing protection mechanisms to a server motherboard prior to its booting. A system configured according to this would, upon receiving power at a motherboard, and prior to booting the motherboard: generate a nonce, send the nonce to a first component on the motherboard, and send the nonce to a second component on the motherboard. The system then receives a response from at least one of the first component on the motherboard and the second component on the motherboard, wherein the response is based on a communication protocol between the first component and the second component, the communication protocol utilizing the nonce. When the response indicates a correct hardware configuration, the system performs the booting of the motherboard.

Abstract: Systems, methods, and computer-readable storage media for hardware recovery are disclosed. In some examples, a system can detect a hardware error and identify a system component associated with the hardware error. The system can then generate a request configured to trigger an operating system of the system to place the system in a particular operating state. The particular operating state can be determined based on a component type of the system component. The particular operating state can be a first sleep state when the component type is a peripheral component or a second sleep state when the component type is a processor, a memory, or a power supply. The second sleep state can result in a lower power resource consumption than the first sleep state. The system can generate an indication that the system component can be replaced without restarting the operating system.

Abstract: A system, method and computer-readable storage devices for providing protection mechanisms to a server motherboard prior to its booting. A system configured according to this would, upon receiving power at a motherboard, and prior to booting the motherboard: generate a nonce, send the nonce to a first component on the motherboard, and send the nonce to a second component on the motherboard. The system then receives a response from at least one of the first component on the motherboard and the second component on the motherboard, wherein the response is based on a communication protocol between the first component and the second component, the communication protocol utilizing the nonce. When the response indicates a correct hardware configuration, the system performs the booting of the motherboard.

Abstract: Various embodiments of the present technology provide methods for activating a security module of a rack system prior to the loading of an operating system. The security module can be configured to examine server platform security, communicate with an administrator through a baseboard management controller (BMC), certify signatures of firmware pieces on a motherboard of the rack system, exclude malware by isolating unsigned UEFI images, examine a signature list and security key installed on the motherboard, and/or report status of security management to a controller of the rack system (e.g., BMC). When the security module determines that an uncertified firmware or a bootable storage with malware is loaded onto the rack system, the security module can stop process(es) associated with the uncertified firmware and/or the bootable storage, and subsequently send a report the administrator.

Abstract: A system and method for providing security key exchange and management prior to the operating system of the server and also provides for executing various security functions to prevent a virus or malicious software from propagating through the server and the network. The system and method utilize the BIOS firmware and baseboard management controller (BMC), which are more secure since they do not rely on open source code for software plug-ins from the user layer. As a result, a secure code can be created for key management with a globally unique identifier (GUID). The system and method provides for a network manager to easily and flexibly manage multiple security keys for a rack server system.

Abstract: A baseboard management controller (BMC) of a system can retrieve logged system events from a non-volatile storage of the BMC and receive a command from an administrator device for the BMC to collect system debug information. The BMC can obtain debug information from a component of the system, in response to receiving the command. The BMC can save the debug information to a debug file and send the debug file to the administrator device.

Abstract: Each of a plurality of Basic Input/Output System (BIOS) performance profiles can be determined upon a corresponding performance goal. A particular performance profile can be selected from the plurality of BIOS performance profiles. A BIOS configuration can be determined for a computer system automatically based at least in part on the particular performance profile or a hardware configuration of the computer system. The computer system can be initialized with the BIOS configuration.

Abstract: A plurality of BIOS default configurations may be is stored in a BIOS of the computer system. A particular BIOS default configuration may be selected from the plurality of BIOS default configurations based at least in part on a server identification (ID) of the computer system or a user command. The computer system is initialized with the particular BIOS default configuration.

Abstract: Various examples of the present technology provide systems and methods for testing whether there is any memory error in a server system, determining physical memory addresses corresponding to a detected memory error on one or more memory devices of the server system, and preventing the physical memory addresses corresponding to the detected memory error from accessing by an operating system, application programs, and/or other components of the server system.

Abstract: A computer system and a diagnostic method thereof are provided. The computer system comprises a system management bus (SMBus) switch, a plurality of servers and a remote management controller (RMC). Each server comprises a diagnostic message port, a basic input output system (BIOS) and a logic circuit. The BIOS outputs a diagnostic message to the diagnostic message port. The logic circuit catches the diagnostic message. The RMC comprises a SMBus host controller. The SMBus host controller controls the SMBus switch to connect the SMBus host controller to a corresponding logic circuit according to a request. The logic circuit responds the diagnostic message to the SMBus host controller according to the request.

Abstract: A computer system and an operation system loading method thereof are provided. The computer system comprises a universal serial bus (USB) storage device storing a boot image, servers and a boot image sharer comprising USB ports, a memory, a first USB host controller and a micro-processor. The micro-processor controls the first USB host controller to emulate each USB port to the USB storage device, and stores the boot image to memory, such that the boot image is shared to the USB ports. The servers are respectively coupled to the USB ports, wherein each server comprises a second USB host controller and a basic input output system (BIOS). The second USB host controller is coupled to one of the USB ports. The BIOS reads the boot image from the emulated USB storage device and loads an operation system according to the boot image.

Abstract: A computer system and a diagnostic method thereof are provided. The computer system comprises a system management bus (SMBus) switch, a plurality of servers and a remote management controller (RMC). Each server comprises a diagnostic message port, a basic input output system (BIOS) and a logic circuit. The BIOS outputs a diagnostic message to the diagnostic message port. The logic circuit catches the diagnostic message. The RMC comprises a SMBus host controller. The SMBus host controller controls the SMBus switch to connect the SMBus host controller to a corresponding logic circuit according to a request. The logic circuit responds the diagnostic message to the SMBus host controller according to the request.

Abstract: A computer system and an operation system loading method thereof are provided. The computer system comprises a universal serial bus (USB) storage device storing a boot image, servers and a boot image sharer comprising USB ports, a memory, a first USB host controller and a micro-processor. The micro-processor controls the first USB host controller to emulate each USB port to the USB storage device, and stores the boot image to memory, such that the boot image is shared to the USB ports. The servers are respectively coupled to the USB ports, wherein each server comprises a second USB host controller and a basic input output system (BIOS). The second USB host controller is coupled to one of the USB ports. The BIOS reads the boot image from the emulated USB storage device and loads an operation system according to the boot image.

Abstract: The invention discloses a remote hardware inspection system, including a remote monitor station and a client server. The monitor station includes a hardware inspection unit and a first network interface. The hardware inspection unit is for generating a hardware inspection command which is transmitted to the server by the first network interface. The server includes a second network interface, an input/output unit, and a managing/controlling unit. The input/output unit has an inspection program. The second network interface receives the hardware inspection command and transmits it to the managing/controlling unit. In response to the hardware inspection command, the managing/controlling unit generates and transmits a trigger signal to the input/output unit to implement the inspection program. Thereby, the inspection program writes data into the target hardware of the server according to the content of the hardware inspection command.

Abstract: The invention discloses a remote hardware inspection system, including a remote monitor station and a client server. The monitor station includes a hardware inspection unit and a first network interface. The hardware inspection unit is for generating a hardware inspection command which is transmitted to the server by the first network interface. The server includes a second network interface, an input/output unit, and a managing/controlling unit. The input/output unit has an inspection program. The second network interface receives the hardware inspection command and transmits it to the managing/controlling unit. In response to the hardware inspection command, the managing/controlling unit generates and transmits a trigger signal to the input/output unit to implement the inspection program. Thereby, the inspection program writes data into the target hardware of the server according to the content of the hardware inspection command.

Abstract: A method of data reading and writing includes the following steps: when a service routine is called by a local device to execute an action of reading in a floppy disk drive or a CD-ROMdrive, the service routine will cancel the original action of accessing the local device, redirect the accessing command and related data, send a network packet including the redirected accessing command and inputted data to the remote device afterwards. Then, the agent program in the remote device will access the remote storage medium according to the received accessing command and related data, and transfer the requested data back to the local device to proceed with a booting procedure or to execute related programs under DOS.