Abstract: A system and method for logging error data from a central processing unit on a computer system using a dedicated crash dump device, is disclosed. The central processing unit has a management engine. The central processing unit sends an error signal. The dedicated crash dump device is coupled to the central processing unit to receive the error signal. A storage device is coupled to the crash dump device. The crash dump device sends a request to the central processing unit for error data. The crash dump device receives error data from the central processing unit. The crash dump device stores the error data in the storage device.

Abstract: Systems and methods are described for improved cooling behavior in computer systems using fan-based cooling systems. In particular, the systems and methods utilize two types of techniques can be used for providing improved cooling behavior: hardware-based techniques and software-based techniques. These techniques can be used separately or in combination.

Abstract: Systems and methods are described for improved cooling behavior in computer systems using fan-based cooling systems. In particular, the systems and methods utilize two types of techniques can be used for providing improved cooling behavior: hardware-based techniques and software-based techniques. These techniques can be used separately or in combination.

Abstract: The present technology provides a system and method for smartly resetting a hang device of a server system based upon a Wake-on-Lan (WoL) message and status of the hang device. The system comprises a management device, a switch, a physical layer (PHY) coupled to a network, a network interface (NIC), a monitoring device and a delay circuit. The PHY is coupled to the network to receive network packets that includes a WoL message. The monitoring device is configured to receive status information from the management device and the WoL message, and reset the management device based upon received information.

Abstract: The present technology provides a system and method for selectively powering down active component(s) of a system based upon PSU status and power demand of the system. The present technology enables the system in operation as long as the system has at least one operative PSU. The system comprises a plurality of active components, two or more PSUs, a management device and a hardware device. The hardware device can receive status information of the two or more PSUs and system power demand information. In response to determining that the power capacity of the two or more PSUs is less than the power demand of the system, the hardware device can determine status of the PSUs. In response to determining that the status of at least one PSU is not ok, the hardware device can turn off at least one of the plurality of active components based upon a power-down sequence.

Abstract: The present technology provides a system and method for smartly resetting a hang device of a server system based upon a Wake-on-Lan (WoL) message and status of the hang device. The system comprises a management device, a switch, a physical layer (PHY) coupled to a network, a network interface (NIC), a monitoring device and a delay circuit. The PHY is coupled to the network to receive network packets that includes a WoL message. The monitoring device is configured to receive status information from the management device and the WoL message, and reset the management device based upon received information.

Abstract: A system and method of using a baseboard management controller (BMC) to detect a fault on a communication bus. The BMC is connected to and monitors the operation of the communication bus. The BMC automatically detects a communication bus hang and reports bus hang to the host. The BMC attempts to access the communication bus. If the BMC can access the communication bus, the BMC then resets all of the devices connected to the communication bus. The BMC then attempts to contact components connected to the devices. If a component is not accessible via its communication device, the BMC blocks the channel used by the component and reports that information. Once the BMC detects that the component has been removed, the BMC attempts to recover the channel via the I2C/SM bus for use by the computer network.

Abstract: A system and method of using a baseboard management controller (BMC) to detect a fault on a communication bus. The BMC is connected to and monitors the operation of the communication bus. The BMC automatically detects a communication bus hang and reports bus hang to the host. The BMC attempts to access the communication bus. If the BMC can access the communication bus, the BMC then resets all of the devices connected to the communication bus. The BMC then attempts to contact components connected to the devices. If a component is not accessible via its communication device, the BMC blocks the channel used by the component and reports that information. Once the BMC detects that the component has been removed, the BMC attempts to recover the channel via the I2C/SM bus for use by the computer network.