System and method for managing, resetting and diagnosing failures of a device management bus
View Patent ↗Embodiments are described for operating a device management bus coupled to a remote access controller and a managed device. The remote access controller detects an inoperable state of the bus and determines a FRU (Field Replaceable Unit) memory is accessible on the managed device. A predefined reset indicator is written to the FRU memory. The managed device monitors for the reset indicator being written to a specified location in FRU memory. Upon detecting the reset indicator in FRU memory, the managed device resets a bus controller coupled to the device management bus and transmits a reset notification on the device management bus. The remote access controller may include an I2C shim that controls access to an I2C multiplexer utilized for transmitting I2C commands from a service processor and an I2C coprocessor, preventing certain inoperable bus states due to concurrent operation of the I2C multiplexer by the I2C coprocessor and the service processor.
1. A system for managing a device management bus coupled to a plurality of managed devices, the system comprising:
a remote access controller configured to:
detect an inoperable state of a device management bus coupling the remote access controller with a first managed device;
determine whether a FRU (Field Replaceable Unit) memory is accessible on the first managed device;
if the memory is accessible, write a reset indicator to the FRU memory of the first managed device; and
monitor the device management bus for a reset notification from the first managed device; and
the first managed device configured to:
detect the reset indicator written to the FRU memory;
reset a bus controller coupled to the device management bus; and
transmit the reset notification on the device management bus.
2. The system of claim 1 , wherein the remote access controller is further configured to:
transmit a plurality of commands to the first managed device via the device management bus; and
store a copy of the transmitted commands in a first stack.
3. The system of claim 2 , wherein the remote access controller is further configured to send an error message in response to the detection of the inoperable state of the device management bus, wherein the error message comprises a portion of the commands from the first stack.
4. The system of claim 3 , wherein the remote access controller is further configured to:
monitor for responses to the transmitted commands from the first managed device;
identify the transmitted commands in the first stack for which no response has been received; and
store the commands with no response to a second stack.
5. The system of claim 4 , wherein the error message includes the transmitted commands from the second stack.
6. The system of claim 1 , wherein the FRU memory is accessed via the device management bus.
7. The system of claim 6 , wherein the reset indicator is written to a predefined location in the FRU memory.
8. A method for managing a device management bus coupled to a plurality of managed devices, the method comprising:
detecting an inoperable state of a device management bus coupling a remote access controller with a first managed device;
determining whether a FRU memory is accessible on the first managed device;
writing a reset indicator to the FRU memory of the first managed device;
monitoring the device management bus for a reset notification from the first managed device;
detecting, by the first managed device, the reset indicator written to the FRU memory; and
resetting, by the first managed device, a bus controller coupled to the device management bus in response to detecting the reset indicator in the FRU memory.
9. The method of claim 8 , further comprising:
transmitting a plurality of commands to the first managed device via the device management bus; and
storing a copy of the transmitted commands in a first stack.
10. The method of claim 9 , further comprising:
sending an error message in response to the detection of the inoperable state of the device management bus, wherein the error message includes a portion of the transmitted commands from the first stack.
11. The method of claim 10 , further comprising:
monitoring for responses to the transmitted commands from the first managed device;
identifying the transmitted commands in the first stack for which no response has been received; and
storing the commands with no response to a second stack.
12. The method of claim 11 , wherein the error message includes a portion of the transmitted commands from the second stack.
13. The method of claim 8 , wherein the FRU memory is accessed via the device management bus.
14. The method of claim 13 , wherein the reset indicator is written to a predefined location in the FRU memory.