Back to results
US 6,550,017 B1Granted
System and method of monitoring a distributed fault tolerant computer system
AssigneeSun Microsystems, Inc.
InventorsHossein Moiin, Peter Martin Grant Dickinson
Life of this patent
Estimating the term…
Abstract
A system and method for monitoring a distributed fault tolerant computer system. A hardware counter mechanism (e.g. a countdown counter) is reset repeatedly by a software reset mechanism during normal operation, thereby preventing the counter mechanism from reaching a count indicative of the existence of a fault. A unit provides a signal to a bus indicative of the status (ON or OFF) of the unit. A management subsystem defines a configuration for the distributed fault tolerant computer system. The management subsystem is responsive to status signals on the bus and selectively reconfigures a stored representation in response to changing status signals on the bus.
Claims65
A monitor system for a distributed fault tolerant computer system, the monitor system comprising:
- a counter mechanism operable to count from a reset value towards a fault value and operable to output a fault signal on reaching said fault value;
- a counter reset routine implemented in software and operable repeatedly to reset the counter mechanism to its reset value during normal operation of the counter reset routine;
- a unit connectable to a bus to supply a status signal indicative of the status of the unit, the unit being responsive to a fault signal output from the counter mechanism to provide an OFF status indication to the bus;
- and
- a management subsystem, the management subsystem defining a configuration for the distributed fault tolerant computer system, the management subsystem being responsive to status signals on the bus and being operable selectively to redefine the configuration of the distributed fault tolerant system dependent upon the state of the status signals;
- wherein each unit of respective nodes is connected to a respective channel on the bus and the management subsystem is responsive to respective status signals on respective channels to determine the status of respective nodes.
3 more elements
A monitor system for a distributed fault tolerant computer system, the monitor system comprising:
- a first counter mechanism operable to count from a reset value towards a fault value and operable to output a fault signal on reaching said fault value;
- a second counter mechanism operable to count from a reset value towards a fault value and operable to output a fault signal on reaching said fault value;
- a counter reset routine implemented in software and operable repeatedly to reset the first and second counter mechanisms to its reset value during normal operation of the counter reset routine;
- a first unit connectable to a first channel on a bus to supply a status signal indicative of the status of the first unit, the first unit being responsive to a fault signal output from the first counter mechanism to provide an OFF status indication for the first unit to the first channel of the bus;
- and a second unit connectable to a first channel on the bus to supply a status signal indicative of the status of the second unit, the second unit being responsive to a fault signal output from the second counter mechanism to provide an OFF status indication for the second unit to the second channel of the bus.
2 more elements
A node of a distributed fault tolerant computer system comprising:
- a first counter mechanism operable to count from a reset value towards a fault value and operable to output a fault signal on reaching said fault value;
- a counter reset routine implemented in software and operable repeatedly to reset the first counter mechanism to its reset value during normal operation of the counter reset routine;
- a first unit connectable to a first channel on a bus to supply a status signal indicative of the status of the first unit, the first unit being responsive to a fault signal output from the first counter mechanism to provide an OFF status indication for the first unit to the first channel of the bus;
- and a second counter mechanism operable to count from a reset value towards a fault value and operable to output a fault signal on reaching said fault value;
- the counter reset routine being operable repeatedly to reset the second counter mechanism to its reset value during normal operation of the counter reset routine;
- and a second unit connectable to a first channel on the bus to supply a status signal indicative of the status of the second unit, the second unit being responsive to a fault signal output from the second counter mechanism to provide an OFF status indication for the second unit to the second channel of the bus.
3 more elements
A distributed fault tolerant computer system comprising a plurality of nodes and a bus, wherein a node of the distributed fault tolerant computer system comprises:
- a first counter mechanism operable to count from a reset value towards a fault value and operable to output a fault signal on reaching said fault value;
- a counter reset routine implemented in software and operable repeatedly to reset the first counter mechanism to its reset value during normal operation of the counter reset routine;
- a first unit connectable to a first channel on the bus to supply a status signal indicative of the status of the first unit, the first unit being responsive to a fault signal output from the first counter mechanism and being operable to provide an OFF status indication for the first unit to the first channel of the bus;
- wherein a node further comprises:
- a second counter mechanism operable to count from a reset value towards a fault value and operable to output a fault signal on reaching said fault value;
- the counter reset routine being operable repeatedly to reset the second counter mechanism to its reset value during normal operation of the counter reset routine;
- and a second unit connectable to a first channel on the bus to supply a status signal indicative of the status of the second unit, the second unit being responsive to a fault signal output from the second counter mechanism to provide an OFF status indication for the second unit to the second channel of the bus.
4 more elements
A monitor system for a distributed fault tolerant computer system, the monitor system comprising:
- a counter mechanism operable to count from a reset value towards a fault value and operable to output a fault signal on reaching said fault value;
- a counter reset routine implemented in software and operable repeatedly to reset the counter mechanism to its reset value during normal operation of the counter reset routine;
- a unit connectable to a bus to supply a status signal indicative of the status of the unit, the unit being responsive to a fault signal output from the counter mechanism to provide an OFF status indication to the bus;
- and a management subsystem, the management subsystem defining a configuration for the distributed fault tolerant computer system, the management subsystem being responsive to status signals on the bus and being operable selectively to redefine the configuration of the distributed fault tolerant system dependent upon the state of the status signals;
- wherein the management subsystem is operable to redefine the configuration of the distributed fault tolerant system in response to detection of a change of state of a node;
- and wherein the management subsystem is operable to redefine the configuration of the distributed fault tolerant system in response to detection of a change of state of a node.
3 more elements
A monitor system for a distributed fault tolerant computer system, the monitor system comprising:
- a counter mechanism operable to count from a reset value towards a fault value and operable to output a fault signal on reaching said fault value;
- a counter reset routine implemented in software and operable repeatedly to reset the counter mechanism to its reset value during normal operation of the counter reset routine;
- a unit connectable to a bus to supply a status signal indicative of the status of the unit, the unit being responsive to a fault signal output from the counter mechanism to provide an OFF status indication to the bus;
- and a management subsystem, the management subsystem defining a configuration for the distributed fault tolerant computer system, the management subsystem being responsive to status signals on the bus and being operable selectively to redefine the configuration of the distributed fault tolerant system dependent upon the state of the status signals;
- wherein the management subsystem is operable to define a node as a member of the fault tolerant computer system when it is associated with an ON status signal.
2 more elements
A monitor system for a distributed fault tolerant computer system, the monitor system comprising:
- a counter mechanism operable to count from a reset value towards a fault value and operable to output a fault signal on reaching said fault value;
- a counter reset routine implemented in software and operable repeatedly to reset the counter mechanism to its reset value during normal operation of the counter reset routine;
- and a unit connectable to a bus to supply a status signal indicative of the status of the unit, the unit being responsive to a fault signal output from the counter mechanism to provide an OFF status indication to the bus;
- wherein the unit is a power supply unit.
1 more element
A node of a distributed fault tolerant computer system comprising:
- a first counter mechanism operable to count from a reset value towards a fault value and operable to output a fault signal on reaching said fault value;
- a counter reset routine implemented in software and operable repeatedly to reset the first counter mechanism to its reset value during normal operation of the counter reset routine;
- a first unit connectable to a first channel on a bus to supply a status signal indicative of the status of the first unit, the first unit being responsive to a fault signal output from the first counter mechanism to provide an OFF status indication for the first unit to the first channel of the bus;
- and a management subsystem, the management subsystem defining a configuration for the distributed fault tolerant computer system, the management subsystem being responsive to status signals on the bus and being operable selectively to redefine the configuration of the distributed fault tolerant system dependent upon the state of the status signals;
- wherein each unit of respective nodes of the distributed fault tolerant computer system is connected to a respective channel on the bus and the management subsystem is responsive to respective status signals on respective channels to determine the status of respective nodes.
2 more elements
A node of a distributed fault tolerant computer system comprising:
- a first counter mechanism operable to count from a reset value towards a fault value and operable to output a fault signal on reaching said fault value;
- a counter reset routine implemented in software and operable repeatedly to reset the first counter mechanism to its reset value during normal operation of the counter reset routine;
- a first unit connectable to a first channel on a bus to supply a status signal indicative of the status of the first unit, the first unit being responsive to a fault signal output from the first counter mechanism to provide an OFF status indication for the first unit to the first channel of the bus;
- and a management subsystem, the management subsystem defining a configuration for the distributed fault tolerant computer system, the management subsystem being responsive to status signals on the bus and being operable selectively to redefine the configuration of the distributed fault tolerant system dependent upon the state of the status signals;
- wherein the management subsystem is operable to redefine the configuration of the distributed fault tolerant system in response to detection of a change of state of a node;
- and wherein the management subsystem is operable to compare system resources to system requirements following a change of state of a node to determine whether reconfiguration of the distributed fault tolerant system is required.
3 more elements
A node of a distributed fault tolerant computer system comprising:
- a first counter mechanism operable to count from a reset value towards a fault value and operable to output a fault signal on reaching said fault value;
- a counter reset routine implemented in software and operable repeatedly to reset the first counter mechanism to its reset value during normal operation of the counter reset routine;
- a first unit connectable to a first channel on a bus to supply a status signal indicative of the status of the first unit, the first unit being responsive to a fault signal output from the first counter mechanism to provide an OFF status indication for the first unit to the first channel of the bus;
- and a management subsystem, the management subsystem defining a configuration for the distributed fault tolerant computer system, the management subsystem being responsive to status signals on the bus and being operable selectively to redefine the configuration of the distributed fault tolerant system dependent upon the state of the status signals;
- wherein the management subsystem is operable to define a node as a member of the fault tolerant computer system when it is associated with an ON status signal.
2 more elements
A node of a distributed fault tolerant computer system comprising:
- a first counter mechanism operable to count from a reset value towards a fault value and operable to output a fault signal on reaching said fault value;
- a counter reset routine implemented in software and operable repeatedly to reset the first counter mechanism to its reset value during normal operation of the counter reset routine;
- and a first unit connectable to a first channel on a bus to supply a status signal indicative of the status of the first unit, the first unit being responsive to a fault signal output from the first counter mechanism to provide an OFF status indication for the first unit to the first channel of the bus;
- wherein the first unit is a first power supply unit.
1 more element
A distributed fault tolerant computer system comprising a plurality of nodes and a bus, wherein a node of the distributed fault tolerant computer system comprises:
- a first counter mechanism operable to count from a reset value towards a fault value and operable to output a fault signal on reaching said fault value;
- a counter reset routine implemented in software and operable repeatedly to reset the first counter mechanism to its reset value during normal operation of the counter reset routine;
- a first unit connectable to a first channel on the bus to supply a status signal indicative of the status of the first unit, the first unit being responsive to a fault signal output from the first counter mechanism and being operable to provide an OFF status indication for the first unit to the first channel of the bus;
- and a management subsystem, the management subsystem defining a configuration for the distributed fault tolerant computer system, the management subsystem being responsive to status signals on the bus and being operable selectively to redefine the configuration of the distributed fault tolerant system dependent upon the state of the status signals;
- wherein each unit of respective nodes of the distributed fault tolerant computer system is connected to a respective channel on the bus and the management subsystem is responsive to respective status signals on respective channels to determine the status of respective nodes.
2 more elements
A distributed fault tolerant computer system comprising a plurality of nodes and a bus, wherein a node of the distributed fault tolerant computer system comprises:
- a first counter mechanism operable to count from a reset value towards a fault value and operable to output a fault signal on reaching said fault value;
- a counter reset routine implemented in software and operable repeatedly to reset the first counter mechanism to its reset value during normal operation of the counter reset routine;
- a first unit connectable to a first channel on the bus to supply a status signal indicative of the status of the first unit, the first unit being responsive to a fault signal output from the first counter mechanism and being operable to provide an OFF status indication for the first unit to the first channel of the bus;
- and a management subsystem, the management subsystem defining a configuration for the distributed fault tolerant computer system, the management subsystem being responsive to status signals on the bus and being operable selectively to redefine the configuration of the distributed fault tolerant system dependent upon the state of the status signals;
- wherein management subsystem is operable to redefine the configuration of the distributed fault tolerant system in response to detection of a change of state of a given node and to define the given node as a member of the fault tolerant computer system where at least one ON status signal is provided from a unit of the given node.
2 more elements
A distributed fault tolerant computer system comprising a plurality of nodes and a bus, wherein a node of the distributed fault tolerant computer system comprises:
- a first counter mechanism operable to count from a reset value towards a fault value and operable to output a fault signal on reaching said fault value;
- a counter reset routine implemented in software and operable repeatedly to reset the first counter mechanism to its reset value during normal operation of the counter reset routine;
- a first unit connectable to a first channel on the bus to supply a status signal indicative of the status of the first unit, the first unit being responsive to a fault signal output from the first counter mechanism and being operable to provide an OFF status indication for the first unit to the first channel of the bus;
- and a management subsystem, the management subsystem defining a configuration for the distributed fault tolerant computer system, the management subsystem being responsive to status signals on the bus and being operable selectively to redefine the configuration of the distributed fault tolerant system dependent upon the state of the status signals;
- wherein the management subsystem is provided at a node of the distributed fault tolerant computer system.
2 more elements
A distributed fault tolerant computer system comprising a plurality of nodes and a bus, wherein a node of the distributed fault tolerant computer system comprises:
- a first counter mechanism operable to count from a reset value towards a fault value and operable to output a fault signal on reaching said fault value;
- a counter reset routine implemented in software and operable repeatedly to reset the first counter mechanism to its reset value during normal operation of the counter reset routine;
- and a first unit connectable to a first channel on the bus to supply a status signal indicative of the status of the first unit, the first unit being responsive to a fault signal output from the first counter mechanism and being operable to provide an OFF status indication for the first unit to the first channel of the bus;
- wherein each said unit is a power supply unit operable to turn off in response to a fault signal output by the respective counter mechanism.
1 more element
Dependencies are inferred from the claim text.