Abstract:
Performance of a bus in a computer system is monitored. A predetermined total period is counted, and usage of the bus for data transfers during the total period is measured. The bus is monitored for active cycles and a period is counted in which the active cycles are present during the total period. The bus is monitored for data transfer cycles and a period is counted in which the data transfer cycles are present during the total period. Bus efficiency is measured based on the active period and data transfer period. Read data usage on the bus is also measured. A first amount of data read by a first device is monitored, and a second amount of read data used by a second bus device is monitored. The read efficiency is determined based on the first and second amounts.
Abstract:
Control is switched from a first server to a second server in a fault tolerant system. The first and second servers are coupled with an expansion bus in an expansion box for communication with the expansion bus. An indication is provided to the second server to indicate the activity state of the first server. Communication between the first server and the expansion box is disabled if the indication indicates the first server is inactive. Communication between the second server and the expansion bus is disabled if the indication indicates that the first server is active. Communication between the second server is enabled if the indication indicates that the first server is inactive. The indication includes a heartbeat message transmitted periodically to the second server. The expansion bus includes a PCI bus.
Abstract:
A computer system has a central processing unit and a bus. A first bus device and a second bus device are connected to the bus. A circuit is connected to configure the second bus device to be addressable by the central processing unit via the bus only by interaction with the first bus device. The first bus device may be an I 2 O processor, and the second bus device may be an I 2 O subordinate bus device.
Abstract:
Access to a bus in a computer system having a CPU and bus devices capable of running cycles on a bus is controlled by an arbiter. The arbiter grants access to the bus according to an arbitration scheme that depends on whether a request for the bus is pending from the CPU, in which a first arbitration scheme arbitrates between the bus devices, and wherein a second arbitration scheme arbitrates between the CPU and at least one other bus device if the CPU request is present.
Abstract:
An apparatus for use in a computer system which delays operation when a wait signal is present, the apparatus providing a delay between back-to-back input/output cycles, the apparatus comprising: means for storing a programmed value that represents the length of delay to be provided between said back-to-back input/output cycles; means coupled to said storing means for producing a signal representing said length of delay; and means receiving said length of delay signal for generating the wait signal that delays the start of a successive inpt/output cycle for the length of time of said programmed delay.
Abstract:
The computer system disclosed includes a direct memory access (DMA) controller which can provide a 32 bit memory address and yet can also provide 24 bit memory address operation to remain compatible with previous systems. The DMA controller also monitors system operation and if only 24 bit address operations are occurring under the control of an external bus master or the DMA controller, the DMA controller drives the top memory address byte provided to a cache memory controller to help insure cache coherency. Additionally, the DMA controller can provide optimal time transfers for word width transfer between an odd starting memory address and an even starting input/output port.
Abstract:
Performance of a bus in a computer system is monitored. A predetermined total period is counted, and usage of the bus for data transfers during the total period is measured. The bus is monitored for active cycles and a period is counted in which the active cycles are present during the total period. The bus is monitored for data transfer cycles and a period is counted in which the data transfer cycles are present during the total period. Bus efficiency is measured based on the active period and data transfer period. Read data usage on the bus is also measured. A first amount of data read by a first device is monitored, and a second amount of read data used by a second bus device is monitored. The read efficiency is determined based on the first and second amounts.