Electrical computers and digital data processing systems: input/ – Intrasystem connection – Bus interface architecture
Reexamination Certificate
1999-05-06
2002-07-16
Lefkowitz, Sumati (Department: 2181)
Electrical computers and digital data processing systems: input/
Intrasystem connection
Bus interface architecture
C710S056000
Reexamination Certificate
active
06421756
ABSTRACT:
FIELD OF THE INVENTION
The present invention relates generally to information processing systems and more particularly to an improved information transfer methodology in a computer related environment.
BACKGROUND OF THE INVENTION
As computer systems and networked computer systems proliferate, and become integrated into more and more information processing systems which are vital to businesses and industries, there is an increasing need for faster information processing and increased data handling capacity. Even with the relatively rapid state-of-the-art advances in processor technology, and the resulting increased processor speeds, a need still exists for faster processors and increased system speeds and bandwidths. As new applications for computers are implemented, new programs are developed and those programs are enriched with new capabilities almost on a daily basis. While such rapid development is highly desirable, there is a capability cost in terms of system speed and bandwidth.
As used herein, the term “bandwidth” is used generally to refer to the amount of information that can be transferred in a given period of time. In transferring information between devices in a computer system, information is frequently temporarily stored in buffers along the path of the information transfer. Such buffers include bridge buffers which are generally located in bridge circuits connecting devices or busses between which the information is to be transferred. In one example, peripheral component interconnect or “PCI” system bridge circuit buffers are assigned to PCI devices, which are installed in PCI “slots” and coupled to an associated PCI bus. Complex computer systems may include many bridge circuits connected between individual PCI busses or connecting a PCI bus to a system bus. In a PCI system, any of the computer system enhancement devices or adapters are generally included on one or more circuit boards which are mounted or inserted into PCI “slots”, i.e. into board connector terminals mounted on a system motherboard.
In general, each PCI bus is connected to a next higher level bus in the system through a PCI bridge circuit. Each PCI bus in a system may have up to four slots (at 33 MHz) for devices or adapters connected to the PCI bus. In extensive computer systems, PCI busses are connected to other PCI busses through PCI-to-PCI bridge circuits which are, in turn, connected to one or more of the slots on higher level PCI busses. Each bridge circuit in the system includes a number of buffers which have been, in the past, assigned to corresponding ones of the PCI slots, for use in temporarily storing information transferred to and from the corresponding assigned devices installed in the PCI slots of the system. For example, in
FIG. 1
, a typical PCI system includes one or more CPUs
101
,
105
, which are connected to a system bus
103
. A memory controller
107
and memory unit
109
are also connected to the system bus
103
. The bus
103
is extended
111
for further system connections to other system devices and networks which are known in the art but are not specifically illustrated in order not to obfuscate the drawings and distract from the disclosure of the present invention.
The system bus
103
is also coupled through a PCI Host Bridge (PHB) circuit
113
to a first PCI bus
119
. The PHB
113
is shown to include a group of buffers
117
and an arbitrator circuit
115
. The first PCI bus
119
includes four devices designated “S1”, “S2”, “S3” and “S4” which are arranged for receiving PCI devices such as I/O adapter devices “A”
121
, “B”
123
, and “C”
125
. The fourth device in the example is a PCI-to-PCI bridge (PPB)
127
to a second PCI bus
129
. The second PCI bus is shown to be connected to three additional I/O adapter devices “E”
131
, “F”
133
and “G”
135
. Each of the PCI devices on the PCI bus has separate “request” (REQ) and “grant” (GNT) lines to the PHB
113
as illustrated such that each PCI device may request and receive control from the arbitrator circuit
115
of the PCI bus
119
for information transfers. The devices under the PPB would request the bus through an arbiter in the PPB.
In the past, the buffers
117
were usually available for any device to utilize, and in some cases, depending on the arbiter utilized, some devices could be temporarily deprived of available buffers because each time a device is granted the bus, it could find that the buffers are full.
Thus there is a need for an improved methodology and implementing system which enables a more advantageous use of buffer availability in transferring information between devices connected within the system.
SUMMARY OF THE INVENTION
A method and implementing computer system is provided in which bridge buffers are grouped together in a pool, and are dynamically assigned and unassigned to devices on the bus based on an “as needed” basis for information transfers. In an exemplary PCI system embodiment, a PHB is coupled to a first PCI bus and one of the devices on the first PCI bus is a PPB which couples the first PCI bus to a second PCI bus. An initial assignment of PHB buffers in the PHB is made relative to the number of PCI adapter devices which are connected both directly and indirectly to the first PCI bus. Devices on both the first and second PCI busses are given approximately equal status in the buffer assignment process. Upon a completion of a data transfer to or from any one of the adapters, the freed-up buffers which were assigned to that particular adapter are dynamically made available and re-assigned to other adapters as needed to optimize use of all of the buffers in the PHB pool.
REFERENCES:
patent: 4603382 (1986-07-01), Cole et al.
patent: 5014265 (1991-05-01), Hahne et al.
patent: 5412781 (1995-05-01), Lukas et al.
patent: 5432908 (1995-07-01), Heddes et al.
patent: 5521923 (1996-05-01), Willmann et al.
patent: 5802055 (1998-09-01), Krein et al.
patent: 5838994 (1998-11-01), Valizadeh
patent: 5907717 (1999-05-01), Ellis
patent: 5916309 (1999-06-01), Brown et al.
patent: 5964859 (1999-10-01), Steinbach et al.
patent: 6021132 (2000-02-01), Muller et al.
patent: 6046817 (2000-04-01), Brown et al.
patent: 6073190 (2000-06-01), Rooney
patent: 6195331 (2001-02-01), Tani
patent: 6240066 (2001-05-01), Nagarajan et al.
Kelley Richard A.
Neal Danny Marvin
Thurber Steven Mark
International Business Machines - Corporation
Lefkowitz Sumati
McBurney Mark E.
Wilder Robert V.
LandOfFree
Buffer assignment for bridges does not yet have a rating. At this time, there are no reviews or comments for this patent.
If you have personal experience with Buffer assignment for bridges, we encourage you to share that experience with our LandOfFree.com community. Your opinion is very important and Buffer assignment for bridges will most certainly appreciate the feedback.
Profile ID: LFUS-PAI-O-2897156