Multiplex communications – Data flow congestion prevention or control
Reexamination Certificate
2000-01-04
2003-11-04
Patel, Ajit (Department: 2661)
Multiplex communications
Data flow congestion prevention or control
C370S428000, C370S468000, C710S052000, C714S724000, C714S733000
Reexamination Certificate
active
06643257
ABSTRACT:
BACKGROUND OF THE INVENTION
A common problem with network systems, such as Ethernet systems, is ensuring that a system can provide adequate bandwidth to one or more destinations from a single input data source. A device which buffers the input data and selects which destination receives this data is often required to work in different network configurations, each with its own bandwidth necessities. In some systems, it is not predetermined 1) which destination will require a given bandwidth, 2) when the bandwidth will be required, and 3) how much bandwidth will be required when requested. As used herein, the term bandwidth is intended to mean the average bandwidth over a period of time. For example, a typical bandwidth with certain networks is 3 gigabits per second. However, during peak times during transmission, the bandwidth may exceed the average for a short period of time. The activity during these intervals of time will be referred to as “peak bandwidth” or “bursts”.
FIGS. 1
a
,
1
b
and
1
c
depict three possible network system configurations, each with a different number of receive devices and each having possibly different bandwidth capabilities. In this system, a buffering and selection device
10
is provided which receives data
12
of a given average bandwidth T from a data source
14
. The buffering and selection device
10
includes selection logic
18
, which provides data to output busses
20
a
-
20
n
. The output busses
20
a
-
20
n
provide data to each receive device, four of which are shown in
FIGS. 1
a
and
1
b
designated as
24
a
,
24
b
,
24
c
and
24
n
and one of which is shown in
FIG. 1
c
and designated as
24
. Receive devices
24
a
,
24
b
,
24
c
and
24
n
each transmits data on data lines
28
a
,
28
b
,
28
c
and
28
n
to a network of users
30
. Typically, the average output bandwidths of the receive devices
24
a
,
24
b
,
24
c
and
24
n
are a fraction of the average bandwidth of the input data
12
on the data source
14
, except in the case where there is only one receive device
24
, as shown in
FIG. 1
c
wherein the receive device has an average bandwidth equal to that of the input data. Preferably, the total average bandwidth output of all of the receive devices
24
a
-
24
n
in each of the configurations of
FIGS. 1
a
,
1
b
and
1
c
is equal to the total average bandwidth of the data
12
from the data source. In any event, data
12
from the data source
14
cannot have a greater average bandwidth than the total average bandwidth of the receive devices, although it may have a lesser average bandwidth.
In operation, the buffering and selection device operates to receive data of an average bandwidth T from a data source, buffer the data when necessary, and transmit the data to one of the receive devices
24
a
,
24
b
,
24
c
or
24
n
under control of the selection logic
18
in the buffering and selection device. Each of the receive devices
24
a
-
24
n
has a limited amount of storage capacity, such that it may receive at peak bandwidths greater than its average output bandwidth for a limited period of time. However, during peak bandwidth transmissions or bursts, any one of the receive devices
24
a
-
24
n
may not be able to transmit data as fast as it is receiving data, and the data may have to be buffered in the device
10
. During operation, real time events in the system may require that any one of the receive devices
24
a
-
24
n
has to temporarily stop the flow of traffic from the buffering and selection device
10
. Even though the buffering and selection device
10
only sends data to one of the receive devices
24
a
,
24
b
,
24
c
or
24
n
individually at a given time and not to two or more in parallel, it must maintain the required average bandwidth T. In such a case, the incoming data may have to be buffered in the device
10
until the receive devices
24
a
-
24
n
are ready to receive. With the buffering and selection device being used with many possible system setups, it is important that the buffering and selection device be able to provide “bandwidth on demand” to the receive devices in many different configurations. Thus, it is necessary to test the buffering and selection device not only in a static test, i.e. by providing input data to the device at a fixed rate of the average bandwidth input with an output also at the fixed rate of the average bandwidth output, but also in a dynamic configuration wherein all of the input and output rates to and from the buffering and selection device are changed depending upon the demands of receive devices.
SUMMARY OF THE INVENTION
The present invention relates to a method of and program for dynamically testing a buffering and selection device wherein the buffering and selection device receives a transmission at an average bandwidth of T and in peak bandwidth bursts that may be greater than T. The buffering and selection device transmits data to one or more receive devices, all of which have a total average bandwidth of at least T. The buffering and selection device has buffers apportioned to each receive device in order to store data that is written in burst mode destined for that receive device. The method includes disabling the output data flow to the receive device being tested and then generating input data to the buffering and selection device tagged for each receive device in burst mode at a preselected number of transfers for each receive device. The program determines when the preselected number of transfers has occurred and then enables data flow to the receive device being tested. It is then determined if output to each receive device has commenced within a preselected latency period, and, if it has, it is determined if the preselected number of transfers of data has occurred within a preselected transfer period, i.e., meets bandwidth requirements.
REFERENCES:
patent: 4638475 (1987-01-01), Koike
patent: 5224092 (1993-06-01), Brandt
patent: 5280469 (1994-01-01), Taniguchi et al.
patent: 5351232 (1994-09-01), Yamashita
patent: 5504754 (1996-04-01), Grunenfelder
patent: 5768259 (1998-06-01), Stock et al.
patent: 5790542 (1998-08-01), Kim et al.
patent: 5940377 (1999-08-01), Sakaue et al.
patent: 05-083291 (1993-04-01), None
patent: 09-289516 (1997-11-01), None
patent: 10-093562 (1998-04-01), None
patent: 10-190665 (1998-07-01), None
patent: WO98/27697 (2000-12-01), None
Likovich, Jr. Robert Brian
Rumph Darryl Jonathan
Winemiller Chad Everett
Blount Steven A
Driggs, Lucas, Brubaker & Hogg
Patel Ajit
LandOfFree
Verifying performance of a buffering and selection network... does not yet have a rating. At this time, there are no reviews or comments for this patent.
If you have personal experience with Verifying performance of a buffering and selection network..., we encourage you to share that experience with our LandOfFree.com community. Your opinion is very important and Verifying performance of a buffering and selection network... will most certainly appreciate the feedback.
Profile ID: LFUS-PAI-O-3141758