Multiplex communications – Network configuration determination – In a bus system
Reexamination Certificate
1998-05-01
2003-05-06
Ton, Dang (Department: 2661)
Multiplex communications
Network configuration determination
In a bus system
C370S503000
Reexamination Certificate
active
06560205
ABSTRACT:
TECHNICAL FIELD
The present invention relates to electronic network systems, and more specifically to a loop network hub designed such that loop address conflicts are reduced by forcing initialization of the loop upon insertion of a new node port into the loop.
BACKGROUND INFORMATION
Electronic data systems are frequently interconnected using network communication systems. Area-wide networks and channels are two approaches that have been developed for computer network architectures. Traditional networks (e.g., LAN's and WAN's) offer a great deal of flexibility and relatively large distance capabilities. Channels, such as the Enterprise System Connection (ESCON) and the Small Computer System Interface (SCSI), have been developed for high performance and reliability. Channels typically use dedicated short-distance connections between computers or between computers and peripherals. Features of both channels and networks have been incorporated into a new network standard known as “Fibre Channel”. Fibre Channel systems combine the speed and reliability of channels with the flexibility and connectivity of networks. Fibre Channel products currently can run at very high data rates, such as 266 Mbps or 1062 Mbps. These speeds are sufficient to handle quite demanding applications, such as uncompressed, full motion, high-quality video. ANSI specifications, such as X3.230-1994 , define the Fibre Channel network. This specification distributes Fibre Channel functions among five layers. The five functional layers of the Fibre Channel are: FC-
0
—the physical media layer; FC-
1
—the coding and encoding layer; FC-
2
—the actual transport mechanism, including the framing protocol and flow control between nodes; FC-
3
—the common services layer; and FC-
4
—the upper layer protocol. There are generally three ways to deploy a Fibre Channel network: simple point-to-point connections; arbitrated loops; and switched fabrics. The simplest topology is the point-to-point configuration, which simply connects any two Fibre Channel systems directly. Arbitrated loops are Fibre Channel ring connections that provide shared access to bandwidth via arbitration. Switched Fibre Channel networks, called “fabrics”, are a form of cross-point switching.
Conventional Fibre Channel Arbitrated Loop (“FC-AL”) protocols provide for loop functionality in the interconnection of devices or loop segments through node ports. However, direct interconnection of node ports is problematic in that a failure at one node port in a loop typically causes the failure of the entire loop. This difficulty is overcome in conventional Fibre Channel technology through the use of hubs. Hubs include a number of hub ports interconnected in a loop topology. Node ports are connected to hub ports, forming a star topology with the hub at the center. Hub ports which are not connected to node ports or which are connected to failed node ports are bypassed. In this way, the loop is maintained despite removal or failure of node ports.
More particularly,
FIG. 1A
illustrates a conventional loop configuration
100
. Four node ports
101
,
102
,
104
,
106
are shown joined together node port to node port. Each node port represents a connection to a device or to another loop. Node port
101
is connected to node port
102
such that data is transmitted from node port
101
to node port
102
. Node port
102
is in turn connected to node port
104
which is in turn connected to node port
106
. Node port
106
is connected to the first node port, node port
101
. In this manner, a loop datapath is established; from node port
100
to node port
102
to node port
104
to node port
106
back to node port
100
.
FIG. 1B
illustrates a loop
107
where node ports
108
,
110
,
112
,
114
are organized in a physical star topology with a hub
116
in the center. Node port
108
is connected to a hub port
118
in hub
116
as are node ports
110
,
112
and
114
to their own respective hub ports
120
,
122
, and
124
. Internal to hub
116
is a loop, where hub ports
118
-
124
of hub
116
form a loop datapath similar to the conventional loop configuration shown in FIG.
1
A.
The use of a hub as a central component to a loop network allows for operation when one or more hub ports are not connected to node ports, or one or more hub ports are connected to node ports which have failed, by bypassing such hub ports. Each hub port typically contains circuitry which provides a bypass mode for the hub port. When a hub port is in bypass mode, data received by the hub port from the previous hub port in the loop is passed directly to the next hub port in the loop.
An additional advantage of the use of hubs is that node ports may be hot insertable. Hot insertable functionality allows the insertion and removal of node ports from a loop without powering down the entire loop or the hub and then restarting again. However, as a result of this hot insertability, the addresses of node ports attached to a loop are not always properly maintained.
Under FC-AL protocols, a loop initialization process is used to provide each node port attached to the loop with a unique address, referred to as an Arbitrated Loop Physical Address (“AL_PA”). Loop initialization is invoked under FC-AL protocols by generating a sequence of Loop Initialization Primitive (“LIP”) ordered sets. In a loop which is not hot insertable, after insertion or removal of a node port the entire loop is restarted and re-initialized. In a hot insertable loop, the loop is not always restarted and so is not necessarily re-initialized upon each insert or removal. As a result, when a new node port is inserted into the loop a unique address may not necessarily be generated if the loop is not re-initialized.
In addition, a hub port may be connected to a hub port on another hub. When hubs are linked one hub to another through hub ports, sometimes hubs do not properly initiate an initialization routine upon insertion, especially in the case of quiescent hubs (i.e., no loop traffic at the time of insertion). At this point there is a possibility of address conflicts between the node ports on the first hub and the node ports on the second hub.
Such an address conflict problem is illustrated in
FIGS. 2A and 2B
. As shown in
FIG. 2A
, four node ports A
1
, B
1
, C
1
, D
1
, are linked to a hub
200
. Three node ports A
2
, B
2
, C
2
, are connected to a hub
202
. The numbers
1
and
2
are illustrative only and in fact the addresses for each node port are still represented by the letter A, B, C, or D. At this point, each node port has a unique address within its own loop. However, when hubs
200
and
202
are joined, as shown in
FIG. 2B
, the addresses for the node ports are no longer necessarily unique. In the single loop shown in
FIG. 2B
, two node ports have address A, two node ports have address B, and two node ports have address C. Upon detecting an address conflict, an error is generated which starts an initialization sequence, ultimately resulting in unique addresses for each node port. However, before that conflict is detected, messages may still continue to pass which are received by incorrect node ports resulting in possible data corruption.
For example, in the situation shown in
FIG. 2A
, when node port B
1
sends data to node port A
1
, the hub ports are adjacent and node port A
1
receives the data from node port B
1
possibly without an error. As shown in
FIG. 2B
, the connection from node port B
1
to node port A
1
may begin without generating an address conflict because messages from B
1
successfully pass along the loop to node port A
1
, the intended destination, as long as node port B
2
was not arbitrating.
However, when node port A
1
attempts to send data to node port B
1
, data corruption may result. In the situation shown in
FIG. 2A
, the data is sent from node port A
1
, past node port C
1
, past node port D
1
, and then to node port B
1
, the intended destination. However, in the situation shown in
FIG. 2B
, data passes from node port A
1
, past node port C
1
, past node port D
Corbett Eddie
Hogan Billy
Emulex Corporation
Fish & Richardson P.C.
Ton Dang
LandOfFree
Method and apparatus for control of soft handoff usage in... does not yet have a rating. At this time, there are no reviews or comments for this patent.
If you have personal experience with Method and apparatus for control of soft handoff usage in..., we encourage you to share that experience with our LandOfFree.com community. Your opinion is very important and Method and apparatus for control of soft handoff usage in... will most certainly appreciate the feedback.
Profile ID: LFUS-PAI-O-3093000