Fibre channel arbitrated loop bufferless switch circuitry to increase bandwidth without significant increase in cost
    2.
    发明申请
    Fibre channel arbitrated loop bufferless switch circuitry to increase bandwidth without significant increase in cost 有权
    光纤通道仲裁环路无缓冲开关电路,增加带宽,而不会显着增加成本

    公开(公告)号:US20090074408A1

    公开(公告)日:2009-03-19

    申请号:US12292440

    申请日:2008-11-19

    IPC分类号: H04J14/00

    摘要: A switch, switched architecture and process for transferring data through an FCAL switch is disclosed. The switch uses multiple switch control circuits each coupled to one FCAL network and all connected to a crossbar switch. The switch control circuits are coupled together by a protocol bus for coordination purposes. Local conversations can occur on each FCAL loop and crossing conversations through the switch can occur concurrently. The OPN primitive us used to establish the connection before any data is transferred thereby eliminating the need for buffer memory in the switch control circuits. The destination address of each OPN is used to address a lookup table in each switch control circuit to determine if the destination node is local. If not, the destination is looked up and a connection request made on the protocol bus. If the remote port is not busy, it sends a reply which causes both ports to establish a data path through the backplane crossbar switch.

    摘要翻译: 公开了一种通过FCAL交换机传输数据的交换机,交换架构和过程。 该开关使用多个开关控制电路,每个开关控制电路都耦合到一个FCAL网络,并且都连接到交叉开关。 开关控制电路通过协议总线耦合在一起用于协调目的。 每个FCAL循环都可能发生本地会话,并且通过交换机交叉的会话可以同时发生。 OPN原语我们用于在传输任何数据之前建立连接,从而无需开关控制电路中的缓冲存储器。 每个OPN的目的地地址用于寻址每个交换机控制电路中的查找表,以确定目的地节点是否是本地的。 如果没有,则查找目的地并在协议总线上进行连接请求。 如果远程端口不忙,它将发送一个应答,这两个端口通过背板交叉开关建立数据路径。

    Fibre channel arbitrated loop bufferless switch circuitry to increase bandwidth without significant increase in cost
    3.
    发明授权
    Fibre channel arbitrated loop bufferless switch circuitry to increase bandwidth without significant increase in cost 有权
    光纤通道仲裁环路无缓冲开关电路,增加带宽,而不会显着增加成本

    公开(公告)号:US07385972B2

    公开(公告)日:2008-06-10

    申请号:US10348648

    申请日:2003-01-21

    IPC分类号: H04L12/56 H04L12/43 H04J3/02

    摘要: A switch, switched architecture and process for transferring data through an FCAL switch is disclosed. The switch uses multiple switch control circuits each coupled to one FCAL network and all connected to a crossbar switch. The switch control circuits are coupled together by a protocol bus for coordination purposes. Local conversations can occur on each FCAL loop and crossing conversations through the switch can occur concurrently. The OPN primitive is used to establish the connection before any data is transferred thereby eliminating the need for buffer memory in the switch control circuits. The destination address of each OPN is used to address a lookup table in each switch control circuit to determine if the destination node is local. If not, the destination is looked up and a connection request made on the protocol bus. If the remote port is not busy, it sends a reply which, causes both ports to establish a data path through the backplane crossbar switch.

    摘要翻译: 公开了一种通过FCAL交换机传输数据的交换机,交换架构和过程。 该开关使用多个开关控制电路,每个开关控制电路都耦合到一个FCAL网络,并且都连接到交叉开关。 开关控制电路通过协议总线耦合在一起用于协调目的。 每个FCAL循环都可能发生本地会话,并且通过交换机交叉的会话可以同时发生。 OPN原语用于在传输任何数据之前建立连接,从而无需开关控制电路中的缓冲存储器。 每个OPN的目的地地址用于寻址每个交换机控制电路中的查找表,以确定目的地节点是否是本地的。 如果没有,则查找目的地并在协议总线上进行连接请求。 如果远程端口不忙,它会发送回复,这两个端口通过背板交叉开关建立数据路径。

    Fibre channel learning bridge, learning half bridge, and protocol
    4.
    发明授权
    Fibre channel learning bridge, learning half bridge, and protocol 有权
    光纤通道学习桥,学习半桥和协议

    公开(公告)号:US06243386B1

    公开(公告)日:2001-06-05

    申请号:US09395644

    申请日:1999-09-14

    IPC分类号: H04L1242

    摘要: A learning half bridge and bridge for a Fibre Channel Arbitrated Loop and switching protocol. A half bridge can be coupled to a local loop segment and a remote loop segment. The half bridge includes transmit and receive ports implementing predetermined switching and conflict resolution rules and a memory storing a forwarding table. Typically the switching rules are implemented using state machines. The state machines implement a switching protocol that controls transitions between states which control switching connections, writing of data to memory and reading of data from memory and preemption of conflicting OPN primitives. Each half bridge includes a local return segment that can be switched by the state machines to bypass the remote loop segment if both the source node and destination node are on the local loop segment so as to make the local loop segment a complete Fibre Channel Arbitrated Loop. Each half bridge learns the locations of nodes by watching the direction of flow, the loop segment from which certain primitives arrived and sequence of OPN, RRDY and CLS primitives propagating on the loop segments and records data in the forwarding table in memory reflecting the locations of nodes about which conclusions have been drawn in accordance with learning rules. A learning bridge is comprised of two half bridges having their remote loop segments cross coupled. Full bridges can be combined with accelerated or nonaccelerated hubs. Conflicting OPNs are preempted using a highest priority address rule.

    摘要翻译: 用于光纤通道仲裁环路和交换协议的学习半桥和桥接器。 半桥可以耦合到本地环路段和远程环路段。 半桥包括实现预定切换和冲突解决规则的发送和接收端口以及存储转发表的存储器。 通常,切换规则是使用状态机实现的。 状态机实现了一种控制切换连接的状态之间的转换的切换协议,将数据写入存储器以及从存储器读取数据以及抢占冲突的OPN原语。 每个半桥包括本地返回段,如果源节点和目标节点都在本地环路段上,则可以由状态机切换以绕过远程环路段,以使本地环路段成为完整的光纤通道仲裁环路 。 每个半桥通过观察流的方向,某些原语到达的循环段以及在循环段上传播的OPN,RRDY和CLS原语的序列,并将存储器中的数据记录在存储器中的位置来记录节点的位置, 根据学习规则绘制结论的节点。 一个学习桥由两个半桥组成,它们的远端环路交叉耦合。 全桥可以与加速或非加速轮毂相结合。 使用最高优先级的地址规则抢占冲突的OPN。

    Fiber channel learning bridge, learning half bridge, and protocol
    5.
    发明授权
    Fiber channel learning bridge, learning half bridge, and protocol 失效
    光纤通道学习桥,学习半桥和协议

    公开(公告)号:US5978379A

    公开(公告)日:1999-11-02

    申请号:US786891

    申请日:1997-01-23

    摘要: A learning half bridge and bridge for a Fibre Channel Arbitrated Loop and switching protocol. A half bridge can be coupled to a local loop segment and a remote loop segment. The half bridge includes transmit and receive ports implementing predetermined switching and conflict resolution rules and a memory storing a forwarding table. Typically the switching rules are implemented using state machines. The state machines implement a switching protocol that controls transitions between states which control switching connections, writing of data to memory and reading of data from memory and preemption of conflicting OPN primitives. Each half bridge includes a local return segment that can be switched by the state machines to bypass the remote loop segment if both the source node and destination node are on the local loop segment so as to make the local loop segment a complete Fibre Channel Arbitrated Loop. Each half bridge learns the locations of nodes by watching the direction of flow, the loop segment from which certain primitives arrived and sequence of OPN, RRDY and CLS primitives propagating on the loop segments and records data in the forwarding table in memory reflecting the locations of nodes about which conclusions have been drawn in accordance with learning rules. A learning bridge is comprised of two half bridges having their remote loop segments cross coupled. Full bridges can be combined with accelerated or nonaccelerated hubs. Conflicting OPNs are preempted using a highest priority address rule.

    摘要翻译: 用于光纤通道仲裁环路和交换协议的学习半桥和桥接器。 半桥可以耦合到本地环路段和远程环路段。 半桥包括实现预定切换和冲突解决规则的发送和接收端口以及存储转发表的存储器。 通常,切换规则是使用状态机实现的。 状态机实现了一种控制切换连接的状态之间的转换的切换协议,将数据写入存储器以及从存储器读取数据以及抢占冲突的OPN原语。 每个半桥包括本地返回段,如果源节点和目标节点都在本地环路段上,则可以由状态机切换以绕过远程环路段,以使本地环路段成为完整的光纤通道仲裁环路 。 每个半桥通过观察流的方向,某些原语到达的循环段以及在循环段上传播的OPN,RRDY和CLS原语的序列,并将存储器中的数据记录在存储器中的位置来记录节点的位置, 根据学习规则绘制结论的节点。 一个学习桥由两个半桥组成,它们的远程环路交叉耦合。 全桥可以与加速或非加速轮毂相结合。 使用最高优先级的地址规则抢占冲突的OPN。

    Fibre channel arbitrated loop bufferless switch circuitry to increase bandwidth without significant increase in cost
    6.
    发明授权
    Fibre channel arbitrated loop bufferless switch circuitry to increase bandwidth without significant increase in cost 有权
    光纤通道仲裁环路无缓冲开关电路,增加带宽,而不会显着增加成本

    公开(公告)号:US08798091B2

    公开(公告)日:2014-08-05

    申请号:US12149373

    申请日:2008-04-30

    IPC分类号: H04L12/43 H04J3/24

    摘要: A switch, switched architecture and process for transferring data through an FCAL switch is disclosed. The switch uses multiple switch control circuits each coupled to one FCAL network and all connected to a crossbar switch. The switch control circuits are coupled together by a protocol bus for coordination purposes. Local conversations can occur on each FCAL loop and crossing conversations through the switch can occur concurrently. The OPN primitive is used to establish the connection before any data is transferred thereby eliminating the need for buffer memory in the switch control circuits. The destination address of each OPN is used to address a lookup table in each switch control circuit to determine if the destination node is local. If not, the destination is looked up and a connection request made on the protocol bus. If the remote port is not busy, it sends a reply which causes both ports to establish a data path through the backplane crossbar switch.

    摘要翻译: 公开了一种通过FCAL交换机传输数据的交换机,交换架构和过程。 该开关使用多个开关控制电路,每个开关控制电路都耦合到一个FCAL网络,并且都连接到交叉开关。 开关控制电路通过协议总线耦合在一起用于协调目的。 每个FCAL循环都可能发生本地会话,并且通过交换机交叉的会话可以同时发生。 OPN原语用于在传输任何数据之前建立连接,从而无需开关控制电路中的缓冲存储器。 每个OPN的目的地地址用于寻址每个交换机控制电路中的查找表,以确定目的地节点是否是本地的。 如果没有,则查找目的地并在协议总线上进行连接请求。 如果远程端口不忙,它将发送一个应答,这两个端口通过背板交叉开关建立数据路径。

    Fibre channel arbitrated loop bufferless switch circuitry to increase bandwidth without significant increase in cost
    7.
    发明授权
    Fibre channel arbitrated loop bufferless switch circuitry to increase bandwidth without significant increase in cost 有权
    光纤通道仲裁环路无缓冲开关电路,增加带宽,而不会显着增加成本

    公开(公告)号:US08767756B2

    公开(公告)日:2014-07-01

    申请号:US12292440

    申请日:2008-11-19

    IPC分类号: H04L12/56

    摘要: A switch, switched architecture and process for transferring data through an FCAL switch is disclosed. The switch uses multiple switch control circuits each coupled to one FCAL network and all connected to a crossbar switch. The switch control circuits are coupled together by a protocol bus for coordination purposes. Local conversations can occur on each FCAL loop and crossing conversations through the switch can occur concurrently. The OPN primitive us used to establish the connection before any data is transferred thereby eliminating the need for buffer memory in the switch control circuits. The destination address of each OPN is used to address a lookup table in each switch control circuit to determine if the destination node is local. If not, the destination is looked up and a connection request made on the protocol bus. If the remote port is not busy, it sends a reply which causes both ports to establish a data path through the backplane crossbar switch.

    摘要翻译: 公开了一种通过FCAL交换机传输数据的交换机,交换架构和过程。 该开关使用多个开关控制电路,每个开关控制电路都耦合到一个FCAL网络,并且都连接到交叉开关。 开关控制电路通过协议总线耦合在一起用于协调目的。 每个FCAL循环都可能发生本地会话,并且通过交换机交叉的会话可以同时发生。 OPN原语我们用于在传输任何数据之前建立连接,从而无需开关控制电路中的缓冲存储器。 每个OPN的目的地地址用于寻址每个交换机控制电路中的查找表,以确定目的地节点是否是本地的。 如果没有,则查找目的地并在协议总线上进行连接请求。 如果远程端口不忙,它将发送一个应答,这两个端口通过背板交叉开关建立数据路径。

    Accelerator fiber channel hub and protocol

    公开(公告)号:US5751715A

    公开(公告)日:1998-05-12

    申请号:US695290

    申请日:1996-08-08

    摘要: An apparatus for accelerated Fiber Channel protocol handshaking and data exchange involves dividing a Fiber Channel arbitrated loop architecture up into a plurality of arbitrated subloops, each of which arbitrates locally using the same fundamentals as the Fiber Channel arbitration protocol but with some slight modifications which do not affect the compatibility of standard Fiber Channel nodes. Each subloop is coupled to a hub port which contains a state machine which does switching function and fill word generation to implement the accelerated protocol by using a plurality of switching, fill word generation and token passing rules. The state machine in each hub port is coupled to its local subloop and to its neighboring hub ports through a single TDMA bus which has timeslots dedicated to carrying broadcast loop and return loop traffic and control token traffic. In some embodiments, the hub ports are coupled to their neighboring hub ports by separate broadcast and return loops and a control loop used for token passing. The accelerated Fiber Channel Arbitrated Loop protocol is carried out by the distributed intelligence of state machines in each hub port which achieve acceleration in a Fiber Channel protocol by performing the following steps: allowing simultaneus local arbitration in all subloops; notifying the local arbitration winner on a subloop coupled to a hub port when an ARB token arrives at that hub port; broadcasting an OPN primitive to all hub ports and subloops to start the process of finding the subloop upon which the destination node is located; identifying the subloop upon which the destination node is found; establishing switching connections to connect the subloop on which the source node is found to the subloop on which the destination node is found and bypassing all subloops upon which neither the source nor destination node is found; completing a data transfer from the source node to the destination node and closing the connection between the source node subloop and the destination node subloop.