CN101394309A

CN101394309A - Cluster system expanding method, apparatus and cluster system

Info

Publication number: CN101394309A
Application number: CNA2008102187318A
Authority: CN
Inventors: 朱建波; 范灵强; 王兵
Original assignee: Huawei Technologies Co Ltd
Current assignee: Huawei Technologies Co Ltd
Priority date: 2008-10-29
Filing date: 2008-10-29
Publication date: 2009-03-25

Abstract

The embodiment of the invention provides a method for expanding a cluster system which comprises at least a CCC, and a newly added CLC is connected with the CCC to form the cluster system. The method comprises the following steps: a control plane is established; and a device management right is switched to the CCC, so as to enable the CCC to manage the newly added CLC. The embodiment of the invention further discloses a cluster route card device, a cluster central exchange device and the cluster system. By adopting the method, smooth expansion can be conducted without the interrupt of the operational equipment service of the CLC current network and the data service, and no software device needs to be changed during the expansion, thereby reducing the investment of a user in the device.

Description

Cluster system capacity expansion method and device and cluster system

Technical Field

The embodiment of the invention relates to the field of network communication, in particular to a cluster system capacity expansion method, a cluster line card device, a cluster central exchange device and a cluster system.

Background

With the further development of networks and the rapid increase of user bandwidth, operators find that in many core application scenarios, the capacity and slot position of a single router cannot meet the service requirement. And the super core node has actually become a bottleneck for further development of services for telecom operators. The router is used as a network cluster system, provides high-reliability data transmission for telecom operators (China telecom, China Mobile and the like), and requires high reliability; while requiring scalability.

The switching planes of the existing router devices all adopt single-stage switching; and the router Cluster equipment is composed of a Cluster Central exchange frame (CCC) and a Cluster Line-card frame (CLC). The existing router cluster equipment adopts a 3-level Clos structure to realize a three-level exchange mechanism, wherein the CLC performs 1-level and 3-level exchange, and the CCC completes 2-level exchange between frames. In a management plane of an existing router cluster device, each CLC is connected to a CCC through two links (two links forming a primary-standby relationship) to form a data channel, and the CCC manages and issues related routes through the data channel.

A router cluster is also called a router matrix or Multi-Chassis interconnection (Multi-Chassis), which simply means that a plurality of routers are interconnected to form a logically integrated router system. Clustering has been generated for two main reasons: firstly, the capacity of a single machine gradually develops to the limit; secondly, the generation of super nodes makes the network structure become more and more complex and the difficulty of maintenance and management is increased.

The introduction of the cluster technology in the router field aims to connect two or more common core routers in a certain way, so that the core routers can perform cooperative work and parallel processing among devices, realize smooth expansion of system capacity, and only represent one logic router to the outside. Users want to expand the capacity and slot position of some nodes as far as possible without affecting the service of the original equipment, and form a router cluster equipment to meet the higher capacity of users, namely, the smooth capacity expansion is required. In the prior art, the CLC and the CCC are to be used as a set of cluster devices, the process is performed without a service, cables between the CLC and the CCC need to be connected, and configuration is done on the two devices, and a set of clusters is formed by restarting.

In the prior art, no matter a CLC is newly added or a CCC is newly added, the capacity expansion of the device is performed under the condition that the CLC service is interrupted, and the smooth capacity expansion cannot be performed under the condition that the data service is not interrupted.

Disclosure of Invention

The technical problem to be solved in the embodiments of the present invention is to provide a cluster system capacity expansion method, a cluster line card device, a cluster central switching device, and a cluster system, which can expand router devices into router cluster devices on line without affecting services of the router devices operated in the current network.

The embodiment of the invention provides a cluster system capacity expansion method, wherein the cluster system comprises at least one cluster central exchange frame (CCC), a newly-added CLC is connected with the CCC to form a cluster system, and the method comprises the following steps:

establishing a control plane;

and switching the device management right to the CCC so that the CCC manages the newly added CLC.

Correspondingly, an embodiment of the present invention further provides a cluster line card device, where the cluster line card device is a cluster line card frame CLC, the CLC is connected to a cluster central switching frame CCC, and the CLC includes:

a port (1) for connecting with the CCC;

a control plane establishing unit (2) for establishing a control plane;

and the switching unit (3) is used for switching the device management right on the CLC to the CCC so that the CCC manages the CLC.

Correspondingly, an embodiment of the present invention further provides a cluster central switching apparatus, where the cluster central switching apparatus is a cluster central switching frame CCC, and the CCC is connected to a cluster line card frame CLC to form a cluster system, where the CCC includes:

a CLC port (4) for connecting with the CLC;

a registering unit (5) for registering to the CLC through an idle port in the active port or the standby port, and registering as a slave frame of the CLC;

a backup relationship processing unit (6) for notifying that the CLC can accept change of backup relationship;

and the management unit (7) is used for managing the CCC and the CLC after the CLC completes control switching.

Correspondingly, an embodiment of the present invention further provides a cluster system, where the system includes at least one cluster central switching frame CCC and the newly added cluster line card device according to any one of claims 12 to 17.

By implementing the embodiment of the invention, smooth capacity expansion can be realized under the condition of not interrupting the service of CLC current network operation equipment and under the condition of not interrupting data service, and hardware equipment does not need to be replaced in the capacity expansion process, so that the investment of a user on equipment can be reduced.

Drawings

In order to more clearly illustrate the embodiments of the present invention or the technical solutions in the prior art, the drawings needed to be used in the description of the embodiments or the prior art will be briefly described below, it is obvious that the drawings in the following description are only some embodiments of the present invention, and for those skilled in the art, other drawings can be obtained according to the drawings without creative efforts.

Fig. 1 is a schematic structural diagram of a cluster line card device according to an embodiment of the present invention;

fig. 2 is a schematic structural diagram of a control plane establishing unit of the cluster line card device of fig. 1;

fig. 3 is a schematic structural diagram of a switching unit of the cluster line card device of fig. 1;

fig. 4 is a schematic structural diagram of a cluster central switching apparatus according to an embodiment of the present invention;

FIG. 5 is a schematic structural diagram of a first embodiment of a cluster system according to the present invention;

FIG. 6 is a schematic structural diagram of a second embodiment of a cluster system according to the present invention;

FIG. 7 is a flowchart illustrating a first embodiment of a cluster system expansion method according to the present invention;

FIG. 8 is a detailed flowchart illustrating the establishment of a control plane in the cluster system extension method of FIG. 7;

fig. 9 is a schematic specific flowchart of the management right of the switching device in the cluster system extension method of fig. 7;

fig. 10 is a schematic structural diagram of a third embodiment of a cluster system according to the embodiment of the present invention;

fig. 11 is a flowchart illustrating a second embodiment of the cluster system expansion method according to the present invention.

Detailed Description

The technical solutions in the embodiments of the present invention will be clearly and completely described below with reference to the drawings in the embodiments of the present invention, and it is obvious that the described embodiments are only a part of the embodiments of the present invention, and not all of the embodiments. All other embodiments obtained by persons of ordinary skill in the art based on the embodiments of the present invention without any creative efforts shall fall within the protection scope of the embodiments of the present invention.

The cluster central switching frame CCC is used to monitor, manage and maintain the whole cluster device, connect the CLCs, and provide a data switching channel of a switching plane between the CLCs. The CCC may include boards such as a Main Processing Unit (MPU) (hereinafter abbreviated as MPU board), an Internal Communication Unit (ICU) (hereinafter abbreviated as ICU board), a Switch Fabric Unit (SFU board), an electrical Cross board (ECU) (hereinafter abbreviated as ECU board), and an Optical Flexible Card (OFC) on the ECU board. Wherein,

the MPU board is the core of system control and management, and at the same time, it is also used as maintenance management unit, and completes the functions of control plane and exchange plane, the central exchange frame generally includes two MPU boards, and forms backup to ensure reliability;

the SFU board is used as a switching network module of the central switching frame and mainly realizes the service switching function among different line card frames; the OFC is an interface card on the ECU board and used for photoelectric and electro-optical conversion functions, and can realize flow relay between the central exchange frame and each line card frame to form a data channel between the CCC and the CLC;

the ECU board is matched with the photonic card OFC and the SFU board to realize a service channel of the multi-frame cluster router, and the ECU board is used as a part of central switching frame service processing to complete the relay between the SFU board and the OFC;

the ICU board is used to implement reliable control information transmission between the central switching frame and the central switching frame, and between the central switching frame and the line card frame, for example, in the CCC-1 system (i.e. 1 central switching frame), the ICU board on the central switching frame may be connected to the main control boards of 4 line card frames through the ethernet ports, and the control information of the main control board of the line card frame is uploaded to the main control board of the central switching frame, and the control information of the main control board of the central switching frame is simultaneously issued to the main control boards of each line card frame. In the CCC-2 system (i.e. there are 2 central switching frames), the ICU board not only completes the control channel between the central switching frame and the line card frame, but also realizes the control channel between the two central switching frames, therefore, the ICU board may include a CLC interface, such as an ethernet type interface, for connecting the cascade interface on the CLC main control board; the ICU board of each central switching frame can be connected through the interface to form a Rapid Ring Protection Protocol (RRPP) Ring. For example, in the CCC-2 system, only one CCC interface on one CCC may be connected to another CCC in the CCC-2 system, but when the cluster system is extended to the CCC-4 or more central switch boxes, two CCC interfaces may be needed on each CCC to connect to other CCCs in the cluster system, and all CCCs form a ring.

In a cluster router composed of multiple boxes, i.e., multiple routers, each single box is called a line card box CLC. Each Line card box may include single boards such as an MPU board, an SFU board, and a Line interface processing unit (LPU), where the MPU is a main control switching unit and is responsible for centralized control and management of the system and data exchange, and generally each Line card box may include two MPU boards to form a backup to ensure reliability. The SFU of the switching network board realizes the centralized and rapid switching of the service data. The LPU is used for completing the functions of fast processing and forwarding of the service, maintaining and managing a link protocol and a service forwarding table and the like.

Fig. 1 is a schematic structural diagram of a cluster line card device according to an embodiment of the present invention, where in the embodiment of the present invention, the cluster line card device is a cluster line card frame CLC, and the CLC is connected to a CCC, and as shown in fig. 1, the CLC includes:

the port 1 is used for connecting with the CCC, and may be one or two, and if the port is two, one of the ports is a main port used for connecting with the CCC, and the other port is a spare port used for connecting with the CCC. In a specific implementation, the above port may be an ethernet type port, such as ge (gigabit ethernet) port, fe (fast ethernet) port, etc.

A control plane establishing unit 2 for establishing a control plane;

a switching unit 3, configured to switch the device management right on the CLC to the CCC, so that the CCC manages the CLC. When the CLC is connected with the CCC through the main and standby links, the device management right on the CLC can be switched to the CCC through the idle link in the main and standby links. Specifically, the switching unit 3 switches the main and standby MPU boards, and changes the operating mode of the newly added CLC to a three-stage switching mode.

As shown in fig. 2, the control plane establishing unit 2 further includes:

a main control board backup relationship changing unit 20, configured to change the backup relationship of the MPU board on the newly added CLC;

and a backup unit 21 for backing up the configuration information of the main MPU board on the CLC to the main MPU board of the CCC. In this case, the main MPU board on the CLC is still the main MPU board on the original CLC, but the spare MPU board on the CLC is the main MPU board on the CCC.

Wherein, the main control board backup relationship changing unit 20 further includes:

and an operation mode setting unit 200, configured to change an operation mode of the CLC to a multi-frame operation mode.

A receiving and registering unit 201, configured to receive, through an idle port in the active port or the standby port, a registration from the CCC after the operating mode setting unit 200 changes the operating mode to the multi-chassis operating mode, and register the CCC as a slave frame of the CLC.

The user can directly operate on the CLC to trigger the main control board backup relationship changing unit 20 to change the backup relationship.

As shown in the schematic structural diagram of the switching unit 3 shown in fig. 3, the switching unit 3 further includes: a control plane switching unit 30 and a switching plane switching unit 31;

a control plane switching unit 30, configured to switch the main MPU board to the main MPU board of the CCC, and perform main/standby switching on the MPU boards, where the main MPU board on the CCC becomes the main MPU board of the CLC, and control plane switching is completed;

and a switching plane switching unit 31 for changing the operation mode of the SFU board of the CLC to a three-stage switching mode.

The user may directly operate on the CLC to trigger the switching unit 3 to operate, or may receive a signal from the CCC through an idle port in the active port or the standby port on the CCC to trigger the switching unit 3 to operate.

The main control board backup relationship changing unit 20 is further configured to change the main control board backup relationship after the cluster system is expanded. In the process of capacity expansion of the cluster system, the main control board backup relationship change unit 20 realizes 1:1 backup of cross-frame MPU boards in the cluster system, that is, 1 main MPU board (main MPU board on CLC) and 1 standby MPU board (main MPU board on CCC). After the cluster system expansion is completed, the backup relationship may continue to be used, and may be changed. For example, the backup relationship is changed to 1: N backup, for example, by taking a CCC-2 cluster system as an example, 2 CCCs are provided in the CCC-2 cluster system, and 2 MPU boards are generally used as main backup for achieving the reliability requirement on each CCC, so that 4 MPU boards are actually provided in the CCC-2 cluster system, and if only 1:1 backup of the MPU boards across frames is realized, 2 MPU boards are actually available in the cluster system, and in order to improve the reliability of the system and avoid resource waste, the available 2 MPU boards can also be used as a secondary backup MPU board and a secondary backup MPU board respectively to realize 1:3 backup of the MPU boards across frames.

The CLC in the embodiments of the present invention includes an MPU board, and the ports and units may be disposed on the MPU board.

Fig. 4 is a schematic structural diagram of a cluster central switching apparatus according to an embodiment of the present invention, where in the embodiment of the present invention, the cluster central switching apparatus is a cluster central switching frame CCC, and the CCC is connected to a cluster line card frame CLC, and optionally, the CCC may be connected to the CLC through a main/standby link. As shown in fig. 4, the CCC includes:

the CLC ports 4 are used for connecting to the CLC, and may be one or two, and when there are two, one of them is an active port used for connecting to the CLC, and the other is a standby port used for connecting to the CLC. In a specific implementation, the above port may be an ethernet type port, such as ge (gigabit ethernet) port, fe (fast ethernet) port, etc.

And a registering unit 5 for registering to the CLC through an idle port of the active port or the standby port, and registering as a slave frame of the CLC.

And the backup relation processing unit 6 is used for informing that the CLC can accept the change of the backup relation. For example, when the implementation is performed by the HA means, the module changes the HA state of the CCC to a multi-frame batch backup state, and constructs and transmits a notification message to the newly added CLC, so that the CLC changes the backup relationship of the main control board after receiving the notification message.

And the management unit 7 is used for managing the CCC and the CLC after the CLC completes control switching.

When there is a new CCC in the cluster system, the original CCC may further include:

the CCC port 8 is used for connecting with one or two CCCs in the cluster system, and when there are two CCCs, the CCCs of the cluster system can be connected into a ring;

a working mode changing unit 9 for changing the working mode of the CCC;

the main control board backup relationship changing unit 10 changes the main-standby relationship of the MPU boards on the CCC, specifically, the standby MPU board of the current CCC is set as the main MPU board on the newly added CCC, that is, the main MPU board on the current CCC remains unchanged, the current CCC takes the main MPU board on the newly added CCC as its own standby MPU board, and further, data backup can be realized, that is, the current CCC backs up the data on the main MPU board to the standby MPU board, that is, the main MPU board on the newly added CCC.

Correspondingly, the ICU card also comprises a communication unit which is used for communicating with other CCCs in the cluster system and selecting the main CCC when more than two CCCs are in the cluster system.

The CCC in an embodiment of the invention includes an MPU board, on which the ports and elements described above may be disposed.

Fig. 5 is a schematic structural diagram of a first embodiment of a cluster system according to the present invention, and as shown in fig. 5, the system includes at least one cluster central switching frame CCC and a newly added line card frame CLC, where the CCC is a cluster central switching device shown in fig. 2, the CLC is a cluster line card device shown in fig. 1, and the CCC is connected to the CLC, where the newly added CLC is used to change a backup relationship of its own MPU board, backup configuration information of an active MPU board to an active MPU board of the CCC, and switch a device management right to the CCC; the CCC is used to manage the cluster system.

Fig. 6 is a schematic structural diagram of a second embodiment of the cluster system of the present invention, and as shown in fig. 6, the cluster system includes a CCC and n CLC, and constitutes a cluster system of CCC + nCLC, and its working principle and capacity expansion method are as described in the above method embodiments, and the CLC extension is added to the cluster system of CCC + nCLC on the basis of the cluster system of CCC + CLC, and then the newly added CLC only needs to be directly connected to the CCC. The CLC is similar to the cluster line card device shown in fig. 1, and the CCC is similar to the cluster central switching device shown in fig. 2, which are not described herein again.

The above-described apparatus and system are described in further detail below in connection with method embodiments of the present invention.

Fig. 7 is a schematic flow diagram of a first embodiment of a cluster system expansion method according to the present invention, in this embodiment, expansion is implemented by adding a CLC to a CCC, in which a cluster system includes at least one cluster central switching frame CCC, and as shown in fig. 7, the method includes:

101, establishing a control plane; and changing the backup relation of the MPU boards on the CLC, and backing up the configuration information of the main MPU board on the CLC to the main MPU board of the CCC. The CCC is connected with the newly-added CLC through a main link and a standby link, the main link and the standby link between the CCC and the CLC are mainly used for interaction of internal management information and comprise backup information, the two links are used for mutual backup, and when one link fails, the management information can still pass through the other link for interaction. The CCC and the CLC are connected through two links, and when the implementation is specific, the connection form of the main and standby links may be directly connected to the CLC and the CCC through a network cable.

At this time, the management right of the CLC is still above the CLC, and the processing and issuing of the relevant route of the cluster system in the form of CLC + CCC must also be completed by the CLC, so that the device management right on the CLC needs to be switched to CCC, and the whole CLC + CCC is managed by CCC.

And 102, switching the device management right to the CCC so that the CCC manages the newly added CLC. Because the management right of the newly added CLC is still on the CLC, no information interaction exists between the newly added CLC and the CCC, the main link and the standby link are in an idle state, the control right can be switched through any link in the main link and the standby link, and preferably, the main link can be preferred when the main link and the standby link are idle. 102 can be realized by means of High reliability (HA), which is a common technical means in the art and is not described herein. The specific implementation of the process 102 may be that the user manually configures the device management right to be switched to the CCC on the CLC, or that the device management right is automatically switched after being automatically detected by the CLC or the CCC. The above switching method can achieve the purpose of switching the device management right, which is obvious to those skilled in the art and will not be described in detail. And after the device management right is switched to the CCC through an idle link in the main and standby links, the CCC manages the newly added CLC. Specifically, the CCC manages the CLC + CCC cluster device through the MPU board of the CCC.

The specific steps of establishing the control plane 101 are shown in fig. 8, and may include:

1011, CCC is connected with the newly added CLC, and the newly added CLC is changed into a multi-frame working mode, wherein the working mode of the CLC comprises a single frame and a multi-frame. Of course, as is well known to those skilled in the art, the working mode of the CCC should also be a multi-frame working mode, and the working mode of the CCC may be many, and is used to indicate that the cluster system includes several CCCs, for example, when the working mode of the CCC is CCC-1, it indicates that the entire cluster system includes one multi-frame working mode of the CCC. Optionally, the CCC is connected to the CLC through an active/standby link.

1012, CCC registers with the CLC in the multi-frame mode, CCC registers as a frame on the CLC, and the CLC considers itself as the master frame and CCC as the slave frame of the CLC. After the CCC registers with the current CLC, the user can log in the CCC from the CLC to check the state of the whole cluster system, change the configuration and the like.

1013, the backup relationship of the MPU boards on the CLC is changed, and the configuration information of the main MPU board on the CLC is backed up to the main MPU board of the CCC. In this case, the main MPU board of the CLC is still the main MPU board on the original CLC, but the spare MPU board of the CLC is the main MPU board on the CCC. The configuration information of the main MPU board on the CLC is backed up to the main MPU board on the CCC, namely the main MPU board on the CCC, by a High-reliability (HA) means.

The CLC in 102 may switch the device management right to the newly added CCC specifically includes a switch control plane and a switch switching plane, as shown in fig. 9. The following are detailed separately:

1021, switching control plane; the new CLC switches the main MPU board and the standby MPU board, at this time, the main MPU board on the CCC becomes the main MPU board of the CLC, and the control layer completes the switching.

1022, switching the switching plane; the newly added CLC changes the working mode of the CLC into a three-stage exchange mode. Because the newly added CLC is originally a first-level switching mode, the working mode of the CLC needs to be changed into a third-level switching mode at present, namely CCC serves as 2-level switching network equipment, and the SFU of a line card frame serves as a 1-level or 3-level switching network, so that a cluster router system with a plurality of equipment cascades and user flow three-level switching is formed, and data can be exchanged among all service boards. In the specific implementation, the newly added CLC includes N +1 SFU boards, where the N SFU boards are responsible for exchanging data, and the 1 SFU board is used as a backup for the N SFU boards, so that the N SFU boards can be changed into the multi-frame operating mode one by one due to the existence of the backup SFU board.

After the device management right on the CLC is switched to the CCC, the entire CLC + CCC cluster device is managed by the MPU board on the CCC. In this embodiment, the CLC is newly added under the CCC to smoothly expand the capacity, and the smoothly expanded capacity can be realized without restarting the newly added CLC, thereby improving the reliability of the smoothly expanded capacity of the cluster system.

In practical application, because the CLC that can be connected under each CCC is limited, for example, in general, one CCC may support at most 4 CLCs, when a CLC is connected under the CCC, the system capacity is still insufficient, and when further capacity expansion is needed, it may need to be implemented by adding a new CCC, so as to form a 2CCC + nCLC cluster system. Therefore, another embodiment of the present invention provides a cluster system, fig. 10 is a schematic structural diagram of a third embodiment of the cluster system of the present invention, and as shown in fig. 10, the system is a cluster system of mCCC + nCLC, where the CLC is similar to the cluster line card device of fig. 1, and the CCC is similar to the cluster central switching device of fig. 2, which are not described herein again. Correspondingly, an embodiment of the present invention further provides another cluster system expansion method, as shown in fig. 11, which is a schematic flow diagram of a second embodiment of the cluster system expansion method of the present invention, where if the integrated system further includes a newly added CCC, the newly added CCC is connected to the CCC, and the newly added CCC is connected to the newly added CLC, the method further includes:

and 201, changing the working modes of the newly added CCC and the CCC, and registering the newly added CCC to the main CCC. The working mode of the newly added CCC and the original CCC is changed into CCC-2, because only one CCC exists in a CCC-1 system, the original CCC can also be regarded as the main CCC, and the newly added CCC is registered to the original CCC to form a frame of the original CCC. For example, if the original CCC-1 system is a CCC-2 system, a new CCC needs to be added to the original CCC in the original cluster system to form a CCC-2 system, and the new CCC is registered to the original CCC in the original cluster system to form a frame of the original CCC, and similarly, if the original CCC-m system is the CCC-m system, and if the new CCC needs to be added to form a CCC- (m +1) system, the working modes of the original m CCCs and the new CCC are set to be CCC- (m +1), and the new CCC is registered to the master CCC.

And 202, changing the main and standby relationship of the MPU boards on the main CCC, specifically, setting the standby MPU board of the main CCC as the main MPU board on the newly-increased CCC, namely, the main MPU board on the main CCC is kept unchanged, and the main CCC takes the main MPU board on the newly-increased CCC as the standby MPU board thereof, so that data backup can be realized, namely, the main CCC backs up the data on the main MPU board to the standby MPU board, namely, the main MPU board on the newly-increased CCC.

If only 2 CCCs are in the cluster system, and 2 CCCs are in a main-standby relationship, only one MPU board on the CCC works at a certain time, at this time, the original CCC is also called as the main CCC, and the newly added CCC is called as the standby CCC. The main CCC controls the whole system, including device-level management and routing, protocol and other controls, and after the main CCC fails, the standby CCC takes over to control the whole system, thereby playing a backup role. When the main MPU board on the main CCC fails, the standby MPU board of the main CCC, namely the main MPU board on the standby CCC, takes over the corresponding work. In fact, it is now the standby CCC that takes over the work of the primary CCC.

If there are N (N is a natural number greater than or equal to 3) CCCs in the cluster system, the N CCCs may be connected two by two to form a Ring network, and the reliability of the CCCs is ensured by operating a Ring network protocol, such as a Resilient Packet Ring (RPR) protocol, an RRPP (fast Ring protection protocol).

Similarly, the cluster system can be expanded to an mCC + nCLC cluster system by continuously adding a CCC or a CLC, the cluster system comprises m CCCs, n CLCs and CCCs, the CCCs are connected with each other, and each CLC is connected with each CCC through a main link and a standby link. The capacity expansion method for each new CCC and each new CLC is the same as the above embodiments.

In the above embodiment, the CLC and the CCC are connected by the active and standby two-path links, which is to improve the reliability of the communication between the CLC and the CCC.

Because the time sequence of adding the CLC or adding the CCC is not limited, the two embodiments may be implemented separately or in combination.

The second embodiment of the method further includes changing the backup relationship of the main control board after the cluster system expands the capacity. In the process of cluster system expansion, 1:1 backup of MPU boards crossing frames in a cluster system is realized, namely 1 main MPU board (main MPU board on CLC) and 1 standby MPU board (main MPU board on CCC). After the cluster system expansion is completed, the backup relationship may continue to be used, and may be changed. For example, the backup relationship is changed to 1: N backup, for example, by taking a CCC-2 cluster system as an example, 2 CCCs are provided in the CCC-2 cluster system, and 2 MPU boards are generally used as main backup for achieving the reliability requirement on each CCC, so that 4 MPU boards are actually provided in the CCC-2 cluster system, and if only 1:1 backup of the MPU boards across frames is realized, 2 MPU boards are actually available in the cluster system, and in order to improve the reliability of the system and avoid resource waste, the available 2 MPU boards can also be used as a secondary backup MPU board and a secondary backup MPU board respectively to realize 1:3 backup of the MPU boards across frames.

In the embodiment of the present invention, the idle link may be an active link or a standby link in the active and standby links, and when both the active link and the standby link are idle, the active link may be preferred.

By implementing the cluster system of the embodiment of the invention, smooth capacity expansion can be realized without interrupting the service of the equipment operated by the current network of the CLC when the CCC is newly added or the CLC is newly added, hardware equipment does not need to be replaced in the capacity expansion process, and the investment of a user on the equipment can be reduced.

Through the above description of the embodiments, those skilled in the art will clearly understand that the embodiments of the present invention may be implemented by software plus a necessary hardware platform, and may also be implemented by hardware entirely. With this understanding, all or part of the technical solutions of the embodiments of the present invention that contribute to the background art may be embodied in the form of a software product, which may be stored in a storage medium, such as a ROM/RAM, a magnetic disk, an optical disk, or the like, and includes several instructions for enabling a computer device (which may be a personal computer, a server, or a network device) to execute the methods according to the embodiments or some parts of the embodiments of the present invention.

The above disclosure is only for the purpose of illustrating the preferred embodiments of the present invention, and it is needless to say that the scope of the embodiments of the present invention should not be limited thereby, and therefore, the scope of the embodiments of the present invention is encompassed by the appended claims.

Claims

1. A cluster system capacity expansion method is characterized in that the cluster system comprises at least one cluster central exchange frame (CCC), and a newly added CLC is connected with the CCC to form a cluster system, and the method comprises the following steps:

establishing a control plane;

2. The method of claim 1, wherein the establishing the control plane comprises:

changing the backup relation of the MPU board on the newly added CLC;

and backing up the configuration information of the main MPU board on the newly-added CLC to the main MPU board of the CCC.

3. The method as claimed in claim 2, wherein said changing the backup relationship of MPU boards on the newly added CLC specifically includes:

changing the working mode of the newly added CLC into a multi-frame working mode;

receiving a registration from the CCC, and turning the CCC into a slave frame on the CLC in a multi-frame mode of operation.

4. The method of claim 1, wherein the switching the device management right to the CCC specifically comprises:

switching the main MPU board of the newly-added CLC to the main MPU board of the CCC;

and changing the working mode of the newly added CLC into a three-stage exchange mode.

5. The method of claim 1, wherein the newly added CLC is coupled to the CCC via a primary/secondary link.

6. The method of claim 5, wherein the switching device management authority on the CCC is specifically: and switching the device management right to the CCC through an idle link in the main and standby links.

7. The method of claim 1, 2, 3, or 4, wherein if the integrated system further comprises a new CCC, the new CCC is coupled to the CCC, and the new CCC is coupled to the new CLC, the method further comprising:

changing the working modes of the newly added CCC and the CCC, and registering the newly added CCC to the original CCC to form a slave frame of the original CCC;

and changing the main-standby relationship of the MPU board on the main CCC.

8. The method according to claim 7, wherein the changing of the main/standby relationship of the MPU boards on the main CCC specifically comprises:

and setting the standby MPU board of the main CCC as the main MPU board on the newly-added CCC.

9. The method of claim 8, wherein if the cluster system comprises at least three CCCs, a plurality of CCCs are connected two-by-two to form a ring network.

10. The method of claim 7, wherein the newly added CCC is connected to the CCC via a primary and a secondary link, and wherein the newly added CCC is connected to the newly added CLC via a primary and a secondary link.

11. The method of claim 8, further comprising:

change backup relationship of MPU board 1: and N backup.

12. The cluster line card device is characterized in that the cluster line card device is a cluster line card frame CLC, the CLC is connected with a cluster central exchange frame CCC, and the CLC comprises:

a port (1) for connecting with the CCC;

a control plane establishing unit (2) for establishing a control plane;

13. The cluster line card apparatus according to claim 12, wherein the control plane establishing unit (2) comprises:

a main control board backup relation changing unit (20) for changing the backup relation of the MPU board on the newly added CLC;

and a backup unit (21) for backing up the configuration information of the main MPU board of the CLC to the main MPU board of the CCC.

14. The cluster line card apparatus of claim 13, wherein the master board backup relationship change unit (20) comprises:

an operation mode setting unit (200) for changing an operation mode of the CLC to a multi-frame operation mode;

a receiving registration unit (201) for receiving registration information from the CCC and registering the CCC as a slave block of the CLC.

15. The cluster line card apparatus according to claim 12, wherein the switching unit (3) comprises:

a control plane switching unit (30) for switching the main MPU board of the CLC to the main MPU board of the CCC;

a switching plane switching unit (31) for changing the operation mode of the CLC to a three-stage switching mode.

16. The cluster line card apparatus of claim 13, wherein the master board backup relationship change unit (20) is further configured to change the backup relationship of the MPU boards by 1: and N backup.

17. The trunking line card apparatus of claim 12, wherein the CLC and the CCC are connected via an active/standby link, and the switching unit (3) is configured to switch a device management right on the CLC to the CCC via an idle link in the active/standby link, so that the CCC manages the CLC.

18. A cluster central switching device is a cluster central switching frame (CCC), the CCC is connected with a cluster line card frame (CLC) to form a cluster system, and the CCC comprises:

a CLC port (4) for connecting with the CLC;

19. The clustered central switching apparatus of claim 18 wherein if the integrated system includes a new CCC, the CCC further comprises:

a CCC port (8) for connecting with a newly added CCC in the cluster system;

an operation mode changing unit (9) for changing the operation mode of the CCC;

and the main control board backup relation changing unit (10) is used for changing the main-standby relation of the MPU boards on the CCC.

20. The clustered central switching apparatus of claim 19, wherein the CCC is coupled to the CLC via active/standby links, wherein the new CCC is coupled to the CCC via active/standby links, and wherein the new CCC is coupled to the CLC via active/standby links.

21. A trunking system, characterized in that it comprises at least one trunking central switching box CCC and newly added trunking line card arrangements according to any of claims 12 to 17.

22. The cluster system according to claim 21, characterized in that the system further comprises a cluster central switching arrangement according to any of claims 18-20.