CN106506408A - A kind of implementation method of 96+6 interface switchboards - Google Patents
A kind of implementation method of 96+6 interface switchboards Download PDFInfo
- Publication number
- CN106506408A CN106506408A CN201611016432.7A CN201611016432A CN106506408A CN 106506408 A CN106506408 A CN 106506408A CN 201611016432 A CN201611016432 A CN 201611016432A CN 106506408 A CN106506408 A CN 106506408A
- Authority
- CN
- China
- Prior art keywords
- switch
- interfaces
- way
- chips
- interface
- Prior art date
- Legal status (The legal status is an assumption and is not a legal conclusion. Google has not performed a legal analysis and makes no representation as to the accuracy of the status listed.)
- Pending
Links
Classifications
-
- H—ELECTRICITY
- H04—ELECTRIC COMMUNICATION TECHNIQUE
- H04L—TRANSMISSION OF DIGITAL INFORMATION, e.g. TELEGRAPHIC COMMUNICATION
- H04L49/00—Packet switching elements
- H04L49/30—Peripheral units, e.g. input or output ports
Landscapes
- Engineering & Computer Science (AREA)
- Computer Networks & Wireless Communication (AREA)
- Signal Processing (AREA)
- Small-Scale Networks (AREA)
- Stored Programmes (AREA)
Abstract
The invention discloses a kind of implementation method of 96+6 interface switchboards, belongs to switch technology field.The switch has 96 1GbE down going ports and 6 40GbE up going ports, switch is cascaded from two-way Switch chips, specifically include main Switch chips, from Switch chips and Peripheral Interface, main Switch chips select 98CX8297, externally provide 88 descending SGMII interfaces and 6 40GbE upstream Interfaces in systems；Marvell 98DX3236 are selected from Switch chips, 8 road SMGII interfaces is externally provided, and is embedded an ARM v7CPU, outside SPI Flash start firmware and operating system for depositing switch.The present invention has Ethernet OAM(Operation Administration Maintenance)s, effectively improves the management to Ethernet and the ability of maintenance, the stable operation of Logistics networks.
Description
Technical field
The present invention relates to switch technology field, specifically a kind of implementation method of 96+6 interface switchboards.
Background technology
With the fast development of distributed storage, distributed storage is more and more extensive in the application of the industries such as medical treatment, education,
Distributed storage is interconnected by multiple memory nodes, and each memory node is relatively independent, is externally provided storage by switch and is connect
Mouthful, but be that each node is a little storage server the characteristics of due to distributed storage, and number of nodes compared with
Many, so also higher to the interface requirement of switch, generally 24 or 48 mouthfuls of traditional exchange interface quantity distributed is deposited
Storage is internal to need multiple switch to be cascaded, and causes whole system extremely complex, reduces the reliability of system.
Content of the invention
The technical assignment of the present invention is for above weak point, there is provided a kind of implementation method of 96+6 interface switchboards,
There is Ethernet OAM(Operation Administration Maintenance)s, effectively improve the management to Ethernet and the ability of maintenance, the stable operation of Logistics networks.
The technical solution adopted for the present invention to solve the technical problems is：
A kind of implementation method of 96+6 interface switchboards, the switch have 96 1GbE down going ports and 6 40GbE up going ports,
Due to the restriction of the SerDes quantity of single Switch chip, in order to realize that 96 1GbE and 6 40GbE interfaces, switch are selected
Cascaded with two-way Switch chips, 98CX8297 the and Marvell AlleyCat of respectively Marvell Lion2 series
The 98DX3236 of series；
98CX8297 is maximum to support that 128 SerDes, high performance SerDes passages can support 1G, 2.5G, 10G and 40G etc.
Multiple transfer rates, maximum exchange bandwidth externally provide 88 descending SGMII interfaces and 6 in systems up to 1280Gbps
40GbE upstream Interfaces, Marvell 98DX3236, the Switch chips externally provide 8 road SMGII interfaces, and embed an ARM
V7CPU, for configuring switch, power consumption is only 7W, plug-in DDR3 internal memories, it is ensured that the high treatment capacity of switch, outside
SPI Flash are used for depositing switch startup firmware and operating system；The switch externally provides 96 1GbE down going ports and 6
40GbE up going ports, with two-way debugging serial ports and management network port all the way, support CLI, Telnet, SNMPv1/v2/v3 and WEB etc.
Multiple way to manages, switch operating system support L2 and L3 agreements from linux operating systems, including static routing, RIP,
OSPF, multicast functionality, IGMP-Snooping, IGMP, PIM-SM and PIM-DM agreement etc., with Ethernet OAM(Operation Administration Maintenance)s.
Embodiment includes following three partial content：
1st, main Switch chips：Main Switch chips select 98CX8297,128 SerDes of maximum support, high performance
SerDes passages can support multiple transfer rates such as 1G, 2.5G, 10G and 40G, maximum exchange bandwidth up to 1280Gbps,
88 descending SGMII interfaces and 6 40GbE upstream Interfaces are externally provided in system.
2nd, from Switch chips：Marvell 98DX3236, the Switch chips is selected externally to provide 8 from Switch chips
Road SMGII interfaces, and an ARM v7CPU is embedded, for configuring switch, power consumption is only 7W, plug-in DDR3 internal memories, it is ensured that
The high treatment capacity of switch, outside SPI Flash are used for depositing switch startup firmware and operating system, by two-way
SFI interfaces are interconnected with main Switch chips, and two-way SFI passages maximum can support 20Gbps, it is ensured that whole system complete
Speed operation.
3rd, Peripheral Interface：The switch externally provides 96 1GbE down going ports and 6 40GbE up going ports, adjusts with two-way
Examination serial ports, multipath I 2 C interface and all the way management network port, management network port are drawn by single port PHY chip 88E1512, are supported
Multiple way to manages such as CLI, Telnet, SNMPv1/v2/v3 and WEB.
Compared to the prior art a kind of implementation method of 96+6 interface switchboards of the present invention, has the advantages that：
Main Switch chips select 98CX8297, and 128 SerDes of maximum support, high performance SerDes passages can be supported
Multiple transfer rates such as 1G, 2.5G, 10G and 40G, maximum exchange bandwidth externally provide 88 in systems up to 1280Gbps
Descending SGMII interfaces and 6 40GbE upstream Interfaces；
Marvell 98DX3236 are selected from Switch chips, the Switch chips externally provide 8 road SMGII interfaces, and embed
One ARM v7CPU, for configuring switch, power consumption is only 7W, plug-in DDR3 internal memories, it is ensured that the efficient process energy of switch
Power, outside SPI Flash are used for depositing switch startup firmware and operating system, by two-way SFI interfaces and main Switch cores
Piece is interconnected, and two-way SFI passages maximum can support 20Gbps, it is ensured that the full speed running of whole system；
Effectively improve the management to Ethernet and the ability of maintenance, the stable operation of Logistics networks.The switch has performance height, work(
The advantages of energy is entirely and interface quantity is many, can be widely applied in various distributed memory systems.
Specific embodiment
With reference to specific embodiment, the invention will be further described.
A kind of implementation method of 96+6 interface switchboards, the switch have 96 1GbE down going ports and 6 40GbE up
Mouthful, due to the restriction of the SerDes quantity of single Switch chip, in order to realize 96 1GbE and 6 40GbE interfaces, switch
Cascaded from two-way Switch chips, the 98CX8297 and Marvell of respectively Marvell Lion2 series
The 98DX3236 of AlleyCat series；
98CX8297 is maximum to support that 128 SerDes, high performance SerDes passages can support 1G, 2.5G, 10G and 40G etc.
Multiple transfer rates, maximum exchange bandwidth externally provide 88 descending SGMII interfaces and 6 in systems up to 1280Gbps
40GbE upstream Interfaces, Marvell 98DX3236, the Switch chips externally provide 8 road SMGII interfaces, and embed an ARM
V7CPU, for configuring switch, power consumption is only 7W, plug-in DDR3 internal memories, it is ensured that the high treatment capacity of switch, outside
SPI Flash are used for depositing switch startup firmware and operating system；The switch externally provides 96 1GbE down going ports and 6
40GbE up going ports, with two-way debugging serial ports and management network port all the way, support CLI, Telnet, SNMPv1/v2/v3 and WEB etc.
Multiple way to manages, switch operating system support L2 and L3 agreements from linux operating systems, including static routing, RIP,
OSPF, multicast functionality, IGMP-Snooping, IGMP, PIM-SM and PIM-DM agreement etc., with Ethernet OAM(Operation Administration Maintenance)s.
Embodiment includes following three partial content：
1st, main Switch chips：Main Switch chips select 98CX8297,128 SerDes of maximum support, high performance
SerDes passages can support multiple transfer rates such as 1G, 2.5G, 10G and 40G, maximum exchange bandwidth up to 1280Gbps,
88 descending SGMII interfaces and 6 40GbE upstream Interfaces are externally provided in system.
2nd, from Switch chips：Marvell 98DX3236, the Switch chips is selected externally to provide 8 from Switch chips
Road SMGII interfaces, and an ARM v7CPU is embedded, for configuring switch, power consumption is only 7W, plug-in DDR3 internal memories, it is ensured that
The high treatment capacity of switch, outside SPI Flash are used for depositing switch startup firmware and operating system, by two-way
SFI interfaces are interconnected with main Switch chips, and two-way SFI passages maximum can support 20Gbps, it is ensured that whole system complete
Speed operation.
3rd, Peripheral Interface：The switch externally provides 96 1GbE down going ports and 6 40GbE up going ports, adjusts with two-way
Examination serial ports, multipath I 2 C interface and all the way management network port, management network port are drawn by single port PHY chip 88E1512, are supported
Multiple way to manages such as CLI, Telnet, SNMPv1/v2/v3 and WEB.
By specific embodiment above, the those skilled in the art can readily realize the present invention.But should
Work as understanding, the present invention is not limited to above-mentioned specific embodiment.On the basis of disclosed embodiment, the technical field
Technical staff can the different technical characteristic of combination in any, different so as to realize
Technical scheme.
In addition to the technical characteristic described in description, the known technology of those skilled in the art is.
Claims (1)
1. a kind of implementation method of 96+6 interface switchboards, it is characterised in that the switch has 96 1GbE down going ports and 6
Individual 40GbE up going ports, switch are cascaded from two-way Switch chips, specifically include main Switch chips, from Switch
Chip and Peripheral Interface；Main Switch chips select 98CX8297, externally provide 88 descending SGMII interfaces and 6 in systems
Individual 40GbE upstream Interfaces；Marvell 98DX3236 are selected from Switch chips, 8 road SMGII interfaces is externally provided, and is embedded
One ARM v7CPU, for configuring switch, outside SPI Flash are used for depositing switch startup firmware and operating system, lead to
Cross two-way SFI interfaces to be interconnected with main Switch chips；Peripheral Interface, has two-way debugging serial ports, multipath I 2 C interface and all the way
Management network port, management network port are drawn by single port PHY chip 88E1512, support CLI, Telnet, SNMPv1/v2/v3 and
WEB way to manages.
Priority Applications (1)
| Application Number | Priority Date | Filing Date | Title |
|---|---|---|---|
| CN201611016432.7A CN106506408A (en) | 2016-11-18 | 2016-11-18 | A kind of implementation method of 96+6 interface switchboards |
Applications Claiming Priority (1)
| Application Number | Priority Date | Filing Date | Title |
|---|---|---|---|
| CN201611016432.7A CN106506408A (en) | 2016-11-18 | 2016-11-18 | A kind of implementation method of 96+6 interface switchboards |
Publications (1)
| Publication Number | Publication Date |
|---|---|
| CN106506408A true CN106506408A (en) | 2017-03-15 |
Family
ID=58324986
Family Applications (1)
| Application Number | Title | Priority Date | Filing Date |
|---|---|---|---|
| CN201611016432.7A Pending CN106506408A (en) | 2016-11-18 | 2016-11-18 | A kind of implementation method of 96+6 interface switchboards |
Country Status (1)
| Country | Link |
|---|---|
| CN (1) | CN106506408A (en) |
Cited By (2)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| CN107493245A (en) * | 2017-09-22 | 2017-12-19 | 锐捷网络股份有限公司 | The board and stream compression forwarding method of interchanger |
| CN112800001A (en) * | 2021-04-13 | 2021-05-14 | 北京乐研科技有限公司 | High-performance Internet of things hardware platform and method based on ARM platform architecture |
-
2016
- 2016-11-18 CN CN201611016432.7A patent/CN106506408A/en active Pending
Cited By (3)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| CN107493245A (en) * | 2017-09-22 | 2017-12-19 | 锐捷网络股份有限公司 | The board and stream compression forwarding method of interchanger |
| CN107493245B (en) * | 2017-09-22 | 2020-04-24 | 锐捷网络股份有限公司 | Board card of switch and data stream forwarding method |
| CN112800001A (en) * | 2021-04-13 | 2021-05-14 | 北京乐研科技有限公司 | High-performance Internet of things hardware platform and method based on ARM platform architecture |
Similar Documents
| Publication | Publication Date | Title |
|---|---|---|
| Hu et al. | Explicit path control in commodity data centers: Design and applications | |
| EP3211858B1 (en) | Networking method for datacenter network and datacenter network | |
| CN100471162C (en) | Method for releasing and processing virtual circuit information and supplier edge device | |
| EP2688243B1 (en) | 50 Gb/s ethernet using serializer/deserializer lanes | |
| CN102668473B (en) | For the system and method for high-performance, low-power data hub interconnection structure | |
| US20150085862A1 (en) | Forwarding Multicast Data Packets | |
| CN103430499B (en) | The method and apparatus of multicast packet Path Setup in network virtualization system | |
| US20140359089A1 (en) | Network proxy for high-performance, low-power data center interconnect fabric | |
| DE112011103123T5 (en) | Performance and performance-optimized computer system architectures and techniques that leverage performance-optimized tree-fabric wiring | |
| CN106209636B (en) | Multicast data packet forwarding method and apparatus from VLAN to VXLAN | |
| EP2355404A1 (en) | Method, device and system for forwarding multicast packets | |
| CN104702506B (en) | A kind of message transmitting method, network node and message transfer system | |
| CN107204907A (en) | Cloud data center interconnected method and device | |
| CN106506408A (en) | A kind of implementation method of 96+6 interface switchboards | |
| KR102171890B1 (en) | Computing system framework with unified storage, processing, and network switching fabrics incorporating network switches and method for making and using the same | |
| CN102811152A (en) | Method for realizing real-time transaction and data exchange of multiple main bus network communication | |
| Nooruzzaman et al. | Hyperscale data center networks with Transparent HyperX architecture | |
| CN202679422U (en) | Cloud computing network architecture | |
| CN110120906A (en) | For realizing the method and apparatus at the dual-active access garden TRILL edge | |
| CN102025614B (en) | Online reconfigurable quaternary tree network on-chip system and reconfiguration method | |
| CN107547247A (en) | Three-layer pipe reason net IP address distribution method and device in intelligent elastic framework | |
| CN105227490A (en) | A kind of method of many device link polymerizations and device | |
| CN204089851U (en) | A kind of Industrial Ethernet bus control unit | |
| CN206433017U (en) | A kind of open high speed exchanges board | |
| CN105490859A (en) | Node positioning method of high-end fault tolerance server |
Legal Events
| Date | Code | Title | Description |
|---|---|---|---|
| C06 | Publication | ||
| PB01 | Publication | ||
| WD01 | Invention patent application deemed withdrawn after publication |
Application publication date: 20170315 |
|
| WD01 | Invention patent application deemed withdrawn after publication |