CN106502933A - A kind of hard disk can dynamically distributes four component server systems - Google Patents
A kind of hard disk can dynamically distributes four component server systems Download PDFInfo
- Publication number
- CN106502933A CN106502933A CN201610961310.9A CN201610961310A CN106502933A CN 106502933 A CN106502933 A CN 106502933A CN 201610961310 A CN201610961310 A CN 201610961310A CN 106502933 A CN106502933 A CN 106502933A
- Authority
- CN
- China
- Prior art keywords
- node
- plx
- hard disk
- pcie
- chips
- 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
-
- G—PHYSICS
- G06—COMPUTING; CALCULATING OR COUNTING
- G06F—ELECTRIC DIGITAL DATA PROCESSING
- G06F13/00—Interconnection of, or transfer of information or other signals between, memories, input/output devices or central processing units
- G06F13/14—Handling requests for interconnection or transfer
- G06F13/16—Handling requests for interconnection or transfer for access to memory bus
- G06F13/1668—Details of memory controller
Landscapes
- Engineering & Computer Science (AREA)
- Theoretical Computer Science (AREA)
- Physics & Mathematics (AREA)
- General Engineering & Computer Science (AREA)
- General Physics & Mathematics (AREA)
- Multi Processors (AREA)
Abstract
The invention discloses a kind of hard disk can dynamically distributes four component server systems, the system includes 4 nodes, each node increases the PCIE of an X16 newly, add an interconnection module based on 9797 chips of PLX between node and hard disk backboard, the interconnection module is managed by ARM CPU, the interconnection between node and node and hard disk dynamically distributes are realized.The present invention can pass through the interconnection between node and node and dynamic hard disk allocative decision realizes variation, the task of complication.Can more interconnect between node, effectively improve the competitiveness of product in market.Can save space, improve node radiating, also reserved space for the integrated more multifunction module of mainboard.Strengthen the performance of product.
Description
Technical field
The present invention relates to server system architecture technical field, and in particular to a kind of hard disk can dynamically distributes four components clothes
Business device system, a kind of based on PCIE SWITCH (PLX9797) chips hard disk can dynamically distributes four component system architectures.
Background technology
With the development of cloud computing technology, application, informationization is gradually coated on the every field of society.The daily work of people
Make that life is more and more diversified, being served by for needs is also more and more, for four traditional components, some and node it
Between do not interconnect, single node task is single, it is impossible to meet diversified demand of the different application to system.
In four traditional components, there is no the framework for interconnecting between node, only 4 two-ways in a 2U space
Server, only controls fan and power supply between each node, for the letter inside single node simply by I2C alternative routes
Cease other nodes to share, and storage medium can not be shared.The demand of present market diversification cannot be met.
As shown in figure 1, the mutual contact mode of four components for conventional architectures, node and hard disk mutual contact mode are direct-connected, node
Without interconnecting relation between node.Except radiating and power supply plan be integrated exterior node be independent four configuration identical two-way
Server, form are single.
Content of the invention
The technical problem to be solved in the present invention is：The present invention is directed to problem above, there is provided a kind of hard disk can dynamically distributes
Four component server systems.On the basis of four traditional component frameworks, each NODE increases the PCIE of an X16 newly, in NODE
Add an interconnection module based on 9797 chips of PLX and hard disk backboard between, solve hard disk dynamically distributes and node is mutual
The problem of connection.
The technical solution adopted in the present invention is：
A kind of hard disk can dynamically distributes four component server systems, the system includes 4 nodes, and each node is newly-increased one
The PCIE of X16, adds an interconnection module based on 9797 chips of PLX, between node and hard disk backboard by ARM CPU
The interconnection module is managed, the interconnection between node and node and hard disk dynamically distributes are realized.
The CPU1 of each node mainboard of the system pulls out the connection of the PCIE to node rear of an X16 to node rear
Device, 4 nodes link to two 9797 chips of PLX by adapter, mutual by one group of X16 PCIE between two chips
Connection, connects the NVME hard disks of 12 piece of 8639 agreement, realizes hard disk by 9797 chips of PLX below every 9797 chip of PLX
Dynamically distributes and the interconnection of node, the embodiment of management layer are to pass through two groups of PCIE X1 with the CPU of an ARM framework
Line is connected to 9797 chips of PLX and manages, and realizes that the interconnection between node is managed.
4 nodes of the system are NODE0, NODE1, NODE2 and NODE3, realize that process is as follows：
1）, single node mainboard be connected X16 PCIE to interface with middle plate；
2）, node NODE0 and NODE1 be connected to 9797 chip of PLX, node NODE2 and NODE3 are connected to a PLX
9797 chips；
3）, between two 9797 chips of PLX by one group of X16 PCIE link；
4）, every 9797 chip of PLX separates the PCIE of X48 again and connects 12 pieces of NVME hard disks；
5）, two 9797 chips of PLX respectively have an X1 PCIE to be connected to distribution of the ARM CPU for link management.
Beneficial effects of the present invention are：
The present invention realizes the data interconnection between node by the mutual contact mode between change node and hard disk, and realizes node
The dynamically distributes of interconnection NVME hard disks, it is achieved that the diversified pattern of four component tasks, improve the market competitiveness of the type.
Description of the drawings
Fig. 1 is traditional four components scheme interconnection architecture schematic diagram；
Fig. 2 is scheme interconnection architecture schematic diagram in four components of the invention.
Specific embodiment
Below according to Figure of description, in conjunction with specific embodiment, the present invention is further described：
Embodiment 1
As shown in Fig. 2 a kind of hard disk can dynamically distributes four component server systems, the system includes 4 nodes, each
NODE increases the PCIE of an X16 newly, between NODE and hard disk backboard adds an interconnection module based on 9797 chips of PLX,
The interconnection module is managed by ARM CPU, the interconnection between node and node and hard disk dynamically distributes are realized.
Embodiment 2
On the basis of embodiment 1, the CPU1 of each node mainboard of system described in the present embodiment pulls out an X16's to node rear
The adapter CONN of PCIE to node rear, 4 nodes link to two 9797 chips of PLX by adapter CONN, two
By one group of X16 PCIE interconnection between chip, below every 9797 chip of PLX, connect the NVME hard disks of 12 piece of 8639 agreement,
The dynamically distributes of hard disk and the interconnection of node are realized by 9797 chips of PLX, the embodiment of management layer is with an ARM
The CPU of framework is connected to 9797 chips of PLX by the line of two groups of PCIE X1 and manages, and realizes the mutual union between node
Reason.
Embodiment 3
On the basis of embodiment 2, described in the present embodiment, systematic realizing program is as follows：
1）, single node mainboard be connected X16 PCIE to interface with middle plate；
2）, node NODE0 and NODE1 be connected to 9797 chip of PLX, node NODE2 and NODE3 are connected to a PLX
9797 chips；
3）, between two 9797 chips of PLX by one group of X16 PCIE link；
4）, every 9797 chip of PLX separates the PCIE of X48 again and connects 12 pieces of NVME hard disks；
5）, two 9797 chips of PLX respectively have an X1 PCIE to be connected to distribution of the ARM CPU for link management.
So, a kind of based on PCIE SWITCH (PLX9797) chips hard disk can four component frameworks of dynamically distributes can be real
Existing.
Embodiment is merely to illustrate the present invention, and not limitation of the present invention, about the ordinary skill of technical field
Personnel, without departing from the spirit and scope of the present invention, can also make a variety of changes and modification, therefore all equivalents
Technical scheme fall within scope of the invention, the scope of patent protection of the present invention should be defined by the claims.
Claims (3)
1. a kind of hard disk can dynamically distributes four component server systems, it is characterised in that the system includes 4 nodes, per
Individual node increases the PCIE of an X16 newly, adds a mutual gang mould based on 9797 chips of PLX between node and hard disk backboard
Group, manages the interconnection module by ARM CPU, realizes the interconnection between node and node and hard disk dynamically distributes.
2. a kind of hard disk according to claim 1 can dynamically distributes four component server systems, it is characterised in that described
The CPU1 of each node mainboard of system pulls out the adapter of the PCIE to node rear of an X16 to node rear, 4 nodes logical
Cross adapter and link to two 9797 chips of PLX, by one group of X16 PCIE interconnection, every PLX 9797 between two chips
Connect the NVME hard disks of 12 piece of 8639 agreement below chip, dynamically distributes and the node that hard disk is realized by PLX 9797 chips
Interconnection, the embodiment of management layer is to be connected to PLX 9797 with the CPU of an ARM framework by the line of two groups of PCIE X1
Chip is managed, and realizes that the interconnection between node is managed.
3. a kind of hard disk according to claim 2 can dynamically distributes four component server systems, it is characterised in that described
4 nodes of system are NODE0, NODE1, NODE2 and NODE3, realize that process is as follows：
1）, single node mainboard be connected X16 PCIE to interface with middle plate；
2）, node NODE0 and NODE1 be connected to 9797 chip of PLX, node NODE2 and NODE3 are connected to a PLX
9797 chips；
3）, between two 9797 chips of PLX by one group of X16 PCIE link；
4）, every 9797 chip of PLX separates the PCIE of X48 again and connects 12 pieces of NVME hard disks；
5）, two 9797 chips of PLX respectively have an X1 PCIE to be connected to distribution of the ARM CPU for link management.
Priority Applications (1)
| Application Number | Priority Date | Filing Date | Title |
|---|---|---|---|
| CN201610961310.9A CN106502933A (en) | 2016-11-04 | 2016-11-04 | A kind of hard disk can dynamically distributes four component server systems |
Applications Claiming Priority (1)
| Application Number | Priority Date | Filing Date | Title |
|---|---|---|---|
| CN201610961310.9A CN106502933A (en) | 2016-11-04 | 2016-11-04 | A kind of hard disk can dynamically distributes four component server systems |
Publications (1)
| Publication Number | Publication Date |
|---|---|
| CN106502933A true CN106502933A (en) | 2017-03-15 |
Family
ID=58322546
Family Applications (1)
| Application Number | Title | Priority Date | Filing Date |
|---|---|---|---|
| CN201610961310.9A Pending CN106502933A (en) | 2016-11-04 | 2016-11-04 | A kind of hard disk can dynamically distributes four component server systems |
Country Status (1)
| Country | Link |
|---|---|
| CN (1) | CN106502933A (en) |
Cited By (5)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| CN106708745A (en) * | 2016-12-05 | 2017-05-24 | 郑州云海信息技术有限公司 | 24-tub NVME dynamic allocation structure and method |
| CN107329801A (en) * | 2017-06-29 | 2017-11-07 | 深信服科技股份有限公司 | A kind of node administration method and device, many component servers |
| CN107423255A (en) * | 2017-05-08 | 2017-12-01 | 郑州云海信息技术有限公司 | A kind of multipath server interconnects topological structure |
| CN107908586A (en) * | 2017-12-22 | 2018-04-13 | 郑州云海信息技术有限公司 | A kind of NVME hard-disc storages structure and its implementation |
| CN114780033A (en) * | 2022-04-22 | 2022-07-22 | 苏州浪潮智能科技有限公司 | JBOD cascade system, storage resource allocation method and device |
Citations (4)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| CN101964205A (en) * | 2010-09-17 | 2011-02-02 | 记忆科技(深圳)有限公司 | ECC (Error Correction Code) module dynamic multiplexing system and method based on solid state disk |
| CN102346520A (en) * | 2010-07-27 | 2012-02-08 | 英业达股份有限公司 | Server system |
| CN103176913A (en) * | 2011-12-26 | 2013-06-26 | 英业达股份有限公司 | Hard disk dynamic mapping method and server for applying same |
| CN104122960A (en) * | 2014-08-15 | 2014-10-29 | 浪潮电子信息产业股份有限公司 | Architecture method for four nodes of 1U high-density server |
-
2016
- 2016-11-04 CN CN201610961310.9A patent/CN106502933A/en active Pending
Patent Citations (4)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| CN102346520A (en) * | 2010-07-27 | 2012-02-08 | 英业达股份有限公司 | Server system |
| CN101964205A (en) * | 2010-09-17 | 2011-02-02 | 记忆科技(深圳)有限公司 | ECC (Error Correction Code) module dynamic multiplexing system and method based on solid state disk |
| CN103176913A (en) * | 2011-12-26 | 2013-06-26 | 英业达股份有限公司 | Hard disk dynamic mapping method and server for applying same |
| CN104122960A (en) * | 2014-08-15 | 2014-10-29 | 浪潮电子信息产业股份有限公司 | Architecture method for four nodes of 1U high-density server |
Cited By (7)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| CN106708745A (en) * | 2016-12-05 | 2017-05-24 | 郑州云海信息技术有限公司 | 24-tub NVME dynamic allocation structure and method |
| CN107423255A (en) * | 2017-05-08 | 2017-12-01 | 郑州云海信息技术有限公司 | A kind of multipath server interconnects topological structure |
| CN107329801A (en) * | 2017-06-29 | 2017-11-07 | 深信服科技股份有限公司 | A kind of node administration method and device, many component servers |
| CN107329801B (en) * | 2017-06-29 | 2020-12-15 | 深信服科技股份有限公司 | Node management method and device and multi-subsatellite server |
| CN107908586A (en) * | 2017-12-22 | 2018-04-13 | 郑州云海信息技术有限公司 | A kind of NVME hard-disc storages structure and its implementation |
| CN114780033A (en) * | 2022-04-22 | 2022-07-22 | 苏州浪潮智能科技有限公司 | JBOD cascade system, storage resource allocation method and device |
| CN114780033B (en) * | 2022-04-22 | 2024-10-22 | 苏州浪潮智能科技有限公司 | JBOD cascade system, storage resource allocation method and device |
Similar Documents
| Publication | Publication Date | Title |
|---|---|---|
| CN106502933A (en) | A kind of hard disk can dynamically distributes four component server systems | |
| CN101594235B (en) | Method for managing blade server based on SMBUS | |
| CN104486130A (en) | Multi-interface management network architecture for cloud server | |
| CN101765838B (en) | Systems and methods for improving performance of a routable structure | |
| US20160292115A1 (en) | Methods and Apparatus for IO, Processing and Memory Bandwidth Optimization for Analytics Systems | |
| CN105099776A (en) | Cloud server management system | |
| CN102929363B (en) | A kind of method for designing of high-density blade server | |
| CN105100234B (en) | A kind of Cloud Server interacted system | |
| CN103634225A (en) | Service bandwidth expansion method in cloud computing network virtualization | |
| CN103106173A (en) | Interconnection method among cores of multi-core processor | |
| CN105763488B (en) | Data center aggregation core switch and backboard thereof | |
| CN104035525A (en) | Computational node | |
| CN106814976A (en) | Cluster storage system and apply its data interactive method | |
| CN107480094A (en) | A kind of pond server system architecture of fusion architecture | |
| CN103064475A (en) | Service device | |
| US20200057679A1 (en) | Hyperscale server architecture | |
| WO2014067264A1 (en) | Switch board and blade server | |
| CN104486256B (en) | The multi plane switching fabric equipment of oriented integration network IA frame serverPC | |
| US20240073100A1 (en) | Isolation method for high-performance computer system, and high-performance computer system | |
| Rumley et al. | End-to-end modeling and optimization of power consumption in HPC interconnects | |
| CN205229926U (en) | 64 treater is in coordination with interconnection plate on server of way | |
| CN208046650U (en) | A kind of hybrid switching board | |
| CN101026575A (en) | High available, high scalble modularized network server system structure | |
| CN206209478U (en) | A kind of server master board that externally can be interconnected at a high speed | |
| CN206021155U (en) | A kind of fusion architecture server |
Legal Events
| Date | Code | Title | Description |
|---|---|---|---|
| C06 | Publication | ||
| PB01 | Publication | ||
| SE01 | Entry into force of request for substantive examination | ||
| SE01 | Entry into force of request for substantive examination | ||
| RJ01 | Rejection of invention patent application after publication |
Application publication date: 20170315 |
|
| RJ01 | Rejection of invention patent application after publication |