CN107135277A - A kind of all-in-one machine realization method and device - Google Patents
A kind of all-in-one machine realization method and device Download PDFInfo
- Publication number
- CN107135277A CN107135277A CN201710545015.XA CN201710545015A CN107135277A CN 107135277 A CN107135277 A CN 107135277A CN 201710545015 A CN201710545015 A CN 201710545015A CN 107135277 A CN107135277 A CN 107135277A
- Authority
- CN
- China
- Prior art keywords
- memory module
- database server
- data
- server
- realization method
- 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
- H04L67/00—Network arrangements or protocols for supporting network services or applications
- H04L67/01—Protocols
- H04L67/10—Protocols in which an application is distributed across nodes in the network
-
- H—ELECTRICITY
- H04—ELECTRIC COMMUNICATION TECHNIQUE
- H04L—TRANSMISSION OF DIGITAL INFORMATION, e.g. TELEGRAPHIC COMMUNICATION
- H04L67/00—Network arrangements or protocols for supporting network services or applications
- H04L67/01—Protocols
- H04L67/10—Protocols in which an application is distributed across nodes in the network
- H04L67/1001—Protocols in which an application is distributed across nodes in the network for accessing one among a plurality of replicated servers
-
- H—ELECTRICITY
- H04—ELECTRIC COMMUNICATION TECHNIQUE
- H04L—TRANSMISSION OF DIGITAL INFORMATION, e.g. TELEGRAPHIC COMMUNICATION
- H04L67/00—Network arrangements or protocols for supporting network services or applications
- H04L67/01—Protocols
- H04L67/10—Protocols in which an application is distributed across nodes in the network
- H04L67/1097—Protocols in which an application is distributed across nodes in the network for distributed storage of data in networks, e.g. transport arrangements for network file system [NFS], storage area networks [SAN] or network attached storage [NAS]
Landscapes
- Engineering & Computer Science (AREA)
- Computer Networks & Wireless Communication (AREA)
- Signal Processing (AREA)
- Information Retrieval, Db Structures And Fs Structures Therefor (AREA)
Abstract
The present invention provides all-in-one machine realization method and device, and the above method comprises the following steps:Data are calculated using at least one database server;The data are managed by least one memory module, collection data are calculated, transmission is rolled into one with store function, deployment faster facilitates enterprise's follow-up business extension and upgraded with applying on-line time.
Description
Technical field
The invention belongs to computer realm, more particularly to a kind of all-in-one machine realization method and device.
Background technology
Large-scale IT enterprises are deployed in as ultra-large (Hyper-Scale) is widely used, the database based on IOE frameworks
Server system needs to tackle the concurrently access of a large number of users, and its systematic function relies on system hardware and software framework, need to optimize application
Program, CPU, internal memory, network, the component such as storage device can just meet customer need.
When application program needs very high storage I/O instruction response speeds (IOPS) and relatively low storage access delay
(Latency) large-scale high-performance storage and high end main frame, are generally bought, not only price is high for these equipment, deployment and autgmentability
It is very poor, and need professional to safeguard.Whole architecture environment complexity is, it is necessary to main frame personnel, S optical fiber switch, memory technology
Personnel participate in deployment and safeguarded.
The database server cluster system of Intrusion Detection based on host and centralised storage framework (i.e. so-called IOE frameworks) generally should
Finance, telecommunications, social security, energy industry are used, client's important core operation system is carry.
Presently relevant technology mainly uses IOE architecture design schemes, and two crucial applied host machines undertake database and calculate clothes
Business device, high-end storage is mapped to crucial applied host machine by FC agreements and deposits data, in a large amount of I O access, two calculate nodes
Simultaneously front end applications can be supported to access.Traditional I/O E framework costs are higher, autgmentability is poor, maintenance cost is high, performance can not also expire
Sufficient big data inquiry.
Current existing database group system is largely using crucial applied host machine and disk array framework, disk array base
This uses traditional mechanical hard disk, and traditional mechanical hard disk has developed decades, can still be dealt with terms of data throughout, and in reply
It is difficult to meet the demand that enterprise accesses high-performance data in terms of high I/O instruction response speeds (IOPS).Traditional mechanical hard disk leads to
Hundreds of IOPS can be often provided, if application needs higher IOPS, need a large amount of mechanical hard disks to build large-scale disk array, and close
Reason puts data.Although recent years, large-scale disk array is also using SSD disks, is limited to fiber bandwidth 16Gb limitations,
Or the application scenarios of big handling capacity can not be met;The technical sophistication degree of other conventional infrastructure limits the hair of flash memory performance
Wave, while bringing huge O&M burden, make enterprise while important operational decision making is maintained, the passive a large amount of bases of input
Facility maintenance cost.
Accordingly, it would be desirable to which a kind of be equipped with the architectural schemes for providing higher performance with lightweight, to solve, autgmentability is poor, safeguard into
This height, performance can not meet the problem of big data is inquired about.
The content of the invention
The present invention provides a kind of all-in-one machine realization method and device, to solve the above problems.
The present invention provides a kind of all-in-one machine realization method.The above method comprises the following steps:
Data are calculated using at least one database server;
The data are managed by least one memory module.
The present invention also provides a kind of all-in-one, including:At least one database server and at least one memory module, its
In, at least one described database server is connected with an at least memory module:
At least one database server, for calculating data;
At least one memory module, for managing the data.
Pass through following scheme:Data are calculated using at least one database server, stored by least one
Module management data, in fusion architecture design, using the X86 servers of standard, will be calculated, storage integration is general fusion cage
Interconnected at a high speed by InfiniBand between structure, node, constitute the load balancing cluster of lightweight, minute integration incorporates one-stop
Rack.Pre-integrated distributed type assemblies, database and cloud platform management system, all soft or hard components are pre-configured with tuning, realize one
Bodyization is quickly delivered, and is equipped with lightweight and is provided higher performance, is minimized TCO while realizing, is maximized ROI.Full flash memory is equipped with
Eliminate conventional architectures I/O and postpone brought processing bottleneck, fully discharge CPU disposal abilities, have brilliance to OLTP database
Performance, with higher cost performance, impayable disposal ability is provided for data bank service.
Brief description of the drawings
Accompanying drawing described herein is used for providing a further understanding of the present invention, constitutes the part of the application, this hair
Bright schematic description and description is used to explain the present invention, does not constitute inappropriate limitation of the present invention.In the accompanying drawings:
Fig. 1 show the all-in-one machine realization method process chart of the embodiment of the present invention 1;
Fig. 2 show the all-in-one machine structure figure of the embodiment of the present invention 2.
Embodiment
Describe the present invention in detail below with reference to accompanying drawing and in conjunction with the embodiments.It should be noted that not conflicting
In the case of, the feature in embodiment and embodiment in the application can be mutually combined.
Fig. 1 show the all-in-one machine realization method process chart of the embodiment of the present invention 1, comprises the following steps:
Step 102:Data are calculated using at least one database server.
Step 104:The data are managed by least one memory module.
Further, it is that the memory module configures at least two flash cards.
Further, at least one described memory module is fused into by collection using Share-Nothing distributed computing technology
Group's formula logical resource pond;
The data are migrated to the database server from the memory module using RDMA zero duplication technologies.
Further, IB networks are passed through between at least one described database server and at least one described memory module
Communication.
Wherein, the database server is general X86 servers.
Therefore, high IOPS flash memory hard disks are configured on general X86 servers, using Share-Nothing distributed frame
Structure, the unified concentrating type logical resource pond of whole station is fused to by the local SSD storages of each node, what memory resource pool was distributed
LUN is by the calculate node of IB network mappings front end, and Infiniband agreements are mainly characterized by high bandwidth, low time delay, system
Favorable expandability.
Network transmission uses RDMA zero duplication technologies, makes data from memory node moves quickly into calculate node, without
Operating system is had any impact, it is not required that use the processing function of how many computer, it eliminates external memory storage and answered
System and text exchange operation, thus memory bandwidth and cpu cycle can be liberated for improving application system performance.
Two DB server (database server) installation operation system Redhat6.5, system is installed Infiniband and driven
Dynamic and storage management software, database can dispose tide K-DB KAC;Three Storage Server need installation operation system
System Redhat 6.5, Infiniband drivings and Sdata storage management software, every Storage Server configure two pieces
PCIE-SSD flash cards;Two DB server and three Storage Server pass through the IB network interconnections.Parameter ginseng is embodied
Examine following table:
Installation parameter refers to following table:
Flash memory technology:It is generally reachable hundreds thousand of at this stage and relative to magnetic disc, flash memory can provide higher IOPS,
Enterprise is largely solved using the bottleneck to IOPS demands, and more values are brought to client.Flash memory technology is removed from office
New on-mechanical structure eliminates the magnetic track formula structure of traditional magnetic disk, can quickly transmit data, greatly improves data reading
Speed is taken, time delay is significantly reduced.The characteristics of flash memory high IOPS, it can effectively tackle and be applied under high virtual machine density
IOPS demands, and linearly upgrading IOPS meets the extension demand of application.
Distributed storage:Using software definition as core, using Share-Nothing distributed structure/architecture, by each node sheet
Ground SSD storages are fused to the unified concentrating type logical resource pond of whole station, realize the Dynamical Deployment of storage resource, improve system
Scale-up and Scale-out various dimensions resilient expansion abilities.Allow user according to business load, dilatation on demand is flexibly flat
Weigh resource.
RDMA zero duplication technologies:RDMA zero-copy network technology causes data to move quickly into long-range system from a system
Unite in memory, without being had any impact to operating system, also avoid the need for using the processing function of how many computer.It disappears
Except external memory storage is replicated and text exchange operation, thus memory bandwidth and cpu cycle can be liberated for improving application system
Performance.
InfiniBand:InfiniBand is a unified interconnection architecture, can both handle storage I/O, network I/0,
Also (IPC) can be communicated between treatment progress.Nfiniband agreements to be mainly characterized by high bandwidth, low time delay, set expandability good
(the Infiniband networks that can easily realize tens thousand of end equipments entirely without congestion), and in single or multiple internet
The I/O passages of redundancy are supported, therefore data center can be kept to remain to operating in local fault.
Fig. 2 show the all-in-one machine structure figure of the embodiment of the present invention 2.
As shown in Fig. 2 all-in-one a kind of according to an embodiment of the invention, including:At least one database server 202
With at least one memory module 204, wherein, at least one described database server and at least one described memory module connect
Connect:
At least one database server 202, for calculating data;
At least one memory module 204, for managing the data.
Further, the memory module 204 includes at least two flash cards.
Further, the memory module 204 using Share-Nothing distributed computing technology by it is described at least one deposit
Storage module is fused into concentrating type logical resource pond;
The database server 202 reads the data using RDMA zero duplication technologies from the memory module.
Further, pass through between at least one described database server 202 and at least one described memory module 204
IB network services.
Further, the database server 202 is general X86 servers.
Based on general X86 Server developments platform, collection data are calculated, transmission is rolled into one with store function, faster portion
On-line time is affixed one's name to and applied, facilitates enterprise's follow-up business extension and upgrades;Million Grade I OPS, the delay of delicate rank are provided, carried
Traffic handing capacity is risen, shortens the business stand-by period, enterprise work efficiency is improved;A whole set of technical scheme full redundancy framework, no list
Point failure, greatly ensure that operation system High Availabitity.
The preferred embodiments of the present invention are the foregoing is only, are not intended to limit the invention, for the skill of this area
For art personnel, the present invention can have various modifications and variations.Within the spirit and principles of the invention, that is made any repaiies
Change, equivalent substitution, improvement etc., should be included in the scope of the protection.
Claims (10)
1. a kind of all-in-one machine realization method, it is characterised in that comprise the following steps:
Data are calculated using at least one database server;
The data are managed by least one memory module.
2. according to the method described in claim 1, it is characterised in that configure at least two flash cards for the memory module.
3. according to the method described in claim 1, it is characterised in that will be described using Share-Nothing distributed computing technology
At least one memory module is fused into concentrating type logical resource pond;
The data are migrated to the database server from the memory module using RDMA zero duplication technologies.
4. according to the method described in claim 1, it is characterised in that at least one described database server and described at least one
Pass through IB network services between individual memory module.
5. method according to any one of claim 1 to 4, it is characterised in that the database server is general X86
Server.
6. a kind of all-in-one, it is characterised in that including:At least one database server and at least one memory module, wherein,
At least one described database server is connected with least one described memory module:
At least one database server, for calculating data;
At least one memory module, for managing the data.
7. all-in-one according to claim 6, it is characterised in that the memory module includes at least two flash cards.
8. all-in-one according to claim 7, it is characterised in that the memory module is divided using Share-Nothing's
At least one described memory module is fused into concentrating type logical resource pond by cloth technology;
The database server reads the data using RDMA zero duplication technologies from the memory module.
9. all-in-one according to claim 6, it is characterised in that at least one described database server with it is described at least
Pass through IB network services between one memory module.
10. the all-in-one according to any one of claim 6 to 9, it is characterised in that the database server is general
X86 servers.
Priority Applications (1)
Application Number | Priority Date | Filing Date | Title |
---|---|---|---|
CN201710545015.XA CN107135277A (en) | 2017-07-06 | 2017-07-06 | A kind of all-in-one machine realization method and device |
Applications Claiming Priority (1)
Application Number | Priority Date | Filing Date | Title |
---|---|---|---|
CN201710545015.XA CN107135277A (en) | 2017-07-06 | 2017-07-06 | A kind of all-in-one machine realization method and device |
Publications (1)
Publication Number | Publication Date |
---|---|
CN107135277A true CN107135277A (en) | 2017-09-05 |
Family
ID=59737373
Family Applications (1)
Application Number | Title | Priority Date | Filing Date |
---|---|---|---|
CN201710545015.XA Pending CN107135277A (en) | 2017-07-06 | 2017-07-06 | A kind of all-in-one machine realization method and device |
Country Status (1)
Country | Link |
---|---|
CN (1) | CN107135277A (en) |
Citations (7)
Publication number | Priority date | Publication date | Assignee | Title |
---|---|---|---|---|
CN103873559A (en) * | 2014-02-13 | 2014-06-18 | 南京斯坦德通信股份有限公司 | Database all-in-one machine capable of realizing high-speed storage |
CN104539679A (en) * | 2014-12-22 | 2015-04-22 | 国网信通亿力科技有限责任公司 | Clustered database system based on distributed flash technology and data transmission method of clustered database system |
CN105474210A (en) * | 2013-07-05 | 2016-04-06 | 蓝色棱镜有限公司 | System for automating processes |
CN105681402A (en) * | 2015-11-25 | 2016-06-15 | 北京文云易迅科技有限公司 | Distributed high speed database integration system based on PCIe flash memory card |
CN105721551A (en) * | 2016-01-21 | 2016-06-29 | 上海龙田数码科技有限公司 | Desktop virtualization realizing method |
CN106547659A (en) * | 2016-11-01 | 2017-03-29 | 郑州云海信息技术有限公司 | A kind of method that TPM functions of modules is tested under Linux |
CN106681738A (en) * | 2017-01-05 | 2017-05-17 | 郑州云海信息技术有限公司 | Method of modifying BIOS current values of Rack server based on Map String |
-
2017
- 2017-07-06 CN CN201710545015.XA patent/CN107135277A/en active Pending
Patent Citations (7)
Publication number | Priority date | Publication date | Assignee | Title |
---|---|---|---|---|
CN105474210A (en) * | 2013-07-05 | 2016-04-06 | 蓝色棱镜有限公司 | System for automating processes |
CN103873559A (en) * | 2014-02-13 | 2014-06-18 | 南京斯坦德通信股份有限公司 | Database all-in-one machine capable of realizing high-speed storage |
CN104539679A (en) * | 2014-12-22 | 2015-04-22 | 国网信通亿力科技有限责任公司 | Clustered database system based on distributed flash technology and data transmission method of clustered database system |
CN105681402A (en) * | 2015-11-25 | 2016-06-15 | 北京文云易迅科技有限公司 | Distributed high speed database integration system based on PCIe flash memory card |
CN105721551A (en) * | 2016-01-21 | 2016-06-29 | 上海龙田数码科技有限公司 | Desktop virtualization realizing method |
CN106547659A (en) * | 2016-11-01 | 2017-03-29 | 郑州云海信息技术有限公司 | A kind of method that TPM functions of modules is tested under Linux |
CN106681738A (en) * | 2017-01-05 | 2017-05-17 | 郑州云海信息技术有限公司 | Method of modifying BIOS current values of Rack server based on Map String |
Non-Patent Citations (1)
Title |
---|
张翔: "超融合数据服务平台在融合媒体的应用", 《广播与电视技术》 * |
Similar Documents
Publication | Publication Date | Title |
---|---|---|
CN108885554B (en) | Method, apparatus, medium, and data center device for allocating resources in a computing environment | |
CN108885582B (en) | Multi-tenant memory services for memory pool architecture | |
CN105978704B (en) | System and method for creating new cloud resource instruction set architecture | |
JP4560435B2 (en) | High performance computing system and high performance computing method | |
JP4986844B2 (en) | System and method for detecting and managing HPC node failures | |
JP4833965B2 (en) | System and method for cluster management based on HPC architecture | |
TWI272502B (en) | System and method for topology-aware job scheduling and backfilling in an HPC environment | |
JP2007533034A (en) | Graphical user interface for managing HPC clusters | |
US10346367B1 (en) | Load shedding techniques for distributed services with persistent client connections to ensure quality of service | |
CN103595799B (en) | A kind of method realizing distributed shared data storehouse | |
CN103226489A (en) | Integrated virtual infrastructure system | |
CN101656718A (en) | Network server system and method for establishing and starting virtual machine thereof | |
CN104135514B (en) | Fusion type virtual storage system | |
CN109547537A (en) | The method for realizing openstack High Availabitity based on SAN storage shared volume | |
CN109302494A (en) | A kind of configuration method of network store system, device, equipment and medium | |
Szalay et al. | Minimizing state access delay for cloud-native network functions | |
Yi et al. | Cloud computing architecture design of database resource pool based on cloud computing | |
CN108696559A (en) | Method for stream processing and device | |
CN107135277A (en) | A kind of all-in-one machine realization method and device | |
Krishnaswamy et al. | A microservices-based virtualized blockchain framework for emerging 5G data networks | |
Gray | Super-servers: Commodity computer clusters pose a software challenge | |
US11650849B2 (en) | Efficient component communication through accelerator switching in disaggregated datacenters | |
Miyoshi et al. | New system architecture for next-generation green data centers: mangrove | |
Yu et al. | Performance studies of a websphere application, trade, in scale-out and scale-up environments | |
US10152337B2 (en) | Logical data shuffling |
Legal Events
Date | Code | Title | Description |
---|---|---|---|
PB01 | 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 | ||
RJ01 | Rejection of invention patent application after publication |
Application publication date: 20170905 |