CN104461396B - A kind of distributed storage extension framework based on fusion architecture - Google Patents
A kind of distributed storage extension framework based on fusion architecture Download PDFInfo
- Publication number
- CN104461396B CN104461396B CN201410801075.XA CN201410801075A CN104461396B CN 104461396 B CN104461396 B CN 104461396B CN 201410801075 A CN201410801075 A CN 201410801075A CN 104461396 B CN104461396 B CN 104461396B
- Authority
- CN
- China
- Prior art keywords
- disk backboard
- disk
- computing module
- backboard
- administrative unit
- 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.)
- Active
Links
- 230000004927 fusion Effects 0.000 title claims abstract description 30
- 238000012545 processing Methods 0.000 claims abstract description 27
- 230000005540 biological transmission Effects 0.000 claims abstract description 11
- 238000004891 communication Methods 0.000 claims abstract description 4
- 238000012546 transfer Methods 0.000 claims description 7
- 238000013461 design Methods 0.000 claims description 5
- 238000012544 monitoring process Methods 0.000 claims description 4
- 238000007726 management method Methods 0.000 abstract description 13
- 238000013500 data storage Methods 0.000 abstract description 6
- 238000005516 engineering process Methods 0.000 abstract description 6
- 238000004364 calculation method Methods 0.000 abstract description 4
- 230000006870 function Effects 0.000 abstract description 3
- 230000002452 interceptive effect Effects 0.000 abstract description 3
- 238000010586 diagram Methods 0.000 description 3
- 230000009286 beneficial effect Effects 0.000 description 2
- 238000011084 recovery Methods 0.000 description 2
- 238000012795 verification Methods 0.000 description 2
- 238000011161 development Methods 0.000 description 1
- 230000000694 effects Effects 0.000 description 1
- 239000002360 explosive Substances 0.000 description 1
- 238000003780 insertion Methods 0.000 description 1
- 230000037431 insertion Effects 0.000 description 1
- 238000012423 maintenance Methods 0.000 description 1
- 238000005457 optimization Methods 0.000 description 1
Classifications
-
- G—PHYSICS
- G06—COMPUTING; CALCULATING OR COUNTING
- G06F—ELECTRIC DIGITAL DATA PROCESSING
- G06F3/00—Input arrangements for transferring data to be processed into a form capable of being handled by the computer; Output arrangements for transferring data from processing unit to output unit, e.g. interface arrangements
- G06F3/06—Digital input from, or digital output to, record carriers, e.g. RAID, emulated record carriers or networked record carriers
- G06F3/0601—Interfaces specially adapted for storage systems
- G06F3/0668—Interfaces specially adapted for storage systems adopting a particular infrastructure
- G06F3/067—Distributed or networked storage systems, e.g. storage area networks [SAN], network attached storage [NAS]
-
- G—PHYSICS
- G06—COMPUTING; CALCULATING OR COUNTING
- G06F—ELECTRIC DIGITAL DATA PROCESSING
- G06F11/00—Error detection; Error correction; Monitoring
- G06F11/30—Monitoring
- G06F11/32—Monitoring with visual or acoustical indication of the functioning of the machine
- G06F11/324—Display of status information
- G06F11/325—Display of status information by lamps or LED's
-
- G—PHYSICS
- G06—COMPUTING; CALCULATING OR COUNTING
- G06F—ELECTRIC DIGITAL DATA PROCESSING
- G06F3/00—Input arrangements for transferring data to be processed into a form capable of being handled by the computer; Output arrangements for transferring data from processing unit to output unit, e.g. interface arrangements
- G06F3/06—Digital input from, or digital output to, record carriers, e.g. RAID, emulated record carriers or networked record carriers
- G06F3/0601—Interfaces specially adapted for storage systems
- G06F3/0668—Interfaces specially adapted for storage systems adopting a particular infrastructure
- G06F3/0671—In-line storage system
- G06F3/0683—Plurality of storage devices
-
- G—PHYSICS
- G06—COMPUTING; CALCULATING OR COUNTING
- G06F—ELECTRIC DIGITAL DATA PROCESSING
- G06F2213/00—Indexing scheme relating to interconnection of, or transfer of information or other signals between, memories, input/output devices or central processing units
- G06F2213/38—Universal adapter
- G06F2213/3802—Harddisk connected to a computer port
Abstract
The present invention discloses a kind of distributed storage extension framework based on fusion architecture, is related to computer systems technology, is made up of two nucleus modules of computing module and memory module, wherein computing module is made up of computing unit, administrative unit and expanding element;The resource storage that memory module is responsible for whole framework includes disk backboard and disk bottom plate;Interactive communication between the administrative unit and computing unit;The expanding element is connected with disk backboard, and disk backboard supports some memory cell;And administrative unit is provided with disk backboard, the administrative unit interconnection of administrative unit and computing module communicate, and the feedback of the information on disk backboard is handled to computing module, and receive processing by computing module transmission Lai management instruction.The present invention realizes the unified fusion of traditional calculations the resource plane and storage resource plane, is provided simultaneously with the data-handling capacity of high speed and the data storage function of Large Copacity, meets the needs of big data epoch are to equipment calculating and storage capacity.
Description
Technical field
The present invention relates to computer systems technology, specifically a kind of distributed storage extensible frame based on fusion architecture
Structure.
Background technology
In traditional server and design Storage, server is often directed to the application of computation-intensive, and stores usual
Accurate pair is to lay particular stress on the intensive application of data storage, and both products are architecturally relatively independent.With network data
The explosive growth of amount, very big demand, conventional conventional store server and frame clothes it is also proposed to the disposal ability of equipment
The architecture design of business device, runs into limitation in terms of performance and expansivity is calculated, the big data epoch can not be met to equipment
Calculate the demand with storage capacity.And with high speed interconnection technology development and possess high density, high modularization and highly integrated
Degree form product is increasingly favored by clients such as data centers, therefore to being provided simultaneously with high speed processing ability and Large Copacity is deposited
The extensive market demand that the product in storage space is brought.
It is multiple information technologies to merge architecture (Converged infrastructure)(IT)Component is melted
Close, composition one is single, the calculating solution of optimization.The component of fusion architecture solution includes server, number
According to storage device, the network equipment and IT infrastructure management, the software with operation flow is automated.Distributed network memory technology
It is to be stored in what data were disperseed in more independent machinery equipments.Distributed network storage system uses expansible system knot
Structure, storage load is shared using more storage servers, position storage information using location server, not only solve traditional collection
The bottleneck problem of single storage server in Chinese style storage system, also improve the reliability, availability and autgmentability of system.
The content of the invention
A kind of bright part in view of the shortcomings of the prior art of we, there is provided distributed storage extension based on fusion architecture
Framework.
A kind of distributed storage extension framework based on fusion architecture of the present invention, solves what the technical problem used
Technical scheme is as follows:Distributed storage extension framework proposes a kind of high density storage architecture expansible based on transverse plane,
By horizontal high-speed expansion plane, realize that traditional calculations the resource plane is united with storage resource plane in new architectural framework
One fusion;The distributed storage extension framework main body is made up of two nucleus modules of computing module and memory module, wherein
Computing module is responsible for its main operational of whole framework, is mainly made up of computing unit, administrative unit and expanding element;Memory module
It is responsible for the resource storage of whole framework, is mainly made up of disk backboard and disk bottom plate.
In the computing module, the computing unit is formed using some processing units, passes through interconnection between processing unit
Bus connects;Administrative center of the administrative unit as whole system, the interactive communication between computing unit;The extension is single
Member is connected with memory module, is on the one hand responsible for the transmission of data between computing module and memory module, on the other hand can be according to place
The instruction for managing unit carries out the operation of data and the control acted to memory module, additionally it is possible to which RAID information in memory module is entered
Row processing, including data redundancy algorithm computing and after encountering problems data CRC verification and recovery.
In the memory module, the disk backboard is mainly responsible for the data transfer between the physical store of front end, with meter
The expanding element connection of module is calculated, while some memory cell can be supported on the disk backboard;And on the disk backboard
Administrative unit is provided with, the administrative unit communicates with the administrative unit interconnection of computing module, and the information on disk backboard is anti-
Computing module of feeding is handled, at the same receive and handle by computing module transmission Lai management instruct;And disk bottom plate connects
System power supply backboard, it is electrically communicate to what is provided on system power supply backboard on disk backboard, ensures the operation of these memory cell.
In addition, the disk bottom plate is connected by cable with preposition UI plates, for providing control signal, and whole magnetic is monitored
The running status for the memory cell supported on disk backboard.
A kind of distributed storage extension framework based on fusion architecture of the present invention has beneficial compared with prior art
Effect is:Distributed storage of the present invention extends framework by horizontal high-speed expansion plane, is realized in new architectural framework
Traditional calculations the resource plane and the unified fusion of storage resource plane, breach and calculate and store in conventional architectures independently of each other not
Beneficial to data message integrated treatment control, storage the drawbacks of, the data processing of high speed can be provided simultaneously with new framework
The data storage function of ability and Large Copacity, meets the needs of big data epoch are to equipment calculating and storage capacity.
Brief description of the drawings
Accompanying drawing 1 extends the theory diagram of framework for the distributed storage of the fusion architecture;
Accompanying drawing 2 extends the schematic diagram of framework for the distributed storage of the fusion architecture;
Accompanying drawing 3 extends the operating diagram of framework for the distributed storage of the fusion architecture;
Description of reference numerals:1st, computing module;2nd, memory module;3rd, administrative unit;4th, expanding element;5th, disk backboard;
6th, disk bottom plate;7th, power supply backboard;8th, preposition UI plates.
Embodiment
For the object, technical solutions and advantages of the present invention are more clearly understood, below in conjunction with specific embodiment, and refer to
Accompanying drawing, a kind of distributed storage extension framework based on fusion architecture of the present invention is further described.
A kind of distributed storage extension framework based on fusion architecture of the present invention, proposes that one kind is based on transverse plane
Expansible high density storage architecture, by horizontal high-speed expansion plane, traditional calculations resource is realized in new architectural framework
Plane carries out unified merge with storage resource plane.Framework is extended based on the distributed storage of fusion architecture, breaches biography
Application is calculated in system server and applies relatively independent design with storage, the data of high speed can be provided simultaneously with new framework
The data storage function of disposal ability and Large Copacity, meets the needs of big data epoch are to equipment calculating and storage capacity.
Embodiment 1:
A kind of distributed storage extension framework based on fusion architecture, the distributed storage extensible frame described in the present embodiment
Structure main body is made up of two nucleus modules of computing module and memory module, and wherein computing module is transported as the core of whole framework
Calculate, be mainly made up of computing unit, administrative unit and expanding element.
The computing unit is formed using some processing units, is connected between processing unit by interconnection bus;
Administrative center of the administrative unit as whole system, the interactive communication between computing unit;
Significant element of the expanding element as the information data processing between memory module, on the one hand as calculating mould
The transmission channel of data between block and memory module, it is responsible for information transfer, plays information transfer bridge beam action;On the other hand can
The control of the operation and action of data is carried out to memory module according to the instruction of computing module, additionally it is possible to RAID in memory module
Information is handled, including data redundancy algorithm computing and after encountering problems data CRC verification and recovery.
In distributed storage extension framework based on fusion architecture described in the present embodiment, the memory module is by disk backboard
Formed with disk bottom plate two parts;
Wherein disk backboard is mainly responsible for the data transfer between the physical store of front end, the expanding element with computing module
Connect, some memory cell can be supported on the disk backboard;Administrative unit, the management are provided with the disk backboard
Unit communicates with the administrative unit interconnection of computing module, the feedback of the information on disk backboard is handled to computing module, together
When receive and handle by computing module transmission Lai management instruct;
On the one hand the disk bottom plate connects the dorsulum of system, disk backboard is electrically communicate to by what is provided on dorsulum
On, ensure the operation of these memory cell;On the other hand it is connected by cable with preposition UI plates, for providing control signal, and
Monitor the running status for the memory cell supported on whole disk backboard.
Embodiment 2:
Distributed storage extension framework based on fusion architecture described in the present embodiment, on the basis of embodiment 1, such as accompanying drawing
Shown in 1, the computing unit of the computing module uses 2 X86-based processing units(Processing unit 1, processing unit 2)Composition,
Processing unit will be connected by the QPI interconnection bus of two high speeds, and transmission rate is up to 9.6GT/s;The expansion of the computing module
Exhibition unit includes RAID buckles and Mini SAS Port, passes through 1 PCIE3.0 between the processing unit 1 and RAID buckles
X4 link connection, main logic unit of the RAID buckles as disk array in system, using the design of Mezz buckles
Form, the instruction of one side reception processing unit, on the other hand control the reading of data in disk array;And RAID buckles itself
After PCIe signals are converted into Mini-SAS signals, connected by the SAS expanding elements on Mini SAS Port and disk backboard
Connect.
On the disk backboard of the memory module support 12 2.5 cun of SAS/SATA memory cell, using 2 memory cell as
1 perpendicular group, 6 perpendicular group is supported in horizontal space altogether;SAS expanding elements, the SAS extensions are also provided with the disk backboard
Unit does not have data-handling capacity in itself, is responsible for data connection and data transmission, and SAS expanding elements are mainly used as connection 12 and deposited
Storage unit, it will be handled in the data transfer of 12 memory cell on disk bottom plate to computing module, and according to processing unit
Or the operational order of RAID buckles operates to the data of memory cell.
Administrative center of the administrative unit of the computing module as whole system, it is total by I2C between processing unit 1
Line connects, and is responsible for the management instruction that reception processing unit is assigned, while the management data that will be responsible for collecting are sent to processing unit
Analyzed and parsed.Disk backboard mainly provides the storage and control to data, also there is an administrative unit on disk backboard,
On the one hand be responsible for disk backboard in itself and 12 state of memory cells monitoring, passing through I2C management bus, to obtain storage single
The information such as voltage, temperature in member;On the other hand it is attached by SGPIO buses and SAS expanding elements, is realized by SGPIO
Monitoring to the configuration operation state of SAS expanding element initialization informations.
Administrative unit on the disk backboard and pass through SGPIO and JATG two between the administrative unit of the computing module
Bus connects;Pass through the pipe in SGPIO bus configurations and initialization hardboard backboard after the administrative unit startup of the computing module
Unit is managed, again can be by two buses of SGPIO and JATG by the feedback of the information on disk backboard after unit normal work to be managed
Handled to computing module, at the same receive and handle by computing module transmission Lai management instruct.
Meanwhile one end of the disk bottom plate of the memory module is provided with power connector, by by the power connector
It is plugged on the power connector of system power supply backboard and is powered to memory module, ensures the steady operation of whole module.In addition, institute
To state and be also provided with managing signal connector on disk bottom plate, the management signal connector is connected with the administrative unit of disk bottom plate,
The management signal connector is connected on the corresponding management signal connector of the preposition UI plates of system, and preposition UI is mainly used to show
Show the running status of memory cell, be easy to the situation of administrative staff's supervising data storage.
The distributed storage extension framework based on fusion architecture, its described computing module are described in embodiment 1 and embodiment 2
Mainboard in system, the memory cell supported on the disk backboard of the memory module is 12 pieces of disks(DISK);Such as the institute of accompanying drawing 2
Show, right side is computing module 1, and left side is memory module 2;Two CPU are provided with computing module 1(Processing unit), management
Unit 3 and expanding element 4;Disk backboard 5 and its 12 disks supported, and and disk are provided with storage module 2
Power supply backboard 7 that bottom plate 6 is connected, preposition UI plates 8, wherein power supply backboard is responsible for providing stable power supply to whole module and supplied
Answer, ensure the steady operation of whole module, disk backboard mainly provides the storage and control to data, and disk backboard supports 12
Memory cell, memory module are used for the data of specific storage entity as the medium of data storage, and preposition UI plates are mainly used to show
Show the running status of this 12 disks.
As shown in Figure 3, the distributed storage extension framework based on fusion architecture, whole memory module described in the present embodiment
2 can also unify to extract from front end, and pull action does not interfere with the operation of whole memory module, will not be to user's actual motion
Application program brings any influence, and each memory cell in memory module also supports online insertion and removal Operation and Maintenance.
Above-mentioned embodiment is only the specific case of the present invention, and scope of patent protection of the invention includes but is not limited to
Above-mentioned embodiment, any meet claims of the present invention and person of an ordinary skill in the technical field is to it
The appropriate change or replacement done, it should all fall into the scope of patent protection of the present invention.
Claims (7)
1. a kind of distributed storage extension framework based on fusion architecture, it is characterised in that propose that one kind can based on transverse plane
The high density storage architecture of extension, by horizontal high-speed expansion plane, realized in new architectural framework computing resource plane with
Storage resource plane unified fusion;The distributed storage extends framework main body by two nucleus modules of computing module and memory module
Composition, wherein computing module is responsible for its main operational of whole framework, mainly by computing unit, administrative unit and expanding element group
Into;Memory module is responsible for the resource storage of whole framework, mainly includes disk backboard and disk bottom plate;
The computing unit uses 2 X86-based processing units:Processing unit 1 and processing unit 2, pass through between processing unit
The QPI interconnection bus connection of two high speeds;Administrative center of the administrative unit as whole system, hands between computing unit
Mutual communication;The expanding element is connected with memory module, is responsible for the transmission of data between computing module and memory module, while can
The control of the operation and action of data is carried out to memory module according to the instruction of processing unit;The expanding element is detained including RAID
Card, passes through PCIE3.0 x4 link connection between the processing unit 1 and RAID buckles;
The disk backboard is mainly responsible for the data transfer between the physical store of front end, connects with the expanding element of computing module
Connect, while some memory cell can be supported on disk backboard;And administrative unit is provided with disk backboard, the administrative unit
Communicated with the administrative unit interconnection of computing module, the feedback of the information on disk backboard is handled to computing module, connect simultaneously
By and handle by computing module transmission come management instruction;
The disk bottom plate connects system power supply backboard, is electrically communicate to what is provided on system power supply backboard on disk backboard, protects
Demonstrate,prove the operation of these memory cell;Meanwhile the disk bottom plate is connected by cable with preposition UI plates, for providing control letter
Number, and monitor the running status for the memory cell supported on whole disk backboard.
2. a kind of distributed storage extension framework based on fusion architecture according to claim 1, it is characterised in that described
RAID buckles use the design form of Mezz buckles.
A kind of 3. distributed storage extension framework based on fusion architecture according to claim 2, it is characterised in that the magnetic
SAS expanding elements are also provided with disk backboard, the SAS expanding elements are responsible for data connection and data transmission, SAS expanding elements
It is mainly used as connecting the memory cell on disk backboard;The expanding element of the computing module also includes Mini SAS Port, institute
State RAID buckles to be connected with the SAS expanding elements on disk backboard by Mini SAS Port, by the data transfer of memory cell
Handled on to computing module, and the data of memory cell are grasped according to the operational order of processing unit or RAID buckles
Make.
A kind of 4. distributed storage extension framework based on fusion architecture according to claim 3, it is characterised in that the magnetic
12 2.5 cun of SAS/SATA memory cell are supported on disk backboard, using 2 memory cell as 1 perpendicular group, are supported altogether in horizontal space
6 perpendicular group.
A kind of 5. distributed storage extension framework based on fusion architecture according to claim 4, it is characterised in that the magnetic
The administrative unit of disk backboard be responsible for disk backboard in itself and 12 state of memory cells monitoring, pass through I2C management bus
Obtain voltage, temperature information in memory cell;It is attached simultaneously by SGPIO buses and SAS expanding elements, passes through SGPIO
Realize the monitoring to the configuration operation state of SAS expanding element initialization informations.
A kind of 6. distributed storage extension framework based on fusion architecture according to claim 1, it is characterised in that the magnetic
Administrative unit on disk backboard and pass through two buses of SGPIO and JATG between the administrative unit of the computing module and connect.
7. a kind of distributed storage extension framework based on fusion architecture according to claim 1, it is characterised in that described to deposit
The one end for storing up the disk bottom plate of module is provided with power connector, by the way that the power connector is plugged on system power supply backboard
Powered to memory module;Management signal connector is additionally provided with the disk bottom plate, the management signal connector and disk bottom
The administrative unit connection of plate, by the corresponding management signal connector that the management signal connector is plugged into the preposition UI plates of system
On communicated.
Priority Applications (1)
Application Number | Priority Date | Filing Date | Title |
---|---|---|---|
CN201410801075.XA CN104461396B (en) | 2014-12-22 | 2014-12-22 | A kind of distributed storage extension framework based on fusion architecture |
Applications Claiming Priority (1)
Application Number | Priority Date | Filing Date | Title |
---|---|---|---|
CN201410801075.XA CN104461396B (en) | 2014-12-22 | 2014-12-22 | A kind of distributed storage extension framework based on fusion architecture |
Publications (2)
Publication Number | Publication Date |
---|---|
CN104461396A CN104461396A (en) | 2015-03-25 |
CN104461396B true CN104461396B (en) | 2018-03-02 |
Family
ID=52907525
Family Applications (1)
Application Number | Title | Priority Date | Filing Date |
---|---|---|---|
CN201410801075.XA Active CN104461396B (en) | 2014-12-22 | 2014-12-22 | A kind of distributed storage extension framework based on fusion architecture |
Country Status (1)
Country | Link |
---|---|
CN (1) | CN104461396B (en) |
Families Citing this family (5)
Publication number | Priority date | Publication date | Assignee | Title |
---|---|---|---|---|
CN104899179A (en) * | 2015-04-03 | 2015-09-09 | 浪潮电子信息产业股份有限公司 | Method for designing multi-path server QPI clamp based on converged infrastructure |
CN105159605A (en) * | 2015-08-24 | 2015-12-16 | 浪潮(北京)电子信息产业有限公司 | Storage server architecture |
CN107491268B (en) * | 2017-07-31 | 2024-02-06 | 郑州云海信息技术有限公司 | JBOD storage architecture supporting hybrid storage mode in high density |
CN111752346A (en) * | 2019-06-24 | 2020-10-09 | 北京京东尚科信息技术有限公司 | Server based on combined architecture |
CN112394882B (en) * | 2020-11-17 | 2022-04-19 | 浙江大华技术股份有限公司 | Data storage method and device, storage medium and electronic device |
Citations (3)
Publication number | Priority date | Publication date | Assignee | Title |
---|---|---|---|---|
CN103970214A (en) * | 2014-05-19 | 2014-08-06 | 浪潮电子信息产业股份有限公司 | Heterogeneous acceleration blade type computer system architecture |
CN104035731A (en) * | 2014-06-16 | 2014-09-10 | 浪潮(北京)电子信息产业有限公司 | Storage head node of blade server |
CN104049698A (en) * | 2014-06-26 | 2014-09-17 | 浪潮电子信息产业股份有限公司 | Storage and compute server based on 6U space |
Family Cites Families (1)
Publication number | Priority date | Publication date | Assignee | Title |
---|---|---|---|---|
JP5720649B2 (en) * | 2011-11-04 | 2015-05-20 | 株式会社リコー | Device management apparatus and program |
-
2014
- 2014-12-22 CN CN201410801075.XA patent/CN104461396B/en active Active
Patent Citations (3)
Publication number | Priority date | Publication date | Assignee | Title |
---|---|---|---|---|
CN103970214A (en) * | 2014-05-19 | 2014-08-06 | 浪潮电子信息产业股份有限公司 | Heterogeneous acceleration blade type computer system architecture |
CN104035731A (en) * | 2014-06-16 | 2014-09-10 | 浪潮(北京)电子信息产业有限公司 | Storage head node of blade server |
CN104049698A (en) * | 2014-06-26 | 2014-09-17 | 浪潮电子信息产业股份有限公司 | Storage and compute server based on 6U space |
Also Published As
Publication number | Publication date |
---|---|
CN104461396A (en) | 2015-03-25 |
Similar Documents
Publication | Publication Date | Title |
---|---|---|
CN104461396B (en) | A kind of distributed storage extension framework based on fusion architecture | |
Benner | Optical interconnect opportunities in supercomputers and high end computing | |
CN105426286B (en) | A kind of system being monitored to whole machine cabinet server | |
CN101739220A (en) | Method for designing multi-controller memory array | |
CN105117170A (en) | Computer system architecture | |
CN104135514B (en) | Fusion type virtual storage system | |
CN104951251B (en) | A kind of cloud server system of fusion architecture | |
CN102546813A (en) | High-performance cluster computing system based on x86PC framework | |
CN102929363B (en) | A kind of method for designing of high-density blade server | |
CN204833236U (en) | Support memory system of hybrid storage | |
CN205139890U (en) | Two memory system that live of two accuses based on X86 framework | |
CN103023973A (en) | Cluster server designing method based on CPCI (Compact Peripheral Component Interconnect) structure | |
CN104991958A (en) | Analysis system and method for power equipment monitoring data | |
CN102404201B (en) | Method of realizing maximum bandwidth of Lustre concurrent file system | |
CN104408014A (en) | System and method for interconnecting processing units of calculation systems | |
CN107220195A (en) | A kind of multichannel computer system architecture for supporting high density NVMe to store | |
CN204557308U (en) | A kind of high density Novel cutter flap-type server based on fusion architecture | |
CN104951024B (en) | A kind of large data all-in-one machine based on electric power application | |
CN107070699A (en) | Controller monitoring is managed in storage system redundancy design method and device | |
CN202443354U (en) | A multi-node cable-free modular computer | |
CN105159605A (en) | Storage server architecture | |
CN105045922A (en) | Electrical equipment monitoring method and device | |
CN104579786B (en) | A kind of server design method based on 2D Torus network topology architectures | |
CN105511990B (en) | Device based on fusion architecture dual redundant degree storage control node framework | |
CN108090011A (en) | A kind of SAS Switch controllers extension framework and design method |
Legal Events
Date | Code | Title | Description |
---|---|---|---|
C06 | Publication | ||
PB01 | Publication | ||
C10 | Entry into substantive examination | ||
SE01 | Entry into force of request for substantive examination | ||
GR01 | Patent grant | ||
GR01 | Patent grant |