CN104158875B - It is a kind of to share the method and system for mitigating data center server task - Google Patents
It is a kind of to share the method and system for mitigating data center server task Download PDFInfo
- Publication number
- CN104158875B CN104158875B CN201410394960.0A CN201410394960A CN104158875B CN 104158875 B CN104158875 B CN 104158875B CN 201410394960 A CN201410394960 A CN 201410394960A CN 104158875 B CN104158875 B CN 104158875B
- Authority
- CN
- China
- Prior art keywords
- data
- processor
- task
- server
- data center
- 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
Landscapes
- Information Retrieval, Db Structures And Fs Structures Therefor (AREA)
Abstract
The present invention provides a kind of method and system for sharing mitigation data center server task, share server inner treater some better simply tasks using the processor stored in network, processor in server can go to perform other complicated tasks, so as to substantially reduce power consumption, it is cost-effective, improve system performance.
Description
Technical field
The present invention relates to a kind of method for sharing mitigation data center server task, more particularly, to one kind based on storage
Microprocessor in network mitigates the method and system of data center server task to share.
Background technology
With the arriving of cloud era, big data (big data) word is mentioned more and more, and people are described with it
The mass data produced with the definition information explosion epoch, and name associated technology to develop and innovate.Data are rapid
Expand and become larger, it decides the future development of enterprise, although many enterprises may not recognize that data explosion increases
The hidden danger of problem is brought, but over time, people will more and more recognize importance of the data to enterprise.Just
Such as《The New York Times》Alleged in one special column of 2 months 2012, " big data " epoch have come, business, it is economical and other
In field, decision-making will be increasingly based on data and analysis and make, and be not based on experience and intuition.Big data analysis often and cloud meter
It is linked together, because large data set analysis needs to come to tens of, hundreds of as the frame Map Reduce in real time
Or even thousands of computers shares out the work.By the end of 2012, data volume was risen to PB from TB (1024GB=1TB) rank
(1024TB=1PB), EB (1024PB=1EB) or even ZB (1024EB=1ZB) rank.The research of International Data Corporation (IDC) (IDC)
The result shows that the data volume that the whole world in 2008 produces is 0.49ZB, the data volume of 2009 is 0.8ZB, and growth in 2010 is
1.2ZB, the quantity of 2011 are more up to 1.82ZB, and equivalent to the whole world, everyone produces the data of more than 200GB.And by 2012
Untill, the data volume of all printing materials of human being's production is 200PB, and all data volumes that the whole mankind said in history are big
It is approximately 5EB.
And it would be of interest to how inquire about or search having for user's care from so huge data for scientific research at present
It is worth data.The structure chart of legacy user's Query Information is as shown in Figure 1.User sends data into network by personal computer
Request, data center server receive order and start inquiry and the search required data message of user from storage network.I
Know, processor can only directly handle the data message in memory, first will be from storage network for so huge data volume
In memory in be transferred in the memory of server, then the processor of server carries out data processing and behaviour to these information
Make, then result is back to client.Obviously, the data message imported from storage network in server is to be far longer than server
It is back to the data message of subscription client.For increasingly huge data system, the speed of processor processes data
Bottleneck is to store the limitation that network imports data into server memory, because whether which kind of memory, such as traditional magnetic
Disk, solid state hard disc, flash memory, and network attached storage (NAS, Network Attached Storage, a kind of dedicated data
Storage server), Direct Attached Storage (DAS, Direct Attached Storage, i.e. external storage pass through connect electricity
Cable is attached directly to a kind of storage organization on server) or redundant array of independent disks (RAID, Redundant Array of
Independent Disks, allow multiple independent hard disks to be combined into a hard disk groups by different modes, the performances of hard disk groups compared with
Single hard disk has greatly improved in performance), the read-write speed to internal storage data is far smaller than to its reading and writing data speed
Rate.At present, in order to improve the speed of processor-server processing data, IMC (IMC, In Memory can be used
Computation) technology improves processing speed, which is the capacity by increasing memory, so as to disposably import
More data volumes, so as to accelerate the speed of processor processes data.This method can no doubt accelerate the speed of data processing,
But for server, its configurable memory size has the upper limit, if capacity reaches the upper limit, only way is just
It is the quantity for increasing server, it is clear that cost price is higher, and since memory is the processor of volatibility, it is necessary to periodically brush
Newly, thus power consumption is also very big.
The real information interested of user is often tip of the iceberg in so huge database, when processor is most of
Between in the data searched for and inquired about those users and really need, the ALU of these feature operations and non-required processor-server
(Arithmetic Logic Unit, arithmetic logic unit) participates in, it may be said that the processor-server most of the time is all in quilt
Waste one's talent on a petty job, there is waist performance.It is known that there is also substantial amounts of microprocessor in network is stored, whether magnetic
Disk, solid state hard disc, flash memory, or NAS, RAID etc., are equipped with microprocessor inside it, their task is exactly single to storage
Member is managed and controls, such as the selection of wear leveling, module, error checking error correction, reading and writing data etc..Some are present in
The microprocessor in network is stored up in performance even no less than the processor of some personal computers, compared to the processor of server
For, their integrated technique node is higher, thus power consumption is relatively low, and cost is also lower, and most of the time, i.e., not
When needing to carry out a large amount of write operations to memory, these microprocessors are in idle condition.
In conclusion the microprocessor in storage network is not fully utilized, the waste of performance is in turn resulted in.
The content of the invention
According to the above problem, the present invention provides it is a kind of share mitigate the method for data center server task, wherein, bag
Include following steps：
Step S1：User sends data requesting instructions by data center server of the electric terminal equipment into network；
Step S2：The data center server obtains user after receiving the data requesting instructions from storage network
Required data message, and the data message needed for user is fed back into the electric terminal equipment；
Wherein, the data center server is configured with first processor, described to deposit to carry out data operation processing task
Storage network configuration has second processor, for carrying out maintenance processing to storage network；
When the second processor is in idle condition, the data center server is by the data operation of part
Reason task is distributed to the second processor and handled, and can be by the second processor directly by user requested data
Feed back to the electric terminal equipment.
Above-mentioned method, wherein, the second processor, which carries out attended operation task, to be included：Wear leveling operation, module
Selection operation, error checking error-correction operation and/or data read-write operation.
Above-mentioned method, wherein, the data-handling capacity of the first processor is better than the data of the second processor
Disposal ability.
Above-mentioned method, wherein, the second processor is micro- by being configured in the storage device in the storage network
Processor.
Above-mentioned method, wherein, the storage device in the storage network is disk, one kind in solid state hard disc, flash memory
Or it is a variety of, and/or the one or more in NAS, DAS and RAID in data center server.
It is a kind of to share the system for mitigating data center server task, wherein, the system comprises：
Electric terminal equipment, data center server and storage network, user is by electric terminal equipment into network
Data center server sends data requesting instructions；The data center server is received after the data requesting instructions from depositing
The data message obtained in network needed for user is stored up, and the data message needed for user is fed back into the electric terminal equipment；
Wherein, the data center server is configured with first processor, described to deposit to carry out data operation processing task
Second processor is configured with storage network, the second processor is used to carry out maintenance processing to storage network；
When the second processor is in idle condition, the data center server handles the part data operation
Task is distributed to the second processor and handled, and can be anti-directly by user requested data by the second processor
It is fed to the user terminal.
Above-mentioned system, wherein, the second processor carries out attended operation task bag to the data center server
Include：Wear leveling operation, module selection operation, error checking error-correction operation and/or data read-write operation.
Above-mentioned system, wherein, the data-handling capacity of the first processor is better than the data of the second processor
Disposal ability.
Above-mentioned system, wherein, the second processor is the microprocessor that is configured in the storage device in storage network
Device.
Above-mentioned system, wherein, the storage device in the storage network is disk, one kind in solid state hard disc, flash memory
Or it is a variety of, and/or the one or more in NAS, DAS and RAID in data center server.
Since present invention employs as above technical solution, one is handled by using the microprocessor in those storage networks
Task a little and being not required data center server ALU largely to participate in, such as data transfer, data query etc., so as to alleviate
The task of server, improves the performance of system.
Brief description of the drawings
Upon reading the detailed description of non-limiting embodiments with reference to the following drawings, the present invention and its feature, outer
Shape and advantage will become more apparent upon.Identical mark indicates identical part in whole attached drawings.Not deliberately proportionally
Draw attached drawing, it is preferred that emphasis is the purport of the present invention is shown.
Fig. 1 legacy users search for the structure chart of data message；
A kind of method schematic diagram for mitigating data center server task of Fig. 2 present invention；
Processor-server performs task A schematic diagrames when Fig. 3 tasks B occupies memory；
Fig. 4, which is utilized, calculates (IMC) technology solution schematic diagram in memory；
Fig. 5 utilizes this method schematic diagram for mitigating server task of the present invention；
Processor-server performs task B2 schematic diagrames when Fig. 6 tasks B1 occupies memory；
Fig. 7, which is utilized, calculates (IMC) technology solution schematic diagram in memory；
Fig. 8 utilizes this 1 schematic diagram of method for mitigating server task of the present invention；
Fig. 9 utilizes this 2 schematic diagram of method for mitigating server task of the present invention；
Figure 10 is the structure diagram of Magnetic Disk Controler in hard disk；
Figure 11 is one schematic diagram A of concrete application of the present invention；
Figure 12 is one schematic diagram B of concrete application of the present invention；
Figure 13 is one schematic diagram C of concrete application of the present invention.
Embodiment
In the following description, a large amount of concrete details are given in order to provide more thorough understanding of the invention.So
And it is obvious to the skilled person that the present invention may not need one or more of these details and be able to
Implement.In other examples, in order to avoid with the present invention obscure, for some technical characteristics well known in the art not into
Row description.
It should be appreciated that the present invention can be implemented in different forms, and it should not be construed as being limited to what is proposed here
Embodiment.On the contrary, providing these embodiments disclosure will be made thoroughly and complete, and will fully convey the scope of the invention to
Those skilled in the art.In the accompanying drawings, for clarity, the size and relative size in Ceng He areas may be exaggerated.From beginning to end
Same reference numerals represent identical element.
In order to thoroughly understand the present invention, detailed step and detailed structure will be proposed in following description, so as to
Explain technical scheme.Presently preferred embodiments of the present invention is described in detail as follows, but in addition to these detailed descriptions, this
Invention can also have other embodiment.
The present invention provides a kind of method for sharing mitigation data center server task, include the following steps：
Step S1：User sends data requesting instructions by data center server of the electric terminal equipment into network.
One optional embodiment is that the electric terminal equipment can be PC or mobile phone.
Step S2：Data center server receives after data requesting instructions the number obtained from storage network needed for user
It is believed that breath, and the data message needed for user is fed back into electric terminal equipment.
In the present invention, data center server is configured with first processor, to carry out data operation processing task, storage
Network configuration has second processor, for carrying out maintenance processing to storage network；When the second processor is in idle condition,
Partial data calculation process task is distributed to second processor and handled by data center server, and can be by second
User requested data is directly fed back to electric terminal equipment by reason device.Mitigate the pressure of first processor by second processor
Power, and then lift whole data center's processing speed.
Preferably, the data-handling capacity of above-mentioned first processor is better than the data-handling capacity of second processor.Into
One step is preferable, and second processor is the microprocessor configured in the storage device being present in storage network, stores network
In storage device include the one or more of such as disk, solid state hard disc, flash memory, and in some server storage networks
All storage devices such as NAS, DAS and RAID.
Preferably, carrying out attended operation task using above-mentioned second processor includes：Wear leveling operation, module selection
Operation, error checking error-correction operation and/or data read-write operation.
Meanwhile present invention also offers it is a kind of share mitigate the system of data center server task, which to include：Electricity
Sub- terminal device, data center server and storage network, user are taken by data center of the electric terminal equipment into network
Business device sends data requesting instructions；Data center server obtains user institute after receiving data requesting instructions from storage network
The data message needed, and the data message needed for user is fed back into electric terminal equipment；Wherein, data center server configures
There is first processor, to carry out data operation processing task, store in network and be configured with second processor, second processor is used for
Maintenance processing is carried out to storage network；When the second processor is in idle condition, data center server is by partial data
Calculation process task, which is distributed to second processor, to be handled, and can be anti-directly by user requested data by second processor
It is fed to user terminal.
Preferably, carrying out attended operation task using above-mentioned second processor includes：Wear leveling operation, module selection
Operation, error checking error-correction operation and/or data read-write operation.
Preferably, the data-handling capacity of above-mentioned first processor is better than the data-handling capacity of second processor.Into
One step is preferable, and second processor is the microprocessor configured in the storage device being present in storage network, stores network
In storage device include such as disk, solid state hard disc, flash memory, and some server storage networks in NAS, DAS and
All storage devices such as RAID.
Just one embodiment of present invention offer is further elaborated below：The present invention proposes a kind of amortization of data center service
Have a high regard for the method for business.Under traditional approach, the original handled task of server is divided into two parts, a part is task A, another
Part is task B.The task that microprocessor is completed in storage network is referred to as task C.And apply the present invention is this to share number
After method according to central server task, the processor in server only completes task A, and stores the microprocessor in network
Share server task B, as shown in Fig. 2, so as to alleviate the task of processor-server, so as to improve system performance.
Wherein, the task A is some complicated tasks that are scientific calculation processing and needing ALU largely to participate in, it is not
Need a large amount of clusters (burst) request of data；Task B is task of the processor-server handled by except task A, is some letters
The repeated task of single non-science calculation process, generally requires substantial amounts of company-data request；Task C is in storage network
The conventional maintenance task completed of microprocessor, such as wear leveling, module selection, error checking error correction, reading and writing data etc..
The present invention can allow processor-server focus on task A, i.e., using the ALU of high-performance data disposal ability come pair
Task A processing；The processing task B that the microprocessor in network can be parallel when not handling the task C i.e. free time is stored at the same time,
So as to reduce the reading speed bottleneck between storage network and server memory, reduce as caused by task B in large capacity
I/O occupation rates between the power consumption and large capacity memory and server deposited, so as to improve server system performance.
Such as in certain server, the mass data needed for task B occupies memory headroom, if processor needs at this time
The required mass data of task A, it is necessary to be imported the memory headroom of server, due to interior by processing task A from storage network
Space is deposited occupied by the data of task B, then the data of task B will be covered by the data of task A, schematic diagram such as Fig. 3
It is shown.If the data needed for task B can be called often, then just need constantly to import memory, power consumption from storage network
Also increase therewith, in addition, reading the processing speed that data limit processor from storage network, can also be dropped therewith in performance
It is low.According to (IMC) technology is calculated in memory, that is, need to increase extra server to reach more memory requirements, such as Fig. 4
It is shown.Obvious this mode can increase system performance, but cost can also greatly increase, and power consumption can also increase.According to this hair
The bright this method for sharing mitigation data center server task, then without increasing the server of the big power consumption of high cost, by number
According to data needed for A import server memory, the high-performance processor of server handles task A, by micro- in storage network
Device is managed to handle task B, the two can be performed parallel, more efficient rapid, high-performance, and be eliminated the data of task B
The power consumption of server memory is imported, the results are shown in Figure 5.
In another example in certain server, the mass data needed for task B1 occupies memory headroom, if processor at this time
Processing task B2 is needed, it is necessary to which the required mass data of task B2 to be imported to the memory headroom of server from storage network,
Since memory headroom is occupied by the data of task B1, then the data of task B1 will be covered by the data of task B2, be shown
It is intended to as shown in Figure 6.If the data needed for task B1 can be called often, then just need constantly to import from storage network
Memory, power consumption also increase therewith, in addition, the processing speed that data limit processor is read from storage network, in performance
It can decrease.According to (IMC) technology is calculated in memory, that is, needing increases extra server is needed with reaching more memories
Ask, as shown in Figure 7.Obvious this mode can increase system performance, but cost can also greatly increase, and power consumption can also increase.If
Using this method for sharing mitigation data center server task of the present invention, then without increasing the service of the big power consumption of high cost
Device, the processor of server continue with task B1, store the microprocessor in network to handle task B2, as a result such as Fig. 8 institutes
Show.If, can also be without the mass data of task B1 and B2 be imported service in order to further discharge processor-server task
Device memory, the multi-microprocessor that need to only store in network come executing tasks parallelly B1 and task B2, and the processor of server can
To go to perform other tasks, the results are shown in Figure 9.This method power consumption for sharing mitigation server task of the obvious present invention is more
Low, cost is lower, and performance will not reduce, as shown in table 1 with computing technique contrast in memory.
Table 1
Concrete application one is named to be described further.
By taking harddisk memory (Hard Disk) as an example, can all there is Magnetic Disk Controler (Hard in present most hard disks
Disk controller), its primary structure is as shown in Figure 10, and as can be seen from Figure, which has a processor, and
And possess the code area of oneself and data field (buffer DRAM).As memory capacity is increasing, storage organization is more and more multiple
Miscellaneous, also higher to the performance requirement of storage control, such as the storage control such as RAID, NAS, its internal processor is all using running quickly
Series processors or high-performance ARM kernels are risen, carries 2GB even memories of larger capacity, these processors not only can be complete
The task traditional into its, as wear leveling, module selection, error checking error correction, control reading and writing data etc., can also carry out completely
Some more complicated arithmetic operations such as data query and search, and at all without high-performance processor in data center server
Participate in.Data can not only be saved and import the time of server memory from storage network, but also be also greatly reduced data and lead
The power consumption entered, releases processor-server, improves performance.
An embodiment is provided again below the present invention to be further elaborated, it is assumed that user A, B, C and D carry out networking trip
Play, such as playing cards, fighting landlord these and uncomplicated game, under conventional situation, server necessarily participates in a series of behaviour of processing
Make, data are imported in server memory from storage network, by the way that data are back to user A, B, C or user D, work after processing
It is as shown in figure 11 to make flow.And apply the present invention it is this share mitigate data center server task method, user A, B, C and
D sends request of data, and the microprocessor stored in network can handle these tasks completely, and workflow is as shown in figure 12, deposits
Microprocessor in storage network handles user data requests, and processed data are back to server, server
By processed data transfer to user, with Figure 11 processes the difference is that processor-server is without to user's request data
Handled, only the request of data of authorized user and data return server, and the data processing operation of user is by storage net
What the microprocessor in network was completed.Further, if user A, B, C and D are authorized users, then at all without server at
Manage device to participate in, store and can directly be carried out data transmission by south bridge between the microprocessor in network and user, as shown in figure 13,
Data are imported in server memory from storage network so as to further avoid, also avoid taking server processor resources,
Processor-server can go to handle other complicated tasks, improve the performance of system.
To sum up illustrate, the present invention proposes this method shared and mitigate data center server task, using storing network
In processor share server inner treater some better simply tasks, such as data transfer, data query etc., so as to subtract
The light task of server, processor-server can go to perform other complicated tasks, so as to substantially reduce power consumption, section
About cost, improves system performance.
Presently preferred embodiments of the present invention is described above.It is to be appreciated that the invention is not limited in above-mentioned
Particular implementation, wherein the equipment and structure be not described in detail to the greatest extent are construed as giving reality with the common mode in this area
Apply；Any those skilled in the art, without departing from the scope of the technical proposal of the invention, all using the disclosure above
Methods and technical content many possible changes and modifications are made to technical solution of the present invention, or be revised as equivalent variations etc.
Embodiment is imitated, this has no effect on the substantive content of the present invention.Therefore, every content without departing from technical solution of the present invention, foundation
The technical spirit of the present invention still falls within the present invention to any simple modifications, equivalents, and modifications made for any of the above embodiments
In the range of technical solution protection.
Claims (2)
1. a kind of share the method for mitigating data center server task, it is characterised in that includes the following steps：
Step S1：User sends data requesting instructions by data center server of the electric terminal equipment into network；
Step S2：The data center server is obtained needed for user after receiving the data requesting instructions from storage network
Data message, and the data message needed for user is fed back into the electric terminal equipment；
Wherein, the data center server is configured with first processor, to carry out data operation processing task；The storage net
Network is configured with second processor, for carrying out maintenance processing to storage network；
When the second processor is in idle condition, the data center server appoints the part data operation processing
Business distribution to the second processor is handled, and user requested data directly is fed back to institute by the second processor
State electric terminal equipment；
The second processor, which carries out attended operation task, to be included：Wear leveling operation, module selection operation, error checking error correction
Operation and/or data read-write operation；
The data-handling capacity of the first processor is better than the data-handling capacity of the second processor；
The second processor is by the microprocessor that configures in the storage device in the storage network；
Storage device in the storage network is disk, the one or more in solid state hard disc, flash memory, and/or data center
The one or more in NAS, DAS and RAID in server.
2. a kind of share the system for mitigating data center server task, it is characterised in that the system comprises：
Electric terminal equipment, data center server and storage network, data of the user by electric terminal equipment into network
Central server sends data requesting instructions；The data center server is received after the data requesting instructions from storage net
The data message needed for user is obtained in network, and the data message needed for user is fed back into the electric terminal equipment；
Wherein, the data center server is configured with first processor, to carry out data operation processing task；The storage net
Second processor is configured with network, the second processor is used to carry out maintenance processing to storage network；
When the second processor is in idle condition, the part data operation is handled task by the data center server
Distribution is handled to the second processor, and by the second processor is directly fed back to user requested data described
User terminal；
The second processor carries out attended operation task to the data center server to be included：Wear leveling operation, module
Selection operation, error checking error-correction operation and/or data read-write operation；
The data-handling capacity of the first processor is better than the data-handling capacity of the second processor；
The second processor is the microprocessor that is configured in the storage device in storage network；
Storage device in the storage network is disk, the one or more in solid state hard disc, flash memory, and/or data center
The one or more in NAS, DAS and RAID in server.
Priority Applications (1)
| Application Number | Priority Date | Filing Date | Title |
|---|---|---|---|
| CN201410394960.0A CN104158875B (en) | 2014-08-12 | 2014-08-12 | It is a kind of to share the method and system for mitigating data center server task |
Applications Claiming Priority (1)
| Application Number | Priority Date | Filing Date | Title |
|---|---|---|---|
| CN201410394960.0A CN104158875B (en) | 2014-08-12 | 2014-08-12 | It is a kind of to share the method and system for mitigating data center server task |
Publications (2)
| Publication Number | Publication Date |
|---|---|
| CN104158875A CN104158875A (en) | 2014-11-19 |
| CN104158875B true CN104158875B (en) | 2018-04-20 |
Family
ID=51884280
Family Applications (1)
| Application Number | Title | Priority Date | Filing Date |
|---|---|---|---|
| CN201410394960.0A Active CN104158875B (en) | 2014-08-12 | 2014-08-12 | It is a kind of to share the method and system for mitigating data center server task |
Country Status (1)
| Country | Link |
|---|---|
| CN (1) | CN104158875B (en) |
Families Citing this family (6)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| CN104571946B (en) * | 2014-11-28 | 2017-06-27 | 中国科学院上海微系统与信息技术研究所 | A kind of storage arrangement and its access method for supporting logic circuit quick search |
| CN104991630B (en) * | 2015-06-15 | 2018-02-27 | 上海新储集成电路有限公司 | The method and server architecture of processor load in a kind of reduction server |
| CN105022698B (en) * | 2015-06-26 | 2020-06-19 | 上海新储集成电路有限公司 | Method for storing special function data by using last-level mixed cache |
| CN105740134B (en) * | 2016-01-29 | 2018-03-20 | 浪潮(北京)电子信息产业有限公司 | A kind of method of testing and device based on file |
| CN107276912B (en) * | 2016-04-07 | 2021-08-27 | 华为技术有限公司 | Memory, message processing method and distributed storage system |
| CN110083480B (en) * | 2019-04-16 | 2023-08-18 | 上海新储集成电路有限公司 | Configurable multifunctional data processing unit |
Citations (6)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| CN1619478A (en) * | 2003-11-21 | 2005-05-25 | 株式会社日立制作所 | Cluster-type storage system and management method thereof |
| CN1673975A (en) * | 2004-03-25 | 2005-09-28 | 株式会社日立制作所 | Storage system |
| CN101038590A (en) * | 2007-04-13 | 2007-09-19 | 武汉大学 | Space data clustered storage system and data searching method |
| CN101105711A (en) * | 2006-07-13 | 2008-01-16 | 国际商业机器公司 | System and method for distributing processing function between main processor and assistant processor |
| CN201011563Y (en) * | 2006-12-01 | 2008-01-23 | 华中科技大学 | Disk array assistant processing controlling card |
| CN102760045A (en) * | 2011-04-29 | 2012-10-31 | 无锡江南计算技术研究所 | Intelligent storage device and data processing method thereof |
-
2014
- 2014-08-12 CN CN201410394960.0A patent/CN104158875B/en active Active
Patent Citations (6)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| CN1619478A (en) * | 2003-11-21 | 2005-05-25 | 株式会社日立制作所 | Cluster-type storage system and management method thereof |
| CN1673975A (en) * | 2004-03-25 | 2005-09-28 | 株式会社日立制作所 | Storage system |
| CN101105711A (en) * | 2006-07-13 | 2008-01-16 | 国际商业机器公司 | System and method for distributing processing function between main processor and assistant processor |
| CN201011563Y (en) * | 2006-12-01 | 2008-01-23 | 华中科技大学 | Disk array assistant processing controlling card |
| CN101038590A (en) * | 2007-04-13 | 2007-09-19 | 武汉大学 | Space data clustered storage system and data searching method |
| CN102760045A (en) * | 2011-04-29 | 2012-10-31 | 无锡江南计算技术研究所 | Intelligent storage device and data processing method thereof |
Also Published As
| Publication number | Publication date |
|---|---|
| CN104158875A (en) | 2014-11-19 |
Similar Documents
| Publication | Publication Date | Title |
|---|---|---|
| CN104158875B (en) | It is a kind of to share the method and system for mitigating data center server task | |
| US11030131B2 (en) | Data processing performance enhancement for neural networks using a virtualized data iterator | |
| US8590050B2 (en) | Security compliant data storage management | |
| Wang et al. | A parallel file system with application-aware data layout policies for massive remote sensing image processing in digital earth | |
| US10318346B1 (en) | Prioritized scheduling of data store access requests | |
| CN105843841A (en) | Small file storing method and system | |
| Zhang et al. | Oceanrt: Real-time analytics over large temporal data | |
| Wang et al. | Bio-inspired cost-effective access to big data | |
| US11494237B2 (en) | Managing workloads of a deep neural network processor | |
| CN105426119A (en) | Storage apparatus and data processing method | |
| CN107895044A (en) | A kind of database data processing method, device and system | |
| Marquez et al. | An Intelligent Approach to Resource Allocation on Heterogeneous Cloud Infrastructures | |
| Cheng et al. | Accelerating scientific workflows with tiered data management system | |
| Imran et al. | Big data analytics tools and platform in big data landscape | |
| Martin et al. | Multi-temperate logical data warehouse design for large-scale healthcare data | |
| CN104636209B (en) | The resource scheduling system and method optimized based on big data and cloud storage system directional properties | |
| Jiyani et al. | NAM: a nearest acquaintance modeling approach for VM allocation using R-Tree | |
| Jin et al. | Optimization of task assignment strategy for map-reduce | |
| CN105224596A (en) | A kind of method of visit data and device | |
| Di Modica et al. | A hierarchical hadoop framework to process geo-distributed big data | |
| CN106033434A (en) | Virtual asset data replica processing method based on data size and popularity | |
| Lu et al. | Collective input/output under memory constraints | |
| US10996945B1 (en) | Splitting programs into distributed parts | |
| SURESH et al. | A New Exploiting Dynamic Resource Allocation for Efficient Parallel Data Processing in the Cloud | |
| WO2020147807A1 (en) | Bucketizing data into buckets for processing by code modules |
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 | ||
| TR01 | Transfer of patent right | ||
| TR01 | Transfer of patent right |
Effective date of registration: 20221101 Address after: 4 / F, building 2, Hunan scientific research achievements transformation center workshop, Longping high tech park, Furong district, Changsha City, Hunan Province 410000 Patentee after: HUNAN QINHAI DIGITAL Co.,Ltd. Address before: 201500 No. 8, building 2, No. 6505, Tingwei Road, Jinshan District, Shanghai Patentee before: SHANGHAI XINCHU INTEGRATED CIRCUIT Co.,Ltd. |
|
| CP03 | Change of name, title or address | ||
| CP03 | Change of name, title or address |
Address after: No. 338, Zhanggongling Road, Longping High tech Park, Furong District, Changsha, Hunan 410000 Patentee after: Hunan Qinhai Digital Co.,Ltd. Address before: 4 / F, building 2, Hunan scientific research achievements transformation center workshop, Longping high tech park, Furong district, Changsha City, Hunan Province 410000 Patentee before: HUNAN QINHAI DIGITAL Co.,Ltd. |