CN102651674A - Data transmission method of reflective memory network - Google Patents
Data transmission method of reflective memory network Download PDFInfo
- Publication number
- CN102651674A CN102651674A CN2012100914403A CN201210091440A CN102651674A CN 102651674 A CN102651674 A CN 102651674A CN 2012100914403 A CN2012100914403 A CN 2012100914403A CN 201210091440 A CN201210091440 A CN 201210091440A CN 102651674 A CN102651674 A CN 102651674A
- Authority
- CN
- China
- Prior art keywords
- data
- node
- storage area
- read
- position offset
- 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.)
- Granted
Links
Images
Landscapes
- Information Retrieval, Db Structures And Fs Structures Therefor (AREA)
Abstract
The invention discloses a data transmission method of a reflective memory network. The method comprises the following steps of: partitioning the onboard memory of a reflective memory card into a global variable area and a node data area; partitioning a data storage area for each node; partitioning a corresponding data position recording area for each node data storage area; when a node writes data into the onboard memory, writing the data into existing data in the data storage area corresponding to the node and updating the data to be position offset according to the data storage position; and when the node reads data, firstly reading the current position offset of a target node, and if the current position offset is different from the position offset of the target node, updating the position offset and reading the data of the target node. In the embodiment of the invention, the node can avoid covering unread data while writing data into the onboard memory, and can judge whether the data read from the target node are repeating data or not, so that data confusion in the data transmission process can be avoided, and further the data transmission efficiency can be improved.
Description
Technical field
The present invention relates to field of data transmission, particularly a kind of reflective memory network data transmission method.
Background technology
In the transfer of data of fiber optic network, the reflective memory net has obtained application more and more widely; The reflective memory net is meant that each node in the network that is communicated with through optical fiber is provided with the reflective memory card; Each reflective memory card includes the twoport internal memory, and each node all can be realized synchronously on the reflective memory card in each node in network at the write operation of the reflective memory card of self.Thereby make each node when the accesses network data, need only the reflective memory card of visit self.Concrete, each reflective memory card includes the corresponding data storage areas of each node in the network, and each data storage areas is used to store the network data with its respective nodes.Each node can be through the data in the reading corresponding data storage area, to realize receiving the data of being sent with the data storage areas node corresponding.
Existing reflective memory net is in data transmission procedure, and the mechanism of reading and writing data of each node is that the plate of operating the reflective memory card alone carries internal memory, controls the access time of each node through SECO.Concrete, after a certain node carries the relevant position of internal memory with the data tablet, other node reading of data; Owing to do not have good handshake mechanism between the node; So can make a certain node after its plate carries the internal memory write data; Can't learn whether other nodes are walked the data read that writes, and other nodes can't learn also whether the data that will read are latest data when reading of data.Like this, when between a plurality of nodes, the transfer of data demand being arranged all, just possible obliterated data, thus cause transfer of data chaotic easily, cause efficiency of transmission to reduce.
Summary of the invention
In view of this; The embodiment of the invention provides a kind of reflective memory network data transmission method; Through being provided with the Data Position recording areas; Thereby can make node identification desire whether reading of data is new data, thereby avoid the data corruption in the data transmission procedure, thereby improve the efficiency of transmission of data.
The embodiment of the invention provides a kind of reflective memory network data transmission method, comprising:
The plate of reflective memory card is carried internal memory be divided into global variable district and node data district;
The data storage area that is used to store data in said node data district for each node division; In said global variable district is that corresponding Data Position recording areas is divided in each node data memory block; Said Data Position recording areas is used for the information data of record data in said data storage area, comprising position offset;
When plate carries internal memory and writes new data, said new data is write existing data back in the data storage area corresponding with said node at node, and the memory location of said new data is updated to position offset; After data were filled with in the data storage area, initial position covered legacy data with the storage new data from the data storage area;
When node read in the reflective memory card destination node data, preset data read the position recording areas in the local internal memory of node, and said data read fetch bit put district is used to write down the destination node data that read the position offset in the Data Position recording areas;
Read the current location side-play amount of Data Position recording areas record in the destination node; The position offset of the said destination node that current location side-play amount and said data read fetch bit put district are write down relatively; When twice offset value is different; Upgrade the position offset in said data read fetch bit put district with the current location side-play amount, and read the data of destination node.
Preferably, in embodiments of the present invention, said Data Position recording areas is greater than said data storage area.
Preferably, in embodiments of the present invention, said node reads and writes data in the internal memory of reflective memory card through driving function.
Preferably, in embodiments of the present invention, the size that the plate of said each node carries internal memory is the same.
Preferably, in embodiments of the present invention, said information data also comprises the original position of said data storage area.
Can find out through technique scheme, in embodiments of the present invention, be divided into global variable district and node data district through plate being carried internal memory; And be that corresponding Data Position recording areas is divided in each node data memory block in the global variable district, come the position offset of record data in said data storage area; Thereby make node when plate carries internal memory and writes data, can avoid covering the data of not read; And; When reading the data of destination node, can judge whether to be repeating data, thereby avoid the confusion of data in the data transmission procedure, and then improve the efficiency of transmission of data.
Description of drawings
Fig. 1 carries the division sketch map of internal memory for plate described in the embodiment of the invention;
Fig. 2 is that the structure in global variable district described in the embodiment of the invention is divided sketch map.
Embodiment
To combine the accompanying drawing in the embodiment of the invention below, the technical scheme in the embodiment of the invention is carried out clear, intactly description, obviously, described embodiment only is the present invention's part embodiment, rather than whole embodiment.Based on the embodiment among the present invention, those of ordinary skills are not making the every other embodiment that is obtained under the creative work prerequisite, all belong to the scope of the present invention's protection.
, plate can avoid covering the data of not read when carrying internal memory and write data in order to make node; And; When reading the data of destination node, can judge whether to be repeating data, thereby avoid the confusion of data in the data transmission procedure, and then improve the efficiency of transmission of data; The embodiment of the invention provides a kind of reflective memory network data transmission method, comprising:
S11, the plate of reflective memory card is carried internal memory be divided into global variable district and node data district;
In embodiments of the present invention, the global variable district is used for storing each node data and carries the information data in the internal memory at plate, comprising position offset.The node data district is used to store the data that each node need be read and write.
S12, be used to store the data storage area of data for each node division in said node data district; In said global variable district is that corresponding Data Position recording areas is divided in each node data memory block; Said Data Position recording areas is used for the information data of record data in said data storage area, comprising position offset;
As shown in Figure 1, owing to carrying internal memory, plate needs each node in the map network, so the node data district need be each node division data storage area; Corresponding, also need divide corresponding Data Position recording areas for the data storage area of each node.
Concrete, when the node in the network is n, can number each node; Then, the node data zoning is divided into n data memory block, each node is corresponding one by one with each data storage area; Preferably, can each data storage area be divided into equal and opposite in direction.
As shown in Figure 2; Memory location for data in the data storage area that writes down each node; Corresponding Data Position recording areas is divided in the data storage area that also need be each node in the global variable district; That is to say, for the global variable district has comprised a plurality of Data Position recording areas, the respectively corresponding node of each Data Position recording areas and a data memory block.In practical application, the information data in the Data Position recording areas specifically can comprise original position field, position offset field and the extended field etc. of corresponding data memory block.The original position field is used for the position offset of the original position of record data memory block.
S13, at node when plate carries internal memory and writes new data, said new data is write in the data storage area corresponding with said node data back, and the memory location of said new data is updated to position offset; After data were filled with in the data storage area, initial position covered legacy data with the storage new data from the data storage area;
Concrete; When the corresponding data storage area of Data Position recording areas does not have data; The original position of this this corresponding data memory block of Data Position recording areas record, concrete can be the position offset of the original position of this corresponding data memory block in node data district original position, promptly; The position offset that can establish node data district original position is 0, and each data storage area is the position offset that benchmark is provided with self with the position offset of node data district original position.
When the data storage area has stored data and deposited new data in once more,, generate new position offset to upgrade this Data Position recording areas record with the length value that newly deposits data in and original position offset addition.Such as, when the Data Position recording areas current location side-play amount of certain node is recorded as 1000, depositing length with its corresponding data storage area data in and be 256 data, the position offset that then upgrades in this Data Position recording areas is 1256.
Because the limited length of data storage area so the situation that the data storage area storage is full of can occur, at this moment, can cover legacy data with the storage new data by initial position from the data storage area; At this moment, the position offset in the Data Position recording areas should deduct the length value of data storage area self for behind the length value and original position offset addition that newly deposit data in.
Through above-mentioned data writing mode; Make node can will newly write data in proper order according to the locus in the data storage area when data storage area in the internal memory carries out write operation and write in the clearance spaces as far as possible in that plate is carried; Thereby the data of having avoided newly not write by sense data cover, so also just avoided because data to lose the transfer of data that is caused chaotic.
S14, when node reads in the reflective memory card destination node data; Preset data reads the position recording areas in the local internal memory of node, and said data read fetch bit put district is used to write down the destination node data that read the position offset in the Data Position recording areas;
When reading in the reflective memory card destination node data at node; Can be clear and definite learn the data after whether the data that read are upgraded; Avoid repeating to read; In the embodiment of the invention, also be provided with data read fetch bit put district, with the position offset of the destination node data that read of record in the Data Position recording areas.Thereby can learn and read at present that in the data storage area position of data in the destination node.
S15, read the current location side-play amount of destination node Data Position recording areas record; The position offset of the destination node that current location side-play amount and data read fetch bit put district are write down relatively; When twice offset value is different; Upgrade the position offset in said data read fetch bit put district with the current location side-play amount, and read the data of destination node.
In data read fetch bit put district, write down the position offset of the Data Position that read, so, will learn whether the desire reading of data is the data after upgrading through this position offset and the current side-play amount of desiring reading of data are compared.Specifically, if the position offset of the destination node that current location side-play amount and data read fetch bit put district are write down is different, then declarative data can be carried out follow-up read operation for the data after upgrading.If the current location side-play amount is the same with the position offset of the destination node that data read fetch bit put district is write down, then the data of declarative data memory block have been read and have not upgraded, so will can not carry out the read operation to these data.
In practical application, the position offset of the destination node that current location side-play amount and data read fetch bit put district are write down is different, comprises two kinds of situation;
The position offset of the destination node that one of which, current location side-play amount are write down greater than data read fetch bit put district;
This feelings show; The memory location of the data of desiring to read does not also arrive the final position of this data storage area; So; The length of these data deducts the position offset of the destination node that is write down in data read fetch bit put district for the current location side-play amount, at this moment, can accomplish data read operation through the data between the position offset that reads the destination node that is write down in current location side-play amount and data read fetch bit put district.
Its two, the position offset of the destination node that the current location side-play amount is write down less than data read fetch bit put district.
Because the limited length of data storage area so the situation that the data storage area storage is full of can occur, at this moment, can cover legacy data with the storage new data by initial position from the data storage area; At this moment, the position offset in the Data Position recording areas should deduct the length value of data storage area self for behind the length value and original position offset addition that newly deposit data in; What the length value of data storage area self was concrete deducts the original position value for the final position value of data storage area.
When above-mentioned situation, the position offset of the destination node that the current location side-play amount of pre-reading data can be write down less than data read fetch bit put district; At this moment; Data are divided into two parts; Between the final position of position offset to this data storage area of the destination node that a part is write down in data read fetch bit put district, another part is between the current location side-play amount of original position to the pre-reading data of this data storage area.
Above-mentioned can learning arranged; In embodiments of the present invention, stored the position offset of reading of data, when reading of data; Through the position offset of reading of data and the side-play amount of desire reading of data compare; Thereby can judge that whether pre-reading data is the data after upgrading, so avoided data repeat read, improved the efficiency of transmission of data.
To the above-mentioned explanation of the disclosed embodiments, make this area professional and technical personnel can realize or use the present invention.Multiple modification to these embodiment will be conspicuous concerning those skilled in the art, and defined General Principle can realize under the situation that does not break away from the spirit or scope of the present invention in other embodiments among this paper.Therefore, the present invention will can not be restricted to these embodiment shown in this paper, but will meet and principle disclosed herein and features of novelty the wideest corresponding to scope.
Claims (5)
1. a reflective memory network data transmission method is characterized in that, comprising:
The plate of reflective memory card is carried internal memory be divided into global variable district and node data district;
The data storage area that is used to store data in said node data district for each node division; In said global variable district is that corresponding Data Position recording areas is divided in each node data memory block; Said Data Position recording areas is used for the information data of record data in said data storage area, comprising position offset;
When plate carries internal memory and writes new data, said new data is write existing data back in the data storage area corresponding with said node at node, and the memory location of said new data is updated to position offset; After data were filled with in the data storage area, initial position covered legacy data with the storage new data from the data storage area;
When node read in the reflective memory card destination node data, preset data read the position recording areas in the local internal memory of node, and said data read fetch bit put district is used to write down the destination node data that read the position offset in the Data Position recording areas;
Read the current location side-play amount of Data Position recording areas record in the destination node; The position offset of the said destination node that current location side-play amount and said data read fetch bit put district are write down relatively; When twice offset value is different; Upgrade the position offset in said data read fetch bit put district with the current location side-play amount, and read the data of destination node.
2. according to the said data transmission method of claim 1, it is characterized in that said Data Position recording areas is greater than said data storage area.
3. according to the said data transmission method of claim 1, it is characterized in that said node reads and writes data in the internal memory of reflective memory card through driving function.
4. according to the said data transmission method of claim 1, it is characterized in that the size that the plate of said each node carries internal memory is the same.
5. according to the said data transmission method of claim 1, it is characterized in that said information data also comprises the original position of said data storage area.
Priority Applications (1)
| Application Number | Priority Date | Filing Date | Title |
|---|---|---|---|
| CN201210091440.3A CN102651674B (en) | 2012-03-30 | 2012-03-30 | Data transmission method of reflective memory network |
Applications Claiming Priority (1)
| Application Number | Priority Date | Filing Date | Title |
|---|---|---|---|
| CN201210091440.3A CN102651674B (en) | 2012-03-30 | 2012-03-30 | Data transmission method of reflective memory network |
Publications (2)
| Publication Number | Publication Date |
|---|---|
| CN102651674A true CN102651674A (en) | 2012-08-29 |
| CN102651674B CN102651674B (en) | 2015-06-24 |
Family
ID=46693573
Family Applications (1)
| Application Number | Title | Priority Date | Filing Date |
|---|---|---|---|
| CN201210091440.3A Active CN102651674B (en) | 2012-03-30 | 2012-03-30 | Data transmission method of reflective memory network |
Country Status (1)
| Country | Link |
|---|---|
| CN (1) | CN102651674B (en) |
Cited By (5)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| CN103678001A (en) * | 2013-11-18 | 2014-03-26 | 中国空间技术研究院 | Multi-node automatic memory allocation method based on reflective memory network |
| CN103761137A (en) * | 2014-01-07 | 2014-04-30 | 中国电子科技集团公司第八研究所 | Optical fiber reflection internal memory card and optical fiber reflection internal memory network |
| CN103870625A (en) * | 2013-11-19 | 2014-06-18 | 北京航天长征飞行器研究所 | Real-time interaction method of data of optical-fiber reflection memory network |
| RU2568785C2 (en) * | 2014-01-24 | 2015-11-20 | Федеральное государственное бюджетное учреждение науки Институт проблем управления им. В.А. Трапезникова Российской академии наук | Transmission of signals by reflective signals between reflective memory devices |
| CN106066830A (en) * | 2016-05-31 | 2016-11-02 | 中国航空工业集团公司西安飞机设计研究所 | A kind of EMS memory management process |
Citations (2)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| CN1595523A (en) * | 2003-09-12 | 2005-03-16 | 联想(北京)有限公司 | A disk storage method |
| CN101493784A (en) * | 2009-02-24 | 2009-07-29 | 中国运载火箭技术研究院 | Reflecting internal memory net dynamic internal memory management method based on distribution simulation |
-
2012
- 2012-03-30 CN CN201210091440.3A patent/CN102651674B/en active Active
Patent Citations (2)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| CN1595523A (en) * | 2003-09-12 | 2005-03-16 | 联想(北京)有限公司 | A disk storage method |
| CN101493784A (en) * | 2009-02-24 | 2009-07-29 | 中国运载火箭技术研究院 | Reflecting internal memory net dynamic internal memory management method based on distribution simulation |
Cited By (7)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| CN103678001A (en) * | 2013-11-18 | 2014-03-26 | 中国空间技术研究院 | Multi-node automatic memory allocation method based on reflective memory network |
| CN103870625A (en) * | 2013-11-19 | 2014-06-18 | 北京航天长征飞行器研究所 | Real-time interaction method of data of optical-fiber reflection memory network |
| CN103870625B (en) * | 2013-11-19 | 2017-05-31 | 北京航天长征飞行器研究所 | Fiber reflection internal memory network data real-time interaction method |
| CN103761137A (en) * | 2014-01-07 | 2014-04-30 | 中国电子科技集团公司第八研究所 | Optical fiber reflection internal memory card and optical fiber reflection internal memory network |
| RU2568785C2 (en) * | 2014-01-24 | 2015-11-20 | Федеральное государственное бюджетное учреждение науки Институт проблем управления им. В.А. Трапезникова Российской академии наук | Transmission of signals by reflective signals between reflective memory devices |
| CN106066830A (en) * | 2016-05-31 | 2016-11-02 | 中国航空工业集团公司西安飞机设计研究所 | A kind of EMS memory management process |
| CN106066830B (en) * | 2016-05-31 | 2018-11-13 | 中国航空工业集团公司西安飞机设计研究所 | A kind of EMS memory management process |
Also Published As
| Publication number | Publication date |
|---|---|
| CN102651674B (en) | 2015-06-24 |
Similar Documents
| Publication | Publication Date | Title |
|---|---|---|
| CN106201355B (en) | Data processing method and device and storage system | |
| CN102508784B (en) | Data storage method of flash memory card in video monitoring equipment, and system thereof | |
| CN112015517B (en) | Block chain node dynamic migration method and system based on k8s cluster | |
| CN101627372B (en) | Selectively utilizing a plurality of disparate solid state storage locations | |
| CN101582092B (en) | Method and device for realizing the store of date in memory | |
| CN102651674A (en) | Data transmission method of reflective memory network | |
| CN102541983B (en) | Method for synchronously caching by multiple clients in distributed file system | |
| CN103677884B (en) | Flash subarea list file is generated and its data updating method, device | |
| CN105938457B (en) | Filter method, device and the data reading system of data | |
| CN103514249B (en) | A kind of automatic data reduction and system and storage device | |
| CN104298681B (en) | A kind of date storage method and device | |
| CN105653396B (en) | Standby system and its backup method | |
| CN102945212A (en) | Pooled partition layout and representation | |
| CN101799788B (en) | Level-to-level administration method and system of storage resources | |
| CN110032521A (en) | For enhancing flash translation layer (FTL) mapping flexibility to obtain performance and service life improved method and system | |
| CN102779096A (en) | Page, block and face-based three-dimensional flash memory address mapping method | |
| CN102779095A (en) | Flash memory device, memory control device, memory control method, and storage system | |
| CN107992430A (en) | Management method, device and the computer-readable recording medium of flash chip | |
| CN101510332B (en) | Method and apparatus for managing memory space of smart card | |
| CN101369245A (en) | System and method for implementing a memory defect map | |
| CN107239526A (en) | File system implementation method, scrap cleaning method, operating position localization method | |
| CN106155915A (en) | The processing method and processing device of data storage | |
| CN102411634A (en) | Data storage method for improving instantaneity of embedded type database | |
| JP2010515128A (en) | Method for managing data in non-volatile memory | |
| CN102831204A (en) | File packaging format with version control ability |
Legal Events
| Date | Code | Title | Description |
|---|---|---|---|
| C06 | Publication | ||
| PB01 | Publication | ||
| C10 | Entry into substantive examination | ||
| SE01 | Entry into force of request for substantive examination | ||
| C14 | Grant of patent or utility model | ||
| GR01 | Patent grant | ||
| CP03 | Change of name, title or address | ||
| CP03 | Change of name, title or address |
Address after: 4 / F, building 1, No.14 Jiuxianqiao Road, Chaoyang District, Beijing 100020 Patentee after: Beijing Jingwei Hengrun Technology Co.,Ltd. Address before: 100101 Beijing Chaoyang District City Anxiang Beili 11 building B block 8 layer Patentee before: Beijing Jingwei HiRain Technologies Co.,Ltd. |
|
| TR01 | Transfer of patent right | ||
| TR01 | Transfer of patent right |
Effective date of registration: 20230614 Address after: 100192 5th floor, Zhizhen building, 7 Zhichun Road, Haidian District, Beijing Patentee after: BEIJING RUNKE GENERAL TECHNOLOGY Co.,Ltd. Address before: 4 / F, building 1, No.14 Jiuxianqiao Road, Chaoyang District, Beijing 100020 Patentee before: Beijing Jingwei Hengrun Technology Co.,Ltd. |