CN101382953A - Interface system for accessing file system in user space and file reading and writing method - Google Patents
Interface system for accessing file system in user space and file reading and writing method Download PDFInfo
- Publication number
- CN101382953A CN101382953A CN 200810216190 CN200810216190A CN101382953A CN 101382953 A CN101382953 A CN 101382953A CN 200810216190 CN200810216190 CN 200810216190 CN 200810216190 A CN200810216190 A CN 200810216190A CN 101382953 A CN101382953 A CN 101382953A
- Authority
- CN
- China
- Prior art keywords
- shared drive
- module
- related data
- metadata cache
- drive module
- 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
Abstract
The invention discloses an interface system which can access a file system in a user space and a method for file reading and writing. The interface system comprises a dynamic link library which is used for providing an access interface of the file system and embedded in an application process address space to operate, and also comprises a shared memory module and an agent process module, wherein, the dynamic link library is connected with the shared memory module through communication; the shared memory module is used for exchanging and sharing relevant data between the processes and storing part of relevant data; the application process is linked with the shared memory module through the dynamic link library and sends parameters which read relevant data to the shared memory module; the shared memory module determines the read relevant data according to the parameters; and if the relevant data exists in the shared memory module, the shared memory module then sends the relevant data to a corresponding buffer area of the application process. Additionally, the invention adopts a sharing mechanism to improve the system processing efficiency.
Description
Technical field
The present invention relates to a kind of in UNIX or (SuSE) Linux OS data storage and access technique, relate in particular to a kind of interface system and file reading and writing method in user's space access file system.
Background technology
At present, a large amount of media data storage and requirements for access are usually arranged in the service operations such as internet, telecommunications, these demands generally require large buffer memory, high reliability and low cost, and general file system generally can't meet the demands.Generally speaking, need exploitation to satisfy the file system of particular demands, and for upper-layer service, the interface of its access file system should keep stable and very strong compatibility.Solution commonly used at present has two kinds, first kind is to utilize the operating system nucleus characteristic, a resident module is as the agency in kernel, this module is transmitted to the request of access of application program the treatment progress of user's space, treatment progress carries out actual data access and operation, and last result still returns to application program by kernel module; Second workaround provides one group of off-gauge interface, provides by dynamic link library, and application program afterwards can the access file system through code revision and recompility link.
Two kinds of methods of the prior art all have its relative merits, for the method for first kind of solution for kernel agent module, advantage is that application program does not need to revise code, it is addressable this file system, and a plurality of consumer process can be visited simultaneously, but because actual file system data treatment progress also is to be positioned at user's space, be equivalent to the extra increase of the visit of file system a link, system handles efficient is descended greatly; For second method, the visit of file system does not need through not influence on the kernel efficient, but because the address space between the application process is to isolate mutually, if a plurality of application processes need the same file in the while access file system, the data of each file all have a copy in each application process in these processes so, so this method is the significant wastage to system resource.This shows that prior art awaits further developing.
Summary of the invention
The present invention provides a kind of interface system and file reading and writing method in user's space access file system for solving defective of the prior art, adopts shared mechanism to improve system handles efficient, improves throughput of system, makes things convenient for the transplanting of application process.
For solving the problems of the technologies described above, the present invention program comprises:
A kind of interface system in user's space access file system, comprise dynamic link library, described dynamic link library is used to provide the access interface of file system and is embedded into operation in the application process address space, wherein, described interface system also comprises shared drive module and agent process module, described dynamic link library and described shared drive module communication link together, and described shared drive is used for exchange and shared related data and storage area related data between process.
Described interface system, wherein, described shared drive module also comprises message queue and at least one metadata cache piece, and described message queue and described metadata cache piece communicate to connect, and described message queue is used to connect communicating by letter between described application process and the described agent process module; Described metadata cache piece is used for exchanges data and the storage area related data between described application process and the described agent process module, and described metadata cache piece has coding.
Described interface system, wherein, described shared drive module comprises a plurality of metadata cache pieces, same metadata cache piece can be used simultaneously by a plurality of application processes.
Described interface system, wherein, described interface system also comprises the agent process module, and described agent process module is connected with described shared drive module communication, and described agent process module is used to handle the request of described shared drive module.
Described interface system, wherein, described interface system also comprises data memory module, and described data memory module is connected with described agent process module communication, and described data memory module is used to store related data.
The file of described interface system is read method, may further comprise the steps:
A1, application process link described shared drive module by described dynamic link library and read the parameter of related data to described shared drive module transmission;
B1, described shared drive module are determined the related data that reads according to described parameter;
C1, if related data be present in the described shared drive module, then described shared drive module sends to related data in the application process corresponding cache region.
Described file is read method, and wherein, described step B1 also comprises: described shared drive module is determined the metadata cache block encoding at related data place according to described parameter.
Described file is read method, and wherein, described step C1 also comprises agent process, and it may further comprise the steps:
C11, if related data is not present in the described shared drive module, then described shared drive distributes the metadata cache piece of a free time and asks described agent process module that related data is copied in the idle metadata cache piece;
C12, described agent process module copy the related data in the data memory module in the idle metadata cache piece to according to described request;
C13, described shared drive module send to related data in the application process corresponding cache region.
The file write method of described interface system may further comprise the steps:
A2, application process send the parameter that need write related data by described dynamic link library link to described shared drive module;
B2, described shared drive module are according to the definite metadata cache piece that need write of described parameter;
C2, if the metadata cache piece that need write is present in described shared drive module, then described application process copies related data to need write metadata cache piece respective offsets address, described shared drive module is put dirty mark with it.
Described file is read method, and wherein, described step C2 also comprises agent process, and it may further comprise the steps:
C21, if the metadata cache piece that need write is not present in described shared drive module, the related data that then described shared drive distributes the metadata cache piece of a free time and asks described agent process module that need are write copies in the idle metadata cache piece;
C22, if need write related data and write for appending, then described agent process module is with the metadata cache piece zero clearing of free time; If need write related data is write-back, then described agent process module is write related data with described need and is copied in the idle metadata cache piece;
C23, application process copy related data the respective offsets address of the metadata cache piece that need write to, and described shared drive module is put dirty mark with it;
C24, described agent process module will be put the metadata cache piece write-back of dirty mark and be removed and put dirty mark.
The invention provides a kind of interface system and file reading and writing method in user's space access file system, adopt shared mechanism and increase the shared drive module, improved system handles efficient, improved throughput of system, made things convenient for the transplanting of application process, improved usage factor of system resource.
Description of drawings
Fig. 1 is the structural representation of interface system among the present invention;
Fig. 2 is a file handle management method schematic flow sheet among the present invention;
Fig. 3 is the schematic flow sheet that file is read method among the present invention;
Fig. 4 is the schematic flow sheet of file write method among the present invention.
Embodiment
Below with reference to accompanying drawing, comparatively detailed explanation is carried out in each preferred embodiment of the present invention.
A kind of interface system in user's space access file system provided by the invention as shown in Figure 1, comprises dynamic link library 101, shared drive module 102, agent process module 103 and data memory module 104; Described dynamic link library 101, described shared drive module 102, described agent process module 103 and described data memory module 104 sequenced communications connect.Described dynamic link library 101 is used to provide the access interface of file system and is embedded into operation in the application process address space, its name is very similar with the standard file system interface, only need to use macro substitution and recompilate link and can normally use, in each interface function inside, all realize the purpose of access file system by visit to shared drive.Described shared drive module 102 is utilized the inter-process communication mechanisms of Unix/Linux operating system, a physical memory can be mapped to the address space of a plurality of processes, be used for exchange and shared related data between process, for reaching efficient and rational and correctly utilizing the purpose of shared drive, also must use thereon a series of synchronously and the mechanism of mutual exclusion mechanism and pass-along message, and storage area related data.Described agent process module 103 is used to handle the request of described shared drive module 102, it obtains the request of application process by shared drive module 102, and make corresponding processing, such as the metadata of obtaining file, file data is read in described shared drive module 102 or the data in the described shared drive module are write file, result after it is handled allows and notifies application process by described shared drive module 102, the all conductively-closeds of these details, but this process application processes is transparent.Described data memory module 104 is used to store related data.
Wherein, the semaphore PV operation of lightweight is used in the synchronous and mutual exclusion of shared drive, and this need be guaranteed by operating system.Except semaphore, shared drive is divided into two and comprises message queue 105 and metadata cache piece 106, described message queue 105 also comprises its control corresponding structure separately with metadata cache piece 106, and these control structures all use semaphore to realize that mutual exclusion is with synchronously.Message queue 105 is used for communicating by letter between application process and the agent process, metadata cache piece 106 is divided with fixed size, such as PAGE_SIZE, representative value is 128KB, can be nearly thousands of, application process and described agent process module are by these metadata cache piece 106 swap datas, and same metadata cache piece 106 can be used by a plurality of application processes simultaneously according to certain rule, each metadata cache piece 106 corresponding coding.
Wherein, the storage of described agent process module and not responsible data; The present invention does not relate to the storage means of data and agent process is visited these data from data storage method.This shows that the present invention has realized improving system handles efficient and the effect that improves throughput of system by increase and scientific allocation corresponding module.
Above-mentioned interface system can realize that file handle management method, file read method and file write method.Described file handle management method, as shown in Figure 2, it may further comprise the steps:
A1, each application process are safeguarded one group of privately owned file handle, the privately owned file handle of other application process of application process inaccessible by described dynamic link library 101;
A2, described agent process module 103 are safeguarded the shared file handle structure;
The privately owned file handle of a3, each application process, a shared file handle in all corresponding the described agent process module 103, shared file handle can corresponding a plurality of application processes privately owned file handle, described agent process module 103 is safeguarded this corresponding relation;
A4, application process use its privately owned file handle that file is conducted interviews, the agent process of described agent process module 103 uses the shared file handle to conduct interviews, and the privately owned file handle that points to identical shared file handle means can share described metadata cache piece 106.
Described file is read method and be may further comprise the steps:
B1, application process are called and are read interface function, import the desired parameters that reads related data by dynamic link module 101 into to described shared drive module 102;
B2, described shared drive module 102 determines to read the coding of the metadata cache piece 106 of related data according to going into ginseng, and searches this metadata cache piece 106;
B3, if described shared drive module 102 has found this metadata cache piece 106, then related data is sent in the application process corresponding cache region, and returns respective function according to going into ginseng;
B4, if described shared drive module 102 do not find this metadata cache piece 106, then described shared drive module 102 is distributed the metadata cache piece of a free time, and asks described agent process module 103 that related data is copied in this idle metadata cache piece 106;
B5, described agent process module 103 read the related datas in the data memory module 104 and copy in this metadata cache pieces 106, and beam back to the requestor and to reply;
B6, described shared drive module send to related data in the application process corresponding cache region, and return respective function.
Described file write method may further comprise the steps:
C1, application process are called and are write interface function, import the desired parameters that need write related data by dynamic link module 101 into to described shared drive module 102;
C2, described shared drive module 102 bases are gone into the definite coding that need write the metadata cache piece 106 of related data of ginseng, and are searched this metadata cache piece 106;
C3, if described shared drive module 102 found this metadata cache piece 106, then from the buffer area of application process, need are write related data and copy this metadata cache piece 106 respective offsets addresses to according to going into ginseng, described shared drive module 102 is put dirty sign with it, and returns respective function;
C4, if described shared drive module 102 do not find this metadata cache piece 106, then described shared drive module 102 is distributed the metadata cache piece of a free time, and asks described agent process module 103 that related data is copied in this idle metadata cache piece 106;
C5, if need write related data and write for appending, then described agent process module 102 is with metadata cache piece 106 zero clearings of free time; If need write related data is write-back, then described agent process module 102 is write related data with described need and is copied in the idle metadata cache piece 106;
C6, application process copy related data the respective offsets address of the metadata cache piece 106 that need write to, and described shared drive module 102 is put dirty mark with it;
C7, described agent process module 102 active scan also will be put the metadata cache piece write-back of dirty mark and be removed and put dirty mark.
Wherein, read in document method and the described written document method described, search among step b4, the c4 in the strategy of idle metadata cache piece 106, if all metadata cache pieces 106 are all busy, certain does not put the metadata cache piece 106 of dirty sign then will to use minimum strategy to swap out recently; If all metadata cache pieces all are equipped with dirty sign, then find a data cache blocks 106 by the minimum strategy of nearest use, the described agent process module 103 of 102 message request of described shared drive module is forced this metadata cache piece 106 of write-back, and 106 of this metadata cache pieces can use after write-back finished.The reading or details that write-back is not concerned about by the present invention of file data among step b5, c5, the c7, in the realization, file data both can be positioned at this locality, and also may be positioned at far-end need both can store portion by access to netwoks, also can have many parts of redundant copy.
For further setting forth method of the present invention, now reading a file with application process is that example describes, and as shown in Figure 3, may further comprise the steps:
Step 301: application process is called the READ function and is promptly read interface function, imports parameter by described dynamic link libraries 101 into to described shared drive module 102 and comprises privately owned file handle, data buffer address, document misregistration position and read byte number etc.;
Step 302: described shared drive module 102 calculates the coding of the metadata cache piece 106 that needs read according to document misregistration position and the byte number of reading;
Step 303: described shared drive module 102 corresponds to the shared file handle of its preservation according to privately owned file handle, and with the coding of metadata cache piece 106 as key assignments, search this metadata cache piece 106 and whether exist, if yes, then enter step 304; If, then do not enter step 305;
Step 304: described shared drive module 102 sends to the related data in the metadata cache piece 106 in the corresponding buffer zone of application process, and the byte number of copy is returned as rreturn value;
Step 305: described shared drive module 102 is distributed the metadata cache piece 106 of a free time;
Step 306: described shared drive module 102 copies relevant data block in the idle data-block cache 106 to described agent process module 103 requests;
Step 307: an agent process in the described agent process module 103 is read related data, and copies in the idle data-block cache in 106;
Step 308: described agent process module 103 is beamed back successful respond to application process;
Step 309: described shared drive module 102 sends to the related data in this metadata cache piece 106 of free time in the corresponding buffer zone of application process, and the byte number of copy is returned as rreturn value.By above-mentioned flow process, improved usage factor of system resource.
As shown in Figure 4, be to adopt application process of the present invention to write the flow process of a file, it may further comprise the steps:
Step 401: application process is called the WRITE function and is promptly write interface function, imports parameter by described dynamic link libraries 101 into to described shared drive module 102 and comprises privately owned file handle, data buffer address, document misregistration position and write byte number etc.;
Step 402: described shared drive module 102 according to the document misregistration position with write the coding that byte number calculates the metadata cache piece 106 that needs write;
Step 403: described shared drive module 102 corresponds to the shared file handle of its preservation according to privately owned file handle, and with the coding of metadata cache piece 106 as key assignments, search this metadata cache piece 106 and whether exist, if yes, then enter step 404; If, then do not enter step 405;
Step 404: described shared drive module 102 is write related data with need and is copied position corresponding this data-block cache 106 to from the corresponding buffer zone of application process, described shared drive module 102 is put this metadata cache block cache 106 dirty signs, and the byte number of copy is returned as rreturn value;
Step 405: described shared drive module 102 is distributed the metadata cache piece 106 of a free time;
Step 406: described shared drive module 102 copies relevant data block in the idle data-block cache 106 to described agent process module 103 requests;
Step 407: if need write related data writes for appending, then described agent process module 102 is with these metadata cache piece 106 zero clearings of free time; If need write related data is write-back, then described agent process module 102 copies related data in this idle metadata cache piece 106 to;
Step 408: described agent process module 103 is beamed back successful respond to application process;
Step 409: application process is write related data with need and is copied position corresponding this metadata cache piece 106 to from corresponding buffer zone, and described shared drive module 102 is put the dirty sign of this metadata cache piece, and the byte number of copy is returned as rreturn value;
Step 410: described agent process module 103 active scan are equipped with the metadata cache piece of dirty sign, and will fall dirty sign behind its write-back clearly.Logical above-mentioned explanation adopts the inventive method to greatly facilitate the transplanting of application process as can be known, has improved system handles efficient.
In sum, a kind of interface system and file reading and writing method provided by the invention in user's space access file system, adopt shared mechanism and increase the shared drive module, and provide the use habit consistent with file system interface, made things convenient for the transplanting of application process, improve system handles efficient, improved throughput of system, made things convenient for the transplanting of application process; Make all parts of system all run on user's space, need not enter operating system nucleus, under the situation of big handling capacity, still have very high efficient, thereby improved the utilization factor of system; And by shared drive mechanism, a plurality of application processes can shared data, has reduced unnecessary spending, has improved the efficient of system handles.
Should be understood that; above-mentioned description at preferred embodiment is comparatively detailed; can not therefore think restriction to scope of patent protection of the present invention; those of ordinary skill in the art is under enlightenment of the present invention; do not breaking away under the scope situation that claim of the present invention protects; can also make various deformation such as replacement, simple combination, these all fall within protection scope of the present invention, and the scope of asking for protection of the present invention should be as the criterion with claims.
Claims (10)
1, a kind of interface system in user's space access file system, comprise dynamic link library, described dynamic link library is used to provide the access interface of file system and is embedded into operation in the application process address space, it is characterized in that, described interface system also comprises shared drive module and agent process module, described dynamic link library and described shared drive module communication link together, and described shared drive is used for exchange and shared related data and storage area related data between process.
2, interface system according to claim 1, it is characterized in that, described shared drive module also comprises message queue and at least one metadata cache piece, described message queue and described metadata cache piece communicate to connect, and described message queue is used to connect communicating by letter between described application process and the described agent process module; Described metadata cache piece is used for exchanges data and the storage area related data between described application process and the described agent process module, and described metadata cache piece has coding.
3, interface system according to claim 2 is characterized in that, described shared drive module comprises a plurality of metadata cache pieces, and same metadata cache piece can be used simultaneously by a plurality of application processes.
4, interface system according to claim 2, it is characterized in that, described interface system also comprises the agent process module, and described agent process module is connected with described shared drive module communication, and described agent process module is used to handle the request of described shared drive module.
5, interface system according to claim 4 is characterized in that, described interface system also comprises data memory module, and described data memory module is connected with described agent process module communication, and described data memory module is used to store related data.
6, a kind of realization read method according to the file of the described interface system of claim 1, may further comprise the steps:
A1, application process link described shared drive module by described dynamic link library and read the parameter of related data to described shared drive module transmission;
B1, described shared drive module are determined the related data that reads according to described parameter;
C1, if related data be present in the described shared drive module, then described shared drive module sends to related data in the application process corresponding cache region.
7, file according to claim 6 is read method, it is characterized in that, described step B1 also comprises: described shared drive module is determined the metadata cache block encoding at related data place according to described parameter.
8, file according to claim 7 is read method, it is characterized in that, described step C1 also comprises agent process, and it may further comprise the steps:
C11, if related data is not present in the described shared drive module, then described shared drive distributes the metadata cache piece of a free time and asks described agent process module that related data is copied in the idle metadata cache piece;
C12, described agent process module copy the related data in the data memory module in the idle metadata cache piece to according to described request;
C13, described shared drive module send to related data in the application process corresponding cache region.
9, a kind of file write method of realizing according to the described interface system of claim 2 may further comprise the steps:
A2, application process send the parameter that need write related data by described dynamic link library link to described shared drive module;
B2, described shared drive module are according to the definite metadata cache piece that need write of described parameter;
C2, if the metadata cache piece that need write is present in described shared drive module, then described application process copies related data to need write metadata cache piece respective offsets address, described shared drive module is put dirty mark with it.
10, file write method according to claim 9 is characterized in that, described step C2 also comprises agent process, and it may further comprise the steps:
C21, if the metadata cache piece that need write is not present in described shared drive module, the related data that then described shared drive distributes the metadata cache piece of a free time and asks described agent process module that need are write copies in the idle metadata cache piece;
C22, if need write related data and write for appending, then described agent process module is with the metadata cache piece zero clearing of free time; If need write related data is write-back, then described agent process module is write related data with described need and is copied in the idle metadata cache piece;
C23, application process copy related data the respective offsets address of the metadata cache piece that need write to, and described shared drive module is put dirty mark with it;
C24, described agent process module will be put the metadata cache piece write-back of dirty mark and be removed and put dirty mark.
Priority Applications (1)
| Application Number | Priority Date | Filing Date | Title |
|---|---|---|---|
| CN 200810216190 CN101382953B (en) | 2008-09-19 | 2008-09-19 | Interface system for accessing file system in user space and file reading and writing method |
Applications Claiming Priority (1)
| Application Number | Priority Date | Filing Date | Title |
|---|---|---|---|
| CN 200810216190 CN101382953B (en) | 2008-09-19 | 2008-09-19 | Interface system for accessing file system in user space and file reading and writing method |
Publications (2)
| Publication Number | Publication Date |
|---|---|
| CN101382953A true CN101382953A (en) | 2009-03-11 |
| CN101382953B CN101382953B (en) | 2013-03-20 |
Family
ID=40462791
Family Applications (1)
| Application Number | Title | Priority Date | Filing Date |
|---|---|---|---|
| CN 200810216190 Expired - Fee Related CN101382953B (en) | 2008-09-19 | 2008-09-19 | Interface system for accessing file system in user space and file reading and writing method |
Country Status (1)
| Country | Link |
|---|---|
| CN (1) | CN101382953B (en) |
Cited By (27)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| CN102147751A (en) * | 2011-04-26 | 2011-08-10 | 北京新媒传信科技有限公司 | Communication method among multiple processes |
| CN102298619A (en) * | 2011-08-10 | 2011-12-28 | 中兴通讯股份有限公司 | Method for fast reading hole document by upper layer document system and system |
| CN102360345A (en) * | 2011-10-11 | 2012-02-22 | 浪潮电子信息产业股份有限公司 | Method for realizing multiple copies of configurable shared library |
| CN102547146A (en) * | 2010-12-29 | 2012-07-04 | 新奥特（北京）视频技术有限公司 | System and method for interacting subtitle data |
| CN102662773A (en) * | 2012-03-13 | 2012-09-12 | 中冶南方工程技术有限公司 | Structured document communication system between multiple processes |
| CN102682129A (en) * | 2012-05-17 | 2012-09-19 | 北京像素软件科技股份有限公司 | Data reading method based on virtual file system |
| CN103176852A (en) * | 2011-12-22 | 2013-06-26 | 腾讯科技（深圳）有限公司 | Method and device for inter-progress communication |
| CN103617039A (en) * | 2013-11-28 | 2014-03-05 | 北京华胜天成科技股份有限公司 | Method and device for accessing user space file system |
| CN103984550A (en) * | 2014-05-15 | 2014-08-13 | 浪潮电子信息产业股份有限公司 | Serial number elongation algorithm of distributed modular system |
| CN104021355A (en) * | 2014-06-20 | 2014-09-03 | 浪潮电子信息产业股份有限公司 | Safety inspection method for simultaneously operating same file through multiple processes |
| CN104239511A (en) * | 2014-09-15 | 2014-12-24 | 西安交通大学 | File system in user space implementation method oriented to MongoDB |
| CN104298932A (en) * | 2014-10-27 | 2015-01-21 | 中国建设银行股份有限公司 | Method and device for calling SO file |
| CN104391662A (en) * | 2014-12-12 | 2015-03-04 | 北京奇虎科技有限公司 | Data reading and writing method and device |
| CN104714792A (en) * | 2013-12-17 | 2015-06-17 | 腾讯科技（深圳）有限公司 | Multi-process shared data processing method and device |
| CN105608159A (en) * | 2015-12-18 | 2016-05-25 | 北京奇虎科技有限公司 | Data caching method and device |
| CN105717516A (en) * | 2016-03-30 | 2016-06-29 | 沈阳泰科易科技有限公司 | Global navigation satellite system (GNSS) data synchronization method and method |
| CN105824763A (en) * | 2015-11-16 | 2016-08-03 | 广东亿迅科技有限公司 | Caching service realization method |
| CN105843693A (en) * | 2016-03-22 | 2016-08-10 | 同济大学 | High-speed maglev transportation simulation oriented memory sharing method |
| CN106406857A (en) * | 2016-08-30 | 2017-02-15 | 惠州学院 | Memory reusing method and device for dynamic link library |
| CN106708631A (en) * | 2016-11-30 | 2017-05-24 | 福建省天奕网络科技有限公司 | Shared memory property modification method and system |
| CN106897440A (en) * | 2017-02-28 | 2017-06-27 | 郑州云海信息技术有限公司 | A kind of distributed file system file read-write processing method |
| CN107944230A (en) * | 2017-11-20 | 2018-04-20 | 山东超越数控电子股份有限公司 | A kind of universal method of software activation verification |
| CN108121594A (en) * | 2016-11-29 | 2018-06-05 | 阿里巴巴集团控股有限公司 | A kind of process management method and device |
| US10061711B2 (en) | 2014-09-01 | 2018-08-28 | Huawei Technologies Co., Ltd. | File access method and apparatus, and storage system |
| US10157143B2 (en) | 2014-09-01 | 2018-12-18 | Huawei Technologies Co., Ltd. | File access method and apparatus, and storage system |
| CN109086136A (en) * | 2018-07-26 | 2018-12-25 | 广东浪潮大数据研究有限公司 | A kind of request processing method and relevant apparatus of Samba software |
| WO2020015670A1 (en) * | 2018-07-20 | 2020-01-23 | 中兴通讯股份有限公司 | File sending method, file receiving method and file transceiving apparatus |
Family Cites Families (1)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| CN100353325C (en) * | 2004-08-23 | 2007-12-05 | 华为技术有限公司 | Method for realing sharing internal stored data base and internal stored data base system |
-
2008
- 2008-09-19 CN CN 200810216190 patent/CN101382953B/en not_active Expired - Fee Related
Cited By (44)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| CN102547146A (en) * | 2010-12-29 | 2012-07-04 | 新奥特（北京）视频技术有限公司 | System and method for interacting subtitle data |
| CN102147751A (en) * | 2011-04-26 | 2011-08-10 | 北京新媒传信科技有限公司 | Communication method among multiple processes |
| CN102147751B (en) * | 2011-04-26 | 2012-11-21 | 北京新媒传信科技有限公司 | Communication method among multiple processes |
| CN102298619A (en) * | 2011-08-10 | 2011-12-28 | 中兴通讯股份有限公司 | Method for fast reading hole document by upper layer document system and system |
| CN102360345A (en) * | 2011-10-11 | 2012-02-22 | 浪潮电子信息产业股份有限公司 | Method for realizing multiple copies of configurable shared library |
| CN103176852A (en) * | 2011-12-22 | 2013-06-26 | 腾讯科技（深圳）有限公司 | Method and device for inter-progress communication |
| CN103176852B (en) * | 2011-12-22 | 2016-05-25 | 腾讯科技（深圳）有限公司 | A kind of method for interprocess communication and device |
| CN102662773A (en) * | 2012-03-13 | 2012-09-12 | 中冶南方工程技术有限公司 | Structured document communication system between multiple processes |
| CN102682129A (en) * | 2012-05-17 | 2012-09-19 | 北京像素软件科技股份有限公司 | Data reading method based on virtual file system |
| CN103617039A (en) * | 2013-11-28 | 2014-03-05 | 北京华胜天成科技股份有限公司 | Method and device for accessing user space file system |
| CN103617039B (en) * | 2013-11-28 | 2017-02-01 | 北京华胜天成科技股份有限公司 | Method and device for accessing user space file system |
| CN104714792B (en) * | 2013-12-17 | 2019-02-26 | 腾讯科技（深圳）有限公司 | Multi-process shared data treating method and apparatus |
| CN104714792A (en) * | 2013-12-17 | 2015-06-17 | 腾讯科技（深圳）有限公司 | Multi-process shared data processing method and device |
| CN103984550A (en) * | 2014-05-15 | 2014-08-13 | 浪潮电子信息产业股份有限公司 | Serial number elongation algorithm of distributed modular system |
| CN103984550B (en) * | 2014-05-15 | 2018-03-27 | 浪潮电子信息产业股份有限公司 | A kind of method of elongated sequence number in distributed modular system |
| CN104021355A (en) * | 2014-06-20 | 2014-09-03 | 浪潮电子信息产业股份有限公司 | Safety inspection method for simultaneously operating same file through multiple processes |
| CN104021355B (en) * | 2014-06-20 | 2017-03-29 | 浪潮电子信息产业股份有限公司 | A kind of multi-process operates the security method menu of same file simultaneously |
| US10157143B2 (en) | 2014-09-01 | 2018-12-18 | Huawei Technologies Co., Ltd. | File access method and apparatus, and storage system |
| US10061711B2 (en) | 2014-09-01 | 2018-08-28 | Huawei Technologies Co., Ltd. | File access method and apparatus, and storage system |
| CN104239511A (en) * | 2014-09-15 | 2014-12-24 | 西安交通大学 | File system in user space implementation method oriented to MongoDB |
| CN104239511B (en) * | 2014-09-15 | 2016-03-30 | 西安交通大学 | A kind of user's space file system implementation method towards MongoDB |
| CN104298932A (en) * | 2014-10-27 | 2015-01-21 | 中国建设银行股份有限公司 | Method and device for calling SO file |
| CN104298932B (en) * | 2014-10-27 | 2017-12-12 | 中国建设银行股份有限公司 | A kind of call method and device of SO files |
| CN104391662A (en) * | 2014-12-12 | 2015-03-04 | 北京奇虎科技有限公司 | Data reading and writing method and device |
| CN104391662B (en) * | 2014-12-12 | 2018-02-09 | 北京奇虎科技有限公司 | A kind of data read-write method and device |
| CN105824763A (en) * | 2015-11-16 | 2016-08-03 | 广东亿迅科技有限公司 | Caching service realization method |
| CN105824763B (en) * | 2015-11-16 | 2019-05-17 | 广东亿迅科技有限公司 | A kind of buffer service implementation method |
| CN105608159B (en) * | 2015-12-18 | 2019-04-19 | 北京奇虎科技有限公司 | The method and apparatus of data buffer storage |
| CN105608159A (en) * | 2015-12-18 | 2016-05-25 | 北京奇虎科技有限公司 | Data caching method and device |
| CN105843693B (en) * | 2016-03-22 | 2019-05-14 | 同济大学 | A kind of shared drive method towards high speed Maglev emulation |
| CN105843693A (en) * | 2016-03-22 | 2016-08-10 | 同济大学 | High-speed maglev transportation simulation oriented memory sharing method |
| CN105717516A (en) * | 2016-03-30 | 2016-06-29 | 沈阳泰科易科技有限公司 | Global navigation satellite system (GNSS) data synchronization method and method |
| CN105717516B (en) * | 2016-03-30 | 2018-04-24 | 沈阳泰科易科技有限公司 | GNSS data synchronous method and device |
| CN106406857B (en) * | 2016-08-30 | 2021-04-13 | 惠州学院 | Memory multiplexing method and device for dynamic link library |
| CN106406857A (en) * | 2016-08-30 | 2017-02-15 | 惠州学院 | Memory reusing method and device for dynamic link library |
| CN108121594A (en) * | 2016-11-29 | 2018-06-05 | 阿里巴巴集团控股有限公司 | A kind of process management method and device |
| WO2018099292A1 (en) * | 2016-11-29 | 2018-06-07 | 阿里巴巴集团控股有限公司 | Process management method and apparatus |
| CN106708631A (en) * | 2016-11-30 | 2017-05-24 | 福建省天奕网络科技有限公司 | Shared memory property modification method and system |
| CN106708631B (en) * | 2016-11-30 | 2020-06-09 | 福建省天奕网络科技有限公司 | Shared memory attribute modifying method and system |
| CN106897440A (en) * | 2017-02-28 | 2017-06-27 | 郑州云海信息技术有限公司 | A kind of distributed file system file read-write processing method |
| CN106897440B (en) * | 2017-02-28 | 2020-06-26 | 郑州云海信息技术有限公司 | File read-write processing method for distributed file system |
| CN107944230A (en) * | 2017-11-20 | 2018-04-20 | 山东超越数控电子股份有限公司 | A kind of universal method of software activation verification |
| WO2020015670A1 (en) * | 2018-07-20 | 2020-01-23 | 中兴通讯股份有限公司 | File sending method, file receiving method and file transceiving apparatus |
| CN109086136A (en) * | 2018-07-26 | 2018-12-25 | 广东浪潮大数据研究有限公司 | A kind of request processing method and relevant apparatus of Samba software |
Also Published As
| Publication number | Publication date |
|---|---|
| CN101382953B (en) | 2013-03-20 |
Similar Documents
| Publication | Publication Date | Title |
|---|---|---|
| CN101382953B (en) | Interface system for accessing file system in user space and file reading and writing method | |
| CA2152752C (en) | Multiprocessor system for locally managing address translation table | |
| US7472252B2 (en) | Merging identical memory pages | |
| CN101419535B (en) | Distributed virtual magnetic disc system of virtual machine | |
| CN109697016B (en) | Method and apparatus for improving storage performance of containers | |
| US8131969B2 (en) | Updating system configuration information | |
| CN110795206B (en) | System and method for facilitating cluster-level caching and memory space | |
| EP2455865A1 (en) | Memory management device | |
| CN102339283A (en) | Access control method for cluster file system and cluster node | |
| CN101986649B (en) | Shared data center used in telecommunication industry billing system | |
| CN110221779B (en) | Construction method of distributed persistent memory storage system | |
| EP2437462B1 (en) | Data access processing method and device | |
| CN102326149A (en) | Realization method and apparatus for internal memory migration | |
| CN112000287B (en) | IO request processing device, method, equipment and readable storage medium | |
| CN110750356B (en) | Multi-core interaction method, system and storage medium suitable for nonvolatile memory | |
| US6473845B1 (en) | System and method for dynamically updating memory address mappings | |
| CN102971727A (en) | Recording dirty information in software distributed shared memory systems | |
| CN107329704A (en) | One kind caching mirror method and controller | |
| CN111309266A (en) | Distributed storage metadata system log optimization system and method based on ceph | |
| CN100338584C (en) | Memory controller having tables mapping memory addresses to memory modules | |
| JPH07262071A (en) | Data base system and load distribution control method | |
| US6298419B1 (en) | Protocol for software distributed shared memory with memory scaling | |
| CN111273860B (en) | Distributed memory management method based on network and page granularity management | |
| CN116431530B (en) | CXL memory module, memory processing method and computer system | |
| JP6343722B2 (en) | Method and device for accessing a data visitor directory in a multi-core system |
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 | ||
| CF01 | Termination of patent right due to non-payment of annual fee | ||
| CF01 | Termination of patent right due to non-payment of annual fee |
Granted publication date: 20130320 Termination date: 20160919 |