CN108810145A - A kind of multinode content distribution network system and method based on P2P - Google Patents
A kind of multinode content distribution network system and method based on P2P Download PDFInfo
- Publication number
- CN108810145A CN108810145A CN201810610934.5A CN201810610934A CN108810145A CN 108810145 A CN108810145 A CN 108810145A CN 201810610934 A CN201810610934 A CN 201810610934A CN 108810145 A CN108810145 A CN 108810145A
- Authority
- CN
- China
- Prior art keywords
- data
- node
- center
- user
- plate
- Prior art date
- Legal status (The legal status is an assumption and is not a legal conclusion. Google has not performed a legal analysis and makes no representation as to the accuracy of the status listed.)
- Pending
Links
Classifications
-
- H—ELECTRICITY
- H04—ELECTRIC COMMUNICATION TECHNIQUE
- H04L—TRANSMISSION OF DIGITAL INFORMATION, e.g. TELEGRAPHIC COMMUNICATION
- H04L67/00—Network arrangements or protocols for supporting network services or applications
- H04L67/01—Protocols
- H04L67/10—Protocols in which an application is distributed across nodes in the network
- H04L67/104—Peer-to-peer [P2P] networks
-
- H—ELECTRICITY
- H04—ELECTRIC COMMUNICATION TECHNIQUE
- H04L—TRANSMISSION OF DIGITAL INFORMATION, e.g. TELEGRAPHIC COMMUNICATION
- H04L67/00—Network arrangements or protocols for supporting network services or applications
- H04L67/01—Protocols
- H04L67/10—Protocols in which an application is distributed across nodes in the network
- H04L67/104—Peer-to-peer [P2P] networks
- H04L67/1074—Peer-to-peer [P2P] networks for supporting data block transmission mechanisms
-
- H—ELECTRICITY
- H04—ELECTRIC COMMUNICATION TECHNIQUE
- H04L—TRANSMISSION OF DIGITAL INFORMATION, e.g. TELEGRAPHIC COMMUNICATION
- H04L67/00—Network arrangements or protocols for supporting network services or applications
- H04L67/01—Protocols
- H04L67/10—Protocols in which an application is distributed across nodes in the network
- H04L67/1097—Protocols in which an application is distributed across nodes in the network for distributed storage of data in networks, e.g. transport arrangements for network file system [NFS], storage area networks [SAN] or network attached storage [NAS]
-
- H—ELECTRICITY
- H04—ELECTRIC COMMUNICATION TECHNIQUE
- H04L—TRANSMISSION OF DIGITAL INFORMATION, e.g. TELEGRAPHIC COMMUNICATION
- H04L67/00—Network arrangements or protocols for supporting network services or applications
- H04L67/50—Network services
- H04L67/55—Push-based network services
Landscapes
- Engineering & Computer Science (AREA)
- Computer Networks & Wireless Communication (AREA)
- Signal Processing (AREA)
- Information Transfer Between Computers (AREA)
Abstract
The present invention provides a kind of the multinode content distribution network system and method for P2P, including the data distribution center of communication connection and plate center;The data at data distribution center, the data order for submitting user are directly distributed to user;The data distribution center includes interior net system and outer net system;Interior net system includes disk array cluster for storing data;Outer net system includes push website cluster and collaboration subsystem;Subsystem is cooperateed with, the scheduling of the task for being responsible for user's submission;Push website cluster, the push for being responsible for user requested data;Plate center, the order information for submitting user are sent to the collaboration subsystem of the plate Distribution Center.
Description
Technical field
The present invention relates to data distribution network technical fields, and in particular to a kind of multinode content distributing network system of P2P
System and method.
Background technology
Nowadays most of remote sensing image data platforms use single node content network dissemination system both at home and abroad, for data
Than for more frequently dynamic content, single node content distributing network can only node and source data node (net in its center for interaction
Stand own system) between do limited transmission optimization, acceleration effect is not obvious, and with system for content present it is increasingly rich
Richness, the business for having emerged even more complex deliver demand, this is also implied that for the publication of data will face more challenges.
Current existing back end selection algorithm can improve the transmission speed of data to a certain extent, but be directed to
Remote sensing image data is larger, is closed between the demand data and geographical location of the limitation of data user group and different zones node
The particularity of system, current node selection algorithm all cannot efficiently improve the distribution efficiency of remote sensing image data.Such as based on
The distance measurement algorithm of longitude and latitude obtains start node by the longitude and latitude telemetry between node and selects sequence, but longitude and latitude
The administration overhead for spending telemetry is larger, and Internet shields the details of physical link in application layer, and physical distance can not be from
Client terminal obtains, so the longitude and latitude telemetry of node has hardly possible acquired;Static state also based on IP address distribution character
Network distance algorithm, i.e., regularity when being distributed according to IP, the distance between static measurement node, but for the solution of IP address
Analysis has certain complex, and the consuming time is longer, so how to be arrived most according to the request of the service ability distributing user of each node
Excellent server node carries out remote sensing image data, and quickly distribution and the research of download problem are very critical.
Invention content
The shortcoming for analyzing current data distribution policy, base is devised on the basis of original data distribution network
In the multinode content distributing network of peer-to-peer network, generated in data dissemination process with to make up original node selection strategy
The problem of unstability and high concurrent.
The technical scheme is that:
A kind of multinode content distribution network system of P2P, including the data distribution center of communication connection and plate center;
The data at data distribution center, the data order for submitting user are directly distributed to user;
The data distribution center includes interior net system and outer net system;
Interior net system includes disk array cluster for storing data;
Outer net system includes push website cluster and collaboration subsystem;
Subsystem is cooperateed with, the scheduling of the task for being responsible for user's submission;
Push website cluster, the push for being responsible for user requested data;
Plate center, the order information for submitting user are sent to the collaboration subsystem of the plate Distribution Center.
Further, plate center, push website cluster and collaboration subsystem respectively include communicating the several of connection
The status of server node, each server node is identical.
Technical solution of the present invention also provides a kind of multinode content distribution method of P2P, comprises the following processes:
Data are directly distributed to user by the data order that user submits to data distribution center, data distribution center;
Order information can be sent to the plate Distribution Center by the data order that user submits to plate center, plate center
Collaboration subsystem;Cooperate with subsystem in data base querying data, if there are required data by plate center completion for database
The download of data.
Further, step cooperates with subsystem in data base querying data, if there are required data by the plate for database
The download of data is completed at center, further includes:
If database does not inquire required data, which is submitted into data distribution center processing, by data
Distribution Center completes the demand of user.
Further, order information can be sent to by the data order that step user submits to plate center, plate center
The collaboration subsystem of the plate Distribution Center;Cooperate with subsystem in data base querying data, if database there are required data by
The download of data is completed at the plate center, implements process:
Collaboration subsystem inquires the data at each plate center, and there will be the plate centers of the data as node, raw
At sequence node;
Sequence node is returned to the plate center of request data, plate center is according to the sequence node received to correspondence
Requesting node downloading data.
Further, sequence node is returned to the plate center of request data by step, and plate center is according to receiving
Sequence node includes to corresponding requesting node downloading data:
Obtain the load capacity index of node;
The priority of node is obtained by the load capacity of node;
Node is ranked up in cache list according to the size of priority, the big node of priority comes cache list
Foremost, when node downloading data using redirecting technique will user request turn to list preceding n position corresponding to
Node, download corresponding data.
Further, the load capacity index of step acquisition node includes the following steps:
Network bandwidth, CPU and the memory space index for obtaining and preserving node, place it in sequence node ZBSeq;
Judge whether to be added to sequence node by the utilization rate of calculation server meshed network bandwidth, CPU and memory space.
Further, node is ranked up in cache list by step according to the size of priority, the big section of priority
Point comes the foremost of cache list, before the request of user is turned to list using redirecting technique when node downloading data
Node corresponding to n position, downloading corresponding data further includes:In downloading process, updating cache in real time list comes row
The node of table foremost is the maximum node of joint behavior index always, then by corresponding task distribute to corresponding node into
Row is downloaded, to realize the load balancing of multitask content distributing network.
The multinode content distributing network based on peer-to-peer network is devised on the basis of original data distribution network,
And the multitask load capacity assessment strategy based on peer-to-peer network is proposed on this network foundation, mainly make up original section
The problem of unstability and high concurrent that point selection strategy generates in data dissemination process, the system include mainly Distribution Center
With plate center.
Intranet is mainly by being formed for a large amount of disk array clusters for storing remote sensing image data, and outer net is mainly by pushing
Website cluster and collaboration subsystem are constituted, and the scheduling for the task that collaboration subsystem responsible user submits, push website is responsible for user
The push of required remote sensing image data.
As can be seen from the above technical solutions, the present invention has the following advantages:Multinode content based on peer-to-peer network point
Hairnet network, in this content distributing network, the status of each server node is identical, can be in server cluster, according to clothes
The performance of business device node is different, rational to carry out the distribution of task, while proposing the assessment strategy based on node load ability,
The poor server node of performance, which can be effectively ensured, to become the bottleneck of whole system, and can make the clothes of better performances
The resource utilization of business device node is effectively improved.
In addition, design principle of the present invention is reliable, and it is simple in structure, there is very extensive application prospect.
It can be seen that compared with prior art, the present invention with substantive distinguishing features outstanding and significantly improving, implementation
Advantageous effect be also obvious.
Description of the drawings
Fig. 1 is the multinode content distribution network system structural schematic diagram of P2P a kind of;
Fig. 2 is that plate Distribution Center and data Distribution Center are formed by centralization peer network architecture topological diagram;
Fig. 3 is that plate Distribution Center is illustrated according to the sequence node received to corresponding requesting node downloading data flow
Figure;
Fig. 4 is topology knot used in each server node of the multinode content distributing network based on peer-to-peer network
Structure;
Fig. 5 is load capacity assessment algorithm flow diagram.
Specific implementation mode
The present invention will be described in detail below in conjunction with the accompanying drawings and by specific embodiment, and following embodiment is to the present invention
Explanation, and the invention is not limited in following implementation.
A kind of multinode content distribution network system for P2P that embodiment 1 provides, including in the data distribution of communication connection
The heart and plate center;
The data at data distribution center, the data order for submitting user are directly distributed to user;
The data distribution center includes interior net system and outer net system;
Interior net system includes disk array cluster for storing data;
Outer net system includes push website cluster and collaboration subsystem;
Subsystem is cooperateed with, the scheduling of the task for being responsible for user's submission;
Push website cluster, the push for being responsible for user requested data;
Plate center, the order information for submitting user are sent to the collaboration subsystem of the plate Distribution Center.
Plate center, push website cluster and collaboration subsystem respectively include communicating several server sections of connection
The status of point, each server node is identical.
The embodiment of the present invention also provides a kind of multinode content distribution method of P2P, comprises the following processes:
Data are directly distributed to user by the data order that user submits to data distribution center, data distribution center;
Order information can be sent to the plate Distribution Center by the data order that user submits to plate center, plate center
Collaboration subsystem;Cooperate with subsystem in data base querying data, if there are required data by plate center completion for database
The download of data.
As shown in Figure 1, wherein data distribution center is roughly the same with the inside composed structure of plate Distribution Center, difference
It is in mostly many compared with the data that plate Distribution Center is stored in the data that data distribution center is stored.Plate is distributed
Some associated mechanisms and scientific research center of center major deployments centered on by data distribution center, plate Distribution Center and data
Distribution Center is formed by centralization peer network architecture topology, as shown in Figure 2.
Plate center and data Distribution Center can directly be the user service respectively administered, and specific workflow is as follows:
a:The remote sensing image data order submitted to data distribution center, data are directly distributed to use by data distribution center
Family.
b:The remote sensing image data order submitted to plate Distribution Center, order information can be sent to the plate by plate center
The collaboration subsystem of block Distribution Center, collaboration subsystem can go son can be with data base querying data, if integrated data inventory
The download of data is then done directly by the plate Distribution Center in data, if not inquiring the data in integrated database,
The data order is then submitted into data distribution center processing, the demand of user is completed by data distribution center.
c:After plate Distribution Center or data distribution center receive data order, collaboration subsystem can be each
The data are inquired at plate center, and there will be the plate Distribution Center of the data as node, then generates sequence node, and will section
Point sequence returns to the plate Distribution Center of request data, and plate Distribution Center asks according to the sequence node received to corresponding
Node downloading data is sought, it is as shown in Figure 3 to download flow.
In this content distributing network, the status of each server node is identical, is all stored with a large amount of remote sensing image number
According to topological structure used in each server node of the multinode content distributing network based on peer-to-peer network, such as Fig. 4 institutes
Show.
Each server node system structure having the same in Fig. 4, and a large amount of data are stored, it can will believe between node
Breath is forwarded, and inquiry request is then transmitted to requesting node again.The Centroid of multinode content distributing network have it is multiple,
Each node forms a peer-to-peer network, exchanges each other's needs between node, shares required resource, can be very good to solve hot localised points
The problems such as effect, alleviates Distribution Center's load pressure.
When customer end A, B, C simultaneously to server node A request datas when, server node A can to server node B,
C, D sends message requesting data, if having the data that user asks, server node B, C, D in the spaces server node B, C, D
Server node B, C, D task amount that can be downloaded can be returned into clothes according to the bandwidth, CUP resources and storage capacity of its node
Be engaged in device A, then uses redirecting technique that the request of user is turned to corresponding node downloading data to realize node server
Load balancing
The addition of lower new node K of ordinary circumstance all can be that server node rank is minimum in whole system, then
The rank for continuously decreasing or increasing oneself after bringing into operation with node K again is adjusting node most to reach optimum state
When good state, the load capacity index of node is obtained first, including:
S11:As soon as a node K is often added in system, related algorithm is disposed in node, to obtain and preserve the net of node
The indexs such as network bandwidth, CPU and memory space place it in sequence node ZBSeq.
S12:Server node determines whether itself adds according to the utilization rate of the network bandwidth of itself, CPU and memory space
Enter to sequence node.Because if any one parameter index utilization rate of the network bandwidth of node, CPU, memory space is excessively high, all can
The efficiency of service of this node is influenced, severe patient can make whole system break down or even paralyse during data are downloaded.
It is assumed that the occupied bandwidth of node K is Wx, the available bandwidth of node K is Wx;Then node K available network bandwidths
Index is as shown in formula 3-1.
It is assumed that it is c that node K, which has n process, each occupied CPU of process,i, then the occupied cpu resource of n process beThe computing capability of node K is cx, then the available cpu resource index of node is as shown in formula 3-2;
It is assumed that it is m that node K, which has y file, each occupied memory space of file,j, then the occupied storage of y file
Space isThe remaining memory spaces of node K are Mx, then the available memory space index of node is as shown in formula 3-3.
In order to prevent because the parameter of some node is unqualified, and influence the service quality of node and the download speed of data
Degree, so when the parameter index of nodeIn any one index be less than 20% when, this node will be washed in a pan
It eliminates, then can set the parameter in its sequence node ZBSeq to FALSE.
S13:The network bandwidth, CPU and memory space of node are obtained by the parameter in sequence node ZBSeq, node
Load capacity has the network bandwidth, CPU and memory space of node to be determined.It is assumed that the occupied bandwidth of node K is wx, node K
Usable bandwidth is Wx;It is assumed that it is c that node K, which has n process, each occupied CPU of process,i, then the occupied CPU of n process
Resource isCup resources all node K are cx;It is assumed that node K has y file, each occupied storage of file empty
Between be mj, then the occupied memory space of y file beThe remaining memory spaces of node K are Mx。
Then the performance indicator of node K consumption is:
The existing performance indicators of node K are:
F=Wx*cx*Mx (3-5)
The load capacity of node K is:
T=log2D/F (3-6)
Thus it can get the load capacity T of node K;
S14:Under normal circumstances, if the remaining bandwidth of a node K accounts for the 80% of its available bandwidth, remaining computing capability
The 80% of its computing capability being accounted for, remaining storage capacity accounts for the 80% of its storage capacity, then it is assumed that the load capacity of the node is normal,
Under the premise of not influencing the machine operation normal service can be provided for system.
Node remaining load ability at this time is
So by node 18 as the separation for weighing a node load ability.
S15:Trigger is set to obtain network bandwidth, CPU, memory space scheduling algorithm, every three hours clocked flips are primary,
Newest parameter information is obtained, and is saved it in sequence node ZBSeq, is only preserved in sequence node ZBSeq nearest one day
Parameter information, remaining information will be deleted.
After obtaining the load capacity of node, the priority of node is obtained by the load capacity of node, is saved with determining
The priority sequence of point, the concrete operations for obtaining node priority sequence are as follows:
S21:When user A asks mass data to node K, node K can believe to the node transmission data of other in system
The message of breath.
S22:It after remaining node receives message, searches and locally whether there is the requested data of user, if it does, section
Point passes through the priority indicator of algorithm 3-7 acquisition nodes according to the load capacity of itself.
Y:For the index of node K remaining load abilities;
Wx:For the available bandwidth of node K;
wx:For the bandwidth occupied in node K operations in nearly one day;
cx:The computing capability of node K;
ci:When there is n process to occupy cpu resource, the cpu resource that each process occupies is ci, 1=<i<=n;
mj:When having j file when using memory space, the memory capacity of each file occupancy is mj, 1=<j<=y;
Mx:The storage capacity of node K.
Each single item is multiplied by 10 in algorithm2It is to be convenient for the rounding of parameter to remove decimal during calculating.
S23:After getting the priority indicator of node, parameter is returned into requesting node K, node K will be according to each node
Priority indicator corresponding node is put into the priority sequence seq of node K, its priority parameters index is descending
Sequence, is the larger node of priority parameters in the exit of the priority sequence seq of node K.Thus the excellent of node K can be obtained
First grade sequence.So the higher node system of those priority can preferentially be selected to provide service when selecting node.
System in the process of running, with the continuous triggering for the timer being arranged in node, in cache list seq
Sequence node also can constantly update, to get the newest parameter index of node, to ensure that remote sensing image data is being distributed
During can get the best node of those service performances and provide service to the user, to improve the distribution speed of data.
As shown in Figure 5, when node has a large amount of request of data, requesting node can send to other server nodes and obtain
The message of data target, other nodes obtain respective priority according to oneself network bandwidth, cpu resource and storage capacity, and
Node is ranked up in cache list seq according to the size of priority, the big node of priority comes cache list seq's
Foremost is turned to the request of user corresponding to the preceding n position of list seq using redirecting technique when node downloading data
Node, download corresponding data.In downloading process, updating cache in real time list seq comes the section of the foremosts list seq
Point is the maximum node of joint behavior index always, and corresponding task, which is then distributed to corresponding node, is downloaded, with reality
The load balancing of existing multitask content distributing network.Node in the process of running, constantly in operational process bandwidth, calculate
Ability and the CUP Resource Calculations priority of oneself, to adjust the cache list seq of node in real time to realize load balancing.
Term " first ", " second ", " third " " in description and claims of this specification and above-mentioned attached drawing
The (if present)s such as four " are for distinguishing similar object, without being used to describe specific sequence or precedence.It should manage
The data that solution uses in this way can be interchanged in the appropriate case, so as to the embodiment of the present invention described herein can in addition to
Here the sequence other than those of diagram or description is implemented.In addition, term " comprising " and " having " and their any deformation,
It is intended to cover and non-exclusive includes.
The foregoing description of the disclosed embodiments enables those skilled in the art to implement or use the present invention.
Various modifications to these embodiments will be apparent to those skilled in the art, as defined herein
General Principle can be realized in other embodiments without departing from the spirit or scope of the present invention.Therefore, of the invention
It is not intended to be limited to the embodiments shown herein, and is to fit to and the principles and novel features disclosed herein phase one
The widest range caused.
Claims (8)
1. the multinode content distribution network system of P2P a kind of, which is characterized in that data distribution center including communication connection and
Plate center;
The data at data distribution center, the data order for submitting user are directly distributed to user;
The data distribution center includes interior net system and outer net system;
Interior net system includes disk array cluster for storing data;
Outer net system includes push website cluster and collaboration subsystem;
Subsystem is cooperateed with, the scheduling of the task for being responsible for user's submission;
Push website cluster, the push for being responsible for user requested data;
Plate center, the order information for submitting user are sent to the collaboration subsystem of the plate Distribution Center.
2. the multinode content distribution network system of P2P according to claim 1 a kind of, which is characterized in that
Plate center, push website cluster and collaboration subsystem respectively include communicating several server nodes of connection, often
The status of a server node is identical.
3. the multinode content distribution method of P2P a kind of, which is characterized in that comprise the following processes:
Data are directly distributed to user by the data order that user submits to data distribution center, data distribution center;
Order information can be sent to the association of the plate Distribution Center by the data order that user submits to plate center, plate center
Same subsystem;Cooperate with subsystem in data base querying data, if there are required data by plate center completion data for database
Download.
4. the multinode content distribution method of P2P according to claim 3 a kind of, which is characterized in that
Step cooperates with subsystem in data base querying data, if there are required data by plate center completion data for database
It downloads, further includes:
If database does not inquire required data, which is submitted into data distribution center processing, by data distribution
Complete the demand of user in center.
5. the multinode content distribution method of P2P according to claim 3 a kind of, which is characterized in that
Order information can be sent to the plate Distribution Center by the data order that step user submits to plate center, plate center
Collaboration subsystem;Cooperate with subsystem in data base querying data, if there are required data by plate center completion for database
The download of data implements process:
Collaboration subsystem inquires the data at each plate center, and there will be the plate centers of the data as node, generates section
Point sequence;
Sequence node is returned to the plate center of request data, plate center is asked according to the sequence node received to corresponding
Seek node downloading data.
6. the multinode content distribution method of P2P according to claim 3 a kind of, which is characterized in that
Sequence node is returned to the plate center of request data by step, and plate center is according to the sequence node received to correspondence
Requesting node downloading data include:
Obtain the load capacity index of node;
The priority of node is obtained by the load capacity of node;
Node is ranked up in cache list according to the size of priority, the big node of priority comes cache list most
Front, the section corresponding to the preceding n position for asking steering list when node downloading data using redirecting technique by user
Point downloads corresponding data.
7. the multinode content distribution method of P2P according to claim 6 a kind of, which is characterized in that
The load capacity index that step obtains node includes the following steps:
Network bandwidth, CPU and the memory space index for obtaining and preserving node, place it in sequence node ZBSeq;Pass through meter
The utilization rate for calculating server node network bandwidth, CPU and memory space judges whether to be added to sequence node.
8. the multinode content distribution method of P2P according to claim 6 a kind of, which is characterized in that
Node is ranked up in cache list by step according to the size of priority, and the big node of priority comes cache list
Foremost, when node downloading data using redirecting technique will user request turn to list preceding n position corresponding to
Node, downloading corresponding data further includes:
In downloading process, updating cache in real time list, the node for coming list foremost is that joint behavior index is maximum always
Node, corresponding task is then distributed into corresponding node and is downloaded, to realize the negative of multitask content distributing network
It carries balanced.
Priority Applications (1)
Application Number | Priority Date | Filing Date | Title |
---|---|---|---|
CN201810610934.5A CN108810145A (en) | 2018-06-13 | 2018-06-13 | A kind of multinode content distribution network system and method based on P2P |
Applications Claiming Priority (1)
Application Number | Priority Date | Filing Date | Title |
---|---|---|---|
CN201810610934.5A CN108810145A (en) | 2018-06-13 | 2018-06-13 | A kind of multinode content distribution network system and method based on P2P |
Publications (1)
Publication Number | Publication Date |
---|---|
CN108810145A true CN108810145A (en) | 2018-11-13 |
Family
ID=64086924
Family Applications (1)
Application Number | Title | Priority Date | Filing Date |
---|---|---|---|
CN201810610934.5A Pending CN108810145A (en) | 2018-06-13 | 2018-06-13 | A kind of multinode content distribution network system and method based on P2P |
Country Status (1)
Country | Link |
---|---|
CN (1) | CN108810145A (en) |
Citations (9)
Publication number | Priority date | Publication date | Assignee | Title |
---|---|---|---|---|
CN102118376A (en) * | 2010-01-06 | 2011-07-06 | 中兴通讯股份有限公司 | CDN server and content download method |
CN102368776A (en) * | 2011-11-25 | 2012-03-07 | 中国科学技术大学 | Optimization function module of node list in content distribution/delivery network (CDN) |
US20120254456A1 (en) * | 2011-03-31 | 2012-10-04 | Juniper Networks, Inc. | Media file storage format and adaptive delivery system |
CN104158904A (en) * | 2014-08-28 | 2014-11-19 | 重庆邮电大学 | Cloud-assisted cooperative downloading method of mobile P2P network |
CN104320487A (en) * | 2014-11-11 | 2015-01-28 | 网宿科技股份有限公司 | HTTP dispatching system and method for content delivery network |
CN104717304A (en) * | 2015-03-31 | 2015-06-17 | 北京科技大学 | CDN-P2P (Content Distribution Network-Peer-to-Peer) content optimizing selecting system |
CN104935640A (en) * | 2015-05-07 | 2015-09-23 | 上海逸云信息科技发展有限公司 | P2P acceleration content distribution network system and method |
CN105068755A (en) * | 2015-07-08 | 2015-11-18 | 南京邮电大学 | Data duplicate storage method facing cloud computing content distribution network |
CN107395708A (en) * | 2017-07-14 | 2017-11-24 | 郑州云海信息技术有限公司 | A kind of method and apparatus for handling download request |
-
2018
- 2018-06-13 CN CN201810610934.5A patent/CN108810145A/en active Pending
Patent Citations (9)
Publication number | Priority date | Publication date | Assignee | Title |
---|---|---|---|---|
CN102118376A (en) * | 2010-01-06 | 2011-07-06 | 中兴通讯股份有限公司 | CDN server and content download method |
US20120254456A1 (en) * | 2011-03-31 | 2012-10-04 | Juniper Networks, Inc. | Media file storage format and adaptive delivery system |
CN102368776A (en) * | 2011-11-25 | 2012-03-07 | 中国科学技术大学 | Optimization function module of node list in content distribution/delivery network (CDN) |
CN104158904A (en) * | 2014-08-28 | 2014-11-19 | 重庆邮电大学 | Cloud-assisted cooperative downloading method of mobile P2P network |
CN104320487A (en) * | 2014-11-11 | 2015-01-28 | 网宿科技股份有限公司 | HTTP dispatching system and method for content delivery network |
CN104717304A (en) * | 2015-03-31 | 2015-06-17 | 北京科技大学 | CDN-P2P (Content Distribution Network-Peer-to-Peer) content optimizing selecting system |
CN104935640A (en) * | 2015-05-07 | 2015-09-23 | 上海逸云信息科技发展有限公司 | P2P acceleration content distribution network system and method |
CN105068755A (en) * | 2015-07-08 | 2015-11-18 | 南京邮电大学 | Data duplicate storage method facing cloud computing content distribution network |
CN107395708A (en) * | 2017-07-14 | 2017-11-24 | 郑州云海信息技术有限公司 | A kind of method and apparatus for handling download request |
Similar Documents
Publication | Publication Date | Title |
---|---|---|
JP4974888B2 (en) | Distributed request routing | |
US8271987B1 (en) | Providing access to tasks that are available to be performed | |
JP5719323B2 (en) | Distributed processing system, dispatcher and distributed processing management device | |
CN100365997C (en) | Distributed hash table in opposite account | |
JP5582344B2 (en) | Connection management system and connection management server linkage method in thin client system | |
CN103701916B (en) | The dynamic load balancing method of distributed memory system | |
US8327371B2 (en) | Multinode server system, load distribution method, resource management server, and program product | |
Cardellini et al. | Request redirection algorithms for distributed web systems | |
US7827286B1 (en) | Providing enhanced access to stored data | |
US20010034752A1 (en) | Method and system for symmetrically distributed adaptive matching of partners of mutual interest in a computer network | |
CN107278365B (en) | Apparatus for scalable peer matching | |
US20040103194A1 (en) | Method and system for server load balancing | |
CN105357246B (en) | Caching method based on information centre's network and system | |
EP3087722B1 (en) | Peer-to-peer network prioritizing propagation of objects through the network | |
WO2013078875A1 (en) | Content management method, device and system | |
CN105450579B (en) | Internet resources pre-add support method, client and middleware server | |
CN102244685A (en) | Distributed type dynamic cache expanding method and system supporting load balancing | |
CN107251533A (en) | The peer device being located at one for equity matching | |
CN103338252A (en) | Distributed database concurrence storage virtual request mechanism | |
Di Modica et al. | Resource and service discovery in SOAs: A P2P oriented semantic approach | |
CN104202386B (en) | A kind of high concurrent amount distributed file system and its secondary load equalization methods | |
Rawadi et al. | Providing local cloud services to mobile devices with inter-cloudlet communication | |
JP6793498B2 (en) | Data store device and data management method | |
CN110198267A (en) | A kind of traffic scheduling method, system and server | |
CN113680050B (en) | Game request processing method and device, computer equipment and readable storage medium |
Legal Events
Date | Code | Title | Description |
---|---|---|---|
PB01 | Publication | ||
PB01 | Publication | ||
SE01 | Entry into force of request for substantive examination | ||
SE01 | Entry into force of request for substantive examination | ||
RJ01 | Rejection of invention patent application after publication |
Application publication date: 20181113 |
|
RJ01 | Rejection of invention patent application after publication |