CN102652425B - Data acquisition method of large-scale network and network node - Google Patents
Data acquisition method of large-scale network and network node Download PDFInfo
- Publication number
- CN102652425B CN102652425B CN201180004193.2A CN201180004193A CN102652425B CN 102652425 B CN102652425 B CN 102652425B CN 201180004193 A CN201180004193 A CN 201180004193A CN 102652425 B CN102652425 B CN 102652425B
- Authority
- CN
- China
- Prior art keywords
- node
- nodes
- statistics
- request
- occupying rate
- 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.)
- Expired - Fee Related
Links
Images
Classifications
-
- H—ELECTRICITY
- H04—ELECTRIC COMMUNICATION TECHNIQUE
- H04L—TRANSMISSION OF DIGITAL INFORMATION, e.g. TELEGRAPHIC COMMUNICATION
- H04L43/00—Arrangements for monitoring or testing data switching networks
-
- H—ELECTRICITY
- H04—ELECTRIC COMMUNICATION TECHNIQUE
- H04L—TRANSMISSION OF DIGITAL INFORMATION, e.g. TELEGRAPHIC COMMUNICATION
- H04L45/00—Routing or path finding of packets in data switching networks
- H04L45/02—Topology update or discovery
Landscapes
- Engineering & Computer Science (AREA)
- Computer Networks & Wireless Communication (AREA)
- Signal Processing (AREA)
- Data Exchanges In Wide-Area Networks (AREA)
Abstract
The present invention relates to a data acquisition method of a large-scale network and a network node. The method organizes the nodes in a whole network according to an N quadtree structure, and employs a recursive way for the information statistic of the nodes, so that the large-scale network node monitoring data can be got statistic real-timely without a need to modify a statistical algorithm and other business logics, thereby improving the statistics speed of the indexes, such as a global resources occupancy rate of the whole network substantially, and responding the requirements of application scenes, such as resource scheduling, etc. in time, and at the same time, reducing the maintenance cost of the large-scale network node substantially.
Description
Technical field
The embodiment of the present invention relates to cloud computing technology, particularly a kind of collecting method of large scale network and network node.
Background technology
Flourish along with cloud computing, the scale of the network architecture is also increasing, therefore, in large scale network, is faced with huge challenge for the statistics of the various information datas of each network node.In traditional method, be all often to obtain by post analysis for statistical indicators such as the global resource occupancies of the whole network.
Available technology adopting post analysis method is added up and is generally taked centralized management pattern large-scale resource index, dividing data warehouse (, management node) and resource node, wherein, resource node is responsible for collection and the transmission of resources occupation rate separately, and management node is responsible for collection and the storage of the whole network global resource related data; Post analysis system is connected with management node, special data mining analysis system, and management node is collected and the whole network global resource related data of storage is carried out data mining analysis, exports final analysis result, passes to decision system as decision-making foundation.But the post analysis method based on this framework is consuming time very long, even a couple of days just can obtain final analysis result often to need several hours.
And need to obtain in real time under the scene of statistics in such as scheduling of resource etc., the data that obtain are more real-time, and effect is just better.Therefore, this post analysis method, under the scenes such as scheduling of resource, just seems nonsensical, and possibility or disabled.This just needs a kind of method badly, solves in large scale network, and the statistical index data such as global resource occupancy can be obtained as early as possible, preferably can Real-time Obtaining.
Summary of the invention
The embodiment of the present invention provides a kind of collecting method and network node of large scale network, in order to solve in large scale network cannot Real-time Obtaining for statistical index data such as global resource occupancies problem.
In view of this, the embodiment of the present invention provides a kind of collecting method of large scale network, comprising:
Management end is chosen arbitrarily a node in network as start node, sends the range of nodes of other nodes in the request of resource occupying rate statistics and described network to described start node, asks described start node to be added up resource occupying rate;
Described start node is according to the range of nodes of other nodes in the described resource occupying rate statistics request receiving and described network, other nodes in described network are divided into N group, from each group, choose arbitrarily a node as a point start node, send respectively the range of nodes of other nodes in the request of described resource occupying rate statistics and this group to each point of start node;
Described each point of start node is according to the range of nodes of other nodes in the described resource occupying rate statistics request receiving and this group, whether the number that judges other nodes in this group is greater than N, if the number of other nodes is less than or equal to N in this group, no longer this group is proceeded to grouping, other nodes in this group are finish node, send respectively the request of described resource occupying rate statistics to described finish node; If the number of other nodes is greater than N in this group, other nodes in this group are continued to be divided into N group, from each group, choose arbitrarily a node and divide start node as lower one deck, divide start node to send respectively the range of nodes of other nodes in the request of described resource occupying rate statistics and this group to each lower one deck;
Repeat above-mentioned determining step, until the number of other nodes except point start node is less than or equal to N in all groupings;
Each finish node, according to the resource occupying rate statistics request of receiving, is added up the resource occupying rate of this finish node, and statistics is reported to point start node under this finish node;
Each point start node is received after the resource occupying rate statistics that jurisdiction node reports, in conjunction with the resource occupying rate statistics of this point of start node, again carry out counting statistics, and the last layer that statistics is reported under this point of start node divides start node, until successively report described start node, calculate final resource occupying rate by described start node;
The final resource occupying rate calculating is reported described management end by described start node.
The embodiment of the present invention also provides a kind of network node, comprising:
Receiving element, for receiving the range of nodes of the request of resource occupying rate statistics and other nodes of the affiliated set of this node, wherein, the request of described resource occupying rate statistics comprises the source IP address and the object IP address, the initial time of statistics and the resource measurement title of end time and request statistics that receive request of the request of initiation, and described range of nodes comprises the set being made up of node identification or the set being made up of the IP address of node;
Judge grouped element, be used for according to the range of nodes of other nodes of set under the request of described resource occupying rate statistics and this node, whether the number that judges other nodes in this set is greater than N, if the number of other nodes is less than or equal to N in this set, no longer this set is proceeded to grouping, other nodes in this set send respectively the request of described resource occupying rate statistics; If the number of other nodes is greater than N in this set, other nodes in this set are continued to be divided into N group, from each group, choose arbitrarily a node, send respectively the range of nodes of other nodes in the request of described resource occupying rate statistics and this group to described node;
Resources occupation rate statistic unit, for the resource occupying rate of this node is carried out to statistical report, and when receiving after the resource occupying rate statistics that jurisdiction node reports, again carry out counting statistics according to following computing formula, obtain the statistics of this node to resource occupying rate, and report this statistics: (this node resources occupation rate+jurisdiction node resource occupancy sum)/(1+ jurisdiction nodes).
As shown from the above technical solution, the collecting method of the large scale network that the embodiment of the present invention provides is by organizing according to N-ary tree structure the node of the whole network, and the Information Statistics of node are adopted to the mode of recurrence, make without amendment statistic algorithm and other service logics, can carry out real-time statistics to large-scale network node monitor data, greatly improve the Statistical Speed of the indexs such as the global resource occupancy of whole network, thereby reach the requirement of timely response application scenarioss such as scheduling of resource, simultaneously, also greatly reduce the maintenance cost of large-scale network node.
Brief description of the drawings
In order to be illustrated more clearly in the technical scheme of the embodiment of the present invention, to the accompanying drawing of required use in embodiment or description of the Prior Art be briefly described below, apparently, accompanying drawing in the following describes is only some embodiments of the present invention, for those of ordinary skill in the art, do not paying under the prerequisite of creative work, can also obtain according to these accompanying drawings other accompanying drawing.
Fig. 1 is the extensive system for cloud computing schematic diagram of embodiment of the present invention application;
Fig. 2 is the schematic diagram of the resource node of the whole network being organized according to tree-shaped hierarchical structure according to the embodiment of the present invention;
Fig. 3 is the schematic flow sheet that according to the embodiment of the present invention, the whole network node is carried out recurrence grouping;
The schematic flow sheet of the collecting method of a kind of large scale network that Fig. 4 provides for the embodiment of the present invention;
The interacting message schematic diagram of the collecting method of a kind of large scale network that Fig. 5 provides for the embodiment of the present invention;
The structural representation of a kind of network node that Fig. 6 provides for the embodiment of the present invention.
Embodiment
Below in conjunction with the accompanying drawing in the embodiment of the present invention, the technical scheme in the embodiment of the present invention is clearly and completely described, obviously, described embodiment is the present invention's part embodiment, instead of whole embodiment.Based on the embodiment in the present invention, those of ordinary skill in the art, not making the every other embodiment obtaining under creative work prerequisite, belong to the scope of protection of the invention.
The system environments of embodiment of the present invention application as shown in Figure 1.Fig. 1 is the schematic diagram of an extensive system for cloud computing.In Fig. 1, when management layer need to be added up the resources occupation rate situation of whole network, from network, choose arbitrarily the cutting point of a node as statistical operation, and computing node is reported the statistics of the resources occupation rate situation of whole network to management layer thus, management level determine whether carrying out dilatation or subtracting the operation of appearance network with this result.Wherein, the computing node in Fig. 1 also can be referred to as resource node or network node, and the embodiment of the present invention does not limit this.
Based on the system environments shown in Fig. 1, the method logic of the embodiment of the present invention is as follows:
1, as shown in Figure 2, the resource node of the whole network (being computing node) is organized according to tree-shaped hierarchical structure, but the status of every layer is equal to, the Information Statistics of node are adopted to the mode of recurrence, can accomplish like this, network size is increasing, but only need to increase level quantity, and without amendment statistic algorithm and other service logics; And each resource node is computing node, formed by two assemblies, the task of an assembly has been synchronous with the information between other nodes, the task of another one assembly has been that the recursive statistics method of the index such as resources occupation rate between node reports.
2, in order to simplify the maintenance of tree-shaped level resource, all resource nodes are consisted of the synchronous collective's (as shown in Figure 1) of computing node information of a decentralization, and wherein, information synchronized algorithm includes but not limited to the methods such as Gossip.Each computing node maintains all computing node information, and these information include but not limited to: the heartbeat of node, the state of node (inefficacy inspection/live/dead), node present load.
3, management end can be initiated the statistics request to statistical indicators such as the whole network resources occupation rates from any one Internet resources node (decentralization computing node), this selected start node will divide into groups to other all nodes so, and group technology includes but not limited to the group technologies such as binary tree; First start node will be divided into n group other nodes, select a point of departure from every group, and statistics request is distributed to these point of departures.Point of departure own jurisdiction computing node is continued to be divided into n component the sending out of recurrence again, until segmentation not again, whole network node grouping is divided logic as shown in Figure 3.
4, when distribution, the computing node that receives request just starts to carry out the statistical computation of the indexs such as own resource occupancy, and wait for that its linchpin belongs to the result of calculation of computing node, after the statistics that belongs to computing node etc. all linchpins has all been reported, this computing node is according to the tabulate statistics that tries again of following formula: (this node resources occupation rate+jurisdiction node resource occupancy sum)/(1+ jurisdiction nodes); Then statistical summaries result is reported to the distribution node of last layer, the statistics final result of the statistical indicator such as the rest may be inferred, the resources occupation rate of the whole network will be aggregated into the node of management end initial request, thereby has completed the resource statistics operation of whole network.
Embodiment mono-
The schematic flow sheet of the collecting method of a kind of large scale network that Fig. 4 provides for the embodiment of the present invention, as shown in Figure 4, the collecting method of the large scale network of the present embodiment can comprise the following steps:
S100, management end are chosen arbitrarily a node in network as start node, send the range of nodes of other nodes in the request of resource occupying rate statistics and described network to described start node, ask described start node to be added up resource occupying rate;
Particularly, the synchronous network of nodal information that described network is decentralization, the each node in this network maintains the information of all nodes.The request of described resource occupying rate statistics comprises: initiate the initial time of the source IP address (as the IP address of management end) of request and the object IP address (as management end is chosen the node IP address as start node at random) of reception request, statistics and the resource measurement title of end time and request statistics.Wherein, described resource measurement, weighs the index of resource service condition, as cpu busy percentage, memory usage, network flow output etc.Described range of nodes, comprising: the set that the set being made up of node identification or the IP address by node form.It should be noted that, described range of nodes both can be carried in the request of resource occupying rate statistics and issue, and also can issue separately, and the embodiment of the present invention does not limit this.
S110, described start node are according to the range of nodes of other nodes in the described resource occupying rate statistics request receiving and described network, other nodes in described network are divided into N group, from each group, choose arbitrarily a node as a point start node, send respectively the range of nodes of other nodes in the request of described resource occupying rate statistics and this group to each point of start node;
It should be noted that, in described network the range of nodes of other nodes be exactly in this network except start node, the set being formed by node identification or the IP address of every other node; And in grouping the range of nodes of other nodes be exactly in this group except point start node, the set being formed by node identification or the IP address of every other node.In addition, other nodes in described network are divided into N group, both can decile, also decile not, preferably N equals 2, but in actual applications, can select as the case may be, and the embodiment of the present invention does not limit this.
For example, the whole network has 99 nodes (being designated 1-99), for example, except start node (electing 1 as), also have 98 nodes (2-99), if N is 2, so just can be divided into 2 groups, then from every group, selects a point of start node (as selected respectively 2 and 51), the scope of first group is exactly (3-50) so, and the scope of second group is exactly (52-99); If but N is 10, can be divided into so 10 groups, from every group, select a point of start node (as selected respectively 2,12,22,32,42,52,62,72,82,92), the scope of first group is just that 13-21, the scope of the 3rd group to the tenth group are respectively 23-31,33-41,43-51,53-61,63-71,73-81 and 93-99 for 3-11, the scope of second group so again.
S120, described each point of start node are according to the range of nodes of other nodes in the described resource occupying rate statistics request receiving and this group, whether the number that judges other nodes in this group is greater than N, if the number of other nodes is less than or equal to N in this group, no longer this group is proceeded to grouping, other nodes in this group are finish node, send respectively the request of described resource occupying rate statistics to described finish node; If the number of other nodes is greater than N in this group, other nodes in this group are continued to be divided into N group, from each group, choose arbitrarily a node and divide start node as lower one deck, divide start node to send respectively the range of nodes of other nodes in the request of described resource occupying rate statistics and this group to each lower one deck;
For example, suppose that the whole network has 99 nodes, N is 10, is exactly 10 groups so, should be 9 groups of 10 nodes compositions, and one group of 8 node, because will select a root node (, start node).In addition, in 10 groups, also have a sub-root node (, point start node) in every group, wherein 9 sub-root nodes are had jurisdiction over separately and are belonged to 9 nodes, and 1 sub-root node linchpin belongs to 7 nodes.When root node issues statistics request to 10 sub-root nodes, subsidiary every sub-root node jurisdiction belongs to the scope of node, when group root node discovery oneself linchpin genus nodes cannot be divided statistics group again, belong to node just directly to linchpin and issue statistics request, in this statistics request, no longer subsidiary linchpin belongs to the scope of node, each node is received after statistics request, in request, do not have jurisdiction over genus range of nodes if found, so just know oneself for leaf node (, finish node), directly report oneself resources occupation rate statistical conditions.
S130, repeat above-mentioned determining step, until the number of other nodes except point start node is less than or equal to N in all groupings;
S140, each finish node, according to the resource occupying rate statistics request of receiving, are added up the resource occupying rate of this finish node, and statistics are reported to point start node under this finish node;
S150, each point start node are received after the resource occupying rate statistics that jurisdiction node reports, in conjunction with the resource occupying rate statistics of this point of start node, again carry out counting statistics, and the last layer that statistics is reported under this point of start node divides start node, until successively report described start node, calculate final resource occupying rate by described start node;
Particularly, this step adopts the mode statistical report of recurrence, until all statisticses are aggregated into start node.Wherein, described start node and a point start node all calculate according to following formula:
(this node resources occupation rate+jurisdiction node resource occupancy sum)/(1+ jurisdiction nodes)
The final resource occupying rate calculating is reported described management end by S160, described start node.
The collecting method of the large scale network that the embodiment of the present invention provides is by organizing according to N-ary tree structure the node of the whole network, and the Information Statistics of node are adopted to the mode of recurrence, make without amendment statistic algorithm and other service logics, can carry out real-time statistics to large-scale network node monitor data, greatly improve the Statistical Speed of the indexs such as the global resource occupancy of whole network, thereby reach the requirement of timely response application scenarioss such as scheduling of resource, meanwhile, also greatly reduce the maintenance cost of large-scale network node.
Embodiment bis-
The interacting message schematic diagram of the collecting method of a kind of large scale network that Fig. 5 provides for the embodiment of the present invention.Wherein, management end is the management layer of the whole network; Start node is a computing node in the whole network selected arbitrarily of management layer; It is that start node divides into groups to all nodes of the whole network that linchpin belongs to node, is divided into after N group, the computing node (being point start node in embodiment mono-) picking out at random from every group; Linchpin belongs to n node layer, is linchpin genus node carries out the grouping of n similar start node node (being equivalent to point start node of n layer in embodiment mono-) to group interior nodes; And finish node is the node after cannot dividing into groups again.As shown in Figure 5, the collecting method of the large scale network of the present embodiment can comprise the following steps:
201, management end sends the request of the whole network resources occupation rate statistics to start node;
In this step, in this whole network resources occupation rate statistics request message, source IP address is the IP address of management end, object IP address is the IP address of the computing node selected at random from current network, in the message of statistics request, also comprise initial time and the statistics end time of statistics, and the resource measurement title of request statistics, as cpu busy percentage, memory usage, network flow output etc.
202, start node is had jurisdiction over genus resources occupation rate statistics to the transmission of linchpin genus node and is asked and have jurisdiction over genus range of nodes;
In this step, this linchpin belongs to the IP address that the source IP address in resources occupation rate statistics request message is start node, and object IP address is by the whole network after the node division N group except start node, the IP address of the computing node that random choose goes out from every group; This node is point start node as lower one deck, and other computing nodes in this group will belong to node as the linchpin of this computing node; Statistics requested part is wherein identical with the request in 201, but also needs to be accompanied with the scope that each point of start node jurisdiction belongs to node.
203, linchpin belongs to node and belongs to n node layer to linchpin and send that linchpin belongs to the request of resources occupation rate statistics and linchpin belongs to range of nodes;
In this step, the linchpin that linchpin genus node is initiated belongs to resources occupation rate statistics asks and has jurisdiction over the IP address that the source IP address of the message that belongs to range of nodes is each point of start node, object IP address is that the node that point start node jurisdiction is belonged to is divided into N group again, and from every group, random choose goes out the IP address of a computing node; This node is using point start node as lower one deck, and in this group, other computing nodes will belong to node as the linchpin of this computing node; Statistics requested part is wherein identical with the request in 201, but also needs to be accompanied with the scope that each point of start node jurisdiction belongs to node.
204, linchpin belongs to n node layer and belongs to the request of resources occupation rate statistics to finish node transmission linchpin;
In this step, it is similar with 203 that the linchpin that linchpin genus n node layer is initiated belongs to the request of resources occupation rate statistics, belongs to but do not need to be accompanied with each linchpin the scope that n node layer jurisdiction belongs to node.
205, finish node returns to resources occupation rate statistics request response to linchpin genus n node layer;
In this step, the IP address that source IP address in the resources occupation rate statistics request response that finish node is sent out is finish node, and being own last layer, object IP address divides the IP address of start node, statistics request response comprises the tolerance title of local resource, as cpu busy percentage, memory usage, network flow output etc., and the corresponding concrete numerical value of these tolerance titles.
206, each node resource occupancy summation of receiving is added own resource occupancy by linchpin genus n node layer, belongs to total nodes add 1 divided by linchpin, obtains this layer of linchpin and belong to the average resources occupation rate statistics of node;
207, linchpin genus n node layer reports this layer of linchpin to belong to resources occupation rate statistics to linchpin genus node;
In this step, the source IP address that this layer of linchpin that linchpin genus n node layer sends belongs in the average resources occupation rate statistics response of node is exactly the IP address of this layer point start node, object IP is the IP address (, from the source address in statistics request) that last layer divides start node; Linchpin belongs to the tolerance title that the average resources occupation rate statistics of node comprises resource, as cpu busy percentage, memory usage, network flow output etc., and the corresponding concrete assembly average of these tolerance titles.
208, each node layer resources occupation rate summation of receiving is added own resource occupancy by linchpin genus node, belongs to total nodes add 1 divided by linchpin, obtains this layer of linchpin and belong to the average resources occupation rate statistics of node;
209, linchpin genus node reports this layer of linchpin to belong to resources occupation rate statistics to start node;
In this step, it is similar with 207 that this layer of linchpin that linchpin genus node sends belongs to the average resources occupation rate statistics of node.
210, each node layer resources occupation rate summation is added own resource occupancy by start node, belongs to total nodes add 1 divided by linchpin, obtains the average resources occupation rate statistics of the whole network;
211, start node reports the average resources occupation rate statistics of the whole network to management end.
In this step, source IP address in the whole network resources occupation rate statistics request response that start node is initiated is exactly the IP address of start node, object IP address is the IP address of management end, the average resources occupation rate statistics of the whole network comprises the tolerance title of resource, as cpu busy percentage, memory usage, network flow output etc., and the corresponding concrete assembly average of these tolerance titles.
The collecting method of the large scale network providing according to the present embodiment, by the node of the whole network is organized according to N-ary tree structure, and the Information Statistics of node are adopted to the mode of recurrence, make without amendment statistic algorithm and other service logics, can carry out real-time statistics to large-scale network node monitor data, greatly improve the Statistical Speed of the indexs such as the global resource occupancy of whole network, thereby reach the requirement of timely response application scenarioss such as scheduling of resource, meanwhile, also greatly reduce the maintenance cost of large-scale network node.
Embodiment tri-
The embodiment of the present invention also provides a kind of apparatus for network node being applied in said method embodiment.The structural representation of a kind of network node that Fig. 6 provides for the embodiment of the present invention, as shown in Figure 6, the network node 30 that the embodiment of the present invention provides can comprise receiving element 31, judge grouped element 32 and resources occupation rate statistic unit 33.Wherein, receiving element 31 is for receiving the range of nodes of other nodes of set under the statistics request of resource occupying rate and this node, wherein, the request of described resource occupying rate statistics comprises the source IP address and the object IP address, the initial time of statistics and the resource measurement title of end time and request statistics that receive request of the request of initiation, and described range of nodes comprises the set being made up of node identification or the set being made up of the IP address of node; Judge that grouped element 32 is for according to the range of nodes of other nodes of set under the request of described resource occupying rate statistics and this node, whether the number that judges other nodes in this set is greater than N, if the number of other nodes is less than or equal to N in this set, no longer this set is proceeded to grouping, other nodes in this set send respectively the request of described resource occupying rate statistics; If the number of other nodes is greater than N in this set, other nodes in this set are continued to be divided into N group, from each group, choose arbitrarily a node, send respectively the range of nodes of other nodes in the request of described resource occupying rate statistics and this group to described node; Resources occupation rate statistic unit 33, for the resource occupying rate of this node is carried out to statistical report, and when receiving after the resource occupying rate statistics that jurisdiction node reports, again carry out counting statistics according to following computing formula, obtain the statistics of this node to resource occupying rate, and report this statistics: (this node resources occupation rate+jurisdiction node resource occupancy sum)/(1+ jurisdiction nodes).
Further, the network node that the embodiment of the present invention provides can also comprise:
Nodal information lock unit 34, synchronous for the whole network nodal information, makes this node maintain the information of all nodes in network.
The network node providing according to the embodiment of the present invention, by the node of the whole network is organized according to N-ary tree structure, and the Information Statistics of node are adopted to the mode of recurrence, make without amendment statistic algorithm and other service logics, can carry out real-time statistics to large-scale network node monitor data, greatly improve the Statistical Speed of the indexs such as the global resource occupancy of whole network, thereby reach the requirement of timely response application scenarioss such as scheduling of resource, meanwhile, also greatly reduce the maintenance cost of large-scale network node.
It should be noted that: receiving element 31 in embodiment tri-, judge that grouped element 32, resources occupation rate statistic unit 33 and nodal information lock unit 34 are hardware.
One of ordinary skill in the art will appreciate that: all or part of step that realizes said method embodiment can complete by the relevant hardware of program command, aforesaid program can be stored in a computer read/write memory medium, this program, in the time carrying out, is carried out the step that comprises said method embodiment; And aforesaid storage medium comprises: various media that can be program code stored such as ROM, RAM, magnetic disc or CDs.
Finally it should be noted that: above embodiment only, in order to technical scheme of the present invention to be described, is not intended to limit; Although the present invention is had been described in detail with reference to previous embodiment, those of ordinary skill in the art is to be understood that: its technical scheme that still can record aforementioned each embodiment is modified, or part technical characterictic is wherein equal to replacement; And these amendments or replacement do not make the essence of appropriate technical solution depart from the spirit and scope of various embodiments of the present invention technical scheme.
Claims (8)
1. a collecting method for large scale network, is characterized in that, comprising:
Management end is chosen arbitrarily a node in network as start node, sends the range of nodes of other nodes in the request of resource occupying rate statistics and described network to described start node, asks described start node to be added up resource occupying rate;
Described start node is according to the range of nodes of other nodes in the described resource occupying rate statistics request receiving and described network, other nodes in described network are divided into N group, from each group, choose arbitrarily a node as a point start node, send respectively the range of nodes of other nodes in the request of described resource occupying rate statistics and this group to each point of start node;
Described each point of start node is according to the range of nodes of other nodes in the described resource occupying rate statistics request receiving and this group, whether the number that judges other nodes in this group is greater than N, if the number of other nodes is less than or equal to N in this group, no longer this group is proceeded to grouping, other nodes in this group are finish node, send respectively the request of described resource occupying rate statistics to described finish node; If the number of other nodes is greater than N in this group, other nodes in this group are continued to be divided into N group, from each group, choose arbitrarily a node and divide start node as lower one deck, divide start node to send respectively the range of nodes of other nodes in the request of described resource occupying rate statistics and this group to each lower one deck;
Repeat above-mentioned determining step, until the number of other nodes except point start node is less than or equal to N in all groupings;
Each finish node, according to the resource occupying rate statistics request of receiving, is added up the resource occupying rate of this finish node, and statistics is reported to point start node under this finish node;
Each point start node is received after the resource occupying rate statistics that jurisdiction node reports, in conjunction with the resource occupying rate statistics of this point of start node, again carry out counting statistics, and the last layer that statistics is reported under this point of start node divides start node, until successively report described start node, calculate final resource occupying rate by described start node;
The final resource occupying rate calculating is reported described management end by described start node.
2. method according to claim 1, is characterized in that, the synchronous network of nodal information that described network is decentralization, and the each node in this network maintains the information of all nodes.
3. method according to claim 1 and 2, it is characterized in that, the request of described resource occupying rate statistics comprises: the source IP address and the object IP address, the initial time of statistics and the resource measurement title of end time and request statistics that receive request of initiating request.
4. method according to claim 1 and 2, is characterized in that, described range of nodes,
Comprise: the set that the set being made up of node identification or the IP address by node form.
5. method according to claim 1 and 2, it is characterized in that, point start node of described every one deck is received after the resource occupying rate statistics that jurisdiction node reports, in conjunction with the resource occupying rate statistics of this point of start node, again carry out counting statistics, comprising:
Point start node of described every one deck, in the time issuing described resource occupying rate statistics request, gathers simultaneously and calculates the resource occupying rate of this node;
When receiving after the resource occupying rate statistics that jurisdiction node reports, again carry out counting statistics according to following computing formula, obtain the statistics of this point of start node to resource occupying rate:
(this node resources occupation rate+jurisdiction node resource occupancy sum)/(1+ jurisdiction nodes).
6. method according to claim 1 and 2, is characterized in that, describedly calculates final resource occupying rate by start node, comprising:
Described start node, in the time issuing described resource occupying rate statistics request, gathers simultaneously and calculates the resource occupying rate of this node;
When receiving after the resource occupying rate statistics that jurisdiction node reports, calculate according to following computing formula, obtain final resource occupying rate:
(this node resources occupation rate+jurisdiction node resource occupancy sum)/(1+ jurisdiction nodes).
7. a network node, is characterized in that, comprising:
Receiving element, for receiving the range of nodes of the request of resource occupying rate statistics and other nodes of the affiliated set of this node, wherein, the request of described resource occupying rate statistics comprises the source IP address and the object IP address, the initial time of statistics and the resource measurement title of end time and request statistics that receive request of the request of initiation, and described range of nodes comprises the set being made up of node identification or the set being made up of the IP address of node;
Judge grouped element, be used for according to the range of nodes of other nodes of set under the request of described resource occupying rate statistics and this node, whether the number that judges other nodes in this set is greater than N, if the number of other nodes is less than or equal to N in this set, no longer this set is proceeded to grouping, other nodes in this set send respectively the request of described resource occupying rate statistics; If the number of other nodes is greater than N in this set, other nodes in this set are continued to be divided into N group, from each group, choose arbitrarily a node, send respectively the range of nodes of other nodes in the request of described resource occupying rate statistics and this group to described node;
Resources occupation rate statistic unit, for the resource occupying rate of this node is carried out to statistical report, and when receiving after the resource occupying rate statistics that jurisdiction node reports, again carry out counting statistics according to following computing formula, obtain the statistics of this node to resource occupying rate, and report this statistics: (this node resources occupation rate+jurisdiction node resource occupancy sum)/(1+ jurisdiction nodes).
8. network node according to claim 7, is characterized in that, described network node also comprises:
Nodal information lock unit, synchronous for the whole network nodal information, makes this node maintain the information of all nodes in network.
Applications Claiming Priority (1)
| Application Number | Priority Date | Filing Date | Title |
|---|---|---|---|
| PCT/CN2011/085057 WO2012109946A1 (en) | 2011-12-30 | 2011-12-30 | Data collection method of large-scale network and network node |
Publications (2)
| Publication Number | Publication Date |
|---|---|
| CN102652425A CN102652425A (en) | 2012-08-29 |
| CN102652425B true CN102652425B (en) | 2014-06-25 |
Family
ID=46671944
Family Applications (1)
| Application Number | Title | Priority Date | Filing Date |
|---|---|---|---|
| CN201180004193.2A Expired - Fee Related CN102652425B (en) | 2011-12-30 | 2011-12-30 | Data acquisition method of large-scale network and network node |
Country Status (2)
| Country | Link |
|---|---|
| CN (1) | CN102652425B (en) |
| WO (1) | WO2012109946A1 (en) |
Families Citing this family (2)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| CN102882740A (en) * | 2012-09-13 | 2013-01-16 | 曙光信息产业(北京)有限公司 | Method for centralized configuration monitoring in cloud environment |
| CN111600748B (en) * | 2020-04-28 | 2023-05-30 | 江苏方天电力技术有限公司 | Code-increasing topology identification system and method based on wireless ad hoc network |
Citations (2)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| CN101667200A (en) * | 2009-09-18 | 2010-03-10 | 浙江大学 | Window query method in P2P environment |
| CN102073695A (en) * | 2010-12-28 | 2011-05-25 | 汉柏科技有限公司 | Progressive statistical method |
Family Cites Families (3)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| TWI444006B (en) * | 2008-12-18 | 2014-07-01 | Univ Nat Taiwan | Keyword: dynamic planning; data transmission method; centralized balance tree algorithm; wireless sensor; |
| US8453156B2 (en) * | 2009-03-30 | 2013-05-28 | Intel Corporation | Method and system to perform load balancing of a task-based multi-threaded application |
| CN101958805B (en) * | 2010-09-26 | 2014-12-10 | 中兴通讯股份有限公司 | Terminal access and management method and system in cloud computing |
-
2011
- 2011-12-30 WO PCT/CN2011/085057 patent/WO2012109946A1/en active Application Filing
- 2011-12-30 CN CN201180004193.2A patent/CN102652425B/en not_active Expired - Fee Related
Patent Citations (2)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| CN101667200A (en) * | 2009-09-18 | 2010-03-10 | 浙江大学 | Window query method in P2P environment |
| CN102073695A (en) * | 2010-12-28 | 2011-05-25 | 汉柏科技有限公司 | Progressive statistical method |
Also Published As
| Publication number | Publication date |
|---|---|
| WO2012109946A1 (en) | 2012-08-23 |
| CN102652425A (en) | 2012-08-29 |
Similar Documents
| Publication | Publication Date | Title |
|---|---|---|
| CN106549806B (en) | A kind of network slice manager and its management method | |
| CN107895176B (en) | Fog calculation system and method for wide-area monitoring and diagnosis of hydroelectric machine group | |
| CN107330056B (en) | Wind power plant SCADA system based on big data cloud computing platform and operation method thereof | |
| CN108366386B (en) | Method for realizing wireless network fault detection by using neural network | |
| CN112698953A (en) | Power grid intelligent operation and detection platform based on micro-service | |
| CN101854652A (en) | Telecommunications network service performance monitoring system | |
| CN107172391A (en) | Distributed video memory management method and system based on Hadoop framework | |
| CN105099798A (en) | Online master station operation monitoring and evaluation method based on index system | |
| CN107820692A (en) | A kind of alarm synchronization method and system | |
| CN102082701B (en) | Method for storing network element positional information and apparatus for same | |
| CN117221088A (en) | Computer network intensity detection system and device | |
| CN102652425B (en) | Data acquisition method of large-scale network and network node | |
| CN102355373B (en) | Method and device for automatically troubleshooting large convergent point hidden troubles of transmission network | |
| CN103118102A (en) | System and method for counting and controlling spatial data access laws under cloud computing environment | |
| CN109165207B (en) | Drinking water mass data storage management method and system based on Hadoop | |
| CN101986608A (en) | Method for evaluating heterogeneous overlay network load balance degree | |
| CN114757448B (en) | Manufacturing inter-link optimal value chain construction method based on data space model | |
| CN106056515A (en) | Community grid event cluster feature extraction method | |
| CN110377757A (en) | A kind of real time knowledge map construction system | |
| CN115374101A (en) | Rail transit station level data management system | |
| CN103458032A (en) | Method and system for dynamic statistics and information compression of spatial data access law | |
| CN113449505A (en) | File comparison method | |
| CN204231561U (en) | Based on the power network video monitoring intelligent analyzing and alarming system of regulation and control integration | |
| CN114124662A (en) | Resource intelligent operation and maintenance system based on cross-network environment | |
| CN109495315B (en) | Metropolitan area network analysis and prediction method under big data environment and readable storage medium |
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 | ||
| TR01 | Transfer of patent right |
Effective date of registration: 20170612 Address after: 510640 Guangdong City, Tianhe District Province, No. five, road, public education building, unit 371-1, unit 2401 Patentee after: Guangdong Gaohang Intellectual Property Operation Co., Ltd. Address before: 518129 Bantian HUAWEI headquarters office building, Longgang District, Guangdong, Shenzhen Patentee before: Huawei Technologies Co., Ltd. |
|
| TR01 | Transfer of patent right | ||
| TR01 | Transfer of patent right |
Effective date of registration: 20170628 Address after: 100000, room 3, building 1, building twenty, 304 yuan an road, Beijing, Chaoyang District Patentee after: Beijing Rong Kuwait Computer Technology Co. Ltd. Address before: 510640 Guangdong City, Tianhe District Province, No. five, road, public education building, unit 371-1, unit 2401 Patentee before: Guangdong Gaohang Intellectual Property Operation Co., Ltd. |
|
| TR01 | Transfer of patent right | ||
| CF01 | Termination of patent right due to non-payment of annual fee |
Granted publication date: 20140625 Termination date: 20201230 |
|
| CF01 | Termination of patent right due to non-payment of annual fee |