CN106375419A - Deployment method and device of distributed cluster - Google Patents
Deployment method and device of distributed cluster Download PDFInfo
- Publication number
- CN106375419A CN106375419A CN201610784139.9A CN201610784139A CN106375419A CN 106375419 A CN106375419 A CN 106375419A CN 201610784139 A CN201610784139 A CN 201610784139A CN 106375419 A CN106375419 A CN 106375419A
- Authority
- CN
- China
- Prior art keywords
- node
- load factor
- distributed type
- current point
- message
- 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
- H04L67/1001—Protocols in which an application is distributed across nodes in the network for accessing one among a plurality of replicated servers
- H04L67/1031—Controlling of the operation of servers by a load balancer, e.g. adding or removing servers that serve requests
Abstract
The invention provides a deployment method and device of a distributed cluster. The deployment method of the distributed cluster comprises the steps of obtaining the number of slave nodes who send information when the information sent by the slave nodes of a server cluster are received, wherein the information is used for marking overload of the slave nodes; judging whether the ratio of the number of the slave nodes to the total number of the slave nodes is greater than or equal to a first preset threshold; and if the ratio is greater than or equal to the first preset value, building a first target slave node, wherein the first target slave node is a newly built slave node. According to the deployment method and device of the distributed cluster, as slave nodes of the server can be added dynamically based on the load conditions of the slave nodes of the server cluster, and the distributed cluster can be deployed dynamically, the purpose of flexible configuration of resources is realized, and the utilization efficiency of the server resources is increased efficiently.
Description
Technical field
The present invention relates to Internet technical field, more particularly, to a kind of dispositions method of distributed type assemblies and device.
Background technology
Under the application scenes of server in the Internet, for example, the backstage clothes of the banking system that user is usually used
Business device, is in each area in different cities or city, they need to process respectively in business due to head office and each branch
From data it is also desirable to exchange each other and process, need under this scene to dispose distributed type assemblies.In correlation technique,
When disposing distributed type assemblies, the from node number of static state setting server cluster.
Under this mode, when the from node average load of server cluster is too high it is impossible to dynamically adjust server cluster
From node number, resource cannot flexible configuration.
Content of the invention
It is contemplated that at least solving one of technical problem in correlation technique to a certain extent.
For this reason, it is an object of the present invention to proposing a kind of dispositions method of distributed type assemblies, can be according to server
The load state of the from node of cluster dynamically increases the from node of server, carries out Dynamical Deployment to distributed type assemblies, reaches money
The purpose of source flexible configuration, effectively lifts the utilization ratio of server resource.
Further object is that proposing a kind of dispositions method of distributed type assemblies.
Further object is that proposing a kind of deployment device of distributed type assemblies.
Further object is that proposing a kind of deployment device of distributed type assemblies.
For reaching above-mentioned purpose, the dispositions method of the distributed type assemblies that first aspect present invention embodiment proposes, comprising:
Receive server cluster from node send message when, obtain send described message from node number, wherein, described
Message is used for from node overload described in labelling;Judge described from node number account for the ratio of from node sum whether more than or
Equal to the first predetermined threshold value;If described ratio reaches described first predetermined threshold value, create first object from node, wherein,
Described first object from node is newly-established from node.
In one embodiment of the invention, also include:
Obtain the load factor meansigma methodss of described server cluster from node on current point in time;
Judge whether described load factor meansigma methodss are less than the second predetermined threshold value;
When described load factor meansigma methodss are less than described second predetermined threshold value, obtain the minimum from node of load factor and make
For the second target from node;
Forbid to described second target from node distribution service request.
In one embodiment of the invention, described forbid to described second target from node distribution service request after,
Also include:
The service request that whether there is in processing is detected on described second target from node;
Do not exist described process in service request when, delete described second target from node.
The dispositions method of the distributed type assemblies that first aspect present invention embodiment proposes, by accounting in the number in from node
From node sum ratio be more than or equal to the first predetermined threshold value when, create first object from node, wherein, first object from
Node be newly-established from node, can according to the load state of the from node of server cluster dynamically increase server from section
Distributed type assemblies are carried out Dynamical Deployment by point, reach the purpose of resource flexible configuration, effectively the utilization effect of lifting server resource
Rate.
For reaching above-mentioned purpose, the dispositions method of the distributed type assemblies that second aspect present invention embodiment proposes, comprising: read
Take the from node of the server cluster loading condition on current point in time, described from node is calculated according to described loading condition and exists
Load factor on described current point in time;Judge described load factor whether more than or equal to default load threshold;Institute
When stating load factor more than or equal to described default load threshold, generate the message for from node overload described in labelling, and
Send the message to management server.
In one embodiment of the invention, load on current point in time for the from node of described reading service device cluster
Situation, comprising:
Each from node reads the loading condition on current point in time according to from node mark from journal file.
In one embodiment of the invention, described journal file is obtained by following steps:
Obtain each from node of described server cluster loading condition on current point in time, and by described load feelings
Condition is corresponding with described from node mark to be write in described journal file.
Second aspect present invention embodiment propose distributed type assemblies dispositions method, by reading service device cluster from
Loading condition on current point in time for the node, calculates load factor on current point in time for the from node according to loading condition,
When load factor is more than or equal to default load threshold, generates the message for labelling from node overload, and message is sent out
Deliver to management server, Dynamical Deployment can be carried out to distributed type assemblies according to the loading condition of from node each in journal file,
Reach the purpose of resource flexible configuration, effectively lift the utilization ratio of server resource.
For reaching above-mentioned purpose, the deployment device of the distributed type assemblies that third aspect present invention embodiment proposes, comprising: the
One acquisition module, for receive server cluster from node send message when, obtain send described message from section
The number of point, wherein, described message is used for from node overload described in labelling;Judge module, for judging the individual of described from node
Whether the ratio that number accounts for from node sum is more than or equal to the first predetermined threshold value;Creation module, for reaching in described ratio
During described first predetermined threshold value, create first object from node, wherein, described first object from node is newly-established from section
Point.
In one embodiment of the invention, also include:
Second acquisition module, the load factor for obtaining described server cluster from node on current point in time is average
Value;
Second judge module, for judging whether described load factor meansigma methodss are less than the second predetermined threshold value;
3rd acquisition module, for when described load factor meansigma methodss are less than described second predetermined threshold value, obtaining load
The minimum from node of index is as the second target from node;
Disabled module, is used for forbidding to described second target from node distribution service request.
In one embodiment of the invention, also include:
Detection module, for detecting the service request that whether there is in described second target from node in processing;
Removing module, for when there is not the service request in described process, deleting described second target from node.
The deployment device of the distributed type assemblies that third aspect present invention embodiment proposes, by accounting in the number in from node
From node sum ratio be more than or equal to the first predetermined threshold value when, create first object from node, wherein, first object from
Node be newly-established from node, can according to the load state of the from node of server cluster dynamically increase server from section
Distributed type assemblies are carried out Dynamical Deployment by point, reach the purpose of resource flexible configuration, effectively the utilization effect of lifting server resource
Rate.
For reaching above-mentioned purpose, the deployment device of the distributed type assemblies that fourth aspect present invention embodiment proposes, comprising: read
Delivery block, for the loading condition on current point in time for the from node of reading service device cluster, according to described loading condition meter
Calculate load factor on described current point in time for the described from node;3rd judge module, for judging that described load factor is
No more than or equal to default load threshold;Generation module, for being more than or equal to described preset negative in described load factor
When carrying threshold value, generate the message for from node overload described in labelling, and send the message to management server.
In one embodiment of the invention, described read module specifically for:
Each from node reads the loading condition on current point in time according to from node mark from journal file.
In one embodiment of the invention, described journal file passes through to obtain with lower module:
Writing module, for obtaining each from node of described server cluster loading condition on current point in time,
And write corresponding with described from node mark for described loading condition in described journal file.
Fourth aspect present invention embodiment propose distributed type assemblies deployment device, by reading service device cluster from
Loading condition on current point in time for the node, calculates load factor on current point in time for the from node according to loading condition,
When load factor is more than or equal to default load threshold, generates the message for labelling from node overload, and message is sent out
Deliver to management server, Dynamical Deployment can be carried out to distributed type assemblies according to the loading condition of from node each in journal file,
Reach the purpose of resource flexible configuration, effectively lift the utilization ratio of server resource.
The aspect that the present invention adds and advantage will be set forth in part in the description, and partly will become from the following description
Obtain substantially, or recognized by the practice of the present invention.
Brief description
The above-mentioned and/or additional aspect of the present invention and advantage will become from the following description of the accompanying drawings of embodiments
Substantially and easy to understand, wherein:
Fig. 1 is the schematic flow sheet of the dispositions method of distributed type assemblies that one embodiment of the invention proposes;
Fig. 2 is the schematic flow sheet of the dispositions method of distributed type assemblies that another embodiment of the present invention proposes;
Fig. 3 is the schematic flow sheet of the dispositions method of distributed type assemblies that another embodiment of the present invention proposes;
Fig. 4 is the schematic flow sheet of the dispositions method of distributed type assemblies that another embodiment of the present invention proposes;
Fig. 5 is the structural representation of the deployment device of the distributed type assemblies that one embodiment of the invention proposes;
Fig. 6 is the structural representation of the deployment device of the distributed type assemblies that another embodiment of the present invention proposes;
Fig. 7 is the structural representation of the deployment device of the distributed type assemblies that another embodiment of the present invention proposes;
Fig. 8 is the structural representation of the deployment device of the distributed type assemblies that another embodiment of the present invention proposes.
Specific embodiment
Embodiments of the invention are described below in detail, the example of described embodiment is shown in the drawings, wherein from start to finish
The element that same or similar label represents same or similar element or has same or like function.Below with reference to attached
The embodiment of figure description is exemplary, is only used for explaining the present invention, and is not considered as limiting the invention.On the contrary, originally
Inventive embodiment includes falling into all changes in the range of the spirit of attached claims and intension, modification and equivalent
Thing.
Fig. 1 is the schematic flow sheet of the dispositions method of distributed type assemblies that one embodiment of the invention proposes.
The executive agent of the present embodiment can be management server.
Referring to Fig. 1, the dispositions method of this distributed type assemblies includes:
S11: in the message that the from node receiving server cluster sends, obtain the individual of the from node sending message
Number, wherein, message is used for labelling from node and transships.
Under the application scenes of server in the Internet, for example, the backstage clothes of the banking system that user is usually used
Business device, is in each area in different cities or city, they need to process respectively in business due to head office and each branch
From data it is also desirable to exchange each other and process, need under this scene to dispose distributed type assemblies.
In an embodiment of the present invention, the message that the from node of server cluster sends is used for labelling from node and transships, pipe
Reason server, in the message that the from node receiving server cluster sends, obtains the number of the from node of overload.
S12: judge that whether the number of from node accounts for the ratio of from node sum more than or equal to the first predetermined threshold value.
Wherein, the first predetermined threshold value can rule of thumb be arranged, for example, could be arranged to 0.8.
In correlation technique, when disposing distributed type assemblies, the from node number of static state setting server cluster.This mode
Under, when the from node average load of server cluster is too high it is impossible to dynamically adjust server node number, resource cannot flexibly be joined
Put.
And in embodiments of the invention, by the number judging from node account for the ratio of from node sum whether more than or
Equal to the first predetermined threshold value, when the ratio accounting for from node sum in the number of from node is more than or equal to the first predetermined threshold value,
Show that the number of the from node transshipped exceedes allowed scope, now, create first object from node, when the new service of appearance
During request, preferentially distribute to the first object from node of new establishment, thus mitigating the load pressure of other from nodes;In from node
Number account for from node sum ratio be less than the first predetermined threshold value when, show transship from node number in allowed band
Interior, now, do not make any process, can according to the load state of the from node of server cluster dynamically increase server from section
Point, reaches the purpose of resource flexible configuration, effectively lifts the utilization ratio of server resource.
S13: if ratio reaches the first predetermined threshold value, create first object from node, wherein, first object from node
For newly-established from node.
Alternatively, when the number in from node accounts for the ratio of from node sum more than or equal to the first predetermined threshold value, table
The number of the from node of bright overload exceedes allowed scope, now, creates first object from node, please when new service
When asking, preferentially distributing to the first object from node of new establishment, thus mitigating the load pressure of other from nodes, realizing to distribution
Formula cluster carries out Dynamical Deployment.
In the present embodiment, preset more than or equal to first by accounting for the ratio of from node sum in the number in from node
During threshold value, create first object from node, wherein, first object from node is newly-established from node, can be according to server
The load state of the from node of cluster dynamically increases the from node of server, carries out Dynamical Deployment to distributed type assemblies, reaches money
The purpose of source flexible configuration, effectively lifts the utilization ratio of server resource.
Fig. 2 is the schematic flow sheet of the dispositions method of distributed type assemblies that another embodiment of the present invention proposes.
The executive agent of the present embodiment can be management server.
Referring to Fig. 2, the dispositions method of this distributed type assemblies includes:
S201: in the message that the from node receiving server cluster sends, obtain the individual of the from node sending message
Number, wherein, message is used for labelling from node and transships.
S202: judge that whether the number of from node accounts for the ratio of from node sum more than or equal to the first predetermined threshold value,
If so, execute s24, otherwise, execute s23.
S203: do not make any process.
Alternatively, when the number in from node accounts for the ratio of from node sum less than the first predetermined threshold value, show overload
The number of from node, in allowed band, now, does not make any process.
S204: create first object from node, wherein, first object from node is newly-established from node.
S205: obtain the load factor meansigma methodss of server cluster from node on current point in time.
In an embodiment of the present invention, server cluster from node can be obtained on current point in time according to following formula
Load factor be:
loadfactor(serveri, t)=λ memoryusage (t)+β cpuusage (t);
Wherein, β, λ are weight factor, and β+λ=1, β, λ can rule of thumb value, memoryusage (t) is t
Memory usage, cpuusage (t) be t cpu utilization rate, i=1,2,3 ... ..., loadfactor (serveri,
T) t server cluster from node i, i.e. server are representediLoad factor.
Alternatively, on labelling current point in time, the load factor meansigma methodss of server cluster from node are
Loadfactoravg (t), then obtaining described load factor meansigma methodss according to following formula is:
In this step, by being weighted at summation to memory usage and cpu utilization rate using different weight factors
Reason, obtains the load factor of server cluster from node, can effectively lift motility and the suitability of the method.
S206: judge whether load factor meansigma methodss are less than the second predetermined threshold value, if so, execute s208, otherwise, execution
s207.
Wherein, the second predetermined threshold value can rule of thumb be arranged, for example, could be arranged to 0.2.
It is understood that when load factor meansigma methodss are less than the second predetermined threshold value, showing server cluster from node
Load too low, now, trigger step s208, load factor meansigma methodss be more than or equal to the second predetermined threshold value when, show
The load of server cluster from node in the reasonable scope, now, is left intact.
S207: do not make any process.
S208: when load factor meansigma methodss are less than the second predetermined threshold value, obtain the minimum from node conduct of load factor
Second target from node.
Alternatively, when load factor meansigma methodss are less than the second predetermined threshold value, show the load of server cluster from node
Too low, now, obtain the minimum from node of load factor as the second target from node, no longer distribute to the second target from node
Service request.
S209 forbids distributing service request to the second target from node.
S210: with the presence or absence of the service request in processing in detection the second target from node.
Alternatively, with the presence or absence of the service request in processing in detection the second target from node, in the second target from node
On deposit in processes service request when, wait the second target from node to be deleted, in the second target from section after being disposed
When service request in processes is not deposited on point, directly delete the second target from node, thus realizing the dynamic configuration of resource.
S211: when not depositing service request in processes, delete the second target from node.
In this step, during by service request in processes not being deposited on the second target from node, delete the second target
From node, can dynamically delete the minimum from node of load factor according to the load factor of the from node of server cluster, to point
Cloth cluster carries out Dynamical Deployment, reaches the purpose of resource flexible configuration, effectively lifts the utilization ratio of server resource.
In the present embodiment, preset more than or equal to first by accounting for the ratio of from node sum in the number in from node
During threshold value, create first object from node, wherein, first object from node is newly-established from node, can be according to server
The load state of the from node of cluster dynamically increases the from node of server, carries out Dynamical Deployment to distributed type assemblies, reaches money
The purpose of source flexible configuration, effectively lifts the utilization ratio of server resource.By being made to internal memory using different weight factors
It is weighted summation process with rate and cpu utilization rate, obtains the load factor of server cluster from node, can effectively lift this
The motility of method is the suitability.It is less than the by the load factor meansigma methodss of server cluster from node on current point in time
During two predetermined threshold value, forbid to the minimum from node of load factor, i.e. the second target from node distribution service request, and second
When target from node does not deposit service request in processes, delete the second target from node, can according to server cluster from
The load factor of node dynamically deletes the minimum from node of load factor, carries out Dynamical Deployment to distributed type assemblies, reaches resource
The purpose of flexible configuration, effectively lifts the utilization ratio of server resource.
Fig. 3 is the schematic flow sheet of the dispositions method of distributed type assemblies that another embodiment of the present invention proposes.
The executive agent of the present embodiment can be server cluster.
Referring to Fig. 3, the dispositions method of this distributed type assemblies includes:
S31: loading condition on current point in time for the from node of reading service device cluster, according to loading condition calculate from
Load factor on current point in time for the node.
In an embodiment of the present invention, loading condition on current point in time for the from node of reading service device cluster, bag
Include: each from node reads the loading condition on current point in time according to from node mark from journal file.
Wherein, journal file is pre-configured with, by obtaining each from node of server cluster in current point in time
On loading condition, and by loading condition and from node mark corresponding write journal file in.
In an embodiment of the present invention, server cluster from node can be obtained on current point in time according to following formula
Load factor be:
loadfactor(serveri, t)=λ memoryusage (t)+β cpuusage (t);
Wherein, β, λ are weight factor, and β+λ=1, β, λ can rule of thumb value, memoryusage (t) is t
Memory usage, cpuusage (t) be t cpu utilization rate, i=1,2,3 ... ..., serveriFor server cluster
From node mark, loadfactor (serveri, t) represent the load factor of t server cluster from node i.
S32: judge load factor whether more than or equal to default load threshold.
Wherein, default load threshold can pre-set, default load threshold be used for labelling server cluster from
Whether node transships on current point in time.
Alternatively, judge that load factor, whether more than or equal to default load threshold, is less than preset negative in load factor
When carrying threshold value, show that the from node of server cluster is not transshipped on current point in time, now, do not make any process;Negative
When load index is more than or presets load threshold, show that the from node of server cluster is transshipped on current point in time, this
When, generate the message for labelling from node overload.
S33: when load factor is more than or equal to default load threshold, generate disappearing for labelling from node overload
Breath, and send a message to management server.
Alternatively, when load factor is more than or presets load threshold, the from node showing server cluster is current
Transship on time point, now, generate the message for labelling from node overload, and send a message to management server.
In the present embodiment, by loading condition on current point in time for the from node of reading service device cluster, according to negative
Load situation calculates load factor on current point in time for the from node, is more than or equal to default load threshold in load factor
When, generate the message for labelling from node overload, and send a message to management server, can be according to each in journal file
The loading condition of from node carries out Dynamical Deployment to distributed type assemblies, reaches the purpose of resource flexible configuration, effectively lifting service
The utilization ratio of device resource.
Fig. 4 is the schematic flow sheet of the dispositions method of distributed type assemblies that another embodiment of the present invention proposes.
Referring to Fig. 4, the dispositions method of this distributed type assemblies includes:
S401: loading condition on current point in time for the from node of server cluster reading service device cluster.
S402: load factor on current point in time for the from node is calculated according to loading condition.
S403: judge load factor whether more than or equal to default load threshold.
S404: when load factor is more than or equal to default load threshold, generate disappearing for labelling from node overload
Breath, and send a message to management server.
The message that the from node of s405: management server the reception server cluster sends.
S406: obtain the number of the from node sending message, wherein, message is used for labelling from node and transships.
S407: judge that whether the number of from node accounts for the ratio of from node sum more than or equal to the first predetermined threshold value.
S408: if ratio reaches the first predetermined threshold value, create first object from node, wherein, first object is from section
Point is newly-established from node.
S409: obtain the load factor meansigma methodss of server cluster from node on current point in time.
S410: judge whether load factor meansigma methodss are less than the second predetermined threshold value.
S411: when load factor meansigma methodss are less than the second predetermined threshold value, obtain the minimum from node conduct of load factor
Second target from node.
S412: forbid distributing service request to the second target from node.
S413: with the presence or absence of the service request in processing in detection the second target from node.
S414: when not depositing service request in processes, delete the second target from node.
The implementation procedure of the present embodiment may refer to the embodiment shown in Fig. 1-Fig. 3, will not be described here.
In the present embodiment, by loading condition on current point in time for the from node of reading service device cluster, according to negative
Load situation calculates load factor on current point in time for the from node, is more than or equal to default load threshold in load factor
When, generate the message for labelling from node overload, and send a message to management server, can be according to each in journal file
The loading condition of from node carries out Dynamical Deployment to distributed type assemblies, reaches the purpose of resource flexible configuration, effectively lifting service
The utilization ratio of device resource.It is more than or equal to the first default threshold by accounting for the ratio of from node sum in the number in from node
During value, create first object from node, wherein, first object from node is newly-established from node, can be according to server set
The load state of the from node of group dynamically increases the from node of server, carries out Dynamical Deployment to distributed type assemblies, reaches resource
The purpose of flexible configuration, effectively lifts the utilization ratio of server resource.By being used to internal memory using different weight factors
Rate and cpu utilization rate are weighted summation process, obtain the load factor of server cluster from node, can effectively lift the party
The motility of method is the suitability.It is less than second by the load factor meansigma methodss of server cluster from node on current point in time
During predetermined threshold value, forbid the from node to load factor minimum, i.e. the second target from node distribution service request, and in the second mesh
When mark from node does not deposit service request in processes, delete the second target from node, can be according to server cluster from section
The load factor of point dynamically deletes the minimum from node of load factor, and distributed type assemblies are carried out with Dynamical Deployment, reaches resource spirit
The purpose of configuration alive, effectively lifts the utilization ratio of server resource.
Fig. 5 is the structural representation of the deployment device of the distributed type assemblies that one embodiment of the invention proposes.This distributed collection
The deployment device 500 of group can be by software, hardware or both be implemented in combination with.
Referring to Fig. 5, the deployment device 500 of this distributed type assemblies may include that the first acquisition module 510, judge module
520, and creation module 530.Wherein,
First acquisition module 510, for when receiving the message of from node transmission of server cluster, obtaining transmission and disappearing
The number of the from node of breath, wherein, message is used for labelling from node and transships.
First judge module 520, whether the ratio that the number for judging from node accounts for from node sum is more than or waits
In the first predetermined threshold value.
Creation module 530, for when ratio reaches the first predetermined threshold value, creating first object from node, wherein, first
Target from node is newly-established from node.
In some embodiments, referring to Fig. 6, the deployment device 500 of this distributed type assemblies can also include:
Second acquisition module 540, for obtaining the load factor meansigma methodss of server cluster from node on current point in time.
Second judge module 550, for judging whether load factor meansigma methodss are less than the second predetermined threshold value.
3rd acquisition module 560, for when load factor meansigma methodss are less than the second predetermined threshold value, obtaining load factor
Little from node is as the second target from node.
Disabled module 570, is used for forbidding distributing service request to the second target from node.
Detection module 580, for detecting the service request that whether there is in the second target from node in processing.
Removing module 590, for when not depositing service request in processes, deleting the second target from node.
It should be noted that explaining to the dispositions method embodiment of distributed type assemblies in earlier figures 1- Fig. 2 embodiment
The bright deployment device being also applied for this distributed type assemblies, it is realized principle and is similar to, and here is omitted.
In the present embodiment, preset more than or equal to first by accounting for the ratio of from node sum in the number in from node
During threshold value, create first object from node, wherein, first object from node is newly-established from node, can be according to server
The load state of the from node of cluster dynamically increases the from node of server, carries out Dynamical Deployment to distributed type assemblies, reaches money
The purpose of source flexible configuration, effectively lifts the utilization ratio of server resource.
Fig. 7 is the structural representation of the deployment device of the distributed type assemblies that another embodiment of the present invention proposes.This is distributed
The deployment device 700 of cluster can be by software, hardware or both be implemented in combination with.
Referring to Fig. 7, the deployment device 700 of this distributed type assemblies may include that read module 710, the 3rd judge module
720, and generation module 730.Wherein,
Read module 710, for the loading condition on current point in time for the from node of reading service device cluster, according to negative
Load situation calculates load factor on current point in time for the from node.
Whether the 3rd judge module 720, for judging load factor more than or equal to default load threshold.
Generation module 730, for when load factor is more than or equal to default load threshold, generating for labelling from section
The message of point overload, and send a message to management server.
In some embodiments, referring to Fig. 8, the deployment device 700 of this distributed type assemblies can also include:
Alternatively, read module 710 specifically for:
Each from node reads the loading condition on current point in time according to from node mark from journal file.
Alternatively, journal file passes through to obtain with lower module:
Writing module 740, for obtaining each from node of server cluster loading condition on current point in time, and
Write corresponding with from node mark for loading condition in journal file.
It should be noted that the explanation to the dispositions method embodiment of distributed type assemblies in aforementioned Fig. 3 embodiment
It is applied to the deployment device of this distributed type assemblies, it is realized principle and is similar to, and here is omitted.
In the present embodiment, by loading condition on current point in time for the from node of reading service device cluster, according to negative
Load situation calculates load factor on current point in time for the from node, is more than or equal to default load threshold in load factor
When, generate the message for labelling from node overload, and send a message to management server, can be according to each in journal file
The loading condition of from node carries out Dynamical Deployment to distributed type assemblies, reaches the purpose of resource flexible configuration, effectively lifting service
The utilization ratio of device resource.
It should be noted that in describing the invention, term " first ", " second " etc. are only used for describing purpose, and not
It is understood that as indicating or implying relative importance.Additionally, in describing the invention, unless otherwise stated, the implication of " multiple "
It is two or more.
In flow chart or here any process described otherwise above or method description are construed as, represent and include
The module of the code of executable instruction of one or more steps for realizing specific logical function or process, fragment or portion
Point, and the scope of the preferred embodiment of the present invention includes other realization, wherein can not press shown or discuss suitable
Sequence, including according to involved function by substantially simultaneously in the way of or in the opposite order, carry out perform function, this should be by the present invention
Embodiment person of ordinary skill in the field understood.
It should be appreciated that each several part of the present invention can be realized with hardware, software, firmware or combinations thereof.Above-mentioned
In embodiment, the software that multiple steps or method can be executed in memory and by suitable instruction execution system with storage
Or firmware is realizing.For example, if realized with hardware, and the same in another embodiment, can use well known in the art under
Any one of row technology or their combination are realizing: have the logic gates for data signal is realized with logic function
Discrete logic, there is the special IC of suitable combinational logic gate circuit, programmable gate array (pga), scene
Programmable gate array (fpga) etc..
Those skilled in the art are appreciated that to realize all or part step that above-described embodiment method carries
Suddenly the program that can be by completes come the hardware to instruct correlation, and described program can be stored in a kind of computer-readable storage medium
In matter, this program upon execution, including one or a combination set of the step of embodiment of the method.
Additionally, can be integrated in a processing module in each functional unit in each embodiment of the present invention it is also possible to
It is that unit is individually physically present it is also possible to two or more units are integrated in a module.Above-mentioned integrated mould
Block both can be to be realized in the form of hardware, it would however also be possible to employ the form of software function module is realized.Described integrated module is such as
Fruit using in the form of software function module realize and as independent production marketing or use when it is also possible to be stored in a computer
In read/write memory medium.
Storage medium mentioned above can be read only memory, disk or CD etc..
In the description of this specification, reference term " embodiment ", " some embodiments ", " example ", " specifically show
The description of example " or " some examples " etc. means specific features, structure, material or the spy describing with reference to this embodiment or example
Point is contained at least one embodiment or the example of the present invention.In this manual, to the schematic representation of above-mentioned term not
Necessarily refer to identical embodiment or example.And, the specific features of description, structure, material or feature can be any
One or more embodiments or example in combine in an appropriate manner.
Although embodiments of the invention have been shown and described above it is to be understood that above-described embodiment is example
Property it is impossible to be interpreted as limitation of the present invention, those of ordinary skill in the art within the scope of the invention can be to above-mentioned
Embodiment is changed, changes, replacing and modification.
Claims (10)
1. a kind of dispositions method of distributed type assemblies is it is characterised in that comprise the following steps:
In the message that the from node receiving server cluster sends, obtain the number of the from node sending described message, its
In, described message is used for from node overload described in labelling;
Judge that whether the number of described from node accounts for the ratio of from node sum more than or equal to the first predetermined threshold value;
If described ratio reaches described first predetermined threshold value, create first object from node, wherein, described first object from
Node is newly-established from node.
2. the dispositions method of distributed type assemblies as claimed in claim 1 is it is characterised in that also include:
Obtain the load factor meansigma methodss of described server cluster from node on current point in time;
Judge whether described load factor meansigma methodss are less than the second predetermined threshold value;
When described load factor meansigma methodss are less than described second predetermined threshold value, obtain the minimum from node of load factor as the
Two target from nodes;
Forbid to described second target from node distribution service request.
3. a kind of dispositions method of distributed type assemblies is it is characterised in that comprise the following steps:
Loading condition on current point in time for the from node of reading service device cluster, according to described loading condition calculate described in from
Load factor on described current point in time for the node;
Judge described load factor whether more than or equal to default load threshold;
When described load factor is more than or equal to described default load threshold, generate for from node overload described in labelling
Message, and send the message to management server.
4. distributed type assemblies as claimed in claim 3 dispositions method it is characterised in that described reading service device cluster from
Loading condition on current point in time for the node, comprising:
Each from node reads the loading condition on current point in time according to from node mark from journal file.
5. the dispositions method of distributed type assemblies as claimed in claim 4 is it is characterised in that described journal file is by following step
Rapid acquisition:
Obtain each from node of described server cluster loading condition on current point in time, and by described loading condition and
Described from node mark is corresponding to be write in described journal file.
6. a kind of deployment device of distributed type assemblies is it is characterised in that include:
First acquisition module, for when receiving the message of from node transmission of server cluster, obtaining and sending described message
From node number, wherein, described message be used for described in labelling from node overload;
First judge module, the number for judging described from node accounts for the ratio of from node sum whether more than or equal to the
One predetermined threshold value;
Creation module, for when described ratio reaches described first predetermined threshold value, creating first object from node, wherein, institute
Stating first object from node is newly-established from node.
7. the deployment device of distributed type assemblies as claimed in claim 6 is it is characterised in that also include:
Second acquisition module, for obtaining the load factor meansigma methodss of described server cluster from node on current point in time;
Second judge module, for judging whether described load factor meansigma methodss are less than the second predetermined threshold value;
3rd acquisition module, for when described load factor meansigma methodss are less than described second predetermined threshold value, obtaining load factor
Minimum from node is as the second target from node;
Disabled module, is used for forbidding to described second target from node distribution service request.
8. a kind of deployment device of distributed type assemblies is it is characterised in that include:
Read module, for the loading condition on current point in time for the from node of reading service device cluster, according to described load
Situation calculates load factor on described current point in time for the described from node;
Whether the 3rd judge module, for judging described load factor more than or equal to default load threshold;
Generation module, for when described load factor is more than or equal to described default load threshold, generating for labelling institute
State the message of from node overload, and send the message to management server.
9. distributed type assemblies as claimed in claim 8 deployment device it is characterised in that described read module specifically for:
Each from node reads the loading condition on current point in time according to from node mark from journal file.
10. the deployment device of distributed type assemblies as claimed in claim 9 is it is characterised in that described journal file is by following
Module obtains:
Writing module, for obtaining each from node of described server cluster loading condition on current point in time, and will
Described loading condition is corresponding with described from node mark to be write in described journal file.
Priority Applications (1)
Application Number | Priority Date | Filing Date | Title |
---|---|---|---|
CN201610784139.9A CN106375419A (en) | 2016-08-31 | 2016-08-31 | Deployment method and device of distributed cluster |
Applications Claiming Priority (1)
Application Number | Priority Date | Filing Date | Title |
---|---|---|---|
CN201610784139.9A CN106375419A (en) | 2016-08-31 | 2016-08-31 | Deployment method and device of distributed cluster |
Publications (1)
Publication Number | Publication Date |
---|---|
CN106375419A true CN106375419A (en) | 2017-02-01 |
Family
ID=57899467
Family Applications (1)
Application Number | Title | Priority Date | Filing Date |
---|---|---|---|
CN201610784139.9A Pending CN106375419A (en) | 2016-08-31 | 2016-08-31 | Deployment method and device of distributed cluster |
Country Status (1)
Country | Link |
---|---|
CN (1) | CN106375419A (en) |
Cited By (8)
Publication number | Priority date | Publication date | Assignee | Title |
---|---|---|---|---|
CN107147547A (en) * | 2017-07-10 | 2017-09-08 | 山东超越数控电子有限公司 | A kind of cluster overall performance monitoring implementation method |
CN109361743A (en) * | 2018-09-30 | 2019-02-19 | 北京金山安全软件有限公司 | Data synchronization method and device, electronic equipment and storage medium |
CN109936473A (en) * | 2017-12-19 | 2019-06-25 | 华耀(中国)科技有限公司 | Distributed computing system and its operation method based on deep learning prediction |
CN110019503A (en) * | 2017-09-01 | 2019-07-16 | 北京京东尚科信息技术有限公司 | The dilatation of Redis cluster and/or the method and device of capacity reducing |
CN110955528A (en) * | 2019-12-31 | 2020-04-03 | 智业软件股份有限公司 | System and method for processing high-concurrency request by external connection service |
CN112019583A (en) * | 2019-05-31 | 2020-12-01 | 北京京东尚科信息技术有限公司 | Method, device and storage medium for determining utilization rate of server cluster resources |
CN112243024A (en) * | 2020-09-17 | 2021-01-19 | 北京金山云网络技术有限公司 | Service control method, device, server and storage medium |
CN113791902A (en) * | 2021-08-31 | 2021-12-14 | 北京达佳互联信息技术有限公司 | Data processing method and device, electronic equipment and storage medium |
Citations (9)
Publication number | Priority date | Publication date | Assignee | Title |
---|---|---|---|---|
CN101014002A (en) * | 2006-12-12 | 2007-08-08 | 华为技术有限公司 | Cluster message transmitting method and distributed cluster system |
CN102426545A (en) * | 2010-10-27 | 2012-04-25 | 微软公司 | Reactive load balancing for distributed systems |
CN102868763A (en) * | 2012-10-08 | 2013-01-09 | 山东省计算中心 | Energy-saving dynamic adjustment method of virtual web application cluster in cloud computing environment |
CN103581039A (en) * | 2013-11-08 | 2014-02-12 | 西安电子科技大学宁波信息技术研究院 | Dynamic load balancing structure of server cluster and application method thereof |
CN103634394A (en) * | 2013-11-28 | 2014-03-12 | 中国科学院信息工程研究所 | Data flow processing-oriented elastic expandable resource managing method and system |
CN103685461A (en) * | 2013-10-24 | 2014-03-26 | 从兴技术有限公司 | Cluster management device, system and method |
CN103812949A (en) * | 2014-03-06 | 2014-05-21 | 中国科学院信息工程研究所 | Task scheduling and resource allocation method and system for real-time cloud platform |
CN104753817A (en) * | 2013-12-25 | 2015-07-01 | 中国移动通信集团公司 | Local analogy method and local analogy system for cloud computing message queue service |
CN105159775A (en) * | 2015-08-05 | 2015-12-16 | 浪潮(北京)电子信息产业有限公司 | Load balancer based management system and management method for cloud computing data center |
-
2016
- 2016-08-31 CN CN201610784139.9A patent/CN106375419A/en active Pending
Patent Citations (9)
Publication number | Priority date | Publication date | Assignee | Title |
---|---|---|---|---|
CN101014002A (en) * | 2006-12-12 | 2007-08-08 | 华为技术有限公司 | Cluster message transmitting method and distributed cluster system |
CN102426545A (en) * | 2010-10-27 | 2012-04-25 | 微软公司 | Reactive load balancing for distributed systems |
CN102868763A (en) * | 2012-10-08 | 2013-01-09 | 山东省计算中心 | Energy-saving dynamic adjustment method of virtual web application cluster in cloud computing environment |
CN103685461A (en) * | 2013-10-24 | 2014-03-26 | 从兴技术有限公司 | Cluster management device, system and method |
CN103581039A (en) * | 2013-11-08 | 2014-02-12 | 西安电子科技大学宁波信息技术研究院 | Dynamic load balancing structure of server cluster and application method thereof |
CN103634394A (en) * | 2013-11-28 | 2014-03-12 | 中国科学院信息工程研究所 | Data flow processing-oriented elastic expandable resource managing method and system |
CN104753817A (en) * | 2013-12-25 | 2015-07-01 | 中国移动通信集团公司 | Local analogy method and local analogy system for cloud computing message queue service |
CN103812949A (en) * | 2014-03-06 | 2014-05-21 | 中国科学院信息工程研究所 | Task scheduling and resource allocation method and system for real-time cloud platform |
CN105159775A (en) * | 2015-08-05 | 2015-12-16 | 浪潮(北京)电子信息产业有限公司 | Load balancer based management system and management method for cloud computing data center |
Cited By (11)
Publication number | Priority date | Publication date | Assignee | Title |
---|---|---|---|---|
CN107147547A (en) * | 2017-07-10 | 2017-09-08 | 山东超越数控电子有限公司 | A kind of cluster overall performance monitoring implementation method |
CN110019503A (en) * | 2017-09-01 | 2019-07-16 | 北京京东尚科信息技术有限公司 | The dilatation of Redis cluster and/or the method and device of capacity reducing |
CN109936473A (en) * | 2017-12-19 | 2019-06-25 | 华耀(中国)科技有限公司 | Distributed computing system and its operation method based on deep learning prediction |
CN109936473B (en) * | 2017-12-19 | 2022-04-08 | 北京华耀科技有限公司 | Deep learning prediction-based distributed computing system and operation method thereof |
CN109361743A (en) * | 2018-09-30 | 2019-02-19 | 北京金山安全软件有限公司 | Data synchronization method and device, electronic equipment and storage medium |
CN109361743B (en) * | 2018-09-30 | 2021-06-04 | 北京聚云立方科技有限公司 | Data synchronization method and device, electronic equipment and storage medium |
CN112019583A (en) * | 2019-05-31 | 2020-12-01 | 北京京东尚科信息技术有限公司 | Method, device and storage medium for determining utilization rate of server cluster resources |
CN110955528A (en) * | 2019-12-31 | 2020-04-03 | 智业软件股份有限公司 | System and method for processing high-concurrency request by external connection service |
CN112243024A (en) * | 2020-09-17 | 2021-01-19 | 北京金山云网络技术有限公司 | Service control method, device, server and storage medium |
CN112243024B (en) * | 2020-09-17 | 2022-05-06 | 北京金山云网络技术有限公司 | Service control method, device, server and storage medium |
CN113791902A (en) * | 2021-08-31 | 2021-12-14 | 北京达佳互联信息技术有限公司 | Data processing method and device, electronic equipment and storage medium |
Similar Documents
Publication | Publication Date | Title |
---|---|---|
CN106375419A (en) | Deployment method and device of distributed cluster | |
CN103778007B (en) | A kind of application management method and device | |
CN106302574B (en) | A kind of service availability management method, device and its network function virtualization architecture | |
CN106603846A (en) | Method for transmitting file and smartphone | |
CN107894920A (en) | Resource allocation method and Related product | |
CN106161076A (en) | Virtual network function extended method and device | |
CN106230997A (en) | A kind of resource regulating method and device | |
CN108804113A (en) | Dispose the method, apparatus and storage medium and electronic equipment that micro services are applied | |
CN105991408A (en) | Message processing method, message processing device and processing server | |
CN106227865A (en) | A kind of display application drawing calibration method and terminal | |
CN108829433A (en) | A kind of web system version dispositions method, equipment and storage medium | |
CN106714123A (en) | Message transmission method and communication device | |
CN106504014A (en) | A kind of moving advertising cloud management platform | |
CN105786399B (en) | A kind of data conversion storage method, apparatus and system | |
CN109218401A (en) | Log collection method, system, computer equipment and storage medium | |
CN105893471A (en) | Data processing method and electronic equipment | |
CN102123511A (en) | Mobile network data transmission method and system as well as mobile terminal | |
CN107943423A (en) | The management method and computer-readable recording medium of storage resource in cloud system | |
CN106372822A (en) | Service object reservation period processing method and apparatus | |
CN106878990B (en) | A kind of information-pushing method and device | |
CN105611519A (en) | Packet gateway enterprise-level charging method and packet gateway enterprise-level charging device | |
CN106874438A (en) | A kind of desktop folder merging method and system | |
US20210382872A1 (en) | Blockchain-based Data Storage Method, Related Device and Storage Medium | |
CN107249021A (en) | Method of data synchronization, device, storage medium, computer equipment and server | |
CN113342776B (en) | Transaction information migration method, device, equipment and medium based on intelligent contract |
Legal Events
Date | Code | Title | Description |
---|---|---|---|
C06 | 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: 20170201 |
|
RJ01 | Rejection of invention patent application after publication |