CN106817408A - A kind of distributed server cluster dispatching method and device - Google Patents
A kind of distributed server cluster dispatching method and device Download PDFInfo
- Publication number
- CN106817408A CN106817408A CN201611229087.5A CN201611229087A CN106817408A CN 106817408 A CN106817408 A CN 106817408A CN 201611229087 A CN201611229087 A CN 201611229087A CN 106817408 A CN106817408 A CN 106817408A
- Authority
- CN
- China
- Prior art keywords
- server
- client
- task
- cluster
- state
- Prior art date
- Legal status (The legal status is an assumption and is not a legal conclusion. Google has not performed a legal analysis and makes no representation as to the accuracy of the status listed.)
- Granted
Links
Classifications
-
- H—ELECTRICITY
- H04—ELECTRIC COMMUNICATION TECHNIQUE
- H04L—TRANSMISSION OF DIGITAL INFORMATION, e.g. TELEGRAPHIC COMMUNICATION
- H04L67/00—Network arrangements or protocols for supporting network services or applications
- H04L67/01—Protocols
- H04L67/10—Protocols in which an application is distributed across nodes in the network
- H04L67/104—Peer-to-peer [P2P] networks
- H04L67/1044—Group management mechanisms
-
- H—ELECTRICITY
- H04—ELECTRIC COMMUNICATION TECHNIQUE
- H04L—TRANSMISSION OF DIGITAL INFORMATION, e.g. TELEGRAPHIC COMMUNICATION
- H04L41/00—Arrangements for maintenance, administration or management of data switching networks, e.g. of packet switching networks
- H04L41/06—Management of faults, events, alarms or notifications
- H04L41/0654—Management of faults, events, alarms or notifications using network fault recovery
- H04L41/0668—Management of faults, events, alarms or notifications using network fault recovery by dynamic selection of recovery network elements, e.g. replacement by the most appropriate element after failure
-
- 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
- H04L43/10—Active monitoring, e.g. heartbeat, ping or trace-route
-
- 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
- H04L43/16—Threshold monitoring
-
- 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
- H04L67/1095—Replication or mirroring of data, e.g. scheduling or transport for data synchronisation between network nodes
-
- H—ELECTRICITY
- H04—ELECTRIC COMMUNICATION TECHNIQUE
- H04L—TRANSMISSION OF DIGITAL INFORMATION, e.g. TELEGRAPHIC COMMUNICATION
- H04L67/00—Network arrangements or protocols for supporting network services or applications
- H04L67/50—Network services
- H04L67/60—Scheduling or organising the servicing of application requests, e.g. requests for application data transmissions using the analysis and optimisation of the required network resources
Landscapes
- Engineering & Computer Science (AREA)
- Computer Networks & Wireless Communication (AREA)
- Signal Processing (AREA)
- Physics & Mathematics (AREA)
- Computing Systems (AREA)
- Mathematical Physics (AREA)
- Theoretical Computer Science (AREA)
- Health & Medical Sciences (AREA)
- Cardiology (AREA)
- General Health & Medical Sciences (AREA)
- Hardware Redundancy (AREA)
- Multi Processors (AREA)
Abstract
The invention discloses a kind of distributed server cluster dispatching method and device, it is related to operation platform administrative skill field, method includes:Master server receives the execution message that the webserver sends through Message Queuing server, wherein, performing message includes the corresponding waiting task of each client-server;Master server obtain from server cluster each from the state of server, at least two from server are included from server cluster;Quantity of the master server according to the client-server of waiting task, the max-thresholds from server calls client-server and each from the state of server, it is determined that need to call from server;Master server the corresponding waiting task of each client-server performed in message is distributed to need to call from server.The embodiment of the present invention in invoking server cluster by, from device is taken, task to be quickly handed down to the corresponding client executing task of task so that utilizing for client is maximized, and realizes High Availabitity.
Description
Technical field
The present invention relates to operation platform administrative skill field, more particularly to a kind of distributed server cluster dispatching method and
Device.
Background technology
Distributed data base system has become the key areas of information processing subject, among developing rapidly, has
As follows a little:1st, it can solve the problems, such as organization's dispersion and data need to connect each other.Such as banking system, head office with
Each area of each branch in different cities or city, they need to process respective data in business, it is also desirable to
Exchange and treatment each other, this is accomplished by distributed system.If the 2, organization needs to increase new relative
Autonomous organization unit carrys out extension mechanism, then distributed data base system can be entered in the case of on current facility influence minimum
Row expands.3rd, the need for equally loaded.Using making topical application reach maximum, this is caused between processor for the decomposition of data
Interfere and be preferably minimized.It is supported between processor and shares, critical bottleneck can be avoided.4th, when existing in existing mechanism
Several Database Systems, and when realizing the necessity increase of global application, it is possible to it is made up of from bottom to top these databases
Distributed data base system.5th, the distributed data base system of equal scale will not be than centralized number on the probability for breaking down
It is low according to storehouse system, but because the influence of its failure is only limitted to local data's application, therefore its reliability for whole system
It is comparing high.
With the rapid growth of business event, the quantity of server and growing day by day to the maintenance needs of server, but
To use single-unit point server in the prior art as task dispatching platform, lack high availability mechanism, tasks carrying it is slow, cannot
Computer group is efficiently managed in time.
Therefore, in sum, method that is a kind of effective and efficiently issuing task can not be provided in the prior art.
The content of the invention
The present invention provides a kind of distributed server cluster dispatching method and device, for solving to carry in the prior art
For the problem of method that is a kind of effective and efficiently issuing task.
The embodiment of the present invention provides a kind of distributed server cluster dispatching method, and methods described includes:
Master server receives the execution message that the webserver sends through Message Queuing server, wherein, the execution disappears
Breath includes the corresponding waiting task of each client-server;
The master server obtains from server cluster each state from server, wherein, it is described from server set
Group includes at least two from server;
The master server is according to the quantity of the client-server of waiting task, described from server calls client
The max-thresholds of server and each described state from server, it is determined that need to call from server;
The corresponding waiting task of each client-server in the execution message is distributed to institute by the master server
State need to call from server.
In the embodiment of the present invention, master server after waiting task is received, according to from server cluster from clothes
It is engaged in the state of device, task quantity, the max-thresholds of each client that can be called from server, each is present from server
Running status, it is determined that need to call from server, and task is handed down to these from server.In the embodiment of the present invention, lead to
Cross call in server cluster from device is taken, task can be quickly handed down to the corresponding client executing task of task so that visitor
Utilizing for family end is maximized, and can be when having from server cluster from server fail, additionally it is possible to will smoothly be appointed
Business is handed down to client, realizes High Availabitity.
Further, the master server by it is described execution message in the corresponding waiting task of each client-server
Be distributed to it is described need call from server, including:
The corresponding waiting task cutting of each client-server in the execution message is each by the master server
It is described need call from the corresponding task list of server, and by the task list be sent to correspondence the need for call from
Server;
The corresponding waiting task of each client-server in the execution message is distributed to institute by the master server
State need call from after server, also include:
For each needs call from server, the needs call from server according to receive task list adjust
Use corresponding client-server;It is described to need the receiving the client-server from server of the task called to process knot
Really, and by the task result webserver is sent to by the Message Queuing server.
In the embodiment of the present invention, the task that master server will get be handed down to calling task correspondence client from service
Device, so as to can determine which client executing task called from server.
Further, the master server obtains from server cluster each state from server, including:
Management server obtains each state from server from server cluster;
The management server is by each from the state synchronized of server at least one standby management server;
The master server determines whether the running status of the management server is normal;
If the master server determines the management server abnormal state, described at least one standby management clothes are called
Any one in business device, obtains each state from server from server cluster.
In the embodiment of the present invention, management server can be by each from the state synchronized of server to standby management server
In, when management server breaks down, can also in time to get each state from server, realizing height can
With.
Further, the management server obtains from server cluster each state from server, including:
For from any one in server cluster from server, if the management server can not in setting time
Get the heartbeat detection information from server, it is determined that the abnormal state from server.
In the embodiment of the present invention, each is connected by heartbeat detection information from server with management server, if management
Server can not receive certain heartbeat detection message from server in setting time, then it is assumed that should can not make from server
With, then master server inquire about state when, the status information from server is no longer provided.
Further, methods described also includes:
If the master server determine it is described from server cluster each from the utilization rate of server be equal to it is described most
During big threshold value, then increase newly from server, it is described to increase newly from server registration in the management server.
In the embodiment of the present invention, when it is determined that the existing requirement that can not have met task treatment from server cluster, then move
State increases from server, realizes scalability.
The present invention also provides a kind of distributed server cluster dispatching device, including:
Receiving unit, for receiving the execution message that the webserver sends through Message Queuing server, wherein, it is described to hold
Row message includes the corresponding waiting task of each client-server;
Acquiring unit, for obtaining from server cluster each state from server, wherein, it is described from server set
Group includes at least two from server;
Determining unit, it is quantity for the client-server according to waiting task, described from server calls client
Hold the max-thresholds and each described state from server of server, it is determined that need to call from server;
Transmitting element, for the corresponding waiting task of each client-server in the execution message to be distributed into institute
State need to call from server.
In the embodiment of the present invention, by, from device is taken, task can be quickly handed down into task pair in invoking server cluster
The client executing task answered so that utilizing for client is maximized, and can be sent out have from server cluster from server
During raw failure, additionally it is possible to task smoothly is handed down into client, High Availabitity is realized.
Further, the determining unit, specifically for:
By the corresponding waiting task cutting of each client-server in the execution message for each needs are called
Called from the corresponding task list of server, and the need for the task list is sent into correspondence from server;
Task list according to receiving calls corresponding client-server;Receive at the task of the client-server
Reason result, and the task result is sent to the webserver by the Message Queuing server.
Further, the acquiring unit, specifically for:
Obtain each state from server from server cluster;
By each from the state synchronized of server at least one standby management server;
Determine whether the running status of the management server is normal;
If it is determined that the management server abnormal state, then call any in described at least one standby management server
One, obtain each state from server from server cluster.
Further, the acquiring unit, specifically for:
For from any one in server cluster from server, if can not be got in setting time described from clothes
The heartbeat detection information of business device, it is determined that the abnormal state from server.
Further, described device also includes:
Dynamic adding unit, for if it is determined that it is described from server cluster each be equal to institute from the utilization rate of server
When stating max-thresholds, then increase newly from server, it is described to increase newly from server registration in the management server.
Brief description of the drawings
Technical scheme in order to illustrate more clearly the embodiments of the present invention, below will be to that will make needed for embodiment description
Accompanying drawing is briefly introduced, it should be apparent that, drawings in the following description are only some embodiments of the present invention, for this
For the those of ordinary skill in field, without having to pay creative labor, it can also be obtained according to these accompanying drawings
His accompanying drawing.
Fig. 1 is the structural representation that a kind of distributed server cluster provided in an embodiment of the present invention dispatches system;
Fig. 2 is the schematic diagram of message queue in a kind of Message Queuing server provided in an embodiment of the present invention;
Fig. 3 is a kind of structural representation of distributed server cluster dispatching device provided in an embodiment of the present invention;
Fig. 4 is a kind of schematic flow sheet of distributed server cluster dispatching method provided in an embodiment of the present invention.
Specific embodiment
In order that the object, technical solutions and advantages of the present invention are clearer, below in conjunction with accompanying drawing the present invention is made into
One step ground is described in detail, it is clear that described embodiment is only some embodiments of the invention, rather than whole implementation
Example.Based on the embodiment in the present invention, what those of ordinary skill in the art were obtained under the premise of creative work is not made
All other embodiment, belongs to the scope of protection of the invention.
The present invention provides a kind of distributed server cluster dispatching method, as shown in figure 1, including:
Master server 101, the webserver 102, Message Queuing server 103, from server 104, client-server
105 and management server 106.
The webserver 102 is used to be managed system, and obtains feedback of the information to upper strata or obtain the life on upper strata
Make and perform order in systems.In embodiments of the present invention, the webserver 102 can formulate task, and task is made
Into task list, it is sent to client-server 105 and performs, wherein the task in task list has in client-server 105
Corresponding relation.
For example, in embodiments of the present invention, the task list that the webserver 102 is formulated as shown in table 1, will specially appoint
Business 1 is handed down to client 1, and task 2 is handed down into client 2, and task 3 is handed down into task end 3.
Task definition | Client side list |
Task definition 1 | Client 1 |
Task definition 2 | Client 2 |
Task definition 3 | Client 3 |
Table 1:Task list
In the embodiment of the present invention, be packaged for task list by master server 101, is encapsulated as an execution message, concurrently
Message Queuing server 103 is given, in embodiments of the present invention, optionally, as shown in Fig. 2 being pressed in Message Queuing server 103
According to the priority for receiving message, multiple message are sequentially arranged, it is assumed that it is the 3rd message in sequence to perform message, then disappearing
After breath queue server 103 has processed the first two message, then the execution message in the embodiment of the present invention is processed.
Optionally, in embodiments of the present invention, Message Queuing server 103 have subscribed the message of the webserver 102, i.e.,
When having newly-increased message in the webserver 102, Message Queuing server 103 can get the newly-increased message.
After master server 101 receives the execution message of the transmission of Message Queuing server 103, determine to hold according to message is performed
Task list in row message, for example, in the embodiment of the present invention, what master server 101 was received is in above-described embodiment in table 1
Task list, then master server 101 then according to task list determine need call from server cluster from server
104。
In embodiments of the present invention, it is that there are a large amount of server clusters from server 104 from server cluster, from service
In device cluster client-server 105 can be called from server 104.
Optionally, in embodiments of the present invention, client can be called from server 104 from each in server cluster
Holding the quantity of server 105 has maximum, and could be arranged to m, i.e., one can call m client from server 104
Server 105.
In embodiments of the present invention, master server 101 is called from before server 104, it is necessary first to it is determined that from server
Each optionally, in embodiments of the present invention, includes abnormal from the state of server 104 from the state of server 104 in cluster
State and normal condition.
In embodiments of the present invention, master server 101 can be obtained from server 104 by management server 106
State, when setting up from server cluster, can send out from server 104 from each in server cluster to management server 106
Connection request is sent, management server 106 can determine to be added to from server cluster from server 104 according to connection request
In.
From server 104 and management server 106 upon establishment of a connection, determined by heartbeat detection message from server
Whether 104 is abnormal, optionally, if management server 106 is not received by the heartbeat sent from server 104 in setting time
Probe message, then it is assumed that to the abnormal state from server 104.
Optionally, in embodiments of the present invention, saved in management server 106 and be registered in management server 105
All status information tables from server 104, the table is periodically updated.For example as shown in table 2, registered in management server 106
It is N number of to have updated 1 time from the status information table of server 104 from server 104, management server 106, then status information table
In save each two state from server.
From server | State 1 | State 2 |
From server 1 | Normally | Normally |
From server 2 | Normally | It is abnormal |
…… | …… | …… |
From server N | Normally | Normally |
Table 2:Status information table in management server
Optionally, in embodiments of the present invention, two status information tables are also saving in management server 106, one is
From the normal information table of state of server 104, as shown in table 3, one is information table from the abnormal state of server 104, such as table 4
It is shown.
From server | State |
From server 1 | Normally |
From server 3 | Normally |
…… | …… |
From server N1 | Normally |
Table 3:Status information table in management server
From server | State |
From server 2 | It is abnormal |
From server 4 | It is abnormal |
…… | …… |
From server N2 | It is abnormal |
Table 4:Status information table in management server
What is preserved in table 3 is entirely that newest state is the normal list from server 104, such as in table 3 from clothes
Business device 1, from server 3 etc.;Optionally, preservation is identification information from server 104, can be from the hard of server 104
Part address can characterize the mark of the uniqueness from server 104 for other.
What table 4 was preserved is entirely that newest state is the abnormal list from server 104, such as in table 4 from service
Device 2, from server 4 etc.;Optionally, preservation is identification information from server 104, can be the hardware from server 104
Address can characterize the mark of the uniqueness from server 104 for other.
Optionally, in embodiments of the present invention, management server 106 can also obtain state for normal from server
In 104 lists each from the working condition of server list 104, in embodiments of the present invention, working condition refers to each
Whether client-server 105 is had called into from server 104, several client-servers 105 are have invoked, as shown in table 5,
It is normal each calling from server 104 from the list of server 104 that state is also saving in management server 106
The quantity of client-server 105.
From server | State | Service condition |
From server 1 | Normally | 2 are called |
From server 3 | Normally | 0 is called |
From server 4 | Normally | M platforms are called |
…… | …… | …… |
Table 5:The working condition table from server preserved in management server
Master server 101 can be in table 5 working condition table determine whether to call from server 104, and also
Can be using how many should be called from server from server 104, for example, in embodiments of the present invention, being called from server 104
The maximum quantity of client-server 105 is m, that is to say, that as from server 4, having called into m platforms client clothes in table 5
Business device 105, then can not recall client-server 105.2 client-servers 105 are had called into from server 1,
Then may call upon m-2 platforms client-server 105.
Optionally, in embodiments of the present invention, all information from server 104 that management server 106 will get
List carries out bottom data duplication, and is copied at least one standby management server 106, in master server 101 to management
Server 106 obtain from the information of server 104 when, it is necessary to first determine whether whether management server 106 abnormal, however, it is determined that management
Server 106 is abnormal, then call other any standby management servers 106 working properly to inquire about from server
104 state.
Master server 101 according to the quantity of the client-server 105 that execution task is needed in the task list for receiving,
Current state from server 104 and call the max-thresholds of client-server 105 from server 104 and determine from clothes
Which calls from server 104 in business device cluster.
In embodiments of the present invention, it is assumed that the quantity for needing the client-server 105 of execution task is n, is inquired
20 from server 104 are had from server cluster, wherein there are 4 to call 0 from server 104, there are 10 from service
Device 104 has called m platforms, and also 6 have been called 2 from server 104, then master server 101 determines to need execution task first
The quantity of client-server 105 whether meet formula 1:
N≤(m-2) × 6+4m (formula 1)
If meeting formula 1, such as n=(m-2) × 6+4m is then called from service cluster except 10 have been called m platform clients
End server 105 it is all from server 104 from beyond server 104, and 4 called 0 client-server 105
From server 104 every call m client-server 105,6 called 2 client-servers 105 from server
104 every call m-2 client-server 105.
Master server 101 will be needed in task list the n client-server 105 of execution task be distributed to it is above-mentioned in it is every
It is individual from server 104, will n client-server 105 be randomly assigned to 10m-12 platforms from server 104, each from
Server 104 calls corresponding client-server 105 to perform and appoints after the client-server 105 for needing to call is received
Task in business list.
In embodiments of the present invention, from server 104 receive call client-server 105 after process task
Task result, and task result is sent to Message Queuing server 103, Message Queuing server 103 is sent to
The webserver 102.
Optionally, in embodiments of the present invention, when it is determined that being unsatisfactory for formula 1, can dynamically increase from server cluster
In from the quantity of server 104, optionally, in embodiments of the present invention, called from database it is new from server 104, and
It is registered in new in management server 106 from server 104.
Based on same design, the embodiment of the present invention also provides a kind of distributed server cluster dispatching device, such as Fig. 3 institutes
Show, including:
Receiving unit 301, for receiving the execution message that the webserver sends through Message Queuing server, wherein, institute
Stating execution message includes the corresponding waiting task of each client-server;
Acquiring unit 302, for obtaining from server cluster each state from server, wherein, it is described from service
Device cluster includes at least two from server;
Determining unit 303, it is quantity for the client-server according to waiting task, described from server calls visitor
The max-thresholds of family end server and each described state from server, it is determined that need to call from server;
Transmitting element 304, for the corresponding waiting task of each client-server in the execution message to be distributed
To it is described need to call from server.
Further, the determining unit 303, specifically for:
By the corresponding waiting task cutting of each client-server in the execution message for each needs are called
Called from the corresponding task list of server, and the need for the task list is sent into correspondence from server;
Task list according to receiving calls corresponding client-server;Receive at the task of the client-server
Reason result, and the task result is sent to the webserver by the Message Queuing server.
Further, the acquiring unit 302, specifically for:
Obtain each state from server from server cluster;
By each from the state synchronized of server at least one standby management server;
Determine whether the running status of the management server is normal;
If it is determined that the management server abnormal state, then call any in described at least one standby management server
One, obtain each state from server from server cluster.
Further, the acquiring unit 302, specifically for:
For from any one in server cluster from server, if can not be got in setting time described from clothes
The heartbeat detection information of business device, it is determined that the abnormal state from server.
Further, described device also includes:
Dynamic adding unit 305, for if it is determined that it is described from server cluster each from utilization rate of server etc.
When the max-thresholds, then increase newly from server, it is described to increase newly from server registration in the management server.
Based on same design, the present invention also provides a kind of distributed server cluster dispatching method, as shown in figure 4, bag
Include:
Step 401, master server receives the execution message that the webserver sends through Message Queuing server, wherein, institute
Stating execution message includes the corresponding waiting task of each client-server;
Step 402, the master server obtains from server cluster each state from server, wherein, it is described from
Server cluster includes at least two from server;
Step 403, the master server according to the quantity of the client-server of waiting task, described adjusted from server
With the max-thresholds of client-server and each described state from server, it is determined that need to call from server;
Step 404, the master server by it is described execution message in the corresponding waiting task of each client-server
Be distributed to it is described need to call from server.
Further, the master server by it is described execution message in the corresponding waiting task of each client-server
Be distributed to it is described need call from server, including:
The corresponding waiting task cutting of each client-server in the execution message is each by the master server
It is described need call from the corresponding task list of server, and by the task list be sent to correspondence the need for call from
Server;
The corresponding waiting task of each client-server in the execution message is distributed to institute by the master server
State need call from after server, also include:
For each needs call from server, the needs call from server according to receive task list adjust
Use corresponding client-server;It is described to need the receiving the client-server from server of the task called to process knot
Really, and by the task result webserver is sent to by the Message Queuing server.
Further, the master server obtains from server cluster each state from server, including:
Management server obtains each state from server from server cluster;
The management server is by each from the state synchronized of server at least one standby management server;
The master server determines whether the running status of the management server is normal;
If the master server determines the management server abnormal state, described at least one standby management clothes are called
Any one in business device, obtains each state from server from server cluster.
Further, the management server obtains from server cluster each state from server, including:
For from any one in server cluster from server, if the management server can not in setting time
Get the heartbeat detection information from server, it is determined that the abnormal state from server.
Further, methods described also includes:
If the master server determine it is described from server cluster each from the utilization rate of server be equal to it is described most
During big threshold value, then increase newly from server, it is described to increase newly from server registration in the management server.
The present invention is the flow with reference to method according to embodiments of the present invention, equipment (system) and computer program product
Figure and/or block diagram are described.It should be understood that every first-class during flow chart and/or block diagram can be realized by computer program instructions
The combination of flow and/or square frame in journey and/or square frame and flow chart and/or block diagram.These computer programs can be provided
The processor of all-purpose computer, special-purpose computer, Embedded Processor or other programmable data processing devices is instructed to produce
A raw machine so that produced for reality by the instruction of computer or the computing device of other programmable data processing devices
The device of the function of being specified in present one flow of flow chart or multiple one square frame of flow and/or block diagram or multiple square frames.
These computer program instructions may be alternatively stored in can guide computer or other programmable data processing devices with spy
In determining the computer-readable memory that mode works so that instruction of the storage in the computer-readable memory is produced and include finger
Make the manufacture of device, the command device realize in one flow of flow chart or multiple one square frame of flow and/or block diagram or
The function of being specified in multiple square frames.
These computer program instructions can be also loaded into computer or other programmable data processing devices so that in meter
Series of operation steps is performed on calculation machine or other programmable devices to produce computer implemented treatment, so as in computer or
The instruction performed on other programmable devices is provided for realizing in one flow of flow chart or multiple flows and/or block diagram one
The step of function of being specified in individual square frame or multiple square frames.
, but those skilled in the art once know basic creation although preferred embodiments of the present invention have been described
Property concept, then can make other change and modification to these embodiments.So, appended claims are intended to be construed to include excellent
Select embodiment and fall into having altered and changing for the scope of the invention.
Obviously, those skilled in the art can carry out various changes and modification without deviating from essence of the invention to the present invention
God and scope.So, if these modifications of the invention and modification belong to the scope of the claims in the present invention and its equivalent technologies
Within, then the present invention is also intended to comprising these changes and modification.
Claims (10)
1. a kind of distributed server cluster dispatching method, it is characterised in that it is described including:
Master server receives the execution message that the webserver sends through Message Queuing server, wherein, in the execution message
Including the corresponding waiting task of each client-server;
The master server obtains from server cluster each state from server, wherein, it is described from server cluster
Including at least two from server;
The master server is according to the quantity of the client-server of waiting task, described from server calls client service
The max-thresholds of device and each described state from server, it is determined that need to call from server;
The corresponding waiting task of each client-server in the execution message is distributed to the need by the master server
To be called from server.
2. method according to claim 1, it is characterised in that the master server is by each client in the execution message
The end corresponding waiting task of server be distributed to it is described need to call from server, including:
The corresponding waiting task cutting of each client-server in the execution message is each described by the master server
What needs were called call from the corresponding task list of server, and the need for the task list is sent into correspondence from service
Device;
The corresponding waiting task of each client-server in the execution message is distributed to the need by the master server
To be called from after server, also include:
For each needs call from server, the needs call from server according to receive task list call it is right
The client-server answered;The task result that the client-server is received from server for needing to call, and
The task result is sent to the webserver by the Message Queuing server.
3. method according to claim 1, it is characterised in that the master server obtain from server cluster each from
The state of server, including:
Management server obtains each state from server from server cluster;
The management server is by each from the state synchronized of server at least one standby management server;
The master server determines whether the running status of the management server is normal;
If the master server determines the management server abnormal state, described at least one standby management server is called
In any one, obtain each state from server from server cluster.
4. method according to claim 3, it is characterised in that the management server obtains from server cluster each
From the state of server, including:
For from any one in server cluster from server, if the management server can not be obtained in setting time
To the heartbeat detection information from server, it is determined that the abnormal state from server.
5. method according to claim 3, it is characterised in that methods described also includes:
If each is equal to the maximum threshold from the utilization rate of server from server cluster described in the master server determination
During value, then increase newly from server, it is described to increase newly from server registration in the management server.
6. a kind of distributed server cluster dispatching device, it is characterised in that including:
Receiving unit, for receiving the execution message that the webserver sends through Message Queuing server, wherein, the execution disappears
Breath includes the corresponding waiting task of each client-server;
Acquiring unit, for obtaining from server cluster each state from server, wherein, it is described from server cluster
Including at least two from server;
Determining unit, it is quantity for the client-server according to waiting task, described from server calls client clothes
Be engaged in the max-thresholds and each described state from server of device, it is determined that need to call from server;
Transmitting element, for the corresponding waiting task of each client-server in the execution message to be distributed into the need
To be called from server.
7. device according to claim 6, it is characterised in that the determining unit, specifically for:
By it is described execution message in the corresponding waiting task cutting of each client-server be it is each it is described need call from
The corresponding task list of server, and call the need for the task list is sent into correspondence from server;
Task list according to receiving calls corresponding client-server;Receive the task treatment knot of the client-server
Really, and by the task result webserver is sent to by the Message Queuing server.
8. device according to claim 6, it is characterised in that the acquiring unit, specifically for:
Obtain each state from server from server cluster;
By each from the state synchronized of server at least one standby management server;
Determine whether the running status of the management server is normal;
If it is determined that the management server abnormal state, then call any one in described at least one standby management server
It is individual, obtain each state from server from server cluster.
9. device according to claim 8, it is characterised in that the acquiring unit, specifically for:
For from any one in server cluster from server, if can not be got in setting time described from server
Heartbeat detection information, it is determined that the abnormal state from server.
10. device according to claim 8, it is characterised in that described device also includes:
Dynamic adding unit, for if it is determined that it is described from server cluster each from the utilization rate of server be equal to it is described most
During big threshold value, then increase newly from server, it is described to increase newly from server registration in the management server.
Priority Applications (1)
Application Number | Priority Date | Filing Date | Title |
---|---|---|---|
CN201611229087.5A CN106817408B (en) | 2016-12-27 | 2016-12-27 | Distributed server cluster scheduling method and device |
Applications Claiming Priority (1)
Application Number | Priority Date | Filing Date | Title |
---|---|---|---|
CN201611229087.5A CN106817408B (en) | 2016-12-27 | 2016-12-27 | Distributed server cluster scheduling method and device |
Publications (2)
Publication Number | Publication Date |
---|---|
CN106817408A true CN106817408A (en) | 2017-06-09 |
CN106817408B CN106817408B (en) | 2020-09-29 |
Family
ID=59110131
Family Applications (1)
Application Number | Title | Priority Date | Filing Date |
---|---|---|---|
CN201611229087.5A Active CN106817408B (en) | 2016-12-27 | 2016-12-27 | Distributed server cluster scheduling method and device |
Country Status (1)
Country | Link |
---|---|
CN (1) | CN106817408B (en) |
Cited By (10)
Publication number | Priority date | Publication date | Assignee | Title |
---|---|---|---|---|
CN107766136A (en) * | 2017-09-30 | 2018-03-06 | 南威软件股份有限公司 | A kind of method of task cluster management and running |
CN108282527A (en) * | 2018-01-22 | 2018-07-13 | 北京百度网讯科技有限公司 | Generate the distributed system and method for Service Instance |
CN109032803A (en) * | 2018-08-01 | 2018-12-18 | 阿里巴巴集团控股有限公司 | Data processing method and device, client |
CN109639506A (en) * | 2019-01-08 | 2019-04-16 | 北京文香信息技术有限公司 | A kind of master-slave control method, device, storage medium and server |
CN109660607A (en) * | 2018-12-05 | 2019-04-19 | 北京金山云网络技术有限公司 | A kind of service request distribution method, method of reseptance, device and server cluster |
CN109936593A (en) * | 2017-12-15 | 2019-06-25 | 网宿科技股份有限公司 | A kind of method and system of message distribution |
CN110262882A (en) * | 2019-06-17 | 2019-09-20 | 北京思特奇信息技术股份有限公司 | A kind of distributed communication command scheduling system and method |
WO2019210580A1 (en) * | 2018-05-04 | 2019-11-07 | 平安科技(深圳)有限公司 | Access request processing method, apparatus, computer device, and storage medium |
CN110928673A (en) * | 2018-09-20 | 2020-03-27 | 北京国双科技有限公司 | Task allocation method and device |
CN111459903A (en) * | 2019-01-21 | 2020-07-28 | 顺丰科技有限公司 | Database management system and method |
Citations (9)
Publication number | Priority date | Publication date | Assignee | Title |
---|---|---|---|---|
CN102521044A (en) * | 2011-12-30 | 2012-06-27 | 北京拓明科技有限公司 | Distributed task scheduling method and system based on messaging middleware |
CN102739775A (en) * | 2012-05-29 | 2012-10-17 | 宁波东冠科技有限公司 | Method for monitoring and managing Internet of Things data acquisition server cluster |
CN103336815A (en) * | 2013-06-27 | 2013-10-02 | 北京京东尚科信息技术有限公司 | System and method of pushing network advertising |
CN103973725A (en) * | 2013-01-28 | 2014-08-06 | 阿里巴巴集团控股有限公司 | Distributed collaboration method and collaboration device |
CN104184756A (en) * | 2013-05-21 | 2014-12-03 | 阿里巴巴集团控股有限公司 | Data synchronization method, device and system |
WO2016039963A2 (en) * | 2014-09-10 | 2016-03-17 | Ebay Inc. | Resource sharing between two resource allocation systems |
CN105959390A (en) * | 2016-06-13 | 2016-09-21 | 乐视控股(北京)有限公司 | Unified management system and method of micro services |
CN105991737A (en) * | 2015-02-26 | 2016-10-05 | 阿里巴巴集团控股有限公司 | Distributed task scheduling method and system |
CN106027634A (en) * | 2016-05-16 | 2016-10-12 | 白杨 | Baiyang message port switch service |
-
2016
- 2016-12-27 CN CN201611229087.5A patent/CN106817408B/en active Active
Patent Citations (9)
Publication number | Priority date | Publication date | Assignee | Title |
---|---|---|---|---|
CN102521044A (en) * | 2011-12-30 | 2012-06-27 | 北京拓明科技有限公司 | Distributed task scheduling method and system based on messaging middleware |
CN102739775A (en) * | 2012-05-29 | 2012-10-17 | 宁波东冠科技有限公司 | Method for monitoring and managing Internet of Things data acquisition server cluster |
CN103973725A (en) * | 2013-01-28 | 2014-08-06 | 阿里巴巴集团控股有限公司 | Distributed collaboration method and collaboration device |
CN104184756A (en) * | 2013-05-21 | 2014-12-03 | 阿里巴巴集团控股有限公司 | Data synchronization method, device and system |
CN103336815A (en) * | 2013-06-27 | 2013-10-02 | 北京京东尚科信息技术有限公司 | System and method of pushing network advertising |
WO2016039963A2 (en) * | 2014-09-10 | 2016-03-17 | Ebay Inc. | Resource sharing between two resource allocation systems |
CN105991737A (en) * | 2015-02-26 | 2016-10-05 | 阿里巴巴集团控股有限公司 | Distributed task scheduling method and system |
CN106027634A (en) * | 2016-05-16 | 2016-10-12 | 白杨 | Baiyang message port switch service |
CN105959390A (en) * | 2016-06-13 | 2016-09-21 | 乐视控股(北京)有限公司 | Unified management system and method of micro services |
Cited By (15)
Publication number | Priority date | Publication date | Assignee | Title |
---|---|---|---|---|
CN107766136A (en) * | 2017-09-30 | 2018-03-06 | 南威软件股份有限公司 | A kind of method of task cluster management and running |
CN109936593B (en) * | 2017-12-15 | 2022-03-01 | 网宿科技股份有限公司 | Method and system for message distribution |
CN109936593A (en) * | 2017-12-15 | 2019-06-25 | 网宿科技股份有限公司 | A kind of method and system of message distribution |
CN108282527B (en) * | 2018-01-22 | 2019-07-09 | 北京百度网讯科技有限公司 | Generate the distributed system and method for Service Instance |
CN108282527A (en) * | 2018-01-22 | 2018-07-13 | 北京百度网讯科技有限公司 | Generate the distributed system and method for Service Instance |
WO2019210580A1 (en) * | 2018-05-04 | 2019-11-07 | 平安科技(深圳)有限公司 | Access request processing method, apparatus, computer device, and storage medium |
WO2020024650A1 (en) * | 2018-08-01 | 2020-02-06 | 阿里巴巴集团控股有限公司 | Data processing method and apparatus, and client |
US11233878B2 (en) | 2018-08-01 | 2022-01-25 | Advanced New Technologies Co., Ltd. | Data processing method, apparatus, and client device |
CN109032803A (en) * | 2018-08-01 | 2018-12-18 | 阿里巴巴集团控股有限公司 | Data processing method and device, client |
CN110928673A (en) * | 2018-09-20 | 2020-03-27 | 北京国双科技有限公司 | Task allocation method and device |
CN109660607A (en) * | 2018-12-05 | 2019-04-19 | 北京金山云网络技术有限公司 | A kind of service request distribution method, method of reseptance, device and server cluster |
CN109660607B (en) * | 2018-12-05 | 2021-08-27 | 北京金山云网络技术有限公司 | Service request distribution method, service request receiving method, service request distribution device, service request receiving device and server cluster |
CN109639506A (en) * | 2019-01-08 | 2019-04-16 | 北京文香信息技术有限公司 | A kind of master-slave control method, device, storage medium and server |
CN111459903A (en) * | 2019-01-21 | 2020-07-28 | 顺丰科技有限公司 | Database management system and method |
CN110262882A (en) * | 2019-06-17 | 2019-09-20 | 北京思特奇信息技术股份有限公司 | A kind of distributed communication command scheduling system and method |
Also Published As
Publication number | Publication date |
---|---|
CN106817408B (en) | 2020-09-29 |
Similar Documents
Publication | Publication Date | Title |
---|---|---|
CN106817408A (en) | A kind of distributed server cluster dispatching method and device | |
US10877801B2 (en) | Systems and methods for scheduling tasks | |
CN106789362A (en) | A kind of device management method and network management system | |
US20040243709A1 (en) | System and method for cluster-sensitive sticky load balancing | |
CN107968802A (en) | The method, apparatus and filtering type scheduler of a kind of scheduling of resource | |
US9244721B2 (en) | Computer system and divided job processing method and program | |
TWI338229B (en) | Dynamically configurable fault tolerance in autonomic computing with multiple service points | |
CN105740063A (en) | Data processing method and apparatus | |
CN108197912A (en) | A kind of transaction processing system and method | |
CN110442610A (en) | The method, apparatus of load balancing calculates equipment and medium | |
US9104486B2 (en) | Apparatuses, systems, and methods for distributed workload serialization | |
CN105933408A (en) | Implementation method and device of Redis universal middleware | |
CN105956481A (en) | Data processing method and device | |
CN113900598A (en) | Block chain based data storage method, device, equipment and storage medium | |
CN107832902A (en) | Reply person's distribution system | |
CN109753593A (en) | Spraying operation method for scheduling task and unmanned plane | |
CN105592551B (en) | A kind of method for channel allocation and device | |
JP5647561B2 (en) | Power system supervisory control system | |
CN108123987A (en) | The method and device of master scheduler is determined from cloud computing system | |
CN112116208A (en) | Automatic case distribution system and method, storage medium and computing device | |
CN106059940A (en) | Flow control method and device | |
CN111258760A (en) | Platform management method, system, device and storage medium | |
CN105491253A (en) | Resource distribution method and system for call center | |
CN103326880B (en) | Genesys calling system high availability cloud computing monitoring system and method | |
CN105429795B (en) | A kind of alarm monitoring system and method |
Legal Events
Date | Code | Title | Description |
---|---|---|---|
PB01 | Publication | ||
PB01 | Publication | ||
SE01 | Entry into force of request for substantive examination | ||
SE01 | Entry into force of request for substantive examination | ||
GR01 | Patent grant | ||
GR01 | Patent grant |