CN112783123B - Workflow scheduling execution unit control method and controller - Google Patents
Workflow scheduling execution unit control method and controller Download PDFInfo
- Publication number
- CN112783123B CN112783123B CN202011623798.7A CN202011623798A CN112783123B CN 112783123 B CN112783123 B CN 112783123B CN 202011623798 A CN202011623798 A CN 202011623798A CN 112783123 B CN112783123 B CN 112783123B
- Authority
- CN
- China
- Prior art keywords
- execution unit
- scheduling execution
- scheduling
- workflow
- module
- Prior art date
- Legal status (The legal status is an assumption and is not a legal conclusion. Google has not performed a legal analysis and makes no representation as to the accuracy of the status listed.)
- Active
Links
Images
Classifications
-
- G—PHYSICS
- G05—CONTROLLING; REGULATING
- G05B—CONTROL OR REGULATING SYSTEMS IN GENERAL; FUNCTIONAL ELEMENTS OF SUCH SYSTEMS; MONITORING OR TESTING ARRANGEMENTS FOR SUCH SYSTEMS OR ELEMENTS
- G05B19/00—Programme-control systems
- G05B19/02—Programme-control systems electric
- G05B19/418—Total factory control, i.e. centrally controlling a plurality of machines, e.g. direct or distributed numerical control [DNC], flexible manufacturing systems [FMS], integrated manufacturing systems [IMS], computer integrated manufacturing [CIM]
- G05B19/41865—Total factory control, i.e. centrally controlling a plurality of machines, e.g. direct or distributed numerical control [DNC], flexible manufacturing systems [FMS], integrated manufacturing systems [IMS], computer integrated manufacturing [CIM] characterised by job scheduling, process planning, material flow
-
- G—PHYSICS
- G05—CONTROLLING; REGULATING
- G05B—CONTROL OR REGULATING SYSTEMS IN GENERAL; FUNCTIONAL ELEMENTS OF SUCH SYSTEMS; MONITORING OR TESTING ARRANGEMENTS FOR SUCH SYSTEMS OR ELEMENTS
- G05B2219/00—Program-control systems
- G05B2219/30—Nc systems
- G05B2219/32—Operator till task planning
- G05B2219/32252—Scheduling production, machining, job shop
-
- Y—GENERAL TAGGING OF NEW TECHNOLOGICAL DEVELOPMENTS; GENERAL TAGGING OF CROSS-SECTIONAL TECHNOLOGIES SPANNING OVER SEVERAL SECTIONS OF THE IPC; TECHNICAL SUBJECTS COVERED BY FORMER USPC CROSS-REFERENCE ART COLLECTIONS [XRACs] AND DIGESTS
- Y02—TECHNOLOGIES OR APPLICATIONS FOR MITIGATION OR ADAPTATION AGAINST CLIMATE CHANGE
- Y02P—CLIMATE CHANGE MITIGATION TECHNOLOGIES IN THE PRODUCTION OR PROCESSING OF GOODS
- Y02P90/00—Enabling technologies with a potential contribution to greenhouse gas [GHG] emissions mitigation
- Y02P90/02—Total factory control, e.g. smart factories, flexible manufacturing systems [FMS] or integrated manufacturing systems [IMS]
Landscapes
- Engineering & Computer Science (AREA)
- General Engineering & Computer Science (AREA)
- Manufacturing & Machinery (AREA)
- Quality & Reliability (AREA)
- Physics & Mathematics (AREA)
- General Physics & Mathematics (AREA)
- Automation & Control Theory (AREA)
- Management, Administration, Business Operations System, And Electronic Commerce (AREA)
Abstract
The invention relates to a workflow scheduling execution unit control method and a controller. The invention can receive the workflow at high speed by adopting a fast path system, is cached by an internal multi-producer single-consumer model queue, and sends the workflow to the workflow scheduling execution unit by the workflow scheduling execution unit distributor according to the workflow scheduling execution unit preselection table. The fast path system is not responsible for building and maintaining the preselection table, and it enables high-speed routing of workflows. The accuracy of the workflow routing to the workflow scheduling execution unit is guaranteed by a workflow scheduling execution unit preselection table, the workflow scheduling execution unit preselection table is constructed and maintained by each module in the slow path system according to the current state (the scale, the capacity and the pressure of the workflow scheduling execution unit), and therefore the receiving problem of high-concurrency and high-flow-rate workflows and the problems of management of a super-large-scale distributed workflow scheduling execution unit and high-speed and accurate routing of large-scale workflows can be solved.
Description
Technical Field
The invention relates to the technical field of workflow scheduling, in particular to a method and a controller for controlling a workflow scheduling execution unit.
Background
A large number of social and industrial processes can be described using workflow, and in a "cloud on everything" environment, large-scale cloud data centers face large-scale workflow reception problems. The large-scale cloud data center can improve the ultra-large-scale distributed workflow scheduling execution unit by utilizing the advantages of the large-scale cloud data center, however, the management of the huge-scale workflow scheduling execution unit becomes a difficult problem to be solved, and meanwhile, how to efficiently and accurately route the workflow to the large-scale workflow scheduling execution unit becomes a new challenge.
Disclosure of Invention
The invention aims to provide a control method and a controller for a workflow scheduling execution unit, which can solve the problems of receiving high-concurrency and high-flow-rate workflows and the problems of management of a super-large-scale distributed workflow scheduling execution unit and high-speed and accurate routing of large-scale workflows.
In order to achieve the purpose, the invention provides the following scheme:
a workflow scheduling execution unit control method includes:
acquiring a first scheduling execution unit registry and scheduling pressure of system workflow; the first schedule execution unit registry comprises: the method comprises the steps that a scheduling execution unit identifier, a self-testing pressure of the scheduling execution unit, a workflow capacity of the scheduling execution unit and remote procedure call information of the scheduling execution unit are obtained; the scheduling execution unit remote procedure call information includes: the network IP address of the dispatching execution unit, the network TCP port number of the dispatching execution unit and the program function path character string of the dispatching execution unit responding to the controller;
generating a scheduling execution unit pre-selection table according to the first scheduling execution unit registry and the scheduling pressure of the current workflow of the system; the scheduling execution unit preselection table is a sequencing array; each entry of the sorting array comprises: the scheduling execution unit identification, the scheduling execution unit bearing capacity and the scheduling execution unit remote procedure call information;
traversing the first scheduling execution unit registry, and determining the total bearing capacity of all scheduling execution units in the first scheduling execution unit registry;
determining the total amount of the workflow in the current system according to the scheduling pressure of the system workflow;
determining the number of the scheduling execution units which are currently opened or closed in the system according to the relation between the total bearing capacity and the total workflow amount to obtain a work scheduling execution unit;
obtaining a first multi-producer single-consumer model queue;
receiving a workflow transmitted by a network, and returning the received workflow to the tail of the first multi-producer single consumer model queue to obtain a second multi-producer single consumer model queue;
acquiring the bearing capacity of each work scheduling execution unit in the scheduling execution unit preselection table, sequentially taking out the workflows with the number corresponding to the bearing capacity of the work scheduling execution unit from the head of a second multi-producer single-consumer model queue, correspondingly sending the taken-out workflows to the work scheduling execution unit, and judging whether the transmission is successful to obtain a first judgment result;
if the first judgment result is yes, taking the second multi-producer single-consumer model queue as a new first multi-producer single-consumer model queue, and then returning to the step of receiving the workflow transmitted by the network, and returning the received workflow to the tail of the first multi-producer single-consumer model queue to obtain a second multi-producer single-consumer model queue;
and if the first judgment result is negative, putting the taken workflow into the second multi-producer single consumer model queue to obtain a new second multi-producer single consumer model queue, taking the new second multi-producer single consumer model queue as a new first multi-producer single consumer model queue, returning to receive the workflow transmitted by the network, and returning the received workflow to the tail of the first multi-producer single consumer model queue to obtain a second multi-producer single consumer model queue.
Preferably, the obtaining the first schedule execution unit registry previously includes:
acquiring a state table of a scheduling execution unit and a registry of a second scheduling execution unit; the state table of the scheduling execution unit stores keep-alive signals sent by the scheduling execution unit in N continuous adjustable time constant periods; the keep-alive signals include: the method comprises the steps that a scheduling execution unit identifier, self-testing pressure of the scheduling execution unit, capacity of the scheduling execution unit, remote procedure call information of the scheduling execution unit and a remote sending timestamp of the scheduling execution unit are obtained;
traversing the state table of the scheduling execution unit, and judging whether the scheduling execution unit in the state table of the scheduling execution unit is contained by the second registration table of the scheduling execution unit, so as to obtain a second judgment result;
when the second judgment result is yes, judging whether the scheduling execution unit is in a survival state according to the keep-alive signal to obtain a third judgment result;
when the third judgment result is negative, deleting the information of the scheduling execution unit, sending a closing command to the scheduling execution unit, and storing the identifier of the scheduling execution unit to a scheduling execution unit blacklist;
and when the third judgment result is yes or the second judgment result is no, updating the information of the scheduling execution unit in the second scheduling execution unit registry or adding a table entry of the second scheduling execution unit registry according to the information of the scheduling execution unit to obtain a first scheduling execution unit registry.
Preferably, judging whether the scheduling execution unit is in a survival state according to the keep-alive signal specifically includes:
using a formula
Determining the average time interval of N continuous keep-alive signals of the scheduling execution unit;
acquiring a preset time constant of the death time of a scheduling execution unit;
judging whether the average time interval is larger than the preset time constant or not;
when the average time interval is larger than the preset time constant, judging that the scheduling execution unit is dead;
when the average time interval is less than or equal to the preset time constant, judging that the scheduling execution unit is alive;
wherein, X is a scheduling execution unit,
to average time interval, TCyi(X) is the time difference between the ith adjustable time constant period and the (i-1) th adjustable time constant period in the schedule execution unit state table for the schedule execution unit X.
Preferably, the determining the number of the scheduling execution units currently turned on or turned off in the system according to the relationship between the total bearing capacity and the total workflow amount to obtain the work scheduling execution unit specifically includes:
acquiring a first threshold control constant and a second threshold control constant;
when the total bearing capacity is smaller than the total workflow capacity and the difference value between the total workflow capacity and the total bearing capacity is larger than the first threshold control constant, starting scheduling execution units with the number equal to that of the first threshold control constant;
and when the total bearing capacity is greater than the total workflow amount and the difference between the total bearing capacity and the total workflow amount is greater than the second threshold control constant, closing the scheduling execution units with the number equal to that of the second threshold control constant.
Corresponding to the control method of the workflow scheduling execution unit, the invention correspondingly provides a workflow scheduling execution unit controller, and the control method of the workflow scheduling execution unit is implanted into the controller; the controller includes: a fast path system and a slow path system;
the fast path system is connected with the slow path system; the fast path system is used for forwarding the workflow; the slow path system is used for scheduling control over the scheduling execution unit.
Preferably, the fast path system comprises: the system comprises a workflow receiving module, a scheduling execution unit distributing module, a network sending module and a first storage module;
the receiving workflow module is connected with the first storage module; the first storage module is connected with the scheduling execution unit distribution module; the scheduling execution unit distribution module is connected with the network sending module;
the first storage module is used for storing a scheduling execution unit preselection table and a multi-producer single-consumer model queue;
the receiving workflow module is used for receiving the workflow transmitted in the network and storing the workflow into the multi-producer single-consumer model queue;
the scheduling execution unit distribution module is used for traversing the scheduling execution unit preselection table, acquiring the bearing capacity of each work scheduling execution unit in the scheduling execution unit preselection table, and sequentially taking out the workflow with the number corresponding to the bearing capacity of the work scheduling execution unit from the head of the multi-producer single-consumer model queue; the scheduling execution unit preselection table is a sequencing array; each entry of the sorting array comprises: the scheduling execution unit identification, the scheduling execution unit bearing capacity and the scheduling execution unit remote procedure call information; the scheduling execution unit remote procedure call information includes: the network IP address of the dispatching execution unit, the network TCP port number of the dispatching execution unit and the program function path character string of the dispatching execution unit responding to the controller;
the network sending module is used for sending the workflow to the scheduling execution unit and the first storage module.
Preferably, the slow path system comprises: the system comprises a scheduling execution unit state tracking module, a scheduling execution unit preselection module, a system pressure evaluation module, a scheduling execution unit start-stop module, a state collection module and a second storage module;
the scheduling execution unit state tracking module is connected with the second storage module; the second storage module is respectively connected with the system pressure evaluation module and the scheduling execution unit preselection module; the scheduling execution unit preselection module is connected with the fast access system; the scheduling execution unit start-stop module is connected with the system pressure evaluation module; the state collection module is connected with the second storage module;
the second storage module is used for storing a scheduling execution unit registry, a scheduling execution unit blacklist and a scheduling execution unit state table; the schedule execution unit registry includes: the method comprises the steps that a scheduling execution unit identifier, a self-testing pressure of the scheduling execution unit, a workflow capacity of the scheduling execution unit and remote procedure call information of the scheduling execution unit are obtained;
the state collection module is used for receiving the keep-alive signals and judging whether the scheduling execution unit blacklist contains the scheduling execution unit, if so, the current receiving is refused, and if not, the scheduling execution unit is written into the scheduling execution unit state table and a keep-alive signal interval is sent to the scheduling execution unit;
the scheduling execution unit state tracking module is used for traversing the scheduling execution unit state table and judging whether the scheduling execution unit in the scheduling execution unit state table is contained by the second scheduling execution unit registry or not; if the scheduling execution unit in the scheduling execution unit state table is contained by the second scheduling execution unit registry, judging whether the scheduling execution unit is in a survival state or not according to the keep-alive signal; if the scheduled execution unit in the scheduled execution unit state table is not included in the second scheduled execution unit registry, updating corresponding data information in the scheduled execution unit registry by using the information of the scheduled execution unit in the scheduled execution unit state table through the scheduled execution unit state tracking module, or adding an entry of the scheduled execution unit registry by using the information of the scheduled execution unit in the scheduled execution unit state table through the scheduled execution unit state tracking module; the scheduling execution unit state tracking module is further configured to delete the scheduling execution unit in the scheduling execution unit registry, and write the identifier of the deleted scheduling execution unit into the scheduling execution unit blacklist after the scheduling execution unit start-stop module sends a close signal to the deleted scheduling execution unit;
the scheduling execution unit preselection module is used for traversing the scheduling execution unit registry and generating the scheduling execution unit preselection table according to the bearing capacity of the scheduling execution unit and the current pressure of the system;
and the system pressure evaluation module is used for traversing the scheduling execution unit registry and determining the number of the currently opened or closed scheduling execution units in the system according to the relationship between the total bearing capacity and the total workflow amount to obtain the working scheduling execution units.
A control device of a workflow scheduling execution unit comprises the workflow scheduling execution unit controller.
According to the specific embodiment provided by the invention, the invention discloses the following technical effects:
the workflow scheduling execution unit control method and the controller provided by the invention can receive the workflow at high speed by adopting a fast path system, are cached by an internal multi-producer single-consumer model queue, and send the workflow to the workflow scheduling execution unit by the workflow scheduling execution unit distributor according to the workflow scheduling execution unit preselection table. The fast path system is not responsible for building and maintaining the preselection table, and it enables high-speed routing of workflows. The accuracy of the workflow routing to the workflow scheduling execution unit is guaranteed by a workflow scheduling execution unit preselection table, the workflow scheduling execution unit preselection table is constructed and maintained by each module in the slow path system according to the current state (the scale, the capacity and the pressure of the workflow scheduling execution unit), and therefore the receiving problem of high-concurrency and high-flow-rate workflows and the problems of management of a super-large-scale distributed workflow scheduling execution unit and high-speed and accurate routing of large-scale workflows can be solved.
Drawings
In order to more clearly illustrate the embodiments of the present invention or the technical solutions in the prior art, the drawings needed to be used in the embodiments will be briefly described below, and it is obvious that the drawings in the following description are only some embodiments of the present invention, and it is obvious for those skilled in the art to obtain other drawings without inventive exercise.
FIG. 1 is a flowchart of a workflow scheduling execution unit control method according to the present invention;
fig. 2 is a schematic structural diagram of a workflow scheduling execution unit controller provided by the present invention.
Description of the symbols:
the system comprises a 1-fast path system, a 1-1 receiving workflow module, a 1-2 scheduling execution unit distribution module, a 1-3 network sending module, a 1-4 first storage module, a 2-slow path system, a 2-1 scheduling execution unit state tracking module, a 2-2 scheduling execution unit preselection module, a 2-3 system pressure evaluation module, a 2-4 scheduling execution unit start-stop module, a 2-5 state collection module and a 2-6 second storage module.
Detailed Description
The technical solutions in the embodiments of the present invention will be clearly and completely described below with reference to the drawings in the embodiments of the present invention, and it is obvious that the described embodiments are only a part of the embodiments of the present invention, and not all of the embodiments. All other embodiments, which can be derived by a person skilled in the art from the embodiments given herein without making any creative effort, shall fall within the protection scope of the present invention.
The invention aims to provide a control method and a controller for a workflow scheduling execution unit, which can solve the problems of receiving high-concurrency and high-flow-rate workflows and the problems of management of a super-large-scale distributed workflow scheduling execution unit and high-speed and accurate routing of large-scale workflows.
In order to make the aforementioned objects, features and advantages of the present invention comprehensible, embodiments accompanied with figures are described in further detail below.
Fig. 1 is a flowchart of a method for controlling a workflow scheduling execution unit according to the present invention, and as shown in fig. 1, the method for controlling the workflow scheduling execution unit includes:
step 100: and acquiring a first scheduling execution unit registry and scheduling pressure of the system workflow. The first schedule execution unit registry includes: the schedule execution unit registry includes: the system comprises a scheduling execution unit identifier, a self-test pressure of the scheduling execution unit, a workflow capacity of the scheduling execution unit and remote procedure call information of the scheduling execution unit. The scheduling execution unit remote procedure call information includes: the network IP address of the dispatching execution unit, the network TCP port number of the dispatching execution unit and the program function path character string of the dispatching execution unit responding to the controller.
Step 101: and generating a scheduling execution unit pre-selection table according to the first scheduling execution unit registry and the scheduling pressure of the current workflow of the system. The scheduling execution unit preselection table is a sort array. The sorting array contains for each entry: the scheduling execution unit identification, the scheduling execution unit bearing capacity and the scheduling execution unit remote procedure call information.
Step 102: and traversing the first scheduling execution unit registry, and determining the total bearing capacity of all scheduling execution units in the first scheduling execution unit registry.
Step 103: and determining the total amount of the workflow in the current system according to the scheduling pressure of the system workflow.
Step 104: and determining the number of the currently opened or closed scheduling execution units in the system according to the relation between the total bearing capacity and the total workflow amount to obtain the work scheduling execution units.
Step 105: a first multi-producer single-consumer model queue is obtained.
Step 106: and receiving the workflow transmitted by the network, and returning the received workflow to the tail of the first multi-producer single-consumer model queue to obtain a second multi-producer single-consumer model queue. This step preferably comprises:
a first threshold control constant and a second threshold control constant are obtained.
And when the total bearing capacity is smaller than the total working flow capacity and the difference value between the total working flow capacity and the total bearing capacity is larger than a first threshold control constant, starting scheduling execution units with the number equal to that of the first threshold control constant.
And when the total bearing capacity is greater than the total workflow amount and the difference between the total bearing capacity and the total workflow amount is greater than a second threshold control constant, closing the scheduling execution units with the number equal to that of the second threshold control constant.
Step 107: and acquiring the bearing capacity of each work scheduling execution unit in the scheduling execution unit preselection table, sequentially taking out the workflows with the number corresponding to the bearing capacity of the work scheduling execution unit from the head of the second multi-producer single-consumer model queue, correspondingly sending the taken-out workflows to the work scheduling execution unit, judging whether the transmission is successful, and obtaining a first judgment result.
Step 108: and if the first judgment result is yes, taking the second multi-producer single-consumer model queue as a new first multi-producer single-consumer model queue, returning to the step of receiving the workflow transmitted by the network, and returning the received workflow to the tail of the first multi-producer single-consumer model queue to obtain the second multi-producer single-consumer model queue.
Step 109: and if the first judgment result is negative, putting the taken workflow into a second multi-producer single consumer model queue to obtain a new second multi-producer single consumer model queue, taking the new second multi-producer single consumer model queue as a new first multi-producer single consumer model queue, returning to receive the workflow transmitted by the network, and returning the received workflow to the tail of the first multi-producer single consumer model queue to obtain a second multi-producer single consumer model queue.
The obtaining of the first schedule execution unit registry in step 100 includes:
and acquiring a scheduling execution unit state table and a second scheduling execution unit registry. The state table of the scheduling execution unit stores the keep-alive signals sent by the scheduling execution unit in N continuous adjustable time constant periods. The keep-alive signals include: the scheduling execution unit identification, the self-test pressure of the scheduling execution unit, the capacity of the scheduling execution unit, the remote procedure call information of the scheduling execution unit and the remote sending time stamp of the scheduling execution unit.
And traversing the state table of the scheduling execution unit, and judging whether the scheduling execution unit in the state table of the scheduling execution unit is contained by the registry of the second scheduling execution unit, so as to obtain a second judgment result.
And when the second judgment result is yes, judging whether the scheduling execution unit is in a survival state according to the keep-alive signal to obtain a third judgment result.
And when the third judgment result is negative, deleting the information of the scheduling execution unit, sending a closing command to the scheduling execution unit, and storing the identifier of the scheduling execution unit to a blacklist of the scheduling execution unit.
And when the third judgment result is yes or the second judgment result is no, updating the scheduling execution unit information in the second scheduling execution unit registry or adding a table entry of the second scheduling execution unit registry according to the information of the scheduling execution unit to obtain the first scheduling execution unit registry.
Preferably, the determining whether the scheduling execution unit is in a survival state according to the keep-alive signal specifically includes:
using a formula
And determining the average time interval of the N continuous keep-alive signals of the scheduling execution unit.
And acquiring a preset time constant of the death time of the scheduling execution unit.
And judging whether the average time interval is larger than a preset time constant or not.
And when the average time interval is larger than the preset time constant, judging that the scheduling execution unit is dead.
And when the average time interval is less than or equal to the preset time constant, judging that the scheduling execution unit is alive.
Wherein, X is a scheduling execution unit,
to average time interval, TCyi(X) is the time difference between the ith adjustable time constant period and the (i-1) th adjustable time constant period in the schedule execution unit state table for the schedule execution unit X.
Corresponding to the control method of the workflow scheduling execution unit, the invention correspondingly sets a workflow scheduling execution unit controller with a 'parallel and dual-channel' mode, and the control method of the workflow scheduling execution unit is implanted in the controller. As shown in fig. 2, the controller includes: a fast path system 1 and a slow path system 2.
The fast path system 1 is connected to the slow path system 2. The fast path system 1 is used to implement forwarding of workflows. The slow path system 2 is used for scheduling control of the scheduling execution unit.
Wherein, the fast access system 1 comprises: the system comprises a receiving workflow module 1-1, a scheduling execution unit distribution module 1-2, a network sending module 1-3 and a first storage module 1-4.
The receiving workflow module 1-1 is connected with a first storage module 1-4. The first memory module 1-4 is connected with the scheduling execution unit distribution module 1-2. The scheduling execution unit distribution module 1-2 is connected with the network transmission module 1-3.
The first storage module 1-4 is used for storing a schedule execution unit pre-selection table and a multi-producer single-consumer model queue.
The receiving workflow module 1-1 is used for receiving the workflow transmitted in the network and storing the workflow into a multi-producer single-consumer model queue.
The scheduling execution unit allocation module 1-2 is configured to traverse the scheduling execution unit preselection table, and is configured to obtain a carrying capacity of each work scheduling execution unit in the scheduling execution unit preselection table, and sequentially fetch a number of workflows corresponding to the carrying capacity of the work scheduling execution unit from a head of a multi-producer single consumer model queue. The scheduling execution unit preselection table is a sort array. The sorting array contains for each entry: the scheduling execution unit identification, the scheduling execution unit bearing capacity and the scheduling execution unit remote procedure call information. The scheduling execution unit remote procedure call information includes: the network sending module 1-3 of the network IP address of the dispatching execution unit, the network TCP port number of the dispatching execution unit and the program function path character string of the response controller of the dispatching execution unit is used for sending the workflow to the dispatching execution unit and the first storage module 1-4.
The slow path system 2 includes: the system comprises a scheduling execution unit state tracking module 2-1, a scheduling execution unit preselection module 2-2, a system pressure evaluation module 2-3, a scheduling execution unit start-stop module 2-4, a state collection module 2-5 and a second storage module 2-6.
The scheduling execution unit state tracking module 2-1 is connected with the second storage module 2-6. The second storage module 2-6 is respectively connected with the system pressure evaluation module 2-3 and the scheduling execution unit pre-selection module 2-2. The scheduling execution unit preselection module 2-2 is connected with the fast path system 1. The scheduling execution unit start-stop module 2-4 is connected with the system pressure evaluation module 2-3. The state collection module 2-5 is connected to a second storage module 2-6.
The second storage module 2-6 is used for storing a schedule execution unit registry, a schedule execution unit blacklist and a schedule execution unit status table. The schedule execution unit registry includes: the system comprises a scheduling execution unit identifier, a self-test pressure of the scheduling execution unit, a workflow capacity of the scheduling execution unit and remote procedure call information of the scheduling execution unit.
The state collection module 2-5 is used for receiving the keep-alive signals and judging whether the scheduling execution unit blacklist includes the scheduling execution unit, if yes, the current receiving is refused, and if not, the scheduling execution unit is written into the scheduling execution unit state table, and the keep-alive signal interval is sent to the scheduling execution unit.
The scheduling execution unit state tracking module 2-1 is configured to traverse the scheduling execution unit state table and determine whether the scheduling execution unit in the scheduling execution unit state table is included in the second scheduling execution unit registry. And if the scheduling execution unit in the scheduling execution unit state table is contained by the second scheduling execution unit registry, judging whether the scheduling execution unit is in a survival state or not according to the keep-alive signal. If the scheduled execution unit in the scheduled execution unit state table is not included in the second scheduled execution unit registry, the corresponding data information in the scheduled execution unit registry is updated by the scheduled execution unit state tracking module 2-1 using the information of the scheduled execution unit in the scheduled execution unit state table, or the entry of the scheduled execution unit registry is added by the scheduled execution unit state tracking module 2-1 using the information of the scheduled execution unit in the scheduled execution unit state table. The scheduling execution unit state tracking module 2-1 is further configured to delete the scheduling execution unit in the scheduling execution unit registry, and write the identifier of the deleted scheduling execution unit into the scheduling execution unit blacklist after the scheduling execution unit start-stop module 2-4 sends a close signal to the deleted scheduling execution unit.
The scheduling execution unit preselection module 2-2 is used for traversing the scheduling execution unit registry and generating a scheduling execution unit preselection table according to the bearing capacity of the scheduling execution unit and the current pressure of the system.
The system pressure evaluation module 2-3 is used for traversing the scheduling execution unit registry and determining the number of the currently opened or closed scheduling execution units in the system according to the relationship between the total bearing capacity and the total workflow amount to obtain the working scheduling execution units.
The following describes a specific workflow of the workflow scheduling execution unit control method and the controller according to a specific embodiment.
Step 1: the state collection module 2-5 receives the scheduling execution unit through the network according to the adjustable time constant period CyThe transmitted schedule execution unit keep-alive signal (simply referred to as keep-alive signal). If the scheduling execution unit is in the scheduling execution unit blacklist, rejecting the receiving; otherwise, writing the scheduling execution unit state table and sending the suggested keep-alive signal interval CC to the scheduling execution unit through the network. Wherein, the keep-alive signal comprises the identification of the scheduling execution unit, the self-testing pressure of the scheduling execution unit and the scheduling executionUnit workflow capacity, schedule execution unit remote procedure call information, and send timestamp. The remote procedure call information of the dispatching execution unit comprises the IP address of the network of the dispatching execution unit, the TCP port number and the name of a function to be executed. The scheduling execution unit state table stores the continuous N adjustable time constant periods C of each scheduling execution unityAnd the scheduling execution unit keep-alive signal is sent in the inner loop. N is set by external parameters when the system is started. Suggesting a keep-alive signal interval CC ═ Cy+Δt，CyThe adjustable time constant period is set by external parameters when the system is started, and the unit is second. Δ t is a random time interval. The transmission time stamp is the number of seconds elapsed from 0 minutes 0 seconds on 1 month 1 day 0 of 1970 to the transmission time point.
Step 2: the scheduling execution unit state tracking module 2-1 traverses the scheduling execution unit state table generated in step 1, and queries each scheduling execution unit X in the table in a scheduling execution unit registry. If the scheduled execution unit X is present in the scheduled execution unit registry, step 3 is performed, otherwise step 5 is performed. The scheduling execution unit registry comprises a scheduling execution unit identifier, a self-test pressure of the scheduling execution unit, a workflow capacity of the scheduling execution unit and remote procedure call information of the scheduling execution unit.
And step 3: and judging the survival state of the scheduling execution unit X in the step 2. The determination method is as follows: average time interval of N continuous keep-alive signals of scheduling execution unit X
If it is not
And judging that the scheduling execution unit X is dead, otherwise, judging that the scheduling execution unit X is alive. And if the judgment result is that the scheduling execution unit X is dead, executing the step 4, otherwise executing the step 5. Wherein, TDEADThe time constant representing the determination of the scheduled execution unit entering the death state is set by an external parameter when the controller is started.
And 4, step 4: and the scheduling execution unit state tracking module 2-1 deletes the scheduling execution unit X in the step 2 in the scheduling execution unit registry, sends a closing signal to the scheduling execution unit X through the scheduling execution unit start-stop module 2-4, and writes the identifier of the scheduling execution unit X into a scheduling execution unit blacklist. The shutdown signal is control data agreed by the controller and the scheduling execution unit. The scheduling execution unit blacklist is used for preventing the state collection module 2-5 from receiving the keep-alive signals sent by the scheduling execution unit which is sent by the scheduling execution unit start-stop module 2-4 to close the signals in step 1 due to unexpected revival or network transmission delay and the like.
And 5: the state tracking module 2-1 of the scheduling execution unit updates the corresponding data of the registry of the scheduling execution unit or newly adds the registry entry of the scheduling execution unit by using the information of the scheduling execution unit X in the step 2 in the state table of the scheduling execution unit.
Step 6: and the scheduling execution unit preselection module 2-2 traverses the scheduling execution unit registry generated comprehensively in the step 4 and the step 5, and generates a scheduling execution unit preselection table according to the bearing capacity C of the scheduling execution unit and the current pressure of the system.
And 7: the system pressure evaluation module 2-3 traverses the scheduling execution unit registration table comprehensively generated in the step 4 and the step 5, and calculates the total bearing capacity SC of all the registered scheduling execution units of the current system1＝∑CiThen, the total amount of the workflow SC in the multi-producer single-consumer model queue is calculated2Comparison of SC1And SC2And (4) relationship. If SC2＞SC1And SC2-SC1＞α1Start-stop module 2-4 start-up alpha by scheduling execution unit1A scheduling execution unit; if SC1＞SC2And SC1-SC2＞α2Randomly selecting alpha from a registry of the scheduling execution unit through the start-stop module 2-4 of the scheduling execution unit2And the scheduling execution unit sends a closing signal to the selected scheduling execution unit through the network. Wherein alpha is1And alpha2The threshold control constant is set by an external parameter when the controller is started.
And 8: the receiving workflow module 1-1 receives the workflow transmitted by the network and puts the workflow into the tail of the multi-producer single-consumer model queue.
And step 9: and the scheduling execution unit distribution module 1-2 traverses the scheduling execution unit preselection table generated in the step 6, and sequentially takes out C workflows aiming at the scheduling execution unit bearing capacity C of each scheduling execution unit Y in the table and from the head of the multi-producer single-consumer model queue generated in the step 8. The scheduling execution unit preselection table is a sequencing array, and each item of the array comprises a scheduling execution unit identifier, a scheduling execution unit bearing capacity C and scheduling execution unit remote procedure call information. Scheduling execution unit bearing capacity C (100-P) Cavl,P∈[0,100]Where P is the dispatch execution Unit pressure, CavlThe execution unit workflow capacity is scheduled.
Step 10: and the scheduling execution unit distribution module 1-2 sends the C workflows obtained in the step 9 to the scheduling execution unit Y in the step 9 through the network sending module 1-3. If the network sending module 1-3 sends successfully, executing step 8; otherwise, step 11 is performed.
Step 11: and the network sending module 1-3 puts the C workflows obtained in the step 10 into a multi-producer single-consumer model queue and executes the step 8.
In addition, the invention also provides a control device of the workflow scheduling execution unit, which mainly comprises the workflow scheduling execution unit controller.
The embodiments in the present description are described in a progressive manner, each embodiment focuses on differences from other embodiments, and the same and similar parts among the embodiments are referred to each other. For the system disclosed by the embodiment, the description is relatively simple because the system corresponds to the method disclosed by the embodiment, and the relevant points can be referred to the method part for description.
The principles and embodiments of the present invention have been described herein using specific examples, which are provided only to help understand the method and the core concept of the present invention; meanwhile, for a person skilled in the art, according to the idea of the present invention, the specific embodiments and the application range may be changed. In view of the above, the present disclosure should not be construed as limiting the invention.
Claims (8)
1. A workflow scheduling execution unit control method is characterized by comprising the following steps:
acquiring a first scheduling execution unit registry and scheduling pressure of system workflow; the first schedule execution unit registry comprises: the method comprises the steps that a scheduling execution unit identifier, a self-testing pressure of the scheduling execution unit, a workflow capacity of the scheduling execution unit and remote procedure call information of the scheduling execution unit are obtained; the scheduling execution unit remote procedure call information includes: the network IP address of the dispatching execution unit, the network TCP port number of the dispatching execution unit and the program function path character string of the dispatching execution unit responding to the controller;
generating a scheduling execution unit pre-selection table according to the first scheduling execution unit registry and the scheduling pressure of the current workflow of the system; the scheduling execution unit preselection table is a sequencing array; each entry of the sorting array comprises: the scheduling execution unit identification, the scheduling execution unit bearing capacity and the scheduling execution unit remote procedure call information;
traversing the first scheduling execution unit registry, and determining the total bearing capacity of all scheduling execution units in the first scheduling execution unit registry;
determining the total amount of the workflow in the current system according to the scheduling pressure of the system workflow;
determining the number of the scheduling execution units which are currently opened or closed in the system according to the relation between the total bearing capacity and the total workflow amount to obtain a work scheduling execution unit;
obtaining a first multi-producer single-consumer model queue;
receiving a workflow transmitted by a network, and returning the received workflow to the tail of the first multi-producer single consumer model queue to obtain a second multi-producer single consumer model queue;
acquiring the bearing capacity of each work scheduling execution unit in the scheduling execution unit preselection table, sequentially taking out the workflows with the number corresponding to the bearing capacity of the work scheduling execution unit from the head of a second multi-producer single-consumer model queue, correspondingly sending the taken-out workflows to the work scheduling execution unit, and judging whether the transmission is successful to obtain a first judgment result;
if the first judgment result is yes, taking the second multi-producer single-consumer model queue as a new first multi-producer single-consumer model queue, and then returning to the step of receiving the workflow transmitted by the network, and returning the received workflow to the tail of the first multi-producer single-consumer model queue to obtain a second multi-producer single-consumer model queue;
and if the first judgment result is negative, putting the taken workflow into the second multi-producer single consumer model queue to obtain a new second multi-producer single consumer model queue, taking the new second multi-producer single consumer model queue as a new first multi-producer single consumer model queue, returning to receive the workflow transmitted by the network, and returning the received workflow to the tail of the first multi-producer single consumer model queue to obtain a second multi-producer single consumer model queue.
2. The method of claim 1, wherein the obtaining a first scheduler execution unit registry previously comprises:
acquiring a state table of a scheduling execution unit and a registry of a second scheduling execution unit; the state table of the scheduling execution unit stores keep-alive signals sent by the scheduling execution unit in N continuous adjustable time constant periods; the keep-alive signals include: the method comprises the steps that a scheduling execution unit identifier, self-testing pressure of the scheduling execution unit, capacity of the scheduling execution unit, remote procedure call information of the scheduling execution unit and a remote sending timestamp of the scheduling execution unit are obtained;
traversing the state table of the scheduling execution unit, and judging whether the scheduling execution unit in the state table of the scheduling execution unit is contained by the second registration table of the scheduling execution unit, so as to obtain a second judgment result;
when the second judgment result is yes, judging whether the scheduling execution unit is in a survival state according to the keep-alive signal to obtain a third judgment result;
when the third judgment result is negative, deleting the information of the scheduling execution unit, sending a closing command to the scheduling execution unit, and storing the identifier of the scheduling execution unit to a scheduling execution unit blacklist;
and when the third judgment result is yes or the second judgment result is no, updating the information of the scheduling execution unit in the second scheduling execution unit registry or adding a table entry of the second scheduling execution unit registry according to the information of the scheduling execution unit to obtain a first scheduling execution unit registry.
3. The method for controlling a workflow scheduling execution unit according to claim 2, wherein judging whether the scheduling execution unit is in a survival state according to the keep-alive signal specifically includes:
using a formula
Determining the average time interval of N continuous keep-alive signals of the scheduling execution unit;
acquiring a preset time constant of the death time of a scheduling execution unit;
judging whether the average time interval is larger than the preset time constant or not;
when the average time interval is larger than the preset time constant, judging that the scheduling execution unit is dead;
when the average time interval is less than or equal to the preset time constant, judging that the scheduling execution unit is alive;
wherein, X is a scheduling execution unit,
to average time interval, TCyi(X) isThe time difference between the ith adjustable time constant period and the (i-1) th adjustable time constant period in the schedule execution unit state table by the schedule execution unit X.
4. The method according to claim 1, wherein the determining the number of the scheduling execution units currently turned on or turned off in the system according to the relationship between the total bearer capacity and the total workflow amount to obtain the work scheduling execution unit specifically comprises:
acquiring a first threshold control constant and a second threshold control constant;
when the total bearing capacity is smaller than the total workflow capacity and the difference value between the total workflow capacity and the total bearing capacity is larger than the first threshold control constant, starting scheduling execution units with the number equal to that of the first threshold control constant;
and when the total bearing capacity is greater than the total workflow amount and the difference between the total bearing capacity and the total workflow amount is greater than the second threshold control constant, closing the scheduling execution units with the number equal to that of the second threshold control constant.
5. A workflow scheduling execution unit controller characterized in that the controller is embedded with the workflow scheduling execution unit control method according to any one of claims 1 to 4; the controller includes: a fast path system and a slow path system;
the fast path system is connected with the slow path system; the fast path system is used for forwarding the workflow; the slow path system is used for scheduling control over the scheduling execution unit.
6. The workflow schedule execution unit controller of claim 5 wherein the fast path system comprises: the system comprises a workflow receiving module, a scheduling execution unit distributing module, a network sending module and a first storage module;
the receiving workflow module is connected with the first storage module; the first storage module is connected with the scheduling execution unit distribution module; the scheduling execution unit distribution module is connected with the network sending module;
the first storage module is used for storing a scheduling execution unit preselection table and a multi-producer single-consumer model queue;
the receiving workflow module is used for receiving the workflow transmitted in the network and storing the workflow into the multi-producer single-consumer model queue;
the scheduling execution unit distribution module is used for traversing the scheduling execution unit preselection table, acquiring the bearing capacity of each work scheduling execution unit in the scheduling execution unit preselection table, and sequentially taking out the workflow with the number corresponding to the bearing capacity of the work scheduling execution unit from the head of the multi-producer single-consumer model queue; the scheduling execution unit preselection table is a sequencing array; each entry of the sorting array comprises: the scheduling execution unit identification, the scheduling execution unit bearing capacity and the scheduling execution unit remote procedure call information; the scheduling execution unit remote procedure call information includes: the network IP address of the dispatching execution unit, the network TCP port number of the dispatching execution unit and the program function path character string of the dispatching execution unit responding to the controller;
the network sending module is used for sending the workflow to the scheduling execution unit and the first storage module.
7. The workflow schedule execution unit controller of claim 6 wherein the slow path system comprises: the system comprises a scheduling execution unit state tracking module, a scheduling execution unit preselection module, a system pressure evaluation module, a scheduling execution unit start-stop module, a state collection module and a second storage module;
the scheduling execution unit state tracking module is connected with the second storage module; the second storage module is respectively connected with the system pressure evaluation module and the scheduling execution unit preselection module; the scheduling execution unit preselection module is connected with the fast access system; the scheduling execution unit start-stop module is connected with the system pressure evaluation module; the state collection module is connected with the second storage module;
the second storage module is used for storing a scheduling execution unit registry, a scheduling execution unit blacklist and a scheduling execution unit state table; the schedule execution unit registry includes: the method comprises the steps that a scheduling execution unit identifier, a self-testing pressure of the scheduling execution unit, a workflow capacity of the scheduling execution unit and remote procedure call information of the scheduling execution unit are obtained;
the state collection module is used for receiving a keep-alive signal and judging whether the scheduling execution unit blacklist contains the scheduling execution unit, if so, the current receiving is refused, and if not, the scheduling execution unit is written into the scheduling execution unit state table and a keep-alive signal interval is sent to the scheduling execution unit;
the scheduling execution unit state tracking module is used for traversing the scheduling execution unit state table and judging whether the scheduling execution unit in the scheduling execution unit state table is contained by a second scheduling execution unit registry or not; if the scheduling execution unit in the scheduling execution unit state table is contained by the second scheduling execution unit registry, judging whether the scheduling execution unit is in a survival state or not according to the keep-alive signal; if the scheduled execution unit in the scheduled execution unit state table is not included in the second scheduled execution unit registry, updating corresponding data information in the scheduled execution unit registry by using the information of the scheduled execution unit in the scheduled execution unit state table through the scheduled execution unit state tracking module, or adding an entry of the scheduled execution unit registry by using the information of the scheduled execution unit in the scheduled execution unit state table through the scheduled execution unit state tracking module; the scheduling execution unit state tracking module is further configured to delete the scheduling execution unit in the scheduling execution unit registry, and write the identifier of the deleted scheduling execution unit into the scheduling execution unit blacklist after the scheduling execution unit start-stop module sends a close signal to the deleted scheduling execution unit;
the scheduling execution unit preselection module is used for traversing the scheduling execution unit registry and generating the scheduling execution unit preselection table according to the bearing capacity of the scheduling execution unit and the current pressure of the system;
and the system pressure evaluation module is used for traversing the scheduling execution unit registry and determining the number of the currently opened or closed scheduling execution units in the system according to the relationship between the total bearing capacity and the total workflow amount to obtain the working scheduling execution units.
8. A workflow schedule execution unit control apparatus comprising the workflow schedule execution unit controller according to any one of claims 5 to 7.
Priority Applications (1)
| Application Number | Priority Date | Filing Date | Title |
|---|---|---|---|
| CN202011623798.7A CN112783123B (en) | 2020-12-30 | 2020-12-30 | Workflow scheduling execution unit control method and controller |
Applications Claiming Priority (1)
| Application Number | Priority Date | Filing Date | Title |
|---|---|---|---|
| CN202011623798.7A CN112783123B (en) | 2020-12-30 | 2020-12-30 | Workflow scheduling execution unit control method and controller |
Publications (2)
| Publication Number | Publication Date |
|---|---|
| CN112783123A CN112783123A (en) | 2021-05-11 |
| CN112783123B true CN112783123B (en) | 2021-11-19 |
Family
ID=75754350
Family Applications (1)
| Application Number | Title | Priority Date | Filing Date |
|---|---|---|---|
| CN202011623798.7A Active CN112783123B (en) | 2020-12-30 | 2020-12-30 | Workflow scheduling execution unit control method and controller |
Country Status (1)
| Country | Link |
|---|---|
| CN (1) | CN112783123B (en) |
Citations (7)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| US6606740B1 (en) * | 1998-10-05 | 2003-08-12 | American Management Systems, Inc. | Development framework for case and workflow systems |
| CN102497310A (en) * | 2011-12-05 | 2012-06-13 | 西安电子科技大学 | Service flow shaping method and device for cascaded port of avionics full duplex switched Ethernet (AFDX) switch |
| KR20150089665A (en) * | 2014-01-28 | 2015-08-05 | 한국전자통신연구원 | Appratus for workflow job scheduling |
| CN106648898A (en) * | 2016-12-28 | 2017-05-10 | 深圳竹信科技有限公司 | Data management method and system applicable to mode of multiple producers and multiple consumers |
| JP2019121240A (en) * | 2018-01-09 | 2019-07-22 | 東芝メモリ株式会社 | Workflow scheduling system, workflow scheduling method and electronic apparatus |
| CN110417812A (en) * | 2019-08-23 | 2019-11-05 | 北京无极芯动科技有限公司 | 5G protocol massages processor architecture and 5G protocol message processing method |
| CN110825527A (en) * | 2019-11-08 | 2020-02-21 | 北京理工大学 | Deadline-budget driven scientific workflow scheduling method in cloud environment |
Family Cites Families (3)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| CN100459586C (en) * | 2006-08-25 | 2009-02-04 | 华为技术有限公司 | Device and method for data flux control |
| US20090089078A1 (en) * | 2007-09-28 | 2009-04-02 | Great-Circle Technologies, Inc. | Bundling of automated work flow |
| CN111506406A (en) * | 2020-04-10 | 2020-08-07 | 深圳前海微众银行股份有限公司 | Workflow scheduling method, device and system and computer readable storage medium |
-
2020
- 2020-12-30 CN CN202011623798.7A patent/CN112783123B/en active Active
Patent Citations (7)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| US6606740B1 (en) * | 1998-10-05 | 2003-08-12 | American Management Systems, Inc. | Development framework for case and workflow systems |
| CN102497310A (en) * | 2011-12-05 | 2012-06-13 | 西安电子科技大学 | Service flow shaping method and device for cascaded port of avionics full duplex switched Ethernet (AFDX) switch |
| KR20150089665A (en) * | 2014-01-28 | 2015-08-05 | 한국전자통신연구원 | Appratus for workflow job scheduling |
| CN106648898A (en) * | 2016-12-28 | 2017-05-10 | 深圳竹信科技有限公司 | Data management method and system applicable to mode of multiple producers and multiple consumers |
| JP2019121240A (en) * | 2018-01-09 | 2019-07-22 | 東芝メモリ株式会社 | Workflow scheduling system, workflow scheduling method and electronic apparatus |
| CN110417812A (en) * | 2019-08-23 | 2019-11-05 | 北京无极芯动科技有限公司 | 5G protocol massages processor architecture and 5G protocol message processing method |
| CN110825527A (en) * | 2019-11-08 | 2020-02-21 | 北京理工大学 | Deadline-budget driven scientific workflow scheduling method in cloud environment |
Non-Patent Citations (2)
| Title |
|---|
| Analysis and Design for Intelligent Manufacturing Cloud Control Systems;Ce Yan et al.;《2020 Chinese Automation Congress》;20201108;第7174-7179页 * |
| 一种基于两级DAG模型的MapReduce工作流异构调度算法;王宇新 等;《计算机工程与科学》;20190831;第1353-1359页 * |
Also Published As
| Publication number | Publication date |
|---|---|
| CN112783123A (en) | 2021-05-11 |
Similar Documents
| Publication | Publication Date | Title |
|---|---|---|
| CN109901926A (en) | Method, server and storage medium based on big data behavior scheduling application task | |
| CN104081736B (en) | The system and method for schedule packet transmissions on client device | |
| CN108156265B (en) | A kind of application control method and mobile device | |
| CN103763378A (en) | Task processing method and system and nodes based on distributive type calculation system | |
| CN109783218A (en) | A kind of container dispatching method based on Kubernetes container cluster with time correlation connection | |
| CN106664254A (en) | Optimizing network traffic management in a mobile network | |
| CN108234348A (en) | A kind of processing method and processing device in queue operation | |
| US8694295B2 (en) | System and method for time virtualization in computer systems | |
| JP2006209457A (en) | Sensor data processing method | |
| CN107526581A (en) | Data update notifying method and device | |
| Banaie et al. | Performance analysis of multithreaded IoT gateway | |
| CN109842621A (en) | A kind of method and terminal reducing token storage quantity | |
| RU2014152794A (en) | INFORMATION PROCESSING SYSTEM, MANAGEMENT METHOD, SERVER, INFORMATION PROCESSING DEVICE AND MEDIA | |
| CN109871273A (en) | A kind of adaptive task moving method and device | |
| CN112783123B (en) | Workflow scheduling execution unit control method and controller | |
| CN113448685A (en) | Pod scheduling method and system based on Kubernetes | |
| CN109783573A (en) | The method of data synchronization and terminal of multichannel push | |
| CN106549786B (en) | Configuration method and device for service provisioning resources | |
| CN103634230B (en) | A kind of network driver layer data packet receiving method based on dynamic prediction and system | |
| CN113364701B (en) | RTT (round trip time) -based congestion control method and equipment combining proportional-integral-derivative control | |
| ATE447813T1 (en) | SYSTEM AND METHOD FOR TIME-BASED PLANNING | |
| CN114489986A (en) | Task scheduling method and device, terminal equipment and storage medium | |
| CN104410511A (en) | Server management method and system | |
| CN110287006A (en) | A kind of data dispatching method and system | |
| WO2019029721A1 (en) | Task scheduling method, apparatus and device, and storage medium |
Legal Events
| Date | Code | Title | Description |
|---|---|---|---|
| PB01 | Publication | ||
| PB01 | Publication | ||
| SE01 | Entry into force of request for substantive examination | ||
| SE01 | Entry into force of request for substantive examination | ||
| GR01 | Patent grant | ||
| GR01 | Patent grant |