CN111629050A - Node scheduling method and device, storage medium and electronic device - Google Patents
Node scheduling method and device, storage medium and electronic device Download PDFInfo
- Publication number
- CN111629050A CN111629050A CN202010443180.6A CN202010443180A CN111629050A CN 111629050 A CN111629050 A CN 111629050A CN 202010443180 A CN202010443180 A CN 202010443180A CN 111629050 A CN111629050 A CN 111629050A
- Authority
- CN
- China
- Prior art keywords
- load
- node
- parameter value
- child
- target
- Prior art date
- Legal status (The legal status is an assumption and is not a legal conclusion. Google has not performed a legal analysis and makes no representation as to the accuracy of the status listed.)
- Pending
Links
- 238000000034 method Methods 0.000 title claims abstract description 51
- 230000003068 static effect Effects 0.000 claims abstract description 34
- 238000004590 computer program Methods 0.000 claims description 17
- 230000000694 effects Effects 0.000 abstract description 4
- 238000004891 communication Methods 0.000 description 8
- 230000008569 process Effects 0.000 description 8
- 238000010586 diagram Methods 0.000 description 6
- 230000008859 change Effects 0.000 description 3
- 230000005540 biological transmission Effects 0.000 description 2
- 238000005516 engineering process Methods 0.000 description 2
- 230000004048 modification Effects 0.000 description 2
- 238000012986 modification Methods 0.000 description 2
- 230000003287 optical effect Effects 0.000 description 2
- 230000009471 action Effects 0.000 description 1
- 238000004422 calculation algorithm Methods 0.000 description 1
- 238000004364 calculation method Methods 0.000 description 1
- 230000003203 everyday effect Effects 0.000 description 1
- 230000006870 function Effects 0.000 description 1
- 230000006872 improvement Effects 0.000 description 1
- 230000001960 triggered effect Effects 0.000 description 1
Images
Classifications
-
- H—ELECTRICITY
- H04—ELECTRIC COMMUNICATION TECHNIQUE
- H04L—TRANSMISSION OF DIGITAL INFORMATION, e.g. TELEGRAPHIC COMMUNICATION
- H04L67/00—Network arrangements or protocols for supporting network services or applications
- H04L67/01—Protocols
- H04L67/10—Protocols in which an application is distributed across nodes in the network
- H04L67/1001—Protocols in which an application is distributed across nodes in the network for accessing one among a plurality of replicated servers
-
- H—ELECTRICITY
- H04—ELECTRIC COMMUNICATION TECHNIQUE
- H04L—TRANSMISSION OF DIGITAL INFORMATION, e.g. TELEGRAPHIC COMMUNICATION
- H04L67/00—Network arrangements or protocols for supporting network services or applications
- H04L67/01—Protocols
- H04L67/10—Protocols in which an application is distributed across nodes in the network
- H04L67/1001—Protocols in which an application is distributed across nodes in the network for accessing one among a plurality of replicated servers
- H04L67/1004—Server selection for load balancing
- H04L67/1006—Server selection for load balancing with static server selection, e.g. the same server being selected for a specific client
-
- H—ELECTRICITY
- H04—ELECTRIC COMMUNICATION TECHNIQUE
- H04L—TRANSMISSION OF DIGITAL INFORMATION, e.g. TELEGRAPHIC COMMUNICATION
- H04L67/00—Network arrangements or protocols for supporting network services or applications
- H04L67/01—Protocols
- H04L67/10—Protocols in which an application is distributed across nodes in the network
- H04L67/1001—Protocols in which an application is distributed across nodes in the network for accessing one among a plurality of replicated servers
- H04L67/1004—Server selection for load balancing
- H04L67/1025—Dynamic adaptation of the criteria on which the server selection is based
Landscapes
- Engineering & Computer Science (AREA)
- Computer Networks & Wireless Communication (AREA)
- Signal Processing (AREA)
- Multi Processors (AREA)
Abstract
The invention provides a node scheduling method and device, a storage medium and an electronic device, wherein the method comprises the steps of determining load parameter values of a plurality of child nodes used for storing data in a distributed cluster, wherein the load parameter values at least comprise one of the following: the method comprises the following steps of obtaining a load static parameter value and a load dynamic parameter value, wherein the load static parameter value refers to hardware configuration of equipment on a storage node, and the load dynamic parameter refers to load amount distributed by the equipment on the storage node; selecting a target child node which meets the load distribution condition from the plurality of child nodes according to the load parameter values of the plurality of child nodes; and storing target data by utilizing the target child node. By the method and the device, the problem that the load of each node in the distributed cluster system cannot be finely controlled and reasonably distributed is solved, and the effect of distributing the service load based on the load parameter value is achieved.
Description
Technical Field
The invention relates to the field of cluster networks and load balancing, in particular to a node scheduling method and device, a storage medium and an electronic device.
Background
In a distributed operation scenario, a cluster network is generally formed by a master node and a plurality of sub-nodes, the master node is responsible for management of service distribution scheduling, node fault tolerance and the like, and the sub-nodes undertake execution of specific services. The core task on the main node is to schedule the total service of the whole system to each child node, so that the child nodes load the service. And each child node can be fairly distributed with the traffic equivalent to the traffic load capacity of the child node through a load balancing debugging algorithm.
Aiming at the problem that the load of each node in a distributed cluster system cannot realize refined control and reasonable distribution in the related technology, an effective solution does not exist at present.
Disclosure of Invention
The embodiment of the invention provides a node scheduling method and device, a storage medium and an electronic device, which are used for at least solving the problem that the load of each node in a distributed cluster system in the related technology cannot be finely controlled and reasonably distributed.
According to an embodiment of the present invention, a node scheduling method is provided, including: determining load parameter values for a plurality of child nodes in a distributed cluster for storing data, wherein the load parameter values include at least one of: the method comprises the following steps of obtaining a load static parameter value and a load dynamic parameter value, wherein the load static parameter value refers to hardware configuration of equipment on a storage node, and the load dynamic parameter refers to load amount distributed by the equipment on the storage node; selecting a target child node which meets the load distribution condition from the plurality of child nodes according to the load parameter values of the plurality of child nodes; and storing target data by utilizing the target child node.
According to another embodiment of the present invention, there is provided a node scheduling apparatus including: a determining module configured to determine load parameter values of a plurality of child nodes in a distributed cluster for storing data, wherein the load parameter values include at least one of: the method comprises the following steps of obtaining a load static parameter value and a load dynamic parameter value, wherein the load static parameter value refers to hardware configuration of equipment on a storage node, and the load dynamic parameter refers to load amount distributed by the equipment on the storage node; a selecting module, configured to select a target child node that meets a load distribution condition from the plurality of child nodes according to the load parameter values of the plurality of child nodes; and the storage module is used for storing the target data by utilizing the target child node.
According to a further embodiment of the present invention, there is also provided a storage medium having a computer program stored therein, wherein the computer program is arranged to perform the steps of any of the above method embodiments when executed.
According to yet another embodiment of the present invention, there is also provided an electronic device, including a memory in which a computer program is stored and a processor configured to execute the computer program to perform the steps in any of the above method embodiments.
According to the invention, the load parameter values of a plurality of sub-nodes used for storing data in the distributed cluster need to be determined when the node scheduling is carried out, and then the target sub-node meeting the load distribution condition is selected from the plurality of sub-nodes according to the load parameter values of the plurality of sub-nodes. Therefore, the problem that the load of each node in the distributed cluster system cannot realize refined control and reasonable distribution can be solved, and the effect of distributing the service load based on the load parameter value is achieved.
Drawings
The accompanying drawings, which are included to provide a further understanding of the invention and are incorporated in and constitute a part of this application, illustrate embodiment(s) of the invention and together with the description serve to explain the invention without limiting the invention. In the drawings:
fig. 1 is a block diagram of a hardware configuration of a computer device of a node scheduling method according to an embodiment of the present invention;
fig. 2 is a flowchart illustrating a node scheduling method according to an embodiment of the present invention;
fig. 3 is a block diagram of a node scheduling apparatus according to an embodiment of the present invention;
fig. 4 is a schematic diagram illustrating a load node selection process in the embodiment of the present application;
fig. 5 is a schematic view of a load fine-tuning process in the embodiment of the present application.
Detailed Description
The invention will be described in detail hereinafter with reference to the accompanying drawings in conjunction with embodiments. It should be noted that the embodiments and features of the embodiments in the present application may be combined with each other without conflict.
It should be noted that the terms "first," "second," and the like in the description and claims of the present invention and in the drawings described above are used for distinguishing between similar elements and not necessarily for describing a particular sequential or chronological order.
Example 1
The method provided by the first embodiment of the present application may be executed in a mobile terminal, a computer terminal, or a similar computing device. Taking the example of running on a computer device, fig. 1 is a hardware structure block diagram of the computer device of the node scheduling method according to the embodiment of the present invention.
The embodiment of the application provides a computer terminal. As shown in fig. 1, the computer device 20 may include: the at least one processor 201, e.g., CPU, the at least one network interface 204, the user interface 203, the memory 205, the at least one communication bus 202, and optionally, a display 206. Wherein a communication bus 202 is used to enable the connection communication between these components. The user interface 203 may include a touch screen, a keyboard or a mouse, among others. The network interface 204 may optionally include a standard wired interface, a wireless interface (e.g., WI-FI interface), and a communication connection may be established with the server via the network interface 204. The memory 205 may be a high-speed RAM memory or a non-volatile memory (non-volatile memory), such as at least one disk memory, and the memory 205 includes a flash in the embodiment of the present invention. The memory 205 may optionally be at least one memory system located remotely from the processor 201. As shown in fig. 1, memory 205, which is a type of computer storage medium, may include an operating system, a network communication module, a user interface module, and program instructions.
It should be noted that the network interface 204 may be connected to a receiver, a transmitter or other communication module, and the other communication module may include, but is not limited to, a WiFi module, a bluetooth module, etc., and it is understood that the computer device in the embodiment of the present invention may also include a receiver, a transmitter, other communication module, etc.
In this embodiment, a node scheduling method operating in a computer terminal is provided, and fig. 2 is a flowchart of a node scheduling method according to an embodiment of the present invention, as shown in fig. 2, the flowchart includes the following steps:
step S202, determining load parameter values of a plurality of child nodes for storing data in the distributed cluster, wherein the load parameter values at least comprise one of the following: the method comprises the following steps of obtaining a load static parameter value and a load dynamic parameter value, wherein the load static parameter value refers to hardware configuration of equipment on a storage node, and the load dynamic parameter refers to load amount distributed by the equipment on the storage node;
it should be noted that the load static parameter value refers to a node capability value, and is usually static information that is fixed and unchangeable, and different devices may have a large difference depending on the hardware resource configuration of the devices on the node.
It should be further noted that the load dynamic parameter value refers to a node pressure value, and is dynamic information that changes constantly, and depends on the load amount allocated to the node, and generally, the higher the load is, the greater the pressure is.
That is, the larger the load static parameter value is, the higher the load that the node expects to be distributed is, and the larger the load dynamic parameter value is, the lower the load that the node expects to be distributed subsequently is. The node load distribution of the whole cluster is based on balanced scheduling among the capability values and the pressure values of the nodes.
Step S204, selecting a target child node meeting load distribution conditions from the child nodes according to the load parameter values of the child nodes;
and step S206, storing target data by using the target child node.
The main node collects the load static parameter values and the load dynamic parameter values of each sub-node, comprehensively calculates the node load parameter values (load coefficients), and guides the service load distribution through the load parameter values. The load distribution on different child nodes can be adjusted according to the service data flow so as to improve the operation efficiency of the service flow to the maximum extent.
Through the steps, load parameter values of a plurality of sub-nodes used for storing data in the distributed cluster need to be determined when node scheduling is carried out, and then target sub-nodes meeting load distribution conditions are selected from the plurality of sub-nodes according to the load parameter values of the plurality of sub-nodes. Therefore, the problem that the load of each node in the distributed cluster system cannot realize refined control and reasonable distribution can be solved, and the effect of distributing the service load based on the load parameter value is achieved.
The method avoids overlarge load difference among storage nodes with different capabilities and also avoids overhigh load path number of a single node, and selects a target child node meeting load distribution conditions from the child nodes according to load parameter values of the child nodes, and comprises the following steps: determining a first sub-node of the plurality of sub-nodes, wherein the load parameter value does not reach the warning load value; and selecting a second child node meeting the load distribution condition from the first child node as the target child node according to the load parameter value of the first child node.
It should be noted that, when a child node reaches the warning load point, it indicates that the child node is currently in a higher-order load state, and when next load distribution is performed, the child node that does not reach the warning load point should be selected preferentially, even if the calculated load coefficient value is higher.
Rational allocation is also required to be considered when accurate node scheduling is realized, so that the operation stability of each node is improved. The method further comprises the following steps: determining a third child node of the plurality of child nodes, in which the load parameter value has reached the warning load value, when it is determined that the first child node does not exist or the second child node does not exist in the plurality of child nodes; and selecting a fourth child node meeting the load distribution condition from the third child nodes as the target child node according to the load parameter value of the third child node.
It should be noted that when the allocation is reasonable, the child nodes which do not reach the warning load point are preferably selected.
Preferably, after selecting a target child node meeting the load distribution condition from the plurality of child nodes according to the load parameter values of the plurality of child nodes, the method further includes: and under the condition that the load parameter value of the load node of the target child node is greater than the load reference value, selecting the child node of which the load parameter value meets the load adjustment condition as the target node to carry out load transfer. The load reference value may be an averaged reference value or other feasible calculation method. In order to ensure rational distribution, it is necessary to divert a limited amount of load, but also to avoid large variations as much as possible.
Preferably, the determining the load parameter values of the plurality of child nodes includes: after determining the load parameter value of the child node N, acquiring a load static parameter value and a load dynamic parameter value of storage equipment on the child node N +1 by traversing the child node N +1 under the condition that the child node N +1 exists, wherein the load static parameter value at least comprises: the maximum value of the allowed access channel of the node C1, the total allowed access bandwidth of the network C2, the number of the storage hard disk groups C3 and the total capacity of the storage hard disks C4, wherein the load dynamic parameter values at least comprise: CPU usage percentage P1, memory usage percentage P2, current access total code stream value P3, current storage total code stream value P4 and current forwarding total code stream value P5; and obtaining a load parameter value of the sub-node N +1 according to the plurality of sub-node load static parameter values and the load dynamic parameter value, wherein the load parameter value R is (P1 × P2 × (P3+ P4+ P5))/(C1 × C2 × C3 × C4).
Specifically, taking the application of the present disclosure to a distributed video stream storage system as an example, the core service of the device on each child node is responsible for video recording and storing the video stream generated by the channel accessing the encoder. The encoder is a front-end device capable of generating a video data stream, the total number of channels of one child node device is fixed, and if some channels are bound with the encoder, the channel is in an allocated state, and if some channels are not bound with any encoder, the channel is in an idle state. That is, the load distribution of the devices on the nodes can be simply equivalent to the operation of performing encoder binding on the channels on the devices, and the load of the encoder is higher when the number of the channels of the encoder is larger.
Recording the maximum value of the allowed access channel of the node as C1; recording the total bandwidth allowed to be accessed by the network as C2 by taking Mbps as a unit; recording the number of the storage hard disk groups as C3; the total capacity of the storage hard disk is marked as C4 in GB.
It should be noted that the CPU and memory parameters of the devices on the child nodes are typically represented in the access channel maximum.
Similarly, the CPU usage percentage of the devices on the node is denoted as P1; recording the memory usage percentage as P2; recording the current access total code stream value as P3 by taking Mbps as a unit; recording the current storage total code stream value as P4 by taking Mbps as a unit; and recording the current forwarding total code stream value as P5 by taking Mbps as a unit.
It should be noted that the CPU utilization of the devices on the child nodes has removed the fluctuation factor, which is used to reflect the average CPU utilization over the current period of time, and is relatively accurate.
Preferably, in the node list that does not reach the warning load point currently, selecting the node with the lowest load coefficient as the distribution node, and determining the load parameter values of the plurality of child nodes for storing data in the distributed cluster, includes: selecting a node with a first load parameter value as a distribution node from a node list of which the target child node does not reach the warning load point, wherein the first load parameter value refers to the load parameter value which does not reach the warning load point; selecting a target child node meeting a load distribution condition from the plurality of child nodes according to the load parameter values of the plurality of child nodes, comprising: and under the condition that a node with a first load parameter value is selected as an allocation node from the node list of which the target sub-node does not reach the warning load point, when the first load parameter value is an invalid value or the load parameter value of the target sub-node is smaller than the first load parameter value, updating the first load parameter value to be the load parameter value of the target sub-node. I.e. the first load parameter value is always pointing to the minimum value of the load factor that has currently been found in the list of nodes that have not reached the alert load point. And after a node with a first load parameter value is selected as an allocation node from a node list of which the target child node does not reach the warning load point, updating the first load parameter value when the first load parameter value is an invalid value or the load parameter value of the target child node is smaller than the first load parameter value. In addition, if the node is found in the node list which does not reach the warning load point, the node does not need to search in the node list which reaches the warning load point.
Preferably, in the child node list that has reached the warning load point currently, the node with the lowest load coefficient may be selected as the distribution node, and the determining the load parameter values of the plurality of child nodes for storing data in the distributed cluster includes: selecting a node with a second load parameter value as an allocation node from a node list of which the target child node reaches the warning load point; wherein the second load parameter value is a load parameter value which reaches a warning load point; selecting a target child node meeting a load distribution condition from the plurality of child nodes according to the load parameter values of the plurality of child nodes, comprising: and under the condition that a node with a second load parameter value is selected as an allocation node from the node list of which the target child node reaches the warning load point, when the second load parameter value is an invalid value or the load parameter value of the target child node is smaller than the first load parameter value, updating the second load parameter value to be the load parameter value of the target child node. I.e. the second load parameter value is always pointing to the minimum value of the load factor that has currently been found in the list of nodes that have reached the alert load point. And selecting a node with a second load parameter value as an allocation node from a node list of which the target child node reaches the warning load point, and updating the second load parameter value when the second load parameter value is an invalid value or the load parameter value of the target child node is smaller than the first load parameter value.
Through the above description of the embodiments, those skilled in the art can clearly understand that the method according to the above embodiments can be implemented by software plus a necessary general hardware platform, and certainly can also be implemented by hardware, but the former is a better implementation mode in many cases. Based on such understanding, the technical solutions of the present invention may be embodied in the form of a software product, which is stored in a storage medium (e.g., ROM/RAM, magnetic disk, optical disk) and includes instructions for enabling a terminal device (e.g., a mobile phone, a computer, a server, or a network device) to execute the method according to the embodiments of the present invention.
Example 2
In this embodiment, a node scheduling apparatus is further provided, and the apparatus is used to implement the foregoing embodiments and preferred embodiments, and details of which have been already described are omitted. As used below, the term "module" may be a combination of software and/or hardware that implements a predetermined function. Although the means described in the embodiments below are preferably implemented in software, an implementation in hardware, or a combination of software and hardware is also possible and contemplated.
Fig. 3 is a block diagram of a node scheduling apparatus according to an embodiment of the present invention, and as shown in fig. 3, the apparatus includes:
a determining module 30, configured to determine load parameter values of a plurality of child nodes in a distributed cluster for storing data, where the load parameter values include at least one of: the method comprises the following steps of obtaining a load static parameter value and a load dynamic parameter value, wherein the load static parameter value refers to hardware configuration of equipment on a storage node, and the load dynamic parameter refers to load amount distributed by the equipment on the storage node;
a selecting module 32, configured to select a target child node that meets a load distribution condition from the plurality of child nodes according to the load parameter values of the plurality of child nodes;
a storage module 34, configured to store the target data using the target child node.
It should be noted that the load static parameter value refers to a node capability value, and is usually static information that is fixed and unchangeable, and different devices may have a large difference depending on the hardware resource configuration of the devices on the node.
It should be further noted that the load dynamic parameter value refers to a node pressure value, and is dynamic information that changes constantly, and depends on the load amount allocated to the node, and generally, the higher the load is, the greater the pressure is.
That is, the larger the load static parameter value is, the higher the load that the node expects to be distributed is, and the larger the load dynamic parameter value is, the lower the load that the node expects to be distributed subsequently is. The node load distribution of the whole cluster is based on balanced scheduling among the capability values and the pressure values of the nodes.
The main node collects the load static parameter values and the load dynamic parameter values of each sub-node, comprehensively calculates the node load parameter values, and guides the service load distribution through the load parameter values. The load distribution on different child nodes can be adjusted according to the service data flow so as to improve the operation efficiency of the service flow to the maximum extent.
Through the modules, load parameter values of a plurality of sub-nodes used for storing data in the distributed cluster need to be determined when node scheduling is carried out, and then target sub-nodes meeting load distribution conditions are selected from the plurality of sub-nodes according to the load parameter values of the plurality of sub-nodes. Therefore, the problem that the load of each node in the distributed cluster system cannot realize refined control and reasonable distribution can be solved, and the effect of distributing the service load based on the load parameter value is achieved.
It should be noted that, the above modules may be implemented by software or hardware, and for the latter, the following may be implemented, but not limited to: the modules are all positioned in the same processor; alternatively, the modules are respectively located in different processors in any combination.
In order to better understand the above node scheduling method flow, the following explains the above technical solution with reference to the preferred embodiment, but is not limited to the technical solution of the embodiment of the present invention.
The preferred embodiment of the invention can calculate the current real-time load coefficient of each storage sub-node, and the node with the lower load coefficient is preferentially scheduled to the task, thereby realizing the refined balance control of the load of each node.
Fig. 4 is a schematic diagram illustrating a load node selection process in the embodiment of the present application.
At step S1, two load factors and a node ID are initially defined. R1 represents a node minimum value coefficient which does not reach the warning load point, and the initial value is an invalid value; r2 represents the node minimum coefficient that has reached the alert load point, the initial value being an invalid value. D represents the finally selected node number, and the initial value is an invalid value.
Step S2, determine whether there is a next storage node?
Step S3, if yes, traverse the next storage node.
In step S4, the ability value score C and the pressure value P of the node are collected.
In step S5, the current node load factor Rx is calculated.
Step S6, is the warning load point reached?
Those nodes that do not reach the warning load point are preferentially selected in said step S6.
Step S7, if not, judging whether R1 is invalid value or Rx < R1. If not, returning to step S2.
The R1 value always points to the load factor minimum value currently found in the list of nodes that have not reached the alert load point in the step S7.
In step S8, if yes, the R1 value is updated to Rx, and the D value is updated.
In step S9, if yes, determine if the R1 value is invalid? If not, returning to step S2.
In step S9, R1 is valid and indicates that the node is found in the node list that has not reached the warning load point, and it is no longer necessary to search the node list that has reached the warning load point.
In step S10, if yes, it is determined whether R2 is invalid or Rx < R2. If not, returning to step S2.
In step S11, if yes, the R2 value is updated to Rx, and the D value is updated.
Fig. 5 is a schematic view of a load fine-tuning process in the embodiment of the present application.
Step S101, an initial load factor of each storage node is calculated.
Step S102, calculating the average load coefficient of all storage nodes.
Step S103, determine whether there is a next storage node?
And step S104, if so, traversing the next storage node.
Step S105, determine whether the node coefficient is higher than the average coefficient by more than 50? If so, the process returns to step S103.
If the node load factor is not too much higher than the average factor in S105, no adjustment is made.
And step S106, if not, starting a fine adjustment action, and selecting the node with the lowest load coefficient as a target node for load service transfer.
Step S107, the limited load is transferred once.
In S107, a limited number of load paths is transferred, i.e., fine adjustment is performed, and a large change is avoided as much as possible.
Step S108, waiting for a period of time.
The waiting time in S108 is because the change of the load factor is not reflected in real time just when the load is transferred, and a process is required.
Step S109, updating the load coefficients of the source node and the target node of the load transfer.
Step S110, if not, the load fine adjustment process is ended.
In order to avoid the situation that the deviation between the expected load of the node and the actual load is overlarge and seriously inconsistent when storage related factors of each storage node change in the running process of the system, the load balancing fine adjustment of the whole node is triggered periodically by adding. The period is set to be once every day, for example, three days, and the triggering time can be selected to be the morning time when the customer visit volume is small.
Embodiments of the present invention also provide a storage medium having a computer program stored therein, wherein the computer program is arranged to perform the steps of any of the above method embodiments when executed.
Alternatively, in the present embodiment, the storage medium may be configured to store a computer program for executing the steps of:
s1, determining load parameter values of a plurality of child nodes for storing data in the distributed cluster, wherein the load parameter values include at least one of: the method comprises the following steps of obtaining a load static parameter value and a load dynamic parameter value, wherein the load static parameter value refers to hardware configuration of equipment on a storage node, and the load dynamic parameter refers to load amount distributed by the equipment on the storage node;
s2, selecting a target child node meeting load distribution conditions from the child nodes according to the load parameter values of the child nodes;
s3, storing the target data by using the target child node.
Optionally, the storage medium is further arranged to store a computer program for performing the steps of:
s4, determining a first sub-node of the plurality of sub-nodes, wherein the load parameter value does not reach the warning load value;
s5, selecting a second child node meeting the load distribution condition from the first child node as the target child node according to the load parameter value of the first child node.
Optionally, the storage medium is further arranged to store a computer program for performing the steps of:
s6, determining a third child node of the plurality of child nodes whose load parameter values have reached the warning load value under the condition that it is determined that the first child node does not exist or the second child node does not exist in the plurality of child nodes;
s7, selecting a fourth child node meeting the load distribution condition from the third child nodes as the target child node according to the load parameter value of the third child node.
Optionally, in this embodiment, the storage medium may include, but is not limited to: various media capable of storing computer programs, such as a usb disk, a Read-Only Memory (ROM), a Random Access Memory (RAM), a removable hard disk, a magnetic disk, or an optical disk.
Embodiments of the present invention also provide an electronic device comprising a memory having a computer program stored therein and a processor arranged to run the computer program to perform the steps of any of the above method embodiments.
Optionally, the electronic apparatus may further include a transmission device and an input/output device, wherein the transmission device is connected to the processor, and the input/output device is connected to the processor.
Optionally, in this embodiment, the processor may be configured to execute the following steps by a computer program:
s1, determining load parameter values of a plurality of child nodes for storing data in the distributed cluster, wherein the load parameter values include at least one of: the method comprises the following steps of obtaining a load static parameter value and a load dynamic parameter value, wherein the load static parameter value refers to hardware configuration of equipment on a storage node, and the load dynamic parameter refers to load amount distributed by the equipment on the storage node;
s2, selecting a target child node meeting load distribution conditions from the child nodes according to the load parameter values of the child nodes;
s3, storing the target data by using the target child node.
Optionally, the specific examples in this embodiment may refer to the examples described in the above embodiments and optional implementation manners, and this embodiment is not described herein again.
It will be apparent to those skilled in the art that the modules or steps of the present invention described above may be implemented by a general purpose computing device, they may be centralized on a single computing device or distributed across a network of multiple computing devices, and alternatively, they may be implemented by program code executable by a computing device, such that they may be stored in a storage device and executed by a computing device, and in some cases, the steps shown or described may be performed in an order different than that described herein, or they may be separately fabricated into individual integrated circuit modules, or multiple ones of them may be fabricated into a single integrated circuit module. Thus, the present invention is not limited to any specific combination of hardware and software.
The above description is only a preferred embodiment of the present invention and is not intended to limit the present invention, and various modifications and changes may be made by those skilled in the art. Any modification, equivalent replacement, or improvement made within the principle of the present invention should be included in the protection scope of the present invention.
Claims (10)
1. A node scheduling method, comprising:
determining load parameter values for a plurality of child nodes in a distributed cluster for storing data, wherein the load parameter values include at least one of: the method comprises the following steps of obtaining a load static parameter value and a load dynamic parameter value, wherein the load static parameter value refers to hardware configuration of equipment on a storage node, and the load dynamic parameter refers to load amount distributed by the equipment on the storage node;
selecting a target child node which meets the load distribution condition from the plurality of child nodes according to the load parameter values of the plurality of child nodes;
and storing target data by utilizing the target child node.
2. The method of claim 1, wherein selecting a target child node among the plurality of child nodes that meets a load distribution condition according to the load parameter values of the plurality of child nodes comprises:
determining a first sub-node of the plurality of sub-nodes, wherein the load parameter value does not reach the warning load value;
and selecting a second child node meeting the load distribution condition from the first child node as the target child node according to the load parameter value of the first child node.
3. The method of claim 2, further comprising:
determining a third child node of the plurality of child nodes, in which the load parameter value has reached the warning load value, when it is determined that the first child node does not exist or the second child node does not exist in the plurality of child nodes;
and selecting a fourth child node meeting the load distribution condition from the third child nodes as the target child node according to the load parameter value of the third child node.
4. The method of claim 1, wherein after selecting a target child node meeting load distribution conditions from the plurality of child nodes according to the load parameter values of the plurality of child nodes, further comprising:
and under the condition that the load parameter value of the load node of the target child node is greater than the load reference value, selecting the child node of which the load parameter value meets the load adjustment condition as the target node to carry out load transfer.
5. The method of claim 1, wherein determining load parameter values for a plurality of child nodes comprises:
after determining the load parameter value of the child node N, acquiring a load static parameter value and a load dynamic parameter value of storage equipment on the child node N +1 by traversing the child node N +1 under the condition that the child node N +1 exists, wherein the load static parameter value at least comprises: the maximum value of the allowed access channel of the node C1, the total allowed access bandwidth of the network C2, the number of the storage hard disk groups C3 and the total capacity of the storage hard disks C4, wherein the load dynamic parameter values at least comprise: CPU usage percentage P1, memory usage percentage P2, current access total code stream value P3, current storage total code stream value P4 and current forwarding total code stream value P5;
and obtaining a load parameter value of the sub-node N +1 according to the plurality of sub-node load static parameter values and the load dynamic parameter value, wherein the load parameter value R is (P1 × P2 × (P3+ P4+ P5))/(C1 × C2 × C3 × C4).
6. The method of claim 1,
determining load parameter values for a plurality of child nodes in a distributed cluster for storing data, comprising:
selecting a node with a first load parameter value as a distribution node from a node list of which the target child node does not reach the warning load point, wherein the first load parameter value refers to the load parameter value which does not reach the warning load point;
selecting a target child node meeting a load distribution condition from the plurality of child nodes according to the load parameter values of the plurality of child nodes, comprising:
and under the condition that a node with a first load parameter value is selected as an allocation node from the node list of which the target sub-node does not reach the warning load point, when the first load parameter value is an invalid value or the load parameter value of the target sub-node is smaller than the first load parameter value, updating the first load parameter value to be the load parameter value of the target sub-node.
7. The method of claim 1,
determining load parameter values for a plurality of child nodes in a distributed cluster for storing data, comprising:
selecting a node with a second load parameter value as an allocation node from a node list of which the target child node reaches the warning load point; wherein the second load parameter value is a load parameter value which reaches a warning load point;
selecting a target child node meeting a load distribution condition from the plurality of child nodes according to the load parameter values of the plurality of child nodes, comprising:
and under the condition that a node with a second load parameter value is selected as an allocation node from the node list of which the target child node reaches the warning load point, when the second load parameter value is an invalid value or the load parameter value of the target child node is smaller than the first load parameter value, updating the second load parameter value to be the load parameter value of the target child node.
8. A node scheduling apparatus, comprising:
a determining module configured to determine load parameter values of a plurality of child nodes in a distributed cluster for storing data, wherein the load parameter values include at least one of: the method comprises the following steps of obtaining a load static parameter value and a load dynamic parameter value, wherein the load static parameter value refers to hardware configuration of equipment on a storage node, and the load dynamic parameter refers to load amount distributed by the equipment on the storage node;
a selecting module, configured to select a target child node that meets a load distribution condition from the plurality of child nodes according to the load parameter values of the plurality of child nodes;
and the storage module is used for storing the target data by utilizing the target child node.
9. A storage medium, in which a computer program is stored, wherein the computer program is arranged to perform the method of any of claims 1 to 7 when executed.
10. An electronic device comprising a memory and a processor, wherein the memory has stored therein a computer program, and wherein the processor is arranged to execute the computer program to perform the method of any of claims 1 to 7.
Priority Applications (1)
| Application Number | Priority Date | Filing Date | Title |
|---|---|---|---|
| CN202010443180.6A CN111629050A (en) | 2020-05-22 | 2020-05-22 | Node scheduling method and device, storage medium and electronic device |
Applications Claiming Priority (1)
| Application Number | Priority Date | Filing Date | Title |
|---|---|---|---|
| CN202010443180.6A CN111629050A (en) | 2020-05-22 | 2020-05-22 | Node scheduling method and device, storage medium and electronic device |
Publications (1)
| Publication Number | Publication Date |
|---|---|
| CN111629050A true CN111629050A (en) | 2020-09-04 |
Family
ID=72272490
Family Applications (1)
| Application Number | Title | Priority Date | Filing Date |
|---|---|---|---|
| CN202010443180.6A Pending CN111629050A (en) | 2020-05-22 | 2020-05-22 | Node scheduling method and device, storage medium and electronic device |
Country Status (1)
| Country | Link |
|---|---|
| CN (1) | CN111629050A (en) |
Cited By (1)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| WO2023207567A1 (en) * | 2022-04-29 | 2023-11-02 | 中兴通讯股份有限公司 | Network service method, master node, sub-node and computer-readable medium |
Citations (5)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| CN103200257A (en) * | 2013-03-28 | 2013-07-10 | 中标软件有限公司 | Node in high availability cluster system and resource switching method of node in high availability cluster system |
| US20160342447A1 (en) * | 2015-05-18 | 2016-11-24 | Krystallize Technologies, Inc. | Automated workload analysis and simulation process |
| CN107623732A (en) * | 2017-09-15 | 2018-01-23 | 郑州云海信息技术有限公司 | A kind of date storage method based on cloud platform, device, equipment and storage medium |
| CN110062027A (en) * | 2019-03-18 | 2019-07-26 | 中科恒运股份有限公司 | Load-balancing method, central server and terminal device |
| CN110545326A (en) * | 2019-09-10 | 2019-12-06 | 杭州数梦工场科技有限公司 | Cluster load scheduling method and device, electronic equipment and storage medium |
-
2020
- 2020-05-22 CN CN202010443180.6A patent/CN111629050A/en active Pending
Patent Citations (5)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| CN103200257A (en) * | 2013-03-28 | 2013-07-10 | 中标软件有限公司 | Node in high availability cluster system and resource switching method of node in high availability cluster system |
| US20160342447A1 (en) * | 2015-05-18 | 2016-11-24 | Krystallize Technologies, Inc. | Automated workload analysis and simulation process |
| CN107623732A (en) * | 2017-09-15 | 2018-01-23 | 郑州云海信息技术有限公司 | A kind of date storage method based on cloud platform, device, equipment and storage medium |
| CN110062027A (en) * | 2019-03-18 | 2019-07-26 | 中科恒运股份有限公司 | Load-balancing method, central server and terminal device |
| CN110545326A (en) * | 2019-09-10 | 2019-12-06 | 杭州数梦工场科技有限公司 | Cluster load scheduling method and device, electronic equipment and storage medium |
Cited By (1)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| WO2023207567A1 (en) * | 2022-04-29 | 2023-11-02 | 中兴通讯股份有限公司 | Network service method, master node, sub-node and computer-readable medium |
Similar Documents
| Publication | Publication Date | Title |
|---|---|---|
| JP3812236B2 (en) | Network management system with event control means | |
| EP2966807B1 (en) | Network usage monitoring and analytics for differentiated data services | |
| CN104322011A (en) | Connectivity service orchestrator | |
| CN105515977B (en) | Method, device and system for acquiring transmission path in network | |
| US20080148270A1 (en) | Method and implementation for storage provisioning planning | |
| WO2015106795A1 (en) | Methods and systems for selecting resources for data routing | |
| Tran et al. | Optimal mapping of virtual networks considering reactive reconfiguration | |
| CN110515728B (en) | Server scheduling method and device, electronic equipment and machine-readable storage medium | |
| KR101448413B1 (en) | Method and apparatus for scheduling communication traffic in atca-based equipment | |
| US9654333B2 (en) | Application allocation in datacenters | |
| EP4187814A1 (en) | Data processing method and device | |
| CN111629050A (en) | Node scheduling method and device, storage medium and electronic device | |
| KR20170014804A (en) | Virtual machine provisioning system and method for cloud service | |
| US11968124B2 (en) | System and method for managing network traffic using fair-share principles | |
| EP3241111B1 (en) | Provisioning of telecommunications resources | |
| CN110324265B (en) | Traffic distribution method, routing method, equipment and network system | |
| US10122812B2 (en) | Push-type information transmission device, push-type information transmission method, and program | |
| JP2012161033A (en) | Resource allocation device, and resource allocation method | |
| JP6511006B2 (en) | Resource allocation management apparatus and allocation destination server determination method | |
| CN105847172B (en) | Job flow control method and device | |
| CN112199179B (en) | Service scheduling method, device, electronic equipment and storage medium | |
| JP7280476B2 (en) | Clustering system and clustering method | |
| EP4068863A1 (en) | Method and system for providing an optimal network slice in a 5g core network | |
| US20220231963A1 (en) | Resource management device, control circuit, storage medium, and resource management method | |
| CN114071761A (en) | Communication control method and device based on intelligent communication management gateway |
Legal Events
| Date | Code | Title | Description |
|---|---|---|---|
| PB01 | Publication | ||
| PB01 | Publication | ||
| SE01 | Entry into force of request for substantive examination | ||
| SE01 | Entry into force of request for substantive examination | ||
| RJ01 | Rejection of invention patent application after publication | ||
| RJ01 | Rejection of invention patent application after publication |
Application publication date: 20200904 |