CN116449935A - Cluster energy-saving management method, electronic equipment and computer storage medium - Google Patents
Cluster energy-saving management method, electronic equipment and computer storage medium Download PDFInfo
- Publication number
- CN116449935A CN116449935A CN202310643706.9A CN202310643706A CN116449935A CN 116449935 A CN116449935 A CN 116449935A CN 202310643706 A CN202310643706 A CN 202310643706A CN 116449935 A CN116449935 A CN 116449935A
- Authority
- CN
- China
- Prior art keywords
- energy
- node
- saving
- nodes
- preset
- Prior art date
- Legal status (The legal status is an assumption and is not a legal conclusion. Google has not performed a legal analysis and makes no representation as to the accuracy of the status listed.)
- Granted
Links
- 238000007726 management method Methods 0.000 title claims abstract description 42
- 238000013468 resource allocation Methods 0.000 claims abstract description 4
- 238000000034 method Methods 0.000 abstract description 3
- 230000006870 function Effects 0.000 description 6
- 230000008859 change Effects 0.000 description 3
- 238000004590 computer program Methods 0.000 description 3
- 241001083847 Berberis Species 0.000 description 2
- 241000196324 Embryophyta Species 0.000 description 2
- 238000004364 calculation method Methods 0.000 description 2
- 238000010586 diagram Methods 0.000 description 2
- 230000000694 effects Effects 0.000 description 2
- 238000005516 engineering process Methods 0.000 description 2
- 230000005012 migration Effects 0.000 description 2
- 238000013508 migration Methods 0.000 description 2
- 238000012545 processing Methods 0.000 description 2
- 238000005057 refrigeration Methods 0.000 description 2
- 238000013459 approach Methods 0.000 description 1
- 238000003491 array Methods 0.000 description 1
- 230000010485 coping Effects 0.000 description 1
- 230000007547 defect Effects 0.000 description 1
- 238000011161 development Methods 0.000 description 1
- 230000010365 information processing Effects 0.000 description 1
- 230000003287 optical effect Effects 0.000 description 1
- 239000007787 solid Substances 0.000 description 1
- 230000007704 transition Effects 0.000 description 1
Classifications
-
- G—PHYSICS
- G06—COMPUTING; CALCULATING OR COUNTING
- G06F—ELECTRIC DIGITAL DATA PROCESSING
- G06F1/00—Details not covered by groups G06F3/00 - G06F13/00 and G06F21/00
- G06F1/26—Power supply means, e.g. regulation thereof
- G06F1/32—Means for saving power
- G06F1/3203—Power management, i.e. event-based initiation of a power-saving mode
-
- G—PHYSICS
- G06—COMPUTING; CALCULATING OR COUNTING
- G06F—ELECTRIC DIGITAL DATA PROCESSING
- G06F1/00—Details not covered by groups G06F3/00 - G06F13/00 and G06F21/00
- G06F1/26—Power supply means, e.g. regulation thereof
- G06F1/32—Means for saving power
- G06F1/3203—Power management, i.e. event-based initiation of a power-saving mode
- G06F1/3206—Monitoring of events, devices or parameters that trigger a change in power modality
-
- G—PHYSICS
- G06—COMPUTING; CALCULATING OR COUNTING
- G06F—ELECTRIC DIGITAL DATA PROCESSING
- G06F1/00—Details not covered by groups G06F3/00 - G06F13/00 and G06F21/00
- G06F1/26—Power supply means, e.g. regulation thereof
- G06F1/32—Means for saving power
- G06F1/3203—Power management, i.e. event-based initiation of a power-saving mode
- G06F1/3234—Power saving characterised by the action undertaken
-
- G—PHYSICS
- G06—COMPUTING; CALCULATING OR COUNTING
- G06F—ELECTRIC DIGITAL DATA PROCESSING
- G06F1/00—Details not covered by groups G06F3/00 - G06F13/00 and G06F21/00
- G06F1/26—Power supply means, e.g. regulation thereof
- G06F1/32—Means for saving power
- G06F1/3203—Power management, i.e. event-based initiation of a power-saving mode
- G06F1/3234—Power saving characterised by the action undertaken
- G06F1/329—Power saving characterised by the action undertaken by task scheduling
-
- 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
Abstract
The invention discloses a cluster energy-saving management method, electronic equipment and a computer storage medium, and relates to the technical field of cloud computing management, wherein the method comprises the following steps: and obtaining the first theoretical energy-saving node quantity and the second theoretical energy-saving node quantity based on state information for representing the running condition of the cluster resources, wherein the second theoretical energy-saving node quantity is determined according to the total number of the nodes, the number of the non-idle nodes, the total number of the used resources of the nodes, the number of single-node resources, the available proportion of the single-node resources and the reserved node quantity. According to the method and the device, the running condition of the nodes in the cluster is adjusted through the preset resource allocation rule, so that the power consumption of the cluster is reduced.
Description
Technical Field
The present disclosure relates to the field of cloud computing management technologies, and in particular, to a cluster energy-saving management method, an electronic device, and a computer storage medium.
Background
With the continuous development of computer field technology, cloud computing has become a popular field in the internet industry, and various cloud manufacturers and enterprises establish numerous public clouds and private clouds. The use of cloud platform relies on a large amount of physical hosts, and physical hosts need to start up the operation always, consume a large amount of electric power, simultaneously, can release heat when physical hosts are operated, need refrigeration plant to dispel the heat to physical hosts, refrigeration plant's operation has further aggravated the consumption of electric power again. Therefore, how to reduce the power consumption and the running cost of the nodes in the cluster becomes an urgent problem to be solved.
Disclosure of Invention
The invention aims to overcome the defects of the prior art, and provides a cluster energy-saving management method, electronic equipment and a computer storage medium, so as to reduce the power consumption and the running cost of a cluster.
In order to solve the technical problems, the invention provides a cluster energy-saving management method, which comprises the following steps:
obtaining a first theoretical energy-saving node quantity and a second theoretical energy-saving node quantity based on state information for representing the running condition of cluster resources, wherein the state information comprises the total number of nodes, the total amount of node used resources, the amount of single node resources, the available proportion of single node resources and the reserved node quantity, and the second theoretical energy-saving node quantity is determined according to the total number of nodes, the total amount of node used resources, the amount of single node resources, the available proportion of single node resources and the reserved node quantity; determining the number of actual energy-saving nodes according to the number of the first theoretical energy-saving nodes and the number of the second theoretical energy-saving nodes; and distributing each node in the actual energy-saving node quantity to enter a preset energy-saving state according to a preset resource distribution rule.
The actual energy-saving node quantity is determined, so that each node in the actual energy-saving node quantity is accurately converted into the preset energy-saving state according to the preset resource allocation rule, and the power consumption and the operation cost of the cluster nodes are reduced.
In some embodiments, the obtaining the first theoretical energy-saving node number and the second theoretical energy-saving node number based on the state information for characterizing the cluster resource operation condition includes:
obtaining the number of used resource nodes based on the total amount of the used resources of the nodes, the single node resource amount and the single node resource availability ratio; and obtaining the second theoretical energy-saving node number based on the node total number, the used resource node number and the reserved node number.
In some embodiments, the determining the actual number of energy saving nodes according to the first theoretical number of energy saving nodes and the second theoretical number of energy saving nodes includes: if the number of the first theoretical energy-saving nodes is larger than the number of the second theoretical energy-saving nodes, the number of the second theoretical energy-saving nodes is used as the number of the actual energy-saving nodes; and if the first theoretical energy-saving node number is smaller than or equal to the second theoretical energy-saving node number, taking the first theoretical energy-saving node number as the actual energy-saving node number.
In some embodiments, the preset energy saving state includes a first energy saving state, a second energy saving state, a third energy saving state, and a fourth energy saving state; the step of allocating each node in the actual energy-saving node number to enter a preset energy-saving state according to a preset resource allocation rule comprises the following steps: determining the number of nodes in a first energy saving state entering the first energy saving state based on the number of the actual energy saving nodes and a preset first distribution value; obtaining a first intermediate energy-saving node number based on the actual energy-saving node number and the first energy-saving state node number; determining the number of nodes in a second energy-saving state entering the second energy-saving state according to the number of the first intermediate energy-saving nodes and a preset second allocation value; obtaining a second intermediate energy-saving node number based on the actual energy-saving node number, the first energy-saving state node number and the second energy-saving state node number; determining the number of nodes in a third energy-saving state entering the third energy-saving state according to the number of the second intermediate energy-saving nodes and a preset third distribution value; and determining a fourth energy-saving state node quantity entering the fourth energy-saving state based on the actual energy-saving node quantity, the first energy-saving state node quantity, the second energy-saving state node quantity and the third energy-saving state node quantity.
In some embodiments, the cluster energy saving management method further comprises: detecting whether the running power of a certain node in the preset energy-saving state meets the preset first consumption power or not, and if the running power of the node is detected to meet the preset first consumption power, marking that the node is in the first energy-saving state; detecting whether the running power of a certain node in the preset energy-saving state meets the preset second consumption power or not, and if the running power of the node is detected to meet the preset second consumption power, marking that the node is in the second energy-saving state; detecting whether the running power of a certain node in the preset energy-saving state meets the preset third power consumption or not, and if the running power of the node is detected to meet the preset third power consumption, marking that the node is in the third energy-saving state; detecting whether the running power of a certain node in the preset energy-saving state meets the preset fourth power consumption, and if the running power of the node is detected to meet the preset fourth power consumption, marking that the node is in the fourth energy-saving state.
In some embodiments, the cluster energy saving management method further comprises: detecting whether the operation states of all the nodes entering the preset energy-saving state meet the operation awakening requirement of the preset nodes or not; when detecting that the nodes to be awakened, the operation states of which meet the operation awakening requirements of the preset nodes, exist in all the nodes, awakening the nodes to be awakened based on the preset energy-saving consumption function and the preset energy-saving awakening duration.
In some embodiments, the cluster energy saving management method further comprises: when the node to be awakened is detected, acquiring the total number of nodes currently in the preset energy-saving state; acquiring the total amount of the current node used resources matched with the total amount of the nodes; and if the total amount of the resources used by the current node meets a preset node resource changing rule, updating the actual energy-saving node amount.
In some embodiments, the cluster energy saving management method further comprises: acquiring a non-idle node; detecting whether each node in the non-idle nodes meets the preset energy saving state, and switching a certain node in the non-idle nodes to the preset energy saving state when detecting that the certain node in the non-idle nodes meets the preset energy saving state.
In addition, the invention also provides electronic equipment, which comprises a processor and a memory, wherein the memory is used for storing instructions, and the processor is used for calling the instructions in the memory so that the electronic equipment executes the cluster energy-saving management method.
In addition, the invention also provides a computer readable storage medium, which stores computer instructions that, when executed on an electronic device, cause the electronic device to execute the cluster energy saving management method.
Compared with the prior art, the cluster energy-saving management method, the electronic equipment and the computer readable storage medium have the advantages that firstly, the first theoretical node number and the second theoretical node number are determined according to the state information of the cluster resource operation condition, and then the actual energy-saving node number is obtained based on the first theoretical node number and the second theoretical node number, so that the node number capable of entering the energy-saving state in the cluster is determined, and the integral operation of the cluster is prevented from being influenced. Then, the number of nodes entering different energy-saving states is obtained by utilizing the preset first distribution value, the preset second distribution value and the preset third distribution value, so that the power consumption of the cluster is reduced, and the normal operation of the cluster is not influenced. And finally, updating the number of the actual energy-saving nodes according to a preset node resource changing rule. Therefore, when the number of the actual energy-saving nodes is changed, the corresponding nodes can be timely adjusted to enter a preset energy-saving state, so that cluster operation is ensured, and power consumption is reduced. Meanwhile, a plurality of nodes in the cluster are circularly in a preset energy-saving state, and the activity of the nodes is maintained.
Drawings
In order to more clearly illustrate the embodiments of the invention or the technical solutions in the prior art, the drawings which are required in the description of the embodiments or the prior art will be briefly described, it being obvious that the drawings in the description below are only some embodiments of the invention, and that other drawings may be obtained according to these drawings without inventive effort for a person skilled in the art.
Fig. 1 is a flowchart illustrating steps of a cluster energy saving management method according to an embodiment of the present application.
Fig. 2 is a schematic structural diagram of an electronic device according to an embodiment of the present application.
Detailed Description
The following description of the embodiments of the present invention will be made clearly and completely with reference to the accompanying drawings, in which it is apparent that the embodiments described are only some embodiments of the present invention, but not all embodiments. All other embodiments, which can be made by those skilled in the art based on the embodiments of the invention without making any inventive effort, are intended to be within the scope of the invention.
The cluster energy-saving management method can be applied to one or more electronic devices. The electronic device is a device capable of automatically performing numerical calculation and/or information processing according to a preset or stored instruction, and may be, for example, a server cluster, or the like.
FIG. 1 is a flowchart illustrating steps of an embodiment of a cluster energy saving management method according to the present application.
Referring to fig. 1, a cluster energy saving management method may include the steps of:
s100, obtaining a first theoretical energy-saving node quantity and a second theoretical energy-saving node quantity based on state information for representing cluster resource operation conditions, wherein the state information comprises node total quantity, node used resource total quantity, single node resource availability ratio and reserved node quantity, and the second theoretical energy-saving node quantity is determined according to the node total quantity, the node used resource total quantity, the single node resource availability ratio and the reserved node quantity.
In some embodiments, a cluster includes multiple cloud platform physical nodes, where the cloud platform physical nodes can be divided into two broad categories, a first type and a second type. The first type of cloud platform physical node is used for deploying the cloud platform foundation support service, and therefore, the cloud platform physical node belonging to the first type must continuously run. The second type of cloud platform physical nodes are used for forming various cloud platform resource pools according to different product types, the running states of the nodes in the cloud product resource pools can be adjusted according to the running conditions of actual product types, and therefore the second type of cloud platform physical nodes can be adjusted to enter an energy-saving state so as to reduce power consumption.
In some embodiments, a first theoretical energy saving node number is obtained. In this embodiment, for example, the number of first theoretical energy-saving nodes in the main resource pool of the current cloud platform is obtained, and the number of the first theoretical energy-saving nodes is denoted as N1.
Obtaining the number of used resource nodes based on the total amount of the used resources of the nodes, the single node resources and the available proportion of the single node resources; and obtaining a second theoretical energy-saving node number based on the node total number, the non-idle node number, the used resource node number and the reserved node number. For example, the total amount of used resources of the node is denoted as b, the amount of resources of a single node is denoted as a, the available proportion of resources of a single node is denoted as k, the number of used resource nodes can be obtained, the number of used resource nodes is denoted as N3, n3= ⌈ b/(aK) ⌉, where ⌈ ⌉ represents an upward rounding function. Further, based on the total number of nodes N, the number of non-idle nodes N2, the number of used resource nodes N3 and the number of reserved nodes, the second theoretical energy-saving node number is obtained, and the number of reserved nodes is recorded as N4. The second theoretical energy saving node number=n-N3-N4. The nodes in the reserved node number N4 can be used for coping with the cloud resource new demand and the node fault migration demand. For example, the number of nodes required to cope with the new cloud resource requirement is comprehensively set according to the size of the cloud platform scale, the nature of the cloud platform operation, the cloud platform creation time and the like, and the number of nodes required to meet the node fault migration requirement is comprehensively set according to the size of the cloud platform scale, the used hardware age, the hardware brands, the hardware historical failure rate and the like, and in other embodiments, the running condition of the nodes with the reserved number of nodes can be set according to the running condition of the actual cloud platform, which is not limited in the application.
S200, determining the actual energy-saving node number according to the first theoretical energy-saving node number and the second theoretical energy-saving node number.
In some embodiments, if the first theoretical energy saving node number is greater than the second theoretical energy saving node number, the second theoretical energy saving node number is taken as the actual energy saving node number. And if the number of the first theoretical energy-saving nodes is smaller than or equal to the number of the second theoretical energy-saving nodes, taking the number of the first theoretical energy-saving nodes as the number of the actual energy-saving nodes. For example, when the number of the first theoretical energy-saving nodes is 100 and the number of the second theoretical energy-saving nodes is 80, the number of the second theoretical energy-saving nodes is taken as the number of the actual energy-saving nodes after the step S100.
S300, distributing each node in the actual energy-saving node number according to a preset resource distribution rule to enter a preset energy-saving state.
In some embodiments, the preset energy saving state includes a first energy saving state, a second energy saving state, a third energy saving state, and a fourth energy saving state. For example, if the CPU of a certain node is turned off and other components are operating normally and the power consumption of the node is generally below 30W, the node in this state may be defined as the node being in the first power saving state. If a node hangs up the memory, i.e. the hard disk is closed after the data in execution is written into the memory, and the power consumption of the node is generally below 10W, the node in this state may be defined as the node being in the second energy-saving state. If the main power supply of a certain node system is turned off, the memory information is written into the hard disk, then all the components stop working, and the consumed power of the node is generally below 10W, the node in the state can be defined as the node in a third energy-saving state. If all devices including a certain node connected with a power supply are closed, only the BMC (Baseboard Manager Controller, baseboard management controller) is kept to be electrified, so that the Mahonia consumption of the node is close to the self consumption of a power supply system, and the consumption power of the node is generally about 0W, the node in the state can be defined as the node in a fourth energy-saving state. The actual definition of the preset energy saving state is different according to the configuration of the node, and in other embodiments, the setting may be performed according to the configuration of the actual node.
In some embodiments, determining a first energy saving state node number to enter a first energy saving state based on the actual energy saving node number and a preset first allocation value; obtaining the number of first intermediate energy-saving nodes based on the number of actual energy-saving nodes and the number of first energy-saving state nodes; determining the number of nodes in a second energy-saving state entering the second energy-saving state according to the number of the first intermediate energy-saving nodes and a preset second allocation value; obtaining the number of second intermediate energy-saving nodes based on the number of actual energy-saving nodes, the number of first energy-saving state nodes and the number of second energy-saving state nodes; determining the number of nodes in a third energy-saving state entering the third energy-saving state according to the number of the second intermediate energy-saving nodes and a preset third distribution value; and determining a fourth energy-saving state node quantity entering a fourth energy-saving state based on the actual energy-saving node quantity, the first energy-saving state node quantity, the second energy-saving state node quantity and the third energy-saving state node quantity. For example, if the number of actual energy-saving nodes is 100 and the first allocation value is preset to be 4, the number of nodes in the first energy-saving state entering the first energy-saving state is obtained, and the number of nodes in the first energy-saving state is recorded as S1, s1= ⌈ 100/4 ⌉ =25; the first intermediate energy saving node number is obtained based on the actual energy saving node number and the first energy saving state node number, and is 100 minus 25, namely 75. And determining the number of the nodes in the second energy-saving state entering the second energy-saving state according to the number of the first intermediate energy-saving nodes and a preset second allocation value. And setting the preset second allocation value to 3, wherein the number of the second energy-saving state nodes entering the second energy-saving state is ⌈/3 ⌉, and the number of the second energy-saving state nodes is recorded as S2, s2=25. And obtaining the second intermediate energy-saving node number based on the actual energy-saving node number, the first energy-saving state node number and the second energy-saving state node number. The number of the second intermediate energy saving nodes is 100-25-25=50. And determining the number of the nodes in the third energy-saving state entering the third energy-saving state according to the number of the second intermediate energy-saving nodes and a preset third distribution value. And setting the preset third allocation value to be 2, and then setting the number of third energy-saving state nodes entering the third energy-saving state to be ⌈/2 ⌉ =25. And determining a fourth energy-saving state node quantity entering a fourth energy-saving state based on the actual energy-saving node quantity, the first energy-saving state node quantity, the second energy-saving state node quantity and the third energy-saving state node quantity. Finally, the number of nodes in the fourth energy saving state entering the fourth energy saving state is 100-25-25-25=25. In other embodiments, the preset first allocation value, the preset second allocation value and the preset third allocation value may be 2, 3 and 4, respectively, and similarly, the calculation manner of calculating the number of nodes in the corresponding energy-saving state entering different energy-saving states may also be a downward rounding.
In some embodiments, for example, the actual number of energy saving nodes is 101, and the preset first allocation value is 4, so as to obtain the number of nodes in the first energy saving state entering the first energy saving state, and the number of nodes in the first energy saving state is recorded as S1, ⌊ 101/⌋ = 25,101- ⌊ 101/4 ⌋, where s1=25+1=26; the first intermediate energy saving node number is obtained based on the actual energy saving node number and the first energy saving state node number, and is 101 minus 21, that is, 80. And determining the number of the nodes in the second energy-saving state entering the second energy-saving state according to the number of the first intermediate energy-saving nodes and a preset second allocation value. If the preset second allocation value is set to 3, the number of second energy-saving state nodes entering the second energy-saving state is ⌊/3 ⌋ + (80- ⌊ 80/3 ⌋ ×3) =28, and the number of second energy-saving state nodes is S2, s2=28. And obtaining the second intermediate energy-saving node number based on the actual energy-saving node number, the first energy-saving state node number and the second energy-saving state node number. The second intermediate energy saving node number is 101-26-28=52. And determining the number of the nodes in the third energy-saving state entering the third energy-saving state according to the number of the second intermediate energy-saving nodes and a preset third distribution value. Setting the preset third allocation value to 2, the number of nodes in the third energy saving state entering the third energy saving state is ⌊/2 ⌋ =26. And determining a fourth energy-saving state node quantity entering a fourth energy-saving state based on the actual energy-saving node quantity, the first energy-saving state node quantity, the second energy-saving state node quantity and the third energy-saving state node quantity. Finally, the number of nodes in the fourth energy saving state entering the fourth energy saving state is 101-28-26-26=21.
In some embodiments, detecting whether the operation power of a certain node in a preset energy saving state meets a preset first consumption power, and if the operation power of the node is detected to meet the preset first consumption power, marking that the node is in the first energy saving state; for example, if the CPU of a certain node is turned off and other components are operating normally and the power consumption of the node is generally below 30W, the node in this state may be defined as the first power saving state. Detecting whether the running power of a certain node in a preset energy-saving state meets a preset second consumption power or not, and if the running power of the node is detected to meet the preset second consumption power, marking that the node is in the second energy-saving state; for example, if a node hangs up to a memory, i.e., the hard disk is closed after the data being executed is written into the memory, and the power consumption of the node is generally less than 10W, the node in this state may be defined as the second energy-saving state. Detecting whether the running power of a certain node in a preset energy-saving state meets a preset third consumption power or not, and if the running power of the node is detected to meet the preset third consumption power, marking that the node is in the third energy-saving state; for example, if a main power supply of a system of a certain node is turned off, memory information is written into a hard disk, then all components stop working, and the power consumption of the node is generally below 10W, the node in this state can be defined as a third energy-saving state. Detecting whether the running power of a certain node in a preset energy-saving state meets the preset fourth power consumption, and if the running power of the node is detected to meet the preset fourth power consumption, marking that the node is in the fourth energy-saving state. For example, if all devices including a certain node connected to a power supply are turned off, only the BMC (Baseboard Manager Controller, baseboard management controller) is kept powered on, so that the mahonia consumption of the node approaches the power supply system self-consumption, and the power consumption of the node is generally about 0W, the node in this state may be defined as a fourth energy-saving state.
In some embodiments, if the wake-up duration of a node is within 1 second, the node is in a first energy saving state; if the wake-up time of a certain node is within a few seconds, the node is in a second energy-saving state; if the wake-up time of a certain node is 10 seconds, the node is in a third energy-saving state; if the wake-up of a certain node needs a complete boot flow, the node is in a fourth energy-saving state.
In some embodiments, the cluster energy saving management method further comprises: detecting whether the operation states of all nodes entering a preset energy-saving state meet the operation awakening requirement of the preset nodes or not; when detecting that the nodes to be awakened exist in all the nodes, the operation states of the nodes meet the operation awakening requirements of the preset nodes, awakening the nodes to be awakened. In this embodiment, the node in the first energy saving state is converted into the fourth energy saving state, the second energy saving state or the normal running state according to the actual running state by presetting the node running wake-up requirement, the node in the second energy saving state is converted into the first energy saving state or the third energy saving state according to the actual running state, the node in the third energy saving state is converted into the second energy saving state or the fourth energy saving state according to the actual running state, and the node in the fourth energy saving state is converted into the first energy saving state according to the actual running state.
In some embodiments, when detecting a node to be awakened, acquiring the total number of nodes currently in a preset energy-saving state; acquiring the total amount of the current node used resources matched with the total amount of the nodes; and if the total amount of the used resources of the current node meets the preset node resource changing rule, updating the actual energy-saving node number. In this embodiment, for example, it is assumed that the total amount of used resources of the current node that matches the total number of nodes is obtained as b1, the total amount of used resources of the node is denoted as b, the amount of resources of a single node is denoted as a, the available proportion of resources of a single node is denoted as k, and the preset node resource change rule is |b1-b|not less than 2×a×k. In other embodiments, the preset node resource change rule may be |b1-b|1.5×aχ k or |b1-b|2.5×aχ k, which may be set according to the actual situation, and the preset node resource change rule is not limited in this application. For example, when the size of the cluster is small (small private cloud cluster), then |b1-b| may be set to 0.5, 1, or 2 times a×k, and when the size of the cluster is large (large public cloud cluster), then |b1-b| may be set to 10, 15, or 20 times a×k.
In some embodiments, non-idle nodes are acquired; detecting whether each node in the non-idle nodes meets a preset energy-saving state, and when detecting that a certain node in the non-idle nodes meets the preset energy-saving state, converting the certain node in the non-idle nodes into the preset energy-saving state. For example, when a certain node is in a non-idle state (i.e., a normal running state), the cluster energy-saving management system detects that the node meets a preset energy-saving state, and if the running condition of the node is that all devices are opened (e.g., a CPU, a memory, a hard disk, etc. are all working), the node transitions the node from the normal running state to the preset energy-saving state according to the actual running condition (e.g., the cluster energy-saving management system detects that the node is not required to keep in the normal running state, and the CPU of the node is required to be closed, and other components are required to work normally).
According to the cluster energy-saving management method, first, the number of first theoretical nodes and the number of second theoretical nodes are determined according to state information of cluster resource operation conditions, and then the number of actual energy-saving nodes is obtained based on the number of first theoretical nodes and the number of second theoretical nodes. Then, the number of nodes entering different energy-saving states is obtained by utilizing the preset first distribution value, the preset second distribution value and the preset third distribution value, so that the power consumption of the cluster is reduced, and the normal operation of the cluster is not influenced. And finally, updating the number of the actual energy-saving nodes according to a preset node resource changing rule. Therefore, when the number of the actual energy-saving nodes is changed, the corresponding nodes can be timely adjusted to enter a preset energy-saving state, so that cluster operation is ensured, and power consumption is reduced. Meanwhile, according to the actual running condition of a certain node, the certain node can be cyclically brought into a first energy-saving state, a second energy-saving state, a third energy-saving state and a fourth energy-saving state, so that the activity of the node is kept. In addition, at the same time, part of nodes enter a preset energy-saving state, and a plurality of different energy-saving states exist, corresponding node numbers are distributed to each energy-saving state, and each node is adjusted to periodically circulate in the preset energy-saving state according to the running condition of an actual cluster, so that cluster power consumption is reduced.
In some embodiments, as shown in fig. 2, the electronic device 100 further discloses an electronic device 100, where the electronic device 100 includes a memory 20 and a processor 30, the memory 20 is used for storing instructions, and the processor 30 is used for calling the instructions in the memory 20, so that the electronic device 100 executes steps in the cluster energy saving management method in the above embodiment, for example, steps S100 to S300 shown in fig. 1. The electronic device 100 may be a device with a clustered energy saving management system deployed. In the embodiment of the present application, description is made taking an example in which the electronic device 100 is a device in which a cluster energy saving management system is disposed.
It will be appreciated by those skilled in the art that the schematic diagram is merely an example of the electronic device 100 and is not meant to be limiting of the electronic device 100, and may include more or fewer components than shown, or may combine certain components, or different components, e.g., the electronic device 100 may also include input-output devices, network access devices, buses, etc.
The processor 30 may be a central processing unit (Central Processing Unit, CPU), but may also be other general purpose processors, digital signal processors (Digital Signal Processor, DSP), application specific integrated circuits (Application Specific Integrated Circuit, ASIC), off-the-shelf programmable gate arrays (Field-Programmable Gate Array, FPGA) or other programmable logic devices, discrete gate or transistor logic devices, discrete hardware components, or the like. The general purpose processor may be a microprocessor, a single-chip microcomputer or the processor 30 may be any conventional processor or the like.
The memory 20 may be used to store computer programs 40 and/or modules/units, and the processor 30 implements various functions of the electronic device 100 by running or executing the computer programs 40 and/or modules/units stored in the memory 20, and invoking data stored in the memory 20. The memory 20 may mainly include a storage program area that may store an operating system, application programs required for at least one function (such as a sound playing function, an image playing function, etc.), and a storage data area; the storage data area may store data (such as audio data) created according to the use of the electronic device 100, and the like. In addition, the memory 20 may include high-speed random access memory, and may also include nonvolatile memory, such as a hard disk, memory, plug-in hard disk, smart Media Card (SMC), secure Digital (SD) Card, flash Card (Flash Card), at least one disk storage device, flash memory device, or other nonvolatile solid state storage device.
The present application also discloses a computer-readable storage medium storing computer instructions that, when executed on the electronic device 100, cause the electronic device 100 to perform the cluster energy-saving management method of the present embodiment. The computer readable storage medium may include: any entity or device capable of carrying the computer program code, a recording medium, a U disk, a removable hard disk, a magnetic disk, an optical disk, a computer Memory, a Read-Only Memory (ROM), a random access Memory (RAM, random Access Memory), an electrical carrier signal, a telecommunications signal, a software distribution medium, and so forth.
In addition, the cluster energy-saving management method, the electronic device and the computer storage medium provided by the embodiment of the invention are described in detail, and specific examples are adopted to illustrate the principle and the implementation of the invention, and the description of the above embodiments is only used for helping to understand the method and the core idea of the invention; meanwhile, as those skilled in the art will have variations in the specific embodiments and application scope in accordance with the ideas of the present invention, the present description should not be construed as limiting the present invention in view of the above.
Claims (10)
1. The cluster energy-saving management method is characterized by comprising the following steps of:
obtaining a first theoretical energy-saving node quantity and a second theoretical energy-saving node quantity based on state information for representing the running condition of cluster resources, wherein the state information comprises the total number of nodes, the total amount of node used resources, the amount of single node resources, the available proportion of single node resources and the reserved node quantity, and the second theoretical energy-saving node quantity is determined according to the total number of nodes, the total amount of node used resources, the amount of single node resources, the available proportion of single node resources and the reserved node quantity;
determining the number of actual energy-saving nodes according to the number of the first theoretical energy-saving nodes and the number of the second theoretical energy-saving nodes;
and distributing each node in the actual energy-saving node quantity to enter a preset energy-saving state according to a preset resource distribution rule.
2. The cluster energy-saving management method according to claim 1, wherein the obtaining the first theoretical energy-saving node number and the second theoretical energy-saving node number based on the state information for characterizing the running condition of the cluster resources includes:
obtaining the number of used resource nodes based on the total amount of the used resources of the nodes, the single node resource amount and the single node resource availability ratio;
and obtaining the second theoretical energy-saving node number based on the node total number, the used resource node number and the reserved node number.
3. The cluster energy saving management method of claim 1, wherein the determining the actual number of energy saving nodes according to the first theoretical number of energy saving nodes and the second theoretical number of energy saving nodes comprises:
if the number of the first theoretical energy-saving nodes is larger than the number of the second theoretical energy-saving nodes, the number of the second theoretical energy-saving nodes is used as the number of the actual energy-saving nodes;
and if the first theoretical energy-saving node number is smaller than or equal to the second theoretical energy-saving node number, taking the first theoretical energy-saving node number as the actual energy-saving node number.
4. The cluster power saving management method of claim 1, wherein the preset power saving state comprises a first power saving state, a second power saving state, a third power saving state, and a fourth power saving state; the step of allocating each node in the actual energy-saving node number to enter a preset energy-saving state according to a preset resource allocation rule comprises the following steps:
determining the number of nodes in a first energy saving state entering the first energy saving state based on the number of the actual energy saving nodes and a preset first distribution value;
obtaining a first intermediate energy-saving node number based on the actual energy-saving node number and the first energy-saving state node number;
determining the number of nodes in a second energy-saving state entering the second energy-saving state according to the number of the first intermediate energy-saving nodes and a preset second allocation value;
obtaining a second intermediate energy-saving node number based on the actual energy-saving node number, the first energy-saving state node number and the second energy-saving state node number;
determining the number of nodes in a third energy-saving state entering the third energy-saving state according to the number of the second intermediate energy-saving nodes and a preset third distribution value;
and determining a fourth energy-saving state node quantity entering the fourth energy-saving state based on the actual energy-saving node quantity, the first energy-saving state node quantity, the second energy-saving state node quantity and the third energy-saving state node quantity.
5. The cluster energy saving management method of claim 4, further comprising:
detecting whether the running power of a certain node in the preset energy-saving state meets the preset first consumption power or not, and if the running power of the node is detected to meet the preset first consumption power, marking that the node is in the first energy-saving state;
detecting whether the running power of a certain node in the preset energy-saving state meets the preset second consumption power or not, and if the running power of the node is detected to meet the preset second consumption power, marking that the node is in the second energy-saving state;
detecting whether the running power of a certain node in the preset energy-saving state meets the preset third power consumption or not, and if the running power of the node is detected to meet the preset third power consumption, marking that the node is in the third energy-saving state;
detecting whether the running power of a certain node in the preset energy-saving state meets the preset fourth power consumption, and if the running power of the node is detected to meet the preset fourth power consumption, marking that the node is in the fourth energy-saving state.
6. The cluster power saving management method of claim 5, further comprising:
detecting whether the operation states of all the nodes entering the preset energy-saving state meet the operation awakening requirement of the preset nodes or not;
when detecting that the nodes to be awakened exist in all the nodes, the operation states of the nodes meet the operation awakening requirements of the preset nodes, awakening the nodes to be awakened.
7. The cluster power saving management method of claim 6, wherein the cluster power saving management method further comprises:
when the node to be awakened is detected, acquiring the total number of nodes currently in the preset energy-saving state;
acquiring the total amount of the current node used resources matched with the total amount of the nodes;
and if the total amount of the resources used by the current node meets a preset node resource changing rule, updating the actual energy-saving node amount.
8. The cluster power saving management method of claim 1, wherein the cluster power saving management method further comprises:
acquiring a non-idle node;
detecting whether each node in the non-idle nodes meets the preset energy saving state, and switching a certain node in the non-idle nodes to the preset energy saving state when detecting that the certain node in the non-idle nodes meets the preset energy saving state.
9. An electronic device comprising a processor and a memory, wherein the memory is configured to store instructions, and wherein the processor is configured to invoke the instructions in the memory, so that the electronic device performs the cluster power saving management method according to any of claims 1 to 8.
10. A computer readable storage medium storing computer instructions which, when run on an electronic device, cause the electronic device to perform the cluster power saving management method of any one of claims 1 to 8.
Priority Applications (1)
| Application Number | Priority Date | Filing Date | Title |
|---|---|---|---|
| CN202310643706.9A CN116449935B (en) | 2023-06-02 | 2023-06-02 | Cluster energy-saving management method, electronic equipment and computer storage medium |
Applications Claiming Priority (1)
| Application Number | Priority Date | Filing Date | Title |
|---|---|---|---|
| CN202310643706.9A CN116449935B (en) | 2023-06-02 | 2023-06-02 | Cluster energy-saving management method, electronic equipment and computer storage medium |
Publications (2)
| Publication Number | Publication Date |
|---|---|
| CN116449935A true CN116449935A (en) | 2023-07-18 |
| CN116449935B CN116449935B (en) | 2023-11-21 |
Family
ID=87135914
Family Applications (1)
| Application Number | Title | Priority Date | Filing Date |
|---|---|---|---|
| CN202310643706.9A Active CN116449935B (en) | 2023-06-02 | 2023-06-02 | Cluster energy-saving management method, electronic equipment and computer storage medium |
Country Status (1)
| Country | Link |
|---|---|
| CN (1) | CN116449935B (en) |
Citations (7)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| CN103645956A (en) * | 2013-12-18 | 2014-03-19 | 浪潮电子信息产业股份有限公司 | Intelligent cluster load management method |
| WO2017166643A1 (en) * | 2016-03-31 | 2017-10-05 | 乐视控股（北京）有限公司 | Method and device for quantifying task resources |
| CN109669526A (en) * | 2018-12-14 | 2019-04-23 | 郑州云海信息技术有限公司 | A method of configuration cluster server energy-saving mode, system, terminal and storage medium |
| CN114327023A (en) * | 2021-12-30 | 2022-04-12 | 上海道客网络科技有限公司 | Energy-saving method and system for Kubernetes cluster, computer medium and electronic equipment |
| CN114710563A (en) * | 2020-12-17 | 2022-07-05 | 华为技术有限公司 | Cluster energy saving method and device |
| CN115061813A (en) * | 2022-06-13 | 2022-09-16 | 远景智能国际私人投资有限公司 | Cluster resource management method, device, equipment and medium |
| CN115334084A (en) * | 2022-08-18 | 2022-11-11 | 陈水兰 | Cloud platform based on cloud computing and internet |
-
2023
- 2023-06-02 CN CN202310643706.9A patent/CN116449935B/en active Active
Patent Citations (7)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| CN103645956A (en) * | 2013-12-18 | 2014-03-19 | 浪潮电子信息产业股份有限公司 | Intelligent cluster load management method |
| WO2017166643A1 (en) * | 2016-03-31 | 2017-10-05 | 乐视控股（北京）有限公司 | Method and device for quantifying task resources |
| CN109669526A (en) * | 2018-12-14 | 2019-04-23 | 郑州云海信息技术有限公司 | A method of configuration cluster server energy-saving mode, system, terminal and storage medium |
| CN114710563A (en) * | 2020-12-17 | 2022-07-05 | 华为技术有限公司 | Cluster energy saving method and device |
| CN114327023A (en) * | 2021-12-30 | 2022-04-12 | 上海道客网络科技有限公司 | Energy-saving method and system for Kubernetes cluster, computer medium and electronic equipment |
| CN115061813A (en) * | 2022-06-13 | 2022-09-16 | 远景智能国际私人投资有限公司 | Cluster resource management method, device, equipment and medium |
| CN115334084A (en) * | 2022-08-18 | 2022-11-11 | 陈水兰 | Cloud platform based on cloud computing and internet |
Non-Patent Citations (1)
| Title |
|---|
| （美）耿怀渝等: "数据中心手册", 机械工业出版社, pages: 342 - 343 * |
Also Published As
| Publication number | Publication date |
|---|---|
| CN116449935B (en) | 2023-11-21 |
Similar Documents
| Publication | Publication Date | Title |
|---|---|---|
| US20160378570A1 (en) | Techniques for Offloading Computational Tasks between Nodes | |
| US20210117307A1 (en) | Automated verification of platform configuration for workload deployment | |
| CN109815007A (en) | Thread control method, device, electronic equipment and storage medium based on cloud monitoring | |
| CN104335529A (en) | Network routing based on resource availability | |
| CN107203255A (en) | Power-economizing method and device are migrated in a kind of network function virtualized environment | |
| CN112162852A (en) | Multi-architecture CPU node management method, device and related components | |
| CN107943269A (en) | Schedule job control method, device, terminal device and storage medium | |
| CN109840141A (en) | Thread control method, device, electronic equipment and storage medium based on cloud monitoring | |
| US20210406053A1 (en) | Rightsizing virtual machine deployments in a cloud computing environment | |
| CN108205622A (en) | The authority control method and device of a kind of application program for mobile terminal | |
| CN109800261A (en) | Dynamic control method, device and the relevant device of double data library connection pool | |
| JP2015106313A (en) | Information processing system, management device, control method for information processing system, and control program for management device | |
| CN116449935B (en) | Cluster energy-saving management method, electronic equipment and computer storage medium | |
| CN116954873B (en) | Heterogeneous computing system, and method, device, equipment and medium for selecting power nodes of heterogeneous computing system | |
| CN116382855B (en) | Virtual machine migration method, electronic equipment and computer storage medium | |
| CN111209333A (en) | Data updating method, device, terminal and storage medium | |
| CN110806918A (en) | Virtual machine operation method and device based on deep learning neural network | |
| EP4206915A1 (en) | Container creation method and apparatus, electronic device, and storage medium | |
| CN109002381A (en) | Process communication monitoring method, electronic device and computer readable storage medium | |
| CN113157390B (en) | Container resource management method and device for power application in power terminal | |
| CN116932194A (en) | Thread execution method, thread execution device, electronic equipment and computer readable storage medium | |
| CN111143055A (en) | Virtual cloud host pre-allocation method and device, readable storage medium and electronic equipment | |
| CN116627240B (en) | Power consumption adjustment method, device, electronic equipment, storage medium and program product | |
| CN109104497A (en) | A kind of method for processing business and device based on cloud platform | |
| CN114780170B (en) | Container resource configuration method, device, equipment 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 |