CN112732408A - Method for computing node resource optimization - Google Patents
Method for computing node resource optimization Download PDFInfo
- Publication number
- CN112732408A CN112732408A CN202110060655.8A CN202110060655A CN112732408A CN 112732408 A CN112732408 A CN 112732408A CN 202110060655 A CN202110060655 A CN 202110060655A CN 112732408 A CN112732408 A CN 112732408A
- Authority
- CN
- China
- Prior art keywords
- virtual machine
- computing
- node
- computing nodes
- migration
- 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
Images
Classifications
-
- G—PHYSICS
- G06—COMPUTING; CALCULATING OR COUNTING
- G06F—ELECTRIC DIGITAL DATA PROCESSING
- G06F9/00—Arrangements for program control, e.g. control units
- G06F9/06—Arrangements for program control, e.g. control units using stored programs, i.e. using an internal store of processing equipment to receive or retain programs
- G06F9/44—Arrangements for executing specific programs
- G06F9/455—Emulation; Interpretation; Software simulation, e.g. virtualisation or emulation of application or operating system execution engines
- G06F9/45533—Hypervisors; Virtual machine monitors
- G06F9/45558—Hypervisor-specific management and integration aspects
-
- G—PHYSICS
- G06—COMPUTING; CALCULATING OR COUNTING
- G06F—ELECTRIC DIGITAL DATA PROCESSING
- G06F9/00—Arrangements for program control, e.g. control units
- G06F9/06—Arrangements for program control, e.g. control units using stored programs, i.e. using an internal store of processing equipment to receive or retain programs
- G06F9/46—Multiprogramming arrangements
- G06F9/50—Allocation of resources, e.g. of the central processing unit [CPU]
- G06F9/5083—Techniques for rebalancing the load in a distributed system
-
- G—PHYSICS
- G06—COMPUTING; CALCULATING OR COUNTING
- G06F—ELECTRIC DIGITAL DATA PROCESSING
- G06F9/00—Arrangements for program control, e.g. control units
- G06F9/06—Arrangements for program control, e.g. control units using stored programs, i.e. using an internal store of processing equipment to receive or retain programs
- G06F9/44—Arrangements for executing specific programs
- G06F9/455—Emulation; Interpretation; Software simulation, e.g. virtualisation or emulation of application or operating system execution engines
- G06F9/45533—Hypervisors; Virtual machine monitors
- G06F9/45558—Hypervisor-specific management and integration aspects
- G06F2009/4557—Distribution of virtual machine instances; Migration and load balancing
-
- G—PHYSICS
- G06—COMPUTING; CALCULATING OR COUNTING
- G06F—ELECTRIC DIGITAL DATA PROCESSING
- G06F9/00—Arrangements for program control, e.g. control units
- G06F9/06—Arrangements for program control, e.g. control units using stored programs, i.e. using an internal store of processing equipment to receive or retain programs
- G06F9/44—Arrangements for executing specific programs
- G06F9/455—Emulation; Interpretation; Software simulation, e.g. virtualisation or emulation of application or operating system execution engines
- G06F9/45533—Hypervisors; Virtual machine monitors
- G06F9/45558—Hypervisor-specific management and integration aspects
- G06F2009/45591—Monitoring or debugging support
Landscapes
- Engineering & Computer Science (AREA)
- Software Systems (AREA)
- Theoretical Computer Science (AREA)
- Physics & Mathematics (AREA)
- General Engineering & Computer Science (AREA)
- General Physics & Mathematics (AREA)
- Debugging And Monitoring (AREA)
Abstract
The invention discloses a method for computing node resource optimization, belonging to the field of cloud computing; s1, setting a utilization rate threshold value in the calculation node by using an algorithm; s2, acquiring the states of the computing nodes in the cluster and the virtual machine states running on each computing node; s3 calls an algorithm to acquire the actual use conditions of each computing node and the virtual machine memory of the triggering warning interface; s4, calculating whether to optimize the resources of the computing node through the simulation migration process; s5, outputting the resource optimization method, and selectively executing automatically; s6 storing the output solution and migration process in a log; the migration in the minimum range is realized, namely the highest utilization rate of the acceptable resources of the computing nodes is taken as a threshold value, the resources of the computing nodes are optimized as soon as possible through the migration of as few virtual machines as possible, on one hand, the alarm is eliminated, on the other hand, the running time of high loads of the computing nodes is reduced, the physical host is protected, and the phenomenon that more serious faults are caused to influence the normal and stable running of the virtual machines of the tenants is avoided.
Description
Technical Field
The invention discloses a method for computing node resource optimization, and relates to the technical field of cloud computing.
Background
In the field of cloud computing, OpenStack is a widely used open source solution that can provide cloud environment construction and management for public clouds or private clouds. In a cloud environment, a customer can purchase cloud hosts with different specifications according to requirements, and for the customer, the customer only pays attention to the availability of the cloud hosts and does not pay attention to the actual running host conditions. For the management side, the cloud hosts are virtual machines belonging to different user groups actually, and the virtual machines are screened and sequenced from all the computing node hosts through a scheduling mechanism of the OpenStack during establishment, and finally a suitable computing node is selected to establish one virtual machine. On one hand, the process needs to utilize a virtualization technology to virtualize the resources of the physical machine of the compute node, and the resources can be allocated to the virtual machine, and in addition, it is noted that in order to reasonably utilize the resources of the physical host, the resources such as vcpu or memory and the like are usually over-allocated; on the other hand, in the process of establishing the virtual machine by the OpenStack, the scheduling process is executed by the Nova component, and the component screens a plurality of computing node hosts according to a plurality of configured filters, which is scheduling. In the scheduling process, a plurality of characteristics need to be considered, the most basic is the filtering of resources, including vcpu, disk and memory, the scheduling of the resources filters out the computing node hosts with enough residual resources, and the computing of the resource usage of the computing nodes in the process utilizes the allocated resources; in addition, other filters include available areas, host aggregation, server _ group, computing node characteristics and the like, and through the scheduling process, a most appropriate host can be selected to be used as a host of the virtual machine.
In summary, the OpenStack management side does not consider the actual resource utilization rate when selecting a host computing node for a client virtual machine, and in an actual production environment, once the client virtual machine is established, operations such as migration and the like are generally not performed in order to ensure that the client virtual machine is stably available; the client virtual machine is not migrated unless special conditions such as failure of the computing node or maintenance of the computing node occur. In a production environment, because the use condition management side of a customer virtual machine cannot control, the condition that the resource utilization rate of one or more computing nodes is far higher than that of other computing nodes may occur, at this time, the continuous high memory utilization rate not only can damage the performance of the physical machine and greatly reduce the service life of the physical machine, but also can cause the physical machine to be down in severe cases, thereby affecting the tenant side in a large area and causing serious faults. In addition, the actual utilization rate of the physical machine resources of the computing nodes is monitored in a general production environment, and once the condition of uneven resource utilization occurs, an alarm is triggered and needs to be processed manually by operation and maintenance personnel; therefore, a method for computing node resource optimization is invented to solve the above problems.
Disclosure of Invention
Aiming at the problems in the prior art, the invention provides a method for computing node resource optimization, which adopts the technical scheme that: a method for computing node resource optimization comprises the following specific steps:
s1, setting a utilization rate threshold value in the calculation node by using an algorithm;
s2, acquiring the states of the computing nodes in the cluster and the virtual machine states running on each computing node;
s3 calls an algorithm to acquire the actual use conditions of each computing node and the virtual machine memory of the triggering warning interface;
s4, calculating whether to optimize the resources of the computing node through the simulation migration process;
s5, outputting the resource optimization method, and selectively executing automatically;
s6 saves the output solution and migration process in a log.
The S2 obtains the states of the computing nodes in the cluster, and the specific steps of the virtual machine state running on each computing node are as follows:
s201 calls OpenStack API to acquire information such as resources of all computing nodes;
s202, acquiring virtual machines on all the computing nodes;
s203, a series of target hosts which meet the requirements in the virtual machines are screened out.
The specific steps of screening out a series of destination hosts meeting the requirements in the virtual machine in S203 include:
s2031, screening the computing nodes in the same available area with the target virtual machine;
s2032, screening the computing nodes included in the host aggregation meeting the requirement of the destination virtual machine;
s2033, screening the computing nodes with the unallocated quantity meeting the destination virtual machine;
s2034, the computing nodes screened by the steps are ranked from low to high according to the actual resource utilization rate and used as alternative nodes.
The specific steps of calling the algorithm to acquire the actual use conditions of each computing node and the virtual machine memory of the triggering warning interface by the S3 are as follows:
s301, utilizing an algorithm to butt a Prometous interface of a monitoring alarm solution;
s302, calling a Prometous interface to obtain the actual resource utilization rate of the physical machine of the current computing node in the cloud environment;
s303, calling a Prometous interface to obtain the actual resource usage amount of each virtual machine;
s304, calculating the resource usage of all the computing nodes according to the actual resource usage and the actual resource usage.
The specific steps of the S4 calculating whether to optimize the resources of the compute node through the simulated migration process are as follows:
s401, sorting the resource utilization rates of the computing nodes from high to low C0-Cn according to the resource utilization rates;
s402, comparing the resource utilization rate of each computing node with the threshold value configured in S1, and dividing the resource utilization rate into two groups, namely a source node and a target node;
s403, for the source node, sorting the source node from high to low according to the resource utilization rate, and preferentially processing the computing node with higher load;
s404, arranging the target nodes in an ascending order according to the resource utilization rate, and preferentially enabling the virtual machines to fall on the computing nodes with smaller loads.
The S5 outputs the resource optimization method, and the specific steps of selectively and automatically executing are as follows:
s501, periodically inquiring the virtual machine state and the computing node where the virtual machine state is located;
s502, if the virtual machine state is active in the period, namely the computing node where the virtual machine is located is the target computing node, the virtual machine is successfully migrated;
in S512, if the virtual machine state is an error abnormal state in the period, the virtual machine migration fails;
in the S522 period, if the virtual machine state is in the migration, the virtual machine does not complete the migration;
s503, after the migration in S502 is successful, the migration operation is carried out on the next virtual machine;
s504 suspends the migration work of the virtual machine which is not successfully migrated in S512 and S522.
In the S501, the virtual machine state and the computing node where the virtual machine state is located are periodically queried, and the available computing nodes are screened for one virtual machine, where the scheduling step is as follows:
s5011, screening computing nodes in the same available area with the target virtual machine;
s5012, screening computing nodes included in host aggregation meeting the target virtual machine requirement;
s5013, screening the computing nodes of which the unallocated quantity meets the target virtual machine;
s5014, the computing nodes screened in the steps are ranked from low to high according to the actual resource utilization rate and used as alternative nodes.
The virtual machine migration in S502 to S522 uses a hot migration method.
The invention has the beneficial effects that: aiming at the condition that the use of computing node resources in a cloud environment is uneven, particularly the use rate of certain or some computing node resources exceeds a certain threshold value, the invention provides a method for optimizing the computing node resources, which realizes the migration in the minimum range, namely the highest use rate of the computing node acceptable resources is taken as the threshold value, the computing node resources are optimized as soon as possible through the migration of as few virtual machines as possible, on one hand, the alarm is eliminated, on the other hand, the running time of high loads of the computing nodes is reduced, a physical host is protected, and the phenomena that more serious faults are caused and the normal and stable running of virtual machines of tenants is influenced are avoided.
Drawings
In order to more clearly illustrate the embodiments of the present invention or the technical solutions in the prior art, the drawings needed to be used in the description of the embodiments or the prior art will be briefly introduced below, and it is obvious that the drawings in the following description are some embodiments of the present invention, and for those skilled in the art, other drawings can be obtained according to these drawings without creative efforts.
FIG. 1 is a flow chart of the method of the present invention; fig. 2 is a flow chart of an implementation of an embodiment of the method of the present invention.
Detailed Description
The present invention is further described below in conjunction with the following figures and specific examples so that those skilled in the art may better understand the present invention and practice it, but the examples are not intended to limit the present invention.
In a cloud computing environment, OpenStack is an open source project aiming at providing a solution for the construction management of public clouds and private clouds, and the solution is widely applied in the market. In a public cloud environment or a private cloud environment, cloud hosts can be developed at computing nodes for customers to use based on the requirements of the customers, the cloud hosts are virtualized resources of computing node servers in a cluster, and in order to improve the reasonable utilization rate of the virtualized resources, resources such as a memory, a hard disk and a vcpu are allowed to be over-configured in OpenStack.
In the solution of OpenStack, the Nova component is a core component, and is mainly responsible for scheduling when establishing a cloud host, and the target computing nodes are selected and ordered through a plurality of filters in the scheduling process, and some basic filters include: CoreFilter-filters hosts according to the number of CPUs, RamFilter-selects hosts with sufficient resources according to the specified RAM value, and the like. Once the cloud host is established, in order to ensure that the client cloud host can operate stably, unless the host computing node has an abnormal fault to affect the operation of the cloud host or special conditions such as maintenance of a physical machine of the computing node are required, the cloud host is generally not migrated. Therefore, it may be the case that the memory usage rate of a certain or some computing nodes is actually much higher than that of other computing nodes, which not only causes a high memory load of a few computing nodes, but also affects the performance of the physical machine if the duration is long, and even causes the nodes to be down so as to affect the stable operation of the cloud host of the client.
The invention provides an algorithm for computing node resource optimization, which aims to automatically perform virtual machine migration in a short time and reduce the alarm duration as much as possible once a certain or some computing node resource utilization rate is over high, and the automatic implementation of the operation and maintenance can greatly reduce the workload of operation and maintenance personnel.
A method for computing node resource optimization comprises the following specific steps:
s1, setting a utilization rate threshold value in the calculation node by using an algorithm;
s2, acquiring the states of the computing nodes in the cluster and the virtual machine states running on each computing node;
s3 calls an algorithm to acquire the actual use conditions of each computing node and the virtual machine memory of the triggering warning interface;
s4, calculating whether to optimize the resources of the computing node through the simulation migration process;
s5, outputting the resource optimization method, and selectively executing automatically;
s6 storing the output solution and migration process in a log;
the invention discloses a method for optimizing computing node resources, which can automatically calculate an optimization scheme under the condition of uneven use of the computing node resources and trigger automatic migration of a virtual machine, thereby realizing automatic optimization of the computing node resources;
when the method is used for optimizing the resources of the computing node, firstly, a threshold value is matched for an algorithm, and a manager sets a utilization rate threshold value in the computing node according to S1 by using the algorithm, wherein the threshold value is tolerable computing node memory utilization rate; then, according to S2, acquiring and computing node states of the masses, including total resources, allocated resources, resource super-allocation ratios and the like of each computing node, and simultaneously acquiring virtual machine states running on each computing node, including allocation conditions of each resource;
once the alarm is triggered, the actual use conditions of each computing node of the triggering alarm interface and the virtual machine memory can be obtained according to an S3 calling algorithm; then calculating whether to optimize the resources of the computing node or not through a simulation migration process by utilizing the data according to S4;
once the solution exists, the solution is output and is selectively and automatically executed according to S5, and the finally output solution and the migration process are stored in a log according to S6, so that operation and maintenance personnel or administrators can conveniently trace the process;
further, in step S2, the state of the computing node in the cluster is obtained, and the specific steps of the virtual machine state running on each computing node are as follows:
s201 calls OpenStack API to acquire information such as resources of all computing nodes;
s202, acquiring virtual machines on all the computing nodes;
s203, screening out a series of target hosts which meet the requirements in the virtual machines;
calling and calling an OpenStack API according to S201 to obtain information of resources and the like of all computing nodes, wherein the information comprises the total amount of resources, the over-proportion, the allocated amount and the like of vcpu, disk and memory, then obtaining virtual machines on all the computing nodes according to S202, wherein the virtual machines comprise virtual machine states, resource allocated amount and the like, and screening out a series of target hosts which meet requirements in the virtual machines according to S203;
further, the step S203 of screening out a series of destination hosts that meet the requirement from the virtual machines includes:
s2031, screening the computing nodes in the same available area with the target virtual machine;
s2032, screening the computing nodes included in the host aggregation meeting the requirement of the destination virtual machine;
s2033, screening the computing nodes with the unallocated quantity meeting the destination virtual machine;
s2034, sorting the computing nodes screened in the steps from low to high according to the actual resource utilization rate, and taking the computing nodes as alternative nodes;
for the computing nodes which calculate the resource utilization rate, the computing nodes are divided into two groups according to whether resources need to be optimized or not according to a threshold value configured by an administrator, wherein the two groups are respectively called as a source node and a target node;
for a source node, sorting the source node from high to low according to the resource utilization rate, and preferentially processing a computing node with a higher load; for the target node, sorting the target nodes from low to high according to the resource utilization rate, and preferentially enabling the virtual machine to fall on the computing node with a smaller load;
further, the specific steps of the S3 algorithm call to obtain the actual usage of each computing node and virtual machine memory of the trigger warning interface are as follows:
s301, utilizing an algorithm to butt a Prometous interface of a monitoring alarm solution;
s302, calling a Prometous interface to obtain the actual resource utilization rate of the physical machine of the current computing node in the cloud environment;
s303, calling a Prometous interface to obtain the actual resource usage amount of each virtual machine;
s304, calculating the resource usage of all the computing nodes according to the actual resource usage rate and the actual resource usage;
further, the step of S4 calculating whether to optimize the resource of the compute node through the simulated migration process includes the following specific steps:
s401, sorting the resource utilization rates of the computing nodes from high to low C0-Cn according to the resource utilization rates;
s402, comparing the resource utilization rate of each computing node with the threshold value configured in S1, and dividing the resource utilization rate into two groups, namely a source node and a target node;
s403, for the source node, sorting the source node from high to low according to the resource utilization rate, and preferentially processing the computing node with higher load;
s404, arranging the target nodes in an ascending order according to the resource utilization rate, and preferentially enabling the virtual machines to fall on the computing nodes with smaller loads;
for each virtual machine simulating migration, the simulation migration operation focuses on the change of the resource utilization rate of the source node and the destination node before and after migration, and the simulation migration operation can be completed by using addition and subtraction operations;
further, the S5 outputs the resource optimization method, and the specific steps selectively performed automatically are as follows:
s501, periodically inquiring the virtual machine state and the computing node where the virtual machine state is located;
s502, if the virtual machine state is active in the period, namely the computing node where the virtual machine is located is the target computing node, the virtual machine is successfully migrated;
in S512, if the virtual machine state is an error abnormal state in the period, the virtual machine migration fails;
in the S522 period, if the virtual machine state is in the migration, the virtual machine does not complete the migration;
s503, after the migration in S502 is successful, the migration operation is carried out on the next virtual machine;
s504, the virtual machines which are not successfully migrated in the S512 and the S522 are stopped from migrating;
further, in the step S501 of periodically querying the virtual machine state and the computing node where the virtual machine is located, screening available computing nodes for one virtual machine, where the scheduling step is as follows:
s5011, screening computing nodes in the same available area with the target virtual machine;
s5012, screening computing nodes included in host aggregation meeting the target virtual machine requirement;
s5013, screening the computing nodes of which the unallocated quantity meets the target virtual machine;
s5014, the computing nodes screened in the steps are ranked from low to high according to the actual resource utilization rate and used as alternative nodes.
The virtual machine in S502-S522 is migrated by means of thermal migration;
in summary, as shown in fig. 2, the present invention provides a method for computing node resource optimization:
firstly, an administrator configures a threshold value of acceptable computing node resource utilization rates, wherein the resource utilization rates are taken as memory utilization rates as examples below;
secondly, calculating the resource utilization rates of all the computing nodes, and sequencing the resource utilization rates from high to low (C0-Cn);
thirdly, comparing the resource utilization rate of each computing node with a configured threshold value, and dividing the resource utilization rate into a source node and a target node;
fourthly, counting the number p of the source nodes, if p is 0, not processing, and turning to the twelfth step; otherwise, turning to the fifth step;
step five, starting to traverse the source node, starting from C0;
sixthly, counting the resource usage of all virtual machines on C0, and sequencing the resource usage from high to low (V0-Vm);
seventhly, screening nodes which can be scheduled from the target nodes aiming at the V0, and assuming that the target nodes are (C00-C0 n);
eighthly, starting from C0n, performing simulated migration on the virtual machine, calculating the resource utilization rate of the target node after each migration is completed, and turning to the 9 th step if the resource utilization rate of the target node is smaller than a threshold value; otherwise, turning to the tenth step;
the ninth step, calculating the resource utilization rate of the source node, if the resource utilization rate is less than a threshold value, recording the host virtual machine pair into a solution, adding the source node into the target node, and then turning to the fifth step; otherwise, turning to the tenth step;
step ten, judging whether partial solutions exist or not, if so, trying to migrate the next virtual machine, and turning to the step eight; if the node has no solution, trying the next node and turning to the fifth step;
step ten, trying to migrate the next virtual machine, and turning to step eight;
step ten, outputting a solution;
step thirteen, judging whether the scheme is to be executed directly, if yes, triggering the virtual machine migration; otherwise the algorithm ends.
Finally, it should be noted that: the above examples are only intended to illustrate the technical solution of the present invention, but not to limit it; although the present invention has been described in detail with reference to the foregoing embodiments, it will be understood by those of ordinary skill in the art that: the technical solutions described in the foregoing embodiments may still be modified, or some technical features may be equivalently replaced; and such modifications or substitutions do not depart from the spirit and scope of the corresponding technical solutions of the embodiments of the present invention.
Claims (8)
1. A method for optimizing computing node resources is characterized by comprising the following specific steps:
s1, setting a utilization rate threshold value in the calculation node by using an algorithm;
s2, acquiring the states of the computing nodes in the cluster and the virtual machine states running on each computing node;
s3 calls an algorithm to acquire the actual use conditions of each computing node and the virtual machine memory of the triggering warning interface;
s4, calculating whether to optimize the resources of the computing node through the simulation migration process;
s5, outputting the resource optimization method, and selectively executing automatically;
s6 saves the output solution and migration process in a log.
2. The method of claim 1, wherein the step S2 of obtaining the states of the compute nodes in the cluster, the virtual machine state running on each compute node comprises the steps of:
s201 calls OpenStack API to acquire information such as resources of all computing nodes;
s202, acquiring virtual machines on all the computing nodes;
s203, a series of target hosts which meet the requirements in the virtual machines are screened out.
3. The method as claimed in claim 2, wherein the step of S203 screening out a series of destination hosts that meet the requirement from the virtual machines comprises:
s2031, screening the computing nodes in the same available area with the target virtual machine;
s2032, screening the computing nodes included in the host aggregation meeting the requirement of the destination virtual machine;
s2033, screening the computing nodes with the unallocated quantity meeting the destination virtual machine;
s2034, the computing nodes screened by the steps are ranked from low to high according to the actual resource utilization rate and used as alternative nodes.
4. The method as claimed in claim 3, wherein the step of calling the algorithm S3 to obtain the actual usage of each computing node and virtual machine memory of the trigger alert interface comprises the following steps:
s301, utilizing an algorithm to butt a Prometous interface of a monitoring alarm solution;
s302, calling a Prometous interface to obtain the actual resource utilization rate of the physical machine of the current computing node in the cloud environment;
s303, calling a Prometous interface to obtain the actual resource usage amount of each virtual machine;
s304, calculating the resource usage of all the computing nodes according to the actual resource usage and the actual resource usage.
5. The method as claimed in claim 4, wherein the step of S4 calculating whether to optimize the resources of the compute node by simulating the migration process comprises:
s401, sorting the resource utilization rates of the computing nodes from high to low C0-Cn according to the resource utilization rates;
s402, comparing the resource utilization rate of each computing node with the threshold value configured in S1, and dividing the resource utilization rate into two groups, namely a source node and a target node;
s403, for the source node, sorting the source node from high to low according to the resource utilization rate, and preferentially processing the computing node with higher load;
s404, arranging the target nodes in an ascending order according to the resource utilization rate, and preferentially enabling the virtual machines to fall on the computing nodes with smaller loads.
6. The method as claimed in claim 5, wherein said S5 outputs the resource optimization method, and the specific steps of the selective automatic execution are as follows:
s501, periodically inquiring the virtual machine state and the computing node where the virtual machine state is located;
s502, if the virtual machine state is active in the period, namely the computing node where the virtual machine is located is the target computing node, the virtual machine is successfully migrated;
in S512, if the virtual machine state is an error abnormal state in the period, the virtual machine migration fails;
in the S522 period, if the virtual machine state is in the migration, the virtual machine does not complete the migration;
s503, after the migration in S502 is successful, the migration operation is carried out on the next virtual machine;
s504 suspends the migration work of the virtual machine which is not successfully migrated in S512 and S522.
7. The method as claimed in claim 6, wherein the step of S501 periodically querying the state of the virtual machine and the computing nodes in which the virtual machine is located, and the step of screening available computing nodes for a virtual machine, comprises:
s5011, screening computing nodes in the same available area with the target virtual machine;
s5012, screening computing nodes included in host aggregation meeting the target virtual machine requirement;
s5013, screening the computing nodes of which the unallocated quantity meets the target virtual machine;
s5014, the computing nodes screened in the steps are ranked from low to high according to the actual resource utilization rate and used as alternative nodes.
8. The method according to claim 6 or 7, wherein the virtual machine migration in S502-S522 is performed by means of thermal migration.
Priority Applications (1)
| Application Number | Priority Date | Filing Date | Title |
|---|---|---|---|
| CN202110060655.8A CN112732408A (en) | 2021-01-18 | 2021-01-18 | Method for computing node resource optimization |
Applications Claiming Priority (1)
| Application Number | Priority Date | Filing Date | Title |
|---|---|---|---|
| CN202110060655.8A CN112732408A (en) | 2021-01-18 | 2021-01-18 | Method for computing node resource optimization |
Publications (1)
| Publication Number | Publication Date |
|---|---|
| CN112732408A true CN112732408A (en) | 2021-04-30 |
Family
ID=75593387
Family Applications (1)
| Application Number | Title | Priority Date | Filing Date |
|---|---|---|---|
| CN202110060655.8A Pending CN112732408A (en) | 2021-01-18 | 2021-01-18 | Method for computing node resource optimization |
Country Status (1)
| Country | Link |
|---|---|
| CN (1) | CN112732408A (en) |
Cited By (3)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| CN115208889A (en) * | 2022-05-12 | 2022-10-18 | 国家信息中心 | High-concurrency high-flow video safety isolation transmission method and system |
| CN115242798A (en) * | 2022-06-30 | 2022-10-25 | 阿里巴巴（中国）有限公司 | Task scheduling method based on edge cloud, electronic equipment and storage medium |
| CN115801575A (en) * | 2022-10-13 | 2023-03-14 | 华为云计算技术有限公司 | Method for optimizing performance of cloud service and cloud management platform |
Citations (5)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| US20130145364A1 (en) * | 2011-12-01 | 2013-06-06 | Tunghai University | Method of dynamic resource allocation for a virtual machine cluster |
| CN106020934A (en) * | 2016-05-24 | 2016-10-12 | 浪潮电子信息产业股份有限公司 | Optimized deployment method based on virtual cluster online migration |
| WO2018177042A1 (en) * | 2017-03-27 | 2018-10-04 | 中兴通讯股份有限公司 | Method and device for realizing resource scheduling |
| CN109447264A (en) * | 2018-09-17 | 2019-03-08 | 浙江工业大学 | Virtual machine under cloud computing environment based on VHAM-R model places genetic optimization method |
| CN110389838A (en) * | 2019-07-24 | 2019-10-29 | 北京邮电大学 | A kind of Real-Time Scheduling suitable for virtual resource and online migration management-control method |
-
2021
- 2021-01-18 CN CN202110060655.8A patent/CN112732408A/en active Pending
Patent Citations (5)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| US20130145364A1 (en) * | 2011-12-01 | 2013-06-06 | Tunghai University | Method of dynamic resource allocation for a virtual machine cluster |
| CN106020934A (en) * | 2016-05-24 | 2016-10-12 | 浪潮电子信息产业股份有限公司 | Optimized deployment method based on virtual cluster online migration |
| WO2018177042A1 (en) * | 2017-03-27 | 2018-10-04 | 中兴通讯股份有限公司 | Method and device for realizing resource scheduling |
| CN109447264A (en) * | 2018-09-17 | 2019-03-08 | 浙江工业大学 | Virtual machine under cloud computing environment based on VHAM-R model places genetic optimization method |
| CN110389838A (en) * | 2019-07-24 | 2019-10-29 | 北京邮电大学 | A kind of Real-Time Scheduling suitable for virtual resource and online migration management-control method |
Non-Patent Citations (1)
| Title |
|---|
| 张宝婷等: "基于CoreOS面向负载整合的集群调度研究", 《计算机系统应用》 * |
Cited By (5)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| CN115208889A (en) * | 2022-05-12 | 2022-10-18 | 国家信息中心 | High-concurrency high-flow video safety isolation transmission method and system |
| CN115208889B (en) * | 2022-05-12 | 2023-11-28 | 国家信息中心 | High-concurrency large-flow video safety isolation transmission method and system |
| CN115242798A (en) * | 2022-06-30 | 2022-10-25 | 阿里巴巴（中国）有限公司 | Task scheduling method based on edge cloud, electronic equipment and storage medium |
| CN115242798B (en) * | 2022-06-30 | 2023-09-26 | 阿里巴巴（中国）有限公司 | Task scheduling method based on edge cloud, electronic equipment and storage medium |
| CN115801575A (en) * | 2022-10-13 | 2023-03-14 | 华为云计算技术有限公司 | Method for optimizing performance of cloud service and cloud management platform |
Similar Documents
| Publication | Publication Date | Title |
|---|---|---|
| US11226846B2 (en) | Systems and methods of host-aware resource management involving cluster-based resource pools | |
| CN112732408A (en) | Method for computing node resource optimization | |
| JP6373482B2 (en) | Interface for controlling and analyzing computer environments | |
| US10289441B1 (en) | Intelligent scale-out federated restore | |
| US20190334770A1 (en) | Adaptive software-defined storage for cloud storage workloads | |
| US11169840B2 (en) | High availability for virtual network functions | |
| EP3201717B1 (en) | Monitoring of shared server set power supply units | |
| CN106095335B (en) | A kind of electric power big data elasticity cloud computing storage platform framework method | |
| CN111913670B (en) | Processing method and device for load balancing, electronic equipment and storage medium | |
| CN103210379A (en) | Server system, management method and device | |
| CN111966449B (en) | Virtual machine backup management method, system, terminal and storage medium | |
| CN111181774A (en) | High-availability method, system, terminal and storage medium for MapReduce task | |
| CN112118314B (en) | Load balancing method and device | |
| CN111181780A (en) | HA cluster-based host pool switching method, system, terminal and storage medium | |
| CN104850394A (en) | Management method of distributed application program and distributed system | |
| US20210224121A1 (en) | Virtual machine-initiated workload management | |
| CN113326097A (en) | Virtual machine speed limiting method, device, equipment and computer storage medium | |
| CN111418187A (en) | Scalable statistics and analysis mechanism in cloud networks | |
| CN115145769A (en) | Intelligent network card and power supply method, device and medium thereof | |
| US11625263B2 (en) | Systems and methods for improved management of virtual machine clusters | |
| CN109408597A (en) | A kind of power grid metering big data storage system and its creation method | |
| US11372702B2 (en) | Optimized high availability management using cluster-wide view | |
| CN107426012A (en) | A kind of fault recovery method and its device based on super fusion architecture | |
| CN112612579B (en) | Virtual machine deployment method, storage medium and computer equipment | |
| CN103973811A (en) | High-availability cluster management method capable of conducting dynamic migration |
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 |
Application publication date: 20210430 |
|
| RJ01 | Rejection of invention patent application after publication |