CN115373804A - Virtual machine scheduling method facing network test in cloud infrastructure - Google Patents
Virtual machine scheduling method facing network test in cloud infrastructure Download PDFInfo
- Publication number
- CN115373804A CN115373804A CN202211322727.2A CN202211322727A CN115373804A CN 115373804 A CN115373804 A CN 115373804A CN 202211322727 A CN202211322727 A CN 202211322727A CN 115373804 A CN115373804 A CN 115373804A
- Authority
- CN
- China
- Prior art keywords
- test
- network
- cloud infrastructure
- resources
- thread
- 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
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]
- G06F9/5061—Partitioning or combining of resources
- G06F9/5077—Logical partitioning of resources; Management or configuration of virtualized resources
-
- 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
- G06F2009/45562—Creating, deleting, cloning virtual machine instances
-
- 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
- G06F2009/45575—Starting, stopping, suspending or resuming virtual machine instances
-
- 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
- G06F2009/45595—Network integration; Enabling network access in virtual machine instances
-
- Y—GENERAL TAGGING OF NEW TECHNOLOGICAL DEVELOPMENTS; GENERAL TAGGING OF CROSS-SECTIONAL TECHNOLOGIES SPANNING OVER SEVERAL SECTIONS OF THE IPC; TECHNICAL SUBJECTS COVERED BY FORMER USPC CROSS-REFERENCE ART COLLECTIONS [XRACs] AND DIGESTS
- Y02—TECHNOLOGIES OR APPLICATIONS FOR MITIGATION OR ADAPTATION AGAINST CLIMATE CHANGE
- Y02D—CLIMATE CHANGE MITIGATION TECHNOLOGIES IN INFORMATION AND COMMUNICATION TECHNOLOGIES [ICT], I.E. INFORMATION AND COMMUNICATION TECHNOLOGIES AIMING AT THE REDUCTION OF THEIR OWN ENERGY USE
- Y02D10/00—Energy efficient computing, e.g. low power processors, power management or thermal management
Landscapes
- Engineering & Computer Science (AREA)
- Software Systems (AREA)
- Theoretical Computer Science (AREA)
- Physics & Mathematics (AREA)
- General Engineering & Computer Science (AREA)
- General Physics & Mathematics (AREA)
- Data Exchanges In Wide-Area Networks (AREA)
Abstract
The invention relates to the technical field of network information, and discloses a virtual machine scheduling method facing a network test in cloud infrastructure.
Description
Technical Field
The invention relates to the technical field of network information, in particular to a virtual machine scheduling method facing a network test in a cloud infrastructure.
Background
With the rapid iteration of the internet of things and network application, the network test requirements of some special scenes cannot be met by the traditional network simulation. The future network test facility aims at meeting various network tests and providing a more real environment to simulate the test environment of a user. The current scheduling method is preemptive, and which test runs first occupies all the starting resources and gets first, no matter the experience of other test users.
In order to improve the experience and fairness of a user for establishing a network test, a virtual machine scheduling method facing the network test in a cloud infrastructure is provided, and the method not only improves the experience of the user (even if a large test is started, other user starting tests are not influenced), but also improves the efficiency of test establishment.
Disclosure of Invention
In order to solve the technical problem, the invention provides a virtual machine scheduling method facing a network test in a cloud infrastructure.
In order to solve the technical problems, the invention adopts the following technical scheme:
a virtual machine scheduling method facing network tests in cloud infrastructure carries out the network tests in test resources, and comprises the following steps:
the method comprises the following steps: when a test user needs to perform a network test, sending test information A containing test resource configuration parameters to a portal and sending an instruction for operating the network test; the test resource configuration parameters are used for creating N test resources (N is more than or equal to 1, N is a parameter which can be set) required by the network test through the cloud infrastructure, and each test resource comprises a virtual machine and a network environment of the virtual machine;
step two: the portal submits the test information A to the orchestrator to carry out a test resource request;
step three: the orchestrator comprises a queue and a thread bound with the queue; traversing all queues after the orchestrator receives the test information each time to obtain a queue B with the least test resources to be created, and sequentially stuffing the test resources to be created in the test information A into the queue B;
step four: starting a network test after test resources are sequentially created by calling an interface of the cloud infrastructure according to a first-in first-out sequence from a queue bound by each thread;
if a certain thread C is in an idle state, the queue bound by the thread C is empty, at the moment, the thread C takes a test resource to be created from the head of the other queues, creates the test resource by calling an interface of the cloud infrastructure and starts the network test;
if a certain thread D is blocked when the test resource is created and started, ending the thread D, and creating a new thread to be bound with the queue bound by the thread D;
step five: and the portal displays the starting state of the network test to the test user.
The cloud infrastructure in the invention is a cloud data center.
Further, before a test user sends test information A to a portal and sends an instruction for running a network test in the first step, firstly planning a network topology, the size of an operating system and virtual resources (including a memory, a GPU or a CPU) required by each network node (virtual machine), controlling the bandwidth and delay of a link between the network nodes, and storing the test information A in a portal background through a programming interface; the portal background checks the test resources which are prepared and applied by the test user through the test information A, and if the remaining hardware resources of the cloud data center are not enough, the portal background directly informs the test user that the network test is failed to be established; the subsequent management of the network test is handed to the portal to be completed; after the above contents are ready, the user sends out an instruction for running the network test.
Further, in the second step, when the portal submits the test information a to the orchestrator and makes a test resource request, the orchestrator checks: whether the grade of the user meets the application condition (for example, the bandwidth applied by the low-grade user can only be 1 MB) or not, whether the mirror image exists or not and whether the residual hardware resources of the cloud data center are sufficient or not are tested.
When the orchestrator checks, in order to reduce the time for starting a network test, the invention changes the checking mode from the original 'cloud-tuned data center interface real-time query' into 'portal maintenance resource table and local checking', such as portal storage mirror name, and synchronizes the latest mirror image of the cloud data center in time, and when a user applies for a test resource, whether the local checking mirror image exists or not; other resources are checked locally for the remainder of the required resources in a similar manner.
The test resource configuration parameters comprise the number of virtual machines required by a network test, the memory of the virtual machines, the number of CPU cores, the number of GPU cards, the capacity of a disk, system images, link bandwidth, link quality and other various virtual or hardware resources; the virtual resources and the hardware resources are collectively called as test resources; the test resources are logically isolated through the cloud data center, and the influence on other network tests is avoided.
The third step of the invention is that the orchestrator dispatches the network test to the thread through the dispatching method to prepare for starting, the dispatching method in the prior art puts all the test resources to be created into a queue, and starts one by one according to the order of first in first out; the scheduling method classifies the test resources to be created according to the test and puts the test resources into different queues, and the queues are not affected mutually. Typically, the number of queues and threads is the same after the orchestrator initializes all the queues and threads.
Furthermore, when the interface of the cloud infrastructure is called to create the test resource in the fourth step, the configuration parameter of the test resource is simply checked; after verification, logic slicing is performed on hardware in the cloud infrastructure according to the test resource configuration parameters, for example, 40GB is divided from a 1TB solid state disk as a main partition of a virtual machine, other resources are also sliced similarly, after all hardware or network resources are sliced, the network test is in a state of being started, and a portal is waited to obtain a network test state.
Further, in the fifth step, when the portal shows the starting state of the network test and the states of the test resources to the test users, the orchestrator polls the creation state of each test resource in the cloud infrastructure and the starting state of the network test, waits for all the test resources required by the network test to be created and the network test to be started, sends the started state of the network test to the portal, and shows the started state of the network test to the test users.
According to the technical scheme, the virtual machine scheduling method facing the network test in the cloud infrastructure is provided aiming at the requirements of fairness, high efficiency and the like when the existing network test is started, so that the experience of a user in the process of establishing the network test is improved.
The invention mainly depends on a data center, abstracts calculation, storage, transmission, a data set and service in the data center into resources, constructs a resource pool, and isolates an operating system and application programs thereof into a safe and portable virtual machine and a virtual network element; in the invention, scheduling and management of virtual resources are realized through orchestrator service, but the traditional scheduling method is not fair enough in resource scheduling, as shown in fig. 2, once a large network test is started, the network test occupies all starting resources (including queues, threads and the like), and at this time, if other users need to start the network test, the network test can only be waited for the completion of the start of the large network test, which may result in: test blocking can greatly affect the time consumed for starting tests of other users, and especially the blocking of a large test can cause the user experience to be poor, doubts about the service capability of the platform and finally cause the user loss.
The invention focuses on improving user experience, and provides a high-performance virtual machine scheduling method to reduce 'start delay' caused by a large-scale test blocking queue, and the advantages of the invention will be described through several scenes in a specific implementation mode.
Drawings
FIG. 1 is a schematic diagram of a virtual machine scheduling method according to the present invention;
FIG. 2 is a diagram illustrating a prior art scenario with a large trial blocking queue;
FIG. 3 is an initialization diagram of the scheduling method of the present invention;
fig. 4 is a schematic flow chart illustrating a scheduling method under normal conditions according to a second embodiment of the present invention;
FIG. 5 is a flowchart illustrating a scheduling method for a large-scale test in the third embodiment of the present invention;
fig. 6 is a flowchart illustrating a scheduling method when there is a thread block in the fourth embodiment of the present invention.
Detailed Description
In order to make the objects, technical solutions and advantages of the present invention clearer, the technical solutions of the present invention will be clearly and completely described below with reference to the accompanying drawings in the embodiments of the present invention, and it is obvious that the described embodiments are some, but not all embodiments of the present invention.
[ EXAMPLES ] A method for producing a semiconductor device
As shown in fig. 3, the initialization process of the virtual machine scheduling method for network test in the cloud infrastructure of the present invention includes the following steps:
(1) Creating a thread;
(2) Creating a queue;
(3) Binding the thread and the queue;
(4) Selecting the shortest queue when the virtual machine is enqueued;
(5) Calling an interface of a cloud data center by a thread;
(6) The operation is started.
[ example two ]
As shown in fig. 4, the normal scheduling process of the virtual machine scheduling method for the network test in the cloud infrastructure of the present invention includes the following steps:
(1) A test user creates a network test;
(2) Selecting a queue with the shortest queue length for enqueuing;
(3) Calling an interface of a cloud data center to create a virtual machine and start a network test;
(4) Informing the orchestrator after the network test is started successfully;
(5) Repeating (3) and (4) for three times if the network test is failed to be established;
(6) And finishing scheduling.
[ EXAMPLE III ]
As shown in fig. 5, the scheduling process when there is a large test in the virtual machine scheduling method for network test in the cloud infrastructure of the present invention includes the following steps:
(1) A user creates a large test; the large-scale test is a network test with complexity or the number of network nodes exceeding a set value;
(2) Selecting a queue with the shortest queue length for enqueuing;
(3) Calling an interface of a cloud data center to create a virtual machine and start a large test;
(4) Informing the orchestrator after the large test is started successfully;
(5) Repeating (3) and (4) three times if the large-scale experiment fails to be established;
(6) The idle thread steals the virtual machine from the queue Q1 and executes the steps from (3) to (5);
(7) And finishing scheduling.
[ EXAMPLE IV ]
As shown in fig. 6, the scheduling process when a thread is blocked in the virtual machine scheduling method for network test in the cloud infrastructure of the present invention includes the following steps:
(1) A user creates a network test;
(2) Selecting a queue with the shortest queue length for enqueuing;
(3) If the thread is blocked, the system re-creates a thread and binds the thread with the queue;
(4) The new thread calls an interface of the cloud data center to create a virtual machine and start a network test;
(5) Informing the orchestrator after the network test is started successfully;
(6) Repeating (4) and (5) for three times if the network test is failed to be established;
(7) And finishing scheduling.
It will be evident to those skilled in the art that the invention is not limited to the details of the foregoing illustrative embodiments, and that the present invention may be embodied in other specific forms without departing from the spirit or essential attributes thereof. The present embodiments are therefore to be considered in all respects as illustrative and not restrictive, the scope of the invention being indicated by the appended claims rather than by the foregoing description, and all changes which come within the meaning and range of equivalency of the claims are therefore intended to be embraced therein, and any reference signs in the claims are not intended to be construed as limiting the claim concerned.
Furthermore, it should be understood that although the present description refers to embodiments, not every embodiment may contain only a single embodiment, and such description is for clarity only, and those skilled in the art should integrate the description, and the embodiments may be combined as appropriate to form other embodiments understood by those skilled in the art.
Claims (4)
1. A virtual machine scheduling method facing network tests in cloud infrastructure carries out the network tests in test resources, and comprises the following steps:
the method comprises the following steps: when a test user needs to perform a network test, sending test information A containing test resource configuration parameters to a portal and sending a command for operating the network test; the test resource configuration parameters are used for creating N test resources (N is more than or equal to 1) required by the network test, and each test resource comprises a virtual machine and a network environment of the virtual machine;
step two: the portal submits the test information A to the orchestrator to carry out a test resource request;
step three: the orchestrator comprises a queue and a thread bound with the queue; traversing all queues after the orchestrator receives the test information each time to obtain a queue B with the least test resources to be created, and sequentially stuffing the test resources to be created in the test information A into the queue B;
step four: sequentially creating test resources from the queue bound by each thread according to the first-in first-out sequence and by calling an interface of the cloud infrastructure; starting a network test;
if a certain thread C is in an idle state, the queue bound by the thread C is empty, and at the moment, the thread C takes a test resource to be created from the head of the other queues, creates the test resource by calling an interface of the cloud infrastructure and starts the network test;
if a certain thread D is blocked when the test resource is created and started, ending the thread D, and creating a new thread to be bound with the queue bound by the thread D;
step five: and the portal displays the starting state of the network test to the test user.
2. The method for scheduling the virtual machine for the network test in the cloud infrastructure according to claim 1, wherein: the test resource configuration parameters comprise the number of virtual machines required by a network test, the memory of the virtual machines, the number of CPU cores, the number of GPU cards, the capacity of a disk, system images, link bandwidth and link quality.
3. The method for scheduling the virtual machine for the network test in the cloud infrastructure according to claim 1, wherein: and step four, when the interface of the cloud infrastructure is called to create the test resources, checking the configuration parameters of the test resources, and logically slicing the hardware in the cloud infrastructure according to the configuration parameters of the test resources after the checking to obtain the test resources.
4. The method for scheduling the virtual machine for the network test in the cloud infrastructure according to claim 1, wherein: and fifthly, when the portal shows the starting state of the network test to the test user, the orchestrator polls the creating state of each test resource in the cloud infrastructure and the starting state of the network test, waits for all test resources required by the network test to be created and the network test to be started, sends the started state of the network test to the portal, and shows the started state of the network test to the test user through the portal.
Priority Applications (1)
| Application Number | Priority Date | Filing Date | Title |
|---|---|---|---|
| CN202211322727.2A CN115373804B (en) | 2022-10-27 | 2022-10-27 | Virtual machine scheduling method facing network test in cloud infrastructure |
Applications Claiming Priority (1)
| Application Number | Priority Date | Filing Date | Title |
|---|---|---|---|
| CN202211322727.2A CN115373804B (en) | 2022-10-27 | 2022-10-27 | Virtual machine scheduling method facing network test in cloud infrastructure |
Publications (2)
| Publication Number | Publication Date |
|---|---|
| CN115373804A true CN115373804A (en) | 2022-11-22 |
| CN115373804B CN115373804B (en) | 2023-03-07 |
Family
ID=84073896
Family Applications (1)
| Application Number | Title | Priority Date | Filing Date |
|---|---|---|---|
| CN202211322727.2A Active CN115373804B (en) | 2022-10-27 | 2022-10-27 | Virtual machine scheduling method facing network test in cloud infrastructure |
Country Status (1)
| Country | Link |
|---|---|
| CN (1) | CN115373804B (en) |
Citations (8)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| CN101038559A (en) * | 2006-09-11 | 2007-09-19 | 中国工商银行股份有限公司 | Batch task scheduling engine and dispatching method |
| US20140146055A1 (en) * | 2012-11-29 | 2014-05-29 | International Business Machines Corporation | Use of snapshots to reduce risk in migration to a standard virtualized environment |
| US20180139148A1 (en) * | 2016-11-15 | 2018-05-17 | Vmware, Inc. | Distributed Resource Scheduling Based on Network Utilization |
| CN109240795A (en) * | 2018-08-10 | 2019-01-18 | 南瑞集团有限公司 | A kind of resource regulating method of the cloud computing resources pool model suitable for super fusion IT infrastructure |
| CN112083932A (en) * | 2020-08-18 | 2020-12-15 | 上海交通大学 | Function preheating system and method on virtual network equipment |
| US20210058388A1 (en) * | 2018-10-08 | 2021-02-25 | Oracle International Corporation | Dedicated network authentication and allocation for dedicated virtual machine host clusters |
| CN113595772A (en) * | 2021-07-16 | 2021-11-02 | 南京赛宁信息技术有限公司 | Multi-user scene multiplexing method and device in shooting range environment |
| US20220100645A1 (en) * | 2020-09-29 | 2022-03-31 | Amazon Technologies, Inc. | Automated testing of systems and applications |
-
2022
- 2022-10-27 CN CN202211322727.2A patent/CN115373804B/en active Active
Patent Citations (8)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| CN101038559A (en) * | 2006-09-11 | 2007-09-19 | 中国工商银行股份有限公司 | Batch task scheduling engine and dispatching method |
| US20140146055A1 (en) * | 2012-11-29 | 2014-05-29 | International Business Machines Corporation | Use of snapshots to reduce risk in migration to a standard virtualized environment |
| US20180139148A1 (en) * | 2016-11-15 | 2018-05-17 | Vmware, Inc. | Distributed Resource Scheduling Based on Network Utilization |
| CN109240795A (en) * | 2018-08-10 | 2019-01-18 | 南瑞集团有限公司 | A kind of resource regulating method of the cloud computing resources pool model suitable for super fusion IT infrastructure |
| US20210058388A1 (en) * | 2018-10-08 | 2021-02-25 | Oracle International Corporation | Dedicated network authentication and allocation for dedicated virtual machine host clusters |
| CN112083932A (en) * | 2020-08-18 | 2020-12-15 | 上海交通大学 | Function preheating system and method on virtual network equipment |
| US20220100645A1 (en) * | 2020-09-29 | 2022-03-31 | Amazon Technologies, Inc. | Automated testing of systems and applications |
| CN113595772A (en) * | 2021-07-16 | 2021-11-02 | 南京赛宁信息技术有限公司 | Multi-user scene multiplexing method and device in shooting range environment |
Non-Patent Citations (1)
| Title |
|---|
| 朱斌等: ""星地融合网络架构及关键技术研究"", 《邮电设计技术》 * |
Also Published As
| Publication number | Publication date |
|---|---|
| CN115373804B (en) | 2023-03-07 |
Similar Documents
| Publication | Publication Date | Title |
|---|---|---|
| US5881269A (en) | Simulation of multiple local area network clients on a single workstation | |
| US8352801B2 (en) | Systems, methods, and apparatus to debug a network application by utilizing a cloned network and an interactive debugging technique | |
| CN109831500A (en) | The synchronous method of configuration file and Pod in Kubernetes cluster | |
| CN111338773A (en) | Distributed timed task scheduling method, scheduling system and server cluster | |
| CN108667719A (en) | A kind of real-time Message Passing method and system | |
| CN105701159B (en) | A kind of data synchronization unit and method | |
| CN110489225A (en) | A kind of service expansion method, device and equipment based on message queue | |
| US20220329495A1 (en) | Network resource management method and system, network equipment and readable storage medium | |
| CN105912455A (en) | Business execution method and server | |
| CN113934763B (en) | SQL query method and device for distributed database | |
| CN114153580A (en) | Cross-multi-cluster work scheduling method and device | |
| CN109547162A (en) | Data communications method based on two sets of unidirectional boundaries | |
| CN110413384A (en) | Delayed tasks processing method and processing device, storage medium, electronic equipment | |
| WO2022257302A1 (en) | Method, apparatus and system for creating training task of ai training platform, and medium | |
| CN107357630A (en) | A kind of method, apparatus and storage medium for realizing that virtual machine is synchronous | |
| CN112925611A (en) | Distributed container scheduling method and system based on shared GPU | |
| CN106293911A (en) | Dispatching System, method | |
| CN106412088B (en) | Data synchronization method and terminal | |
| CN114363269B (en) | Message transmission method, system, equipment and medium | |
| CN115373804B (en) | Virtual machine scheduling method facing network test in cloud infrastructure | |
| CN107066341A (en) | Event Routing Framework and method between a kind of software module | |
| CN115688495B (en) | Distributed LVC simulation system collaborative planning method, server and storage medium | |
| CN109032753A (en) | A kind of isomery virtual hard disk trustship method, system, storage medium and Nova platform | |
| CN111522630B (en) | Method and system for executing planned tasks based on batch dispatching center | |
| CN116737560B (en) | Intelligent training system based on intelligent guide control |
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 |