CN112130955A - Virtual machine scheduling method based on converged framework cloud platform - Google Patents
Virtual machine scheduling method based on converged framework cloud platform Download PDFInfo
- Publication number
- CN112130955A CN112130955A CN202010908221.4A CN202010908221A CN112130955A CN 112130955 A CN112130955 A CN 112130955A CN 202010908221 A CN202010908221 A CN 202010908221A CN 112130955 A CN112130955 A CN 112130955A
- Authority
- CN
- China
- Prior art keywords
- virtual machine
- scheduling
- cloud platform
- node
- method based
- 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
-
- 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
-
- 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
Landscapes
- Engineering & Computer Science (AREA)
- Software Systems (AREA)
- Theoretical Computer Science (AREA)
- Physics & Mathematics (AREA)
- General Engineering & Computer Science (AREA)
- General Physics & Mathematics (AREA)
- Computer Networks & Wireless Communication (AREA)
- Signal Processing (AREA)
- Stored Programmes (AREA)
Abstract
The invention relates to the field of virtual machine scheduling, and discloses a virtual machine scheduling method based on a fusion framework cloud platform. The scheduling is divided into scheduling when starting up and scheduling when running; the scheduling is to directly start the virtual machine at the mirror image storage node when starting up, and the scheduling in operation is to migrate the running virtual machine from the source node to the mirror image storage node for running, thereby realizing the scheduling in operation. The scheduling method provided by the invention reduces data exchange among nodes, reduces network pressure, and after scheduling is completed, virtual machine processes and disk reading are operated in the same node, thereby shortening IO paths and improving the performance of the virtual machine.
Description
Technical Field
The invention relates to the field of virtual machine scheduling, in particular to a virtual machine scheduling method based on a fusion framework cloud platform.
Background
With the advent of the cloud computing era, the use of virtualization technology is inevitable. The virtualization technology enables the physical resources which are originally fixed and not easy to stretch to be abstracted into configurable virtual resources by using software, the original physical boundary is broken through by the flexible mode, and the computing resources and the storage resources required by the virtual machine are distributed in different physical nodes. In a virtualization environment, original physical equipment is virtualized into a plurality of virtual machines for users to use, a single node can run the plurality of virtual machines, and optimal scheduling of the virtual machines is an important link for improving the utilization rate of virtual resources and improving reliability.
Based on a cloud platform with a fusion architecture, nodes in the platform provide computing resources (CPU and memory) and also provide storage resources, a virtual machine runs at a certain node and uses the CPU and memory resources of the node, but the node at which the disk image of the virtual machine should be stored is calculated according to a hash algorithm. Each node of the platform is provided with a hash value range, a hash value is obtained by calculating the disk image of the virtual machine through a hash algorithm, and the node which the virtual machine image should be stored in is determined by comparing the hash value range of the node with the hash value.
At present, virtual machine scheduling is mainly performed through quantity balancing and physical resource (CPU + memory) utilization balancing, the quantity balancing scheduling is to schedule a virtual machine to balance the quantity of virtual machines of each node, and the physical resource scheduling is to schedule a migration virtual machine to balance the physical resource utilization rate of each node. However, these scheduling methods have a defect in a converged storage environment, for example, as shown in fig. 1, a cloud platform has a node a and a node B, according to the existing scheduling method, a virtual machine VM1 and a virtual machine VM3 operate at the node a, a virtual machine VM2 and a virtual machine VM4 operate at the node B, an image of the virtual machine VM1 is stored at the node B, and an image of the virtual machine VM2 is stored at the node a, in this case, data reading of the virtual machine needs to be accessed across nodes through a network, which increases the pressure on the network and also affects the usability of the virtual machine.
Disclosure of Invention
The technical problem to be solved by the invention is as follows: aiming at the existing problems, the virtual machine scheduling method based on the fusion framework cloud platform is provided, and the virtual machine scheduling method is mainly realized by acquiring the storage position of the virtual machine mirror image and then by the storage position.
The technical scheme adopted by the invention is as follows: a virtual machine scheduling method based on a converged architecture cloud platform comprises the following steps:
determining and acquiring a storage position of a virtual machine mirror image;
and when the virtual machine is started and operated, scheduling the virtual machine according to the acquired mirror image storage position.
Further, the step of determining and acquiring a storage location of the virtual machine image includes:
acquiring a disk name for storing a virtual machine image and calculating a hash value of the disk;
and according to the hash value of the disk, determining the position of the disk in the node by contrasting the hash value range of the node, and further acquiring the storage position of the virtual machine image.
Further, the scheduling step of the virtual machine during startup comprises:
and acquiring the storage position of the virtual machine image, and directly starting the virtual machine at the storage position of the virtual machine image to finish scheduling.
Further, the scheduling step of the virtual machine at runtime includes:
and acquiring the storage position of the virtual machine mirror image, migrating the running virtual machine from the source node to the mirror image storage point for running, and finishing scheduling.
Further, all the virtual machines are sequentially queued to be scheduled according to the scheduling step during startup or the scheduling step during running.
Further, the hash value range of the cloud platform node is set by the system when the node is created.
Compared with the prior art, the beneficial effects of adopting the technical scheme are as follows:
1) the invention realizes a virtual machine scheduling migration method, reduces data exchange among nodes and reduces network pressure;
2) after the scheduling is completed, the virtual machine process and the disk reading are operated at the same node, so that the io path is shortened, and the performance of the virtual machine is improved.
Drawings
FIG. 1 is a schematic diagram of a relationship between a node where a virtual machine runs and a node where mirror image storage is located.
FIG. 2 is a schematic flow diagram of the process.
FIG. 3 is a flow diagram illustrating a process for obtaining a storage location of a virtual machine image.
Fig. 4 is a schematic flowchart of scheduling when the virtual machine is powered on.
FIG. 5 is a flow diagram illustrating scheduling of virtual machine runtime.
Detailed Description
The invention is further described below with reference to the accompanying drawings.
The embodiment provides a virtual machine scheduling method based on a converged architecture cloud platform, which includes the following two steps, as shown in fig. 2:
step 1: determining and acquiring a storage position of a virtual machine mirror image;
step 2: and when the virtual machine is started and operated, scheduling the virtual machine according to the acquired mirror image storage position.
Specifically, as shown in fig. 3, the obtaining of the storage location of the virtual machine image in step 1 includes the following steps:
step 11: acquiring a disk name for storing a virtual machine mirror image;
step 12: finding the disk and calculating the hash value of the disk;
step 13: comparing the hash value of the disk with the hash value range of the nodes in the cloud platform to find out the position of the disk;
step 14: and acquiring the position of the disk in the node, and then acquiring the storage position of the virtual machine image.
The cloud platform system sets a hash value range for each node when the node disk is created, so that when the storage position of the virtual machine image is searched, the storage position of the virtual machine image in the node can be found only by obtaining the hash value of the disk and comparing the hash value with the hash value range of the cloud platform node.
After the storage position of the virtual machine image is obtained, the scheduling of the virtual machine can be started. The scheduling of the virtual machine is divided into scheduling at startup and scheduling at runtime. All the virtual machines in the cloud platform are sequentially queued to complete scheduling.
Specifically, the scheduling steps during startup are shown in fig. 4:
the method comprises the steps of firstly obtaining a storage node of a virtual machine mirror image, and then directly starting the virtual machine at the mirror image storage node to finish scheduling.
The steps at runtime are shown in FIG. 5:
the method comprises the steps of firstly obtaining a storage node of a virtual machine image, migrating a running virtual machine from a source node to the storage node of the virtual machine image to run, and finishing scheduling, wherein the source node represents a node at which the virtual machine starts to run.
The invention is not limited to the foregoing embodiments. The invention extends to any novel feature or any novel combination of features disclosed in this specification and any novel method or process steps or any novel combination of features disclosed. Those skilled in the art to which the invention pertains will appreciate that insubstantial changes or modifications can be made without departing from the spirit of the invention as defined by the appended claims.
Claims (6)
1. A virtual machine scheduling method based on a converged architecture cloud platform is characterized by comprising the following steps:
determining and acquiring a storage position of a virtual machine mirror image;
and when the virtual machine is started and operated, scheduling the virtual machine according to the acquired mirror image storage position.
2. The virtual machine scheduling method based on the converged architecture cloud platform according to claim 1, wherein the step of determining and acquiring the storage location of the virtual machine image comprises:
acquiring a disk name for storing a virtual machine image and calculating a hash value of the disk;
and determining the position of the disk in the node according to the hash value of the disk and the hash value range of the cloud platform node, and further acquiring the storage position of the virtual machine image.
3. The virtual machine scheduling method based on the converged architecture cloud platform according to claim 1, wherein the scheduling step of the virtual machine during startup comprises:
and acquiring the storage position of the virtual machine image, and directly starting the virtual machine at the storage position of the virtual machine image to finish scheduling.
4. The virtual machine scheduling method based on the converged architecture cloud platform according to claim 1, wherein the scheduling step of the virtual machine during runtime includes:
and acquiring the storage position of the virtual machine mirror image, migrating the running virtual machine from the source node to the mirror image storage point for running, and finishing scheduling.
5. The virtual machine scheduling method based on the converged-architecture cloud platform according to claim 3 or 4, wherein all the virtual machines are sequentially queued for scheduling according to the scheduling step at startup or the scheduling step at runtime.
6. The virtual machine scheduling method based on the converged architecture cloud platform according to claim 1, wherein the hash value range of the cloud platform nodes is set by a system when the nodes are created.
Priority Applications (1)
Application Number | Priority Date | Filing Date | Title |
---|---|---|---|
CN202010908221.4A CN112130955A (en) | 2020-09-02 | 2020-09-02 | Virtual machine scheduling method based on converged framework cloud platform |
Applications Claiming Priority (1)
Application Number | Priority Date | Filing Date | Title |
---|---|---|---|
CN202010908221.4A CN112130955A (en) | 2020-09-02 | 2020-09-02 | Virtual machine scheduling method based on converged framework cloud platform |
Publications (1)
Publication Number | Publication Date |
---|---|
CN112130955A true CN112130955A (en) | 2020-12-25 |
Family
ID=73848749
Family Applications (1)
Application Number | Title | Priority Date | Filing Date |
---|---|---|---|
CN202010908221.4A Pending CN112130955A (en) | 2020-09-02 | 2020-09-02 | Virtual machine scheduling method based on converged framework cloud platform |
Country Status (1)
Country | Link |
---|---|
CN (1) | CN112130955A (en) |
Citations (8)
Publication number | Priority date | Publication date | Assignee | Title |
---|---|---|---|---|
CN104391735A (en) * | 2014-11-14 | 2015-03-04 | 深信服网络科技(深圳)有限公司 | Method and system for scheduling virtual machines in virtualized all-in-one machine cluster |
CN105471959A (en) * | 2015-08-03 | 2016-04-06 | 汉柏科技有限公司 | Starting method and device of virtual machine in cluster network |
CN105511952A (en) * | 2014-09-22 | 2016-04-20 | 苏宁云商集团股份有限公司 | Resource self-migration method and system based on cloud computing platform |
US20160124978A1 (en) * | 2014-11-04 | 2016-05-05 | Rubrik, Inc. | Fault tolerant distributed job scheduler |
CN106850598A (en) * | 2016-12-06 | 2017-06-13 | 中国电子科技集团公司第三十二研究所 | Uniform resource management system and method for whole-ship computing environment |
CN107479942A (en) * | 2016-06-08 | 2017-12-15 | 深圳市深信服电子科技有限公司 | The client operating system of virtual machine starts method and device |
CN108932256A (en) * | 2017-05-25 | 2018-12-04 | 中兴通讯股份有限公司 | Distributed data redistribution control method, device and data management server |
US10761869B2 (en) * | 2017-06-26 | 2020-09-01 | Wangsu Science & Technology Co., Ltd. | Cloud platform construction method and cloud platform storing image files in storage backend cluster according to image file type |
-
2020
- 2020-09-02 CN CN202010908221.4A patent/CN112130955A/en active Pending
Patent Citations (8)
Publication number | Priority date | Publication date | Assignee | Title |
---|---|---|---|---|
CN105511952A (en) * | 2014-09-22 | 2016-04-20 | 苏宁云商集团股份有限公司 | Resource self-migration method and system based on cloud computing platform |
US20160124978A1 (en) * | 2014-11-04 | 2016-05-05 | Rubrik, Inc. | Fault tolerant distributed job scheduler |
CN104391735A (en) * | 2014-11-14 | 2015-03-04 | 深信服网络科技(深圳)有限公司 | Method and system for scheduling virtual machines in virtualized all-in-one machine cluster |
CN105471959A (en) * | 2015-08-03 | 2016-04-06 | 汉柏科技有限公司 | Starting method and device of virtual machine in cluster network |
CN107479942A (en) * | 2016-06-08 | 2017-12-15 | 深圳市深信服电子科技有限公司 | The client operating system of virtual machine starts method and device |
CN106850598A (en) * | 2016-12-06 | 2017-06-13 | 中国电子科技集团公司第三十二研究所 | Uniform resource management system and method for whole-ship computing environment |
CN108932256A (en) * | 2017-05-25 | 2018-12-04 | 中兴通讯股份有限公司 | Distributed data redistribution control method, device and data management server |
US10761869B2 (en) * | 2017-06-26 | 2020-09-01 | Wangsu Science & Technology Co., Ltd. | Cloud platform construction method and cloud platform storing image files in storage backend cluster according to image file type |
Similar Documents
Publication | Publication Date | Title |
---|---|---|
US10339236B2 (en) | Techniques for improving computational throughput by using virtual machines | |
US9619263B2 (en) | Using cooperative greedy ballooning to reduce second level paging activity | |
Liu et al. | Multi-objective scheduling of scientific workflows in multisite clouds | |
CN105468362A (en) | Application deployment method and cloud computing system | |
JP5460430B2 (en) | Dynamic compiler program, dynamic compilation method, and dynamic compilation apparatus | |
US9396004B1 (en) | System and method for management of a configuration of a virtual machine | |
US10785109B1 (en) | Automated generation of a network service design | |
CN105573830A (en) | Virtual machine migration method | |
JP5780377B2 (en) | Information processing system and application transfer method | |
JP2018139064A (en) | Virtual computer system and resource allocation method thereof | |
WO2022100439A1 (en) | Workflow patching | |
EP3719645A1 (en) | Extension application mechanisms through intra-process operation systems | |
US20230289207A1 (en) | Techniques for Concurrently Supporting Virtual NUMA and CPU/Memory Hot-Add in a Virtual Machine | |
KR102315102B1 (en) | Method, device, apparatus, and medium for booting a virtual machine | |
CN112631994A (en) | Data migration method and system | |
CN112711462A (en) | Cloud platform virtual CPU hot binding method and device and computer readable storage medium | |
US20220229689A1 (en) | Virtualization platform control device, virtualization platform control method, and virtualization platform control program | |
US10387578B1 (en) | Utilization limiting for nested object queries | |
CN112130955A (en) | Virtual machine scheduling method based on converged framework cloud platform | |
CN112363671B (en) | Virtual machine template mirror image storage method based on fusion framework cloud platform | |
CN113326098B (en) | Cloud management platform supporting KVM virtualization and container virtualization | |
Chen et al. | Improving hadoop monetary efficiency in the cloud using spot instances | |
US11461131B2 (en) | Hosting virtual machines on a secondary storage system | |
CN106991058B (en) | Method and device for processing pre-fetched files | |
TW201328248A (en) | Method for updating system firmware and server system using the same |
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: 20201225 |
|
RJ01 | Rejection of invention patent application after publication |