CN110688214A - Management method and system of heterogeneous resource pool - Google Patents
Management method and system of heterogeneous resource pool Download PDFInfo
- Publication number
- CN110688214A CN110688214A CN201810737252.0A CN201810737252A CN110688214A CN 110688214 A CN110688214 A CN 110688214A CN 201810737252 A CN201810737252 A CN 201810737252A CN 110688214 A CN110688214 A CN 110688214A
- Authority
- CN
- China
- Prior art keywords
- resource
- option
- distributed
- virtual
- pool
- 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
- 238000007726 management method Methods 0.000 title claims abstract description 57
- 238000000034 method Methods 0.000 claims abstract description 32
- 238000005516 engineering process Methods 0.000 claims description 13
- 238000013500 data storage Methods 0.000 claims description 6
- 238000010276 construction Methods 0.000 abstract description 7
- 238000010586 diagram Methods 0.000 description 3
- 239000000835 fiber Substances 0.000 description 2
- 238000004458 analytical method Methods 0.000 description 1
- 230000009286 beneficial effect Effects 0.000 description 1
- 238000004891 communication Methods 0.000 description 1
- 230000008878 coupling Effects 0.000 description 1
- 238000010168 coupling process Methods 0.000 description 1
- 238000005859 coupling reaction Methods 0.000 description 1
- 238000007405 data analysis Methods 0.000 description 1
- 230000007547 defect Effects 0.000 description 1
- 238000005065 mining Methods 0.000 description 1
- 238000012986 modification Methods 0.000 description 1
- 230000004048 modification Effects 0.000 description 1
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
- G06F9/46—Multiprogramming arrangements
- G06F9/50—Allocation of resources, e.g. of the central processing unit [CPU]
- G06F9/5005—Allocation of resources, e.g. of the central processing unit [CPU] to service a request
- G06F9/5027—Allocation of resources, e.g. of the central processing unit [CPU] to service a request the resource being a machine, e.g. CPUs, Servers, Terminals
- G06F9/5038—Allocation of resources, e.g. of the central processing unit [CPU] to service a request the resource being a machine, e.g. CPUs, Servers, Terminals considering the execution order of a plurality of tasks, e.g. taking priority or time dependency constraints into consideration
-
- 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
- G06F9/48—Program initiating; Program switching, e.g. by interrupt
- G06F9/4806—Task transfer initiation or dispatching
- G06F9/4843—Task transfer initiation or dispatching by program, e.g. task dispatcher, supervisor, operating system
- G06F9/4881—Scheduling strategies for dispatcher, e.g. round robin, multi-level priority queues
Landscapes
- Engineering & Computer Science (AREA)
- Software Systems (AREA)
- Theoretical Computer Science (AREA)
- Physics & Mathematics (AREA)
- General Engineering & Computer Science (AREA)
- General Physics & Mathematics (AREA)
- Information Retrieval, Db Structures And Fs Structures Therefor (AREA)
Abstract
The invention provides a management method and a system of a heterogeneous resource pool, wherein the method comprises the following steps: displaying a resource option list on an operation interface, wherein the resource option list comprises a plurality of resource options; if a resource option selected by a user in the resource option list is received, displaying a resource application interface corresponding to the received resource option according to the corresponding relation between the preset resource option and the resource application interface; if receiving resource application information input by a user through a resource application interface, generating a resource application request based on the received resource application information; and determining a resource pool to which the resource to be allocated belongs from a plurality of pre-constructed heterogeneous resource pools by using the generated resource application request, and sending the resource application request to the determined resource pool so that the resource pool allocates the resource according to the resource application request. By applying the technical scheme provided by the embodiment of the invention, the construction process of the resource pool management system is simplified, and the resource management cost is saved.
Description
Technical Field
The present invention relates to the field of communications technologies, and in particular, to a method and a system for managing a heterogeneous resource pool.
Background
In the construction process of the private cloud, some resource pools have high requirements on hardware and need to run on a physical server with high performance, and because the resource pools have high dependency on the hardware, the resource pools are inconvenient to uniformly manage.
Disclosure of Invention
The invention aims to overcome the defects of the prior art and provides a management method and a management system of a heterogeneous resource pool so as to simplify the construction process of a resource pool management system and save the resource management cost.
The invention is realized by the following steps:
in a first aspect, the present invention provides a method for managing a heterogeneous resource pool, where the method includes:
step 1), displaying a resource option list on an operation interface, wherein the resource option list comprises a plurality of resource options; if receiving the resource option selected by the user in the resource option list, executing the step 2);
step 2), displaying a resource application interface corresponding to the received resource option according to the corresponding relation between the preset resource option and the resource application interface; if receiving resource application information input by a user through the resource application interface, generating a resource application request based on the received resource application information;
and 3) determining a resource pool to which the resource to be allocated belongs from a plurality of pre-constructed heterogeneous resource pools by using the generated resource application request, and sending the resource application request to the determined resource pool so that the resource pool allocates the resource according to the resource application request.
Optionally, the resource option list includes at least two of a virtual resource option, a high IO resource option, and a distributed resource option, and the multiple heterogeneous resource pools include at least two of a virtual resource pool, a high IO resource pool, and a distributed resource pool, where the virtual resource option acts on the virtual resource pool, the high IO resource option acts on the high IO resource pool, and the distributed resource option acts on the distributed resource pool.
Optionally, if it is received that the resource option selected by the user in the resource option list is a virtual resource option, the step 2) specifically includes:
displaying a virtual resource application interface corresponding to the virtual resource option according to a corresponding relation between a preset resource option and the resource application interface, wherein the virtual resource application interface comprises a virtual computing resource input box, a virtual storage resource input box and an operating system type option list;
and if receiving the virtual computing resources input by the user in the virtual computing resource input box, the virtual storage resources input in the virtual storage resource input box and the operating system type selected in the operating system type option list, generating a resource application request based on the received virtual computing resources, virtual storage resources and operating system type.
Optionally, if it is received that the resource option selected by the user in the resource option list is a high IO resource option, the step 2) specifically includes:
displaying a high IO resource application interface corresponding to the high IO resource option according to a corresponding relation between preset resource options and a resource application interface, wherein the high IO resource application interface comprises a high IO computing resource input box, a high IO storage resource input box, a database type option list and a data table number input box;
and if receiving the high IO computing resources input by the user in the high IO computing resource input box, the high IO storage resources input by the high IO storage resource input box, the database type selected in the database type option list and the data table number input in the data table number input box, generating a resource application request based on the received high IO computing resources, the high IO storage resources, the database type and the data table number.
Optionally, if it is received that the resource option selected by the user in the resource option list is a distributed resource option, the step 2) specifically includes:
displaying a distributed resource application interface corresponding to the distributed resource option according to a corresponding relation between a preset resource option and the resource application interface, wherein the distributed resource application interface comprises a computing node number input box, a distributed computing resource input box, a distributed storage resource input box and a distributed platform type option list;
if receiving the distributed computing resources input by the user in the distributed computing resource input box, the distributed storage resources input in the distributed storage resource input box, the distributed platform types selected in the distributed platform type option list and the computing node number input in the computing node number input box, generating a resource application request based on the received distributed computing resources, distributed storage resources, distributed platform types and computing node numbers.
Optionally, the resource application request includes a resource type, and determining, by using the generated resource application request, a resource pool to which a resource to be allocated belongs from a plurality of pre-constructed heterogeneous resource pools includes:
and searching a preset resource list by using the resource type in the generated resource application request, obtaining a resource address corresponding to the resource type, determining a resource pool to which the resource to be allocated belongs as the resource pool with the resource address, and storing the corresponding relation between the resource type and the resource address by using the resource list.
Optionally, the virtual resource pool is pre-constructed in the following manner:
virtualizing a first type of physical server by a virtualization technology to obtain a plurality of virtual servers; the first type of physical server is a physical server used for constructing a virtual resource pool;
and deploying an operating system on each virtual server, and connecting each virtual server after the operating system is deployed with the first storage service cluster to obtain a virtual resource pool.
Optionally, the high IO resource pool is pre-constructed in the following manner:
and deploying a database on each second type of physical server, and connecting each second type of physical server after the database is deployed with a second storage service cluster to obtain a high IO resource pool, wherein the second type of physical server is a physical server for constructing the high IO resource pool.
Optionally, the distributed resource pool is pre-constructed in the following manner:
and integrating the resources of the third type of physical server according to the cluster by deploying a cluster management system to obtain a distributed resource pool, wherein the third type of physical server is a physical server for constructing the distributed resource pool, and the distributed resources provided by the distributed resource pool comprise structured data storage resources based on column storage and big data computing resources based on a distributed file system.
In a second aspect, the present invention provides a management system for heterogeneous resource pools, the system comprising a resource management platform, a virtual resource pool, a high IO resource pool, and a distributed resource pool, wherein,
the resource management platform is used for displaying a resource option list on an operation interface, wherein the resource option list comprises a plurality of resource options; if the resource option selected by the user in the resource option list is received, displaying a resource application interface corresponding to the received resource option according to the corresponding relation between the preset resource option and the resource application interface; if receiving resource application information input by a user through the resource application interface, generating a resource application request based on the received resource application information; determining a resource pool to which resources to be allocated belong from a plurality of pre-constructed heterogeneous resource pools by using the generated resource application request, and sending the resource application request to the determined resource pool;
the virtual resource pool is used for allocating virtual resources aiming at the resource application request after receiving the resource application request;
the high IO resource pool is used for allocating high IO resources aiming at the resource application request after receiving the resource application request;
the distributed resource pool is used for distributing distributed resources aiming at the resource application request after receiving the resource application request.
The invention has the following beneficial effects: by applying the technical scheme provided by the embodiment of the invention, a resource option list is displayed on an operation interface, wherein the resource option list comprises a plurality of resource options; if the resource option selected by the user in the resource option list is received, displaying a resource application interface corresponding to the received resource option; if receiving resource application information input by a user through a resource application interface, generating a resource application request based on the received resource application information; and sending the resource application request to the determined resource pool, so that the determined resource pool allocates resources for the resource application request, unified management of various heterogeneous resource pools is realized, the construction process of a resource pool management system is simplified, and the management cost is saved.
Drawings
In order to more clearly illustrate the embodiments of the present invention or the technical solutions in the prior art, the drawings used in the description of the embodiments or the prior art will be briefly described below, it is obvious that the drawings in the following description are only some embodiments of the present invention, and for those skilled in the art, other drawings can be obtained according to the drawings without creative efforts.
Fig. 1 is a schematic flowchart of a management method for a heterogeneous resource pool according to an embodiment of the present invention;
fig. 2 is a schematic structural diagram of a management system for heterogeneous resource pools according to an embodiment of the present invention;
fig. 3 is another schematic structural diagram of a management system for heterogeneous resource pools according to an embodiment of the present invention.
Detailed Description
The technical solutions in the embodiments of the present invention will be clearly and completely described below with reference to the drawings in the embodiments of the present invention, and it is obvious that the described embodiments are only a part of the embodiments of the present invention, and not all of the embodiments. All other embodiments, which can be derived by a person skilled in the art from the embodiments given herein without making any creative effort, shall fall within the protection scope of the present invention.
In order to simplify the construction process of a resource pool management system and save the resource management cost, the embodiment of the invention provides a management method and a management system of a heterogeneous resource pool.
First, a method for managing a heterogeneous resource pool provided in an embodiment of the present invention is described below. It should be noted that an execution subject of the management method for the heterogeneous resource pool provided in the embodiment of the present invention may be an electronic device such as a server or a computer, or may also be functional software such as a resource management platform.
Referring to fig. 1, an embodiment of the present invention provides a method for managing a heterogeneous resource pool, where the method includes:
step 1), displaying a resource option list on an operation interface, wherein the resource option list comprises a plurality of resource options; if receiving the resource option selected by the user in the resource option list, executing the step 2);
step 2), displaying a resource application interface corresponding to the received resource option according to the corresponding relation between the preset resource option and the resource application interface; if receiving resource application information input by a user through a resource application interface, generating a resource application request based on the received resource application information;
and 3) determining a resource pool to which the resource to be allocated belongs from a plurality of pre-constructed heterogeneous resource pools by using the generated resource application request, and sending the resource application request to the determined resource pool so that the resource pool allocates the resource according to the resource application request.
The resource pool may provide computing resources, storage resources, and network resources, which may be dynamically provided to the user for use according to user requirements, and the heterogeneous resource pool may include at least two different resource pools, for example, at least two of a virtual resource pool, a high IO resource pool, and a distributed resource pool.
Database services with high IO (Input/Output) requirements can be run on physical servers of a high IO resource pool, the high IO resource pool can be formed by a cluster of physical servers with high IO performance to provide high IO resources, some big data services can be run on physical servers of a distributed resource pool, the distributed resource pool can be formed by a cluster of physical servers with distributed platforms (such as Hadoop, Spark and the like) deployed to provide distributed resources, and a virtual resource pool can be formed by a cluster of virtual servers to run different virtualized operating systems to provide virtual resources.
In one implementation, the resource option list includes a virtual resource option, a high IO resource option, and a distributed resource option. In other implementations, the resource option list may include only the virtual resource option and the high IO resource option, or only the virtual resource option and the distributed resource option, or may include other resource options, such as a database resource option, and so on. The virtual resource option may act on the virtual resource pool, the high IO resource option may act on the high IO resource pool, and the distributed resource option may act on the distributed resource pool.
The corresponding relation between the resource options and the resource application interface can be established in advance, one resource option can correspond to one resource application interface, the resource application interface corresponding to each resource option can be different, and the resource application interface corresponding to the resource option can be displayed on the operation interface after the resource option selected by the user is received, so that the user can input resource application information through the resource application interface, and the contents of different resource application interfaces can be different.
Specifically, if it is received that the resource option selected by the user in the resource option list is a virtual resource option, the step 2) specifically includes:
displaying a virtual resource application interface corresponding to the virtual resource option according to the corresponding relation between the preset resource option and the resource application interface, wherein the virtual resource application interface comprises a virtual computing resource input box, a virtual storage resource input box and an operating system type option list;
and if receiving the virtual computing resources input by the user in the virtual computing resource input box, the virtual storage resources input in the virtual storage resource input box and the operating system type selected in the operating system type option list, generating a resource application request based on the received virtual computing resources, virtual storage resources and operating system type.
In other implementations, the virtual resource application interface may further include a virtual Machine type and a number of required virtual machines, where the virtual Machine type includes a vmware (virtual Machine ware) virtual Machine, an XEN virtual Machine, a PowerVM virtual Machine, and the like. The VMware virtual machine is a virtual machine provided with VMware software, the XEN virtual machine is a virtual machine adopting XEN virtualization technology, the XEN virtual machine can be migrated among a plurality of physical hosts in real time without stopping, and the PowerVM virtual machine is a virtual machine adopting PowerVM virtualization technology.
The virtual computing resource input box may be configured to input a size of a Central Processing Unit (CPU), a size of a memory, and the like of the virtual machine, the virtual storage resource input box may be configured to input a size of a storage capacity that is requested, the type of the operating system includes a Windows operating system, a Linux operating system, and the like, and the virtual resource request interface may further display the resource type as a virtual resource.
The method for generating the resource application request is not limited, and for example, the DOM method, the SAX method, and the JDOM method may be adopted to generate the resource application request based on the received virtual computing resource, virtual storage resource, and operating system type.
In another implementation manner, if it is received that the resource option selected by the user in the resource option list is a high IO resource option, the step 2) specifically includes:
displaying a high IO resource application interface corresponding to the high IO resource option according to a corresponding relation between preset resource options and the resource application interface, wherein the high IO resource application interface comprises a high IO computing resource input box, a high IO storage resource input box, a database type option list and a data table number input box;
if receiving the high IO computing resources input by the user in the high IO computing resource input box, the high IO storage resources input in the high IO storage resource input box, the database type selected in the database type option list and the data table number input in the data table number input box, generating a resource application request based on the received high IO computing resources, the high IO storage resources, the database type and the data table number.
In other implementation manners, the high IO resource application interface may further include the number of required computing nodes, and one computing node may refer to one physical server forming the high IO resource pool. The list of database type options may include at least one database type option, such as an Oracle database, a Sybase database, and so forth. The number of data tables may be the number of data tables that the user needs to store, and may be, for example, 1, 2, 10, 100, etc.
The high IO computing resource input box can be used for inputting the size of a CPU (Central processing Unit) and the size of a memory of a physical server with high IO performance, and can also be used for inputting the total size of the CPU and the total size of the memory of all physical servers with high IO performance, and the like, the high IO storage resource input box can be used for inputting the size of storage capacity in a high IO pool, and the high IO resource application interface can also display that the resource type is high IO resource.
High IO has the following characteristics: 1. high random IOPS (number of IO requests processed Per Second), for example, random read IOPS can reach 40000 in a typical scenario, 2, high throughput, for example, random read throughput can reach 300MB/s in a typical scenario, and 3, low latency, for example, providing microsecond access latency.
In another implementation manner, if it is received that the resource option selected by the user in the resource option list is a distributed resource option, step 2) specifically includes:
displaying a distributed resource application interface corresponding to the distributed resource option according to the corresponding relation between the preset resource option and the resource application interface, wherein the distributed resource application interface comprises a computing node number input frame, a distributed computing resource input frame, a distributed storage resource input frame and a distributed platform type option list;
if receiving the distributed computing resources input by the user in the distributed computing resource input box, the distributed storage resources input in the distributed storage resource input box, the distributed platform type selected in the distributed platform type option list and the computing node number input in the computing node number input box, generating a resource application request based on the received distributed computing resources, distributed storage resources, distributed platform types and computing node numbers.
In addition, the distributed resource application interface may further display that the resource type is a distributed resource, the distributed computing resource input box may be configured to input a CPU size, a memory size, and the like of one physical server in the applied distributed resource pool, and may also be configured to input a total CPU size, a total memory size, and the like of all physical servers in the applied distributed resource pool, the distributed storage resource input box may be configured to input a storage capacity size in the applied distributed resource pool, the distributed platform type option includes at least one distributed platform type, and the computing node number input box may be configured to input the number of physical servers in the required distributed resource pool.
The distributed platform type can be Hadoop, Spark, LSF and the like, the distributed platform can provide support for file operation, storage and the like, and distributed computing and task processing work such as distribution, tracking, execution and the like of tasks can be realized.
Lsf (load Sharing facility) is a piece of distributed cluster management system software, and is responsible for management of computing resources and scheduling of batch jobs. The method provides a uniform cluster resource access interface for users, and enables the users to transparently access the whole cluster resource. LSFs have good scalability and high availability, supporting almost all mainstream operating systems.
Hadoop is an open source distributed computing platform under the Apache (Apache) software foundation. Hadoop with HDFS (Hadoop Distributed file system) and MapReduce (a programming model) as cores provides a Distributed infrastructure with transparent system bottom details for users. Spark is an open source distributed cluster computing environment similar to Hadoop and will not be described in detail herein.
In addition, in an implementation manner, the resource application interfaces corresponding to each resource option may be the same, and a user may input different resource application information through the same application interface to apply for resources in different resource pool clusters.
For example, each resource application interface may include a resource type selection list, a machine type selection list, a computing resource input box, a storage resource input box, and a node number input box, where the resource type selection list includes virtual resources, high IO resources, and distributed resources, and when the resource type is a virtual resource, the machine type selection list includes a VMware type, an XEN type, and a PowerVM type; the machine type selection list includes Oracle, Sybase, etc. when the resource type is a high IO resource, and Hadoop, Spark, LSF, etc. when the resource type is a distributed resource.
Therefore, the technical scheme provided by the embodiment of the invention realizes the unified management of various heterogeneous resource pools, simplifies the construction process of the resource pool management system and saves the resource management cost.
In one implementation, the virtual resource pool may be pre-constructed in the following manner:
virtualizing a first type of physical server by a virtualization technology to obtain a plurality of virtual servers; the first type of physical server is a physical server for constructing a virtual resource cluster;
and deploying an operating system on each virtual server, and connecting each virtual server after the operating system is deployed with the first storage service cluster to obtain a virtual resource pool.
The first type of physical server may be an X86 physical server of a general specification, and in other implementations, may also be a tower server, a rack server, a blade server, and the like, and the number of the first type of physical servers may be plural, and may exist in a server cluster.
The first type of physical server can be virtualized through virtualization technology, and the virtualization technology comprises the following steps: the method comprises the following steps of CPU virtualization, memory virtualization, device I/O virtualization and the like, so that a plurality of virtual servers (virtual machines) can be operated on a single physical server, application programs can be deployed in the virtual servers, dependence of the application programs on a bottom system and hardware can be abstracted, the close coupling relation between the application programs and the bottom system and the hardware is removed, the difference and the compatibility of the physical equipment are transparent to upper application, different virtual machines are isolated from each other and do not influence each other, different operating systems can be operated, and different application services are provided.
The common virtual machine technologies mainly include KVM, XEN and VMware, the KVM is called Kernel-Based virtual machine, and is a virtualization technology realized Based on a Linux Kernel. Operating systems include UNIX, Linux, Windows, and the like.
The first Storage service cluster may be a file system on a Network formed by adding a Storage device to the first type of physical server cluster through a standard Network topology structure (such as an ethernet structure) in an NAS (Network Attached Storage) manner; the Storage system can also be a special Storage Network formed by connecting a Storage array and a first type of physical server through a fiber channel switch in an SAN (Storage Area Network) mode, or a Storage platform formed by adopting a mixed mode of NAS and SAN, wherein the NAS can reduce the access burden of the server to the SAN, and the SAN can realize the rapid Storage and reading of application data by reducing the large-capacity Storage burden of non-critical data of NAS equipment.
Therefore, by applying the embodiment of the invention, the traditional physical server can be subjected to virtualization multiplexing through a virtualization technology, so that the resource utilization rate of the physical server is improved, and the first storage service cluster is utilized to realize the rapid storage and reading of the application data.
In another implementation, the high IO resource pool may be pre-constructed in the following manner:
and deploying a database on each second-class physical server, connecting each second-class physical server after the database is deployed with a second storage service cluster to obtain a high IO resource pool, wherein the second-class physical server is a physical server for constructing the high IO resource pool.
The number of the second type physical servers may be multiple, and the second type physical servers may exist in a server cluster, the second type physical servers and the first type physical servers may be servers in the server cluster which respectively exist independently, the second type physical servers may be physical servers with high IO performance, the physical servers may be tower servers, rack servers, blade servers, and the like, and the second type physical servers may specifically be X86 servers with high IO performance. The database can be an Oracle database, a Sybase database and the like.
The high IO resource pool can meet the application requirements of various database (such as a high-performance Oracle database) services and unstructured data with high IO requirements, the unstructured data application with high IO requirements has large unstructured data volume and high requirements on storage capacity and read-write speed, and typical applications include: video type applications, information databases, video information retrieval applications, and the like. In order to better support the two services, the high IO resource pool may be divided into two parts, one part includes a high IO database resource region mainly based on physical resources to provide services for various databases with high IO requirements, and the other part includes a computing resource region for providing computing resource services for unstructured data storage.
The second storage service cluster and the first storage service cluster may be two independent storage service clusters, the second storage service cluster may be a high-performance storage array, and specifically may be a dedicated storage network formed by connecting a storage array and a first type of physical server through a fiber channel switch in an SAN manner, or may be a storage platform formed by mixing and matching an NAS and an SAN in other implementation manners.
Therefore, the embodiment of the invention realizes the resource service provision for various database businesses with high IO requirements and unstructured data storage businesses.
Specifically, the distributed resource pool may be pre-constructed in the following manner:
and integrating the resources of the third type of physical server according to the cluster by deploying a cluster management system to obtain a distributed resource pool, wherein the third type of physical server is a physical server for constructing the distributed resource pool, and the distributed resources provided by the distributed resource pool comprise structured data storage resources based on column storage and big data computing resources based on a distributed file system.
The third type of physical server may exist in the form of a server cluster, the second type of physical server, the first type of physical server may be servers in three independent server clusters, the third type of physical server may be a physical server in a general specification, the physical server may be a tower server, a rack server, a blade server, and the like, and the third type of physical server may be an X86 server in a general specification.
The cluster management system can be Hadoop, Spark, LSF and the like, and by deploying the cluster management system, all high-performance distributed computing resources can be integrated according to a cluster to provide uniform service for the outside, and the service provided by the distributed resource pool comprises: the method comprises the steps of large data computing cluster service based on massive structured data storage and real-time query of column storage, and large data analysis processing computing cluster service based on a distributed file system.
The distributed resource pool may provide resource support for data warehouse applications, big data processing applications, and structured and unstructured collision applications. The application has high requirements on the performance of query, retrieval, analysis, mining and collision of mass data, and the processing speed is improved by calculating with a distributed parallel computing framework.
In an implementation manner, the resource application request includes a resource type, and the resource pool to which the resource to be allocated belongs is determined from a plurality of pre-constructed heterogeneous resource pools by using the generated resource application request, which may specifically be: and searching a preset resource list by using the resource type in the resource application request, obtaining a resource address corresponding to the resource type, determining a resource pool to which the resource to be allocated belongs as the resource pool with the resource address, and storing the corresponding relation between the resource type and the resource address by using the resource list.
For each resource pool, a resource list of the resource pool may be preset, and the resource list may store a corresponding relationship between a resource type and a resource address in the resource pool.
For example, the virtual resource pool supports heterogeneous virtualization platforms of different manufacturers, and comprises a VMware virtualization platform, an XEN virtualization platform and a PowerVM virtualization platform, each virtualization platform can provide an API interface address and an IP address of the virtualization platform, and a virtual resource list of the virtual resource pool can store the corresponding relationship between the virtualization platform type and the IP address, so that unified management of heterogeneous virtualization platforms of different manufacturers is realized, and a user can conveniently select different virtualization platforms according to own requirements.
The high IO resource pool can also be pre-established with a high IO resource list, and the high IO resource pool can also provide various heterogeneous database platforms, such as an Oracle database platform, a Sybase database platform and the like, each database platform can provide its own IP address, and the high IO resource list can store the corresponding relation between the type of the database platform and the IP address, so that the uniform management of heterogeneous database platforms of different manufacturers is realized, and a user can conveniently select different database platforms according to own requirements.
The distributed resource pool can be pre-established with a distributed resource list, and can also provide various heterogeneous distributed platforms, such as a Hadoop distributed platform, a Spark distributed platform, an LSF distributed platform and the like, and the distributed resource list can store the corresponding relation between the type of the distributed platform and the IP address, so that the heterogeneous distributed platforms of different manufacturers can be uniformly managed, and users can conveniently select different distributed platforms according to own requirements.
By applying the technical scheme provided by the embodiment of the invention, not only can various heterogeneous resource pools be managed, but also services of different manufacturers or different platforms can be provided for different types of resource pools, and the management of heterogeneous platforms in the various resource pools is realized.
Corresponding to the above method embodiment, the embodiment of the present invention further provides a management system for a heterogeneous resource pool.
Referring to fig. 2, fig. 2 is a schematic structural diagram of a management system of heterogeneous resource pools according to an embodiment of the present invention, where the system includes a resource management platform 201, a virtual resource pool 202, a high IO resource pool 203, and a distributed resource pool 204, where,
the resource management platform 201 is configured to display a resource option list on the operation interface, where the resource option list includes multiple resource options; if a resource option selected by a user in the resource option list is received, displaying a resource application interface corresponding to the received resource option according to the corresponding relation between the preset resource option and the resource application interface; if receiving resource application information input by a user through a resource application interface, generating a resource application request based on the received resource application information; determining a resource pool to which resources to be allocated belong from a plurality of pre-constructed heterogeneous resource pools by using the generated resource application request, and sending the resource application request to the determined resource pool;
the virtual resource pool 202 is used for allocating virtual resources according to the resource application request after receiving the resource application request;
the high IO resource pool 203 is used for allocating high IO resources for the resource application request after receiving the resource application request;
the distributed resource pool 204 is configured to, after receiving the resource application request, allocate distributed resources for the resource application request.
Therefore, by applying the technical scheme provided by the embodiment of the invention, the construction process of the resource pool management system is simplified, the resource management cost is saved, and the unified management of various heterogeneous resource pools is realized.
In one implementation, as shown in fig. 3, the resource management platform includes an interface layer, a resource description layer, and a resource scheduling layer; the virtual resource pool comprises a virtual resource pool management unit and a virtual resource cluster, the high IO resource pool comprises a high IO resource pool management unit and a high IO resource cluster, the distributed resource pool comprises a distributed resource pool management unit and a distributed resource cluster,
the interface layer is used for connecting the virtual resource pool management unit, the high IO resource pool management unit and the distributed resource pool management unit, and establishing a resource list of each resource pool, wherein the resource list is used for storing the corresponding relation between the resource type and the resource address;
the resource pool may include a management unit and a resource cluster, and the management unit may manage each resource in the resource cluster.
The interface layer realizes the unified access problem of different resource pools and products of different manufacturers, shields the difference of the bottom layer technology and supports the application of the upper resource cloud. Different users and applications see resources, and the underlying software and hardware technical details are not concerned.
The resource description layer can establish three resource models for the three resource pools, specifically a virtual resource model, a high IO resource model and a distributed resource model; the virtual resource model can be used for acquiring resource application information such as virtual computing resources, virtual storage resources and virtual machine types input by a user and generating a resource application request based on the received resource application information; the high IO resource model can be used for acquiring resource application information such as high IO computing resources, high IO storage resources, database types and data sheet numbers input by a user and generating a resource application request based on the received resource application information; the distributed resource model can obtain distributed computing resources, distributed storage resources, selected distributed platform types and the number of computing nodes input by a user, and generates a resource application request based on the received resource application information;
the resource scheduling layer can obtain the resource application request generated by the resource description layer, determine the resource pool to which the resource to be allocated belongs from the various pre-constructed heterogeneous resource pools based on the resource application request, and send the resource application request to the determined resource pool to complete the scheduling of the resource application request.
By applying the technical scheme provided by the embodiment of the invention, each resource pool can be accessed to heterogeneous resources of different manufacturers of the same type or different technologies, so that the unified management of the heterogeneous resources in various resource pools is realized.
The above description is only for the purpose of illustrating the preferred embodiments of the present invention and is not to be construed as limiting the invention, and any modifications, equivalents, improvements and the like that fall within the spirit and principle of the present invention are intended to be included therein.
Claims (10)
1. A method for managing heterogeneous resource pools, the method comprising:
step 1), displaying a resource option list on an operation interface, wherein the resource option list comprises a plurality of resource options; if receiving the resource option selected by the user in the resource option list, executing the step 2);
step 2), displaying a resource application interface corresponding to the received resource option according to the corresponding relation between the preset resource option and the resource application interface; if receiving resource application information input by a user through the resource application interface, generating a resource application request based on the received resource application information;
and 3) determining a resource pool to which the resource to be allocated belongs from a plurality of pre-constructed heterogeneous resource pools by using the generated resource application request, and sending the resource application request to the determined resource pool so that the resource pool allocates the resource according to the resource application request.
2. The method of claim 1, wherein the resource option list comprises at least two of a virtual resource option, a high IO resource option, and a distributed resource option, and wherein the heterogeneous resource pools comprise at least two of a virtual resource pool, a high IO resource pool, and a distributed resource pool, and wherein the virtual resource option acts on the virtual resource pool, the high IO resource option acts on the high IO resource pool, and the distributed resource option acts on the distributed resource pool.
3. The method according to claim 2, wherein if it is received that the resource option selected by the user in the resource option list is a virtual resource option, the step 2) specifically comprises:
displaying a virtual resource application interface corresponding to the virtual resource option according to a corresponding relation between a preset resource option and the resource application interface, wherein the virtual resource application interface comprises a virtual computing resource input box, a virtual storage resource input box and an operating system type option list;
and if receiving the virtual computing resources input by the user in the virtual computing resource input box, the virtual storage resources input in the virtual storage resource input box and the operating system type selected in the operating system type option list, generating a resource application request based on the received virtual computing resources, virtual storage resources and operating system type.
4. The method according to claim 2, wherein if it is received that the resource option selected by the user in the resource option list is a high IO resource option, the step 2) specifically comprises:
displaying a high IO resource application interface corresponding to the high IO resource option according to a corresponding relation between preset resource options and a resource application interface, wherein the high IO resource application interface comprises a high IO computing resource input box, a high IO storage resource input box, a database type option list and a data table number input box;
and if receiving the high IO computing resources input by the user in the high IO computing resource input box, the high IO storage resources input by the high IO storage resource input box, the database type selected in the database type option list and the data table number input in the data table number input box, generating a resource application request based on the received high IO computing resources, the high IO storage resources, the database type and the data table number.
5. The method according to claim 2, wherein if it is received that the resource option selected by the user in the resource option list is a distributed resource option, the step 2) specifically comprises:
displaying a distributed resource application interface corresponding to the distributed resource option according to a corresponding relation between a preset resource option and the resource application interface, wherein the distributed resource application interface comprises a computing node number input box, a distributed computing resource input box, a distributed storage resource input box and a distributed platform type option list;
if receiving the distributed computing resources input by the user in the distributed computing resource input box, the distributed storage resources input in the distributed storage resource input box, the distributed platform types selected in the distributed platform type option list and the computing node number input in the computing node number input box, generating a resource application request based on the received distributed computing resources, distributed storage resources, distributed platform types and computing node numbers.
6. The method according to claim 1, wherein the resource application request includes a resource type, and determining, from a plurality of pre-constructed heterogeneous resource pools, a resource pool to which a resource to be allocated belongs by using the generated resource application request includes:
and searching a preset resource list by using the resource type in the generated resource application request, obtaining a resource address corresponding to the resource type, determining a resource pool to which the resource to be allocated belongs as the resource pool with the resource address, wherein the resource list is used for storing the corresponding relation between the resource type and the resource address.
7. The method of claim 2, wherein the virtual resource pool is pre-built by:
virtualizing a first type of physical server by a virtualization technology to obtain a plurality of virtual servers; the first type of physical server is a physical server used for constructing a virtual resource pool;
and deploying an operating system on each virtual server, and connecting each virtual server after the operating system is deployed with the first storage service cluster to obtain a virtual resource pool.
8. The method of claim 2, wherein the high IO resource pool is pre-built by:
and deploying a database on each second type of physical server, and connecting each second type of physical server after the database is deployed with a second storage service cluster to obtain a high IO resource pool, wherein the second type of physical server is a physical server for constructing the high IO resource pool.
9. The method of claim 2, wherein the distributed resource pool is pre-built by:
and integrating the resources of the third type of physical server according to the cluster by deploying a cluster management system to obtain a distributed resource pool, wherein the third type of physical server is a physical server for constructing the distributed resource pool, and the distributed resources provided by the distributed resource pool comprise structured data storage resources based on column storage and big data computing resources based on a distributed file system.
10. A management system of heterogeneous resource pools, the system comprising a resource management platform, a virtual resource pool, a high IO resource pool, and a distributed resource pool, wherein,
the resource management platform is used for displaying a resource option list on an operation interface, wherein the resource option list comprises a plurality of resource options; if the resource option selected by the user in the resource option list is received, displaying a resource application interface corresponding to the received resource option according to the corresponding relation between the preset resource option and the resource application interface; if receiving resource application information input by a user through the resource application interface, generating a resource application request based on the received resource application information; determining a resource pool to which resources to be allocated belong from a plurality of pre-constructed heterogeneous resource pools by using the generated resource application request, and sending the resource application request to the determined resource pool;
the virtual resource pool is used for allocating virtual resources aiming at the resource application request after receiving the resource application request;
the high IO resource pool is used for allocating high IO resources aiming at the resource application request after receiving the resource application request;
the distributed resource pool is used for distributing distributed resources aiming at the resource application request after receiving the resource application request.
Priority Applications (1)
| Application Number | Priority Date | Filing Date | Title |
|---|---|---|---|
| CN201810737252.0A CN110688214A (en) | 2018-07-06 | 2018-07-06 | Management method and system of heterogeneous resource pool |
Applications Claiming Priority (1)
| Application Number | Priority Date | Filing Date | Title |
|---|---|---|---|
| CN201810737252.0A CN110688214A (en) | 2018-07-06 | 2018-07-06 | Management method and system of heterogeneous resource pool |
Publications (1)
| Publication Number | Publication Date |
|---|---|
| CN110688214A true CN110688214A (en) | 2020-01-14 |
Family
ID=69107344
Family Applications (1)
| Application Number | Title | Priority Date | Filing Date |
|---|---|---|---|
| CN201810737252.0A Pending CN110688214A (en) | 2018-07-06 | 2018-07-06 | Management method and system of heterogeneous resource pool |
Country Status (1)
| Country | Link |
|---|---|
| CN (1) | CN110688214A (en) |
Cited By (4)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| CN112506650A (en) * | 2020-11-27 | 2021-03-16 | 中国建设银行股份有限公司 | Resource allocation method, system, computer device and storage medium |
| CN113326129A (en) * | 2021-05-31 | 2021-08-31 | 广东轩辕网络科技股份有限公司 | Heterogeneous virtual resource management system and method |
| CN115567537A (en) * | 2022-09-20 | 2023-01-03 | 中国联合网络通信集团有限公司 | Resource scheduling method and equipment |
| CN117194023A (en) * | 2023-09-07 | 2023-12-08 | 上海利唐信息科技有限公司 | A resource isolation control method, device and storage medium |
Citations (4)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| US6460082B1 (en) * | 1999-06-17 | 2002-10-01 | International Business Machines Corporation | Management of service-oriented resources across heterogeneous media servers using homogenous service units and service signatures to configure the media servers |
| CN103200020A (en) * | 2012-01-04 | 2013-07-10 | 中兴通讯股份有限公司 | Resource allocating method and resource allocating system |
| US20140006482A1 (en) * | 2012-07-02 | 2014-01-02 | Vmware, Inc. | Method and system for providing inter-cloud services |
| CN107979620A (en) * | 2016-10-25 | 2018-05-01 | 北京计算机技术及应用研究所 | Isomery mixes cloud computing system |
-
2018
- 2018-07-06 CN CN201810737252.0A patent/CN110688214A/en active Pending
Patent Citations (4)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| US6460082B1 (en) * | 1999-06-17 | 2002-10-01 | International Business Machines Corporation | Management of service-oriented resources across heterogeneous media servers using homogenous service units and service signatures to configure the media servers |
| CN103200020A (en) * | 2012-01-04 | 2013-07-10 | 中兴通讯股份有限公司 | Resource allocating method and resource allocating system |
| US20140006482A1 (en) * | 2012-07-02 | 2014-01-02 | Vmware, Inc. | Method and system for providing inter-cloud services |
| CN107979620A (en) * | 2016-10-25 | 2018-05-01 | 北京计算机技术及应用研究所 | Isomery mixes cloud computing system |
Non-Patent Citations (1)
| Title |
|---|
| 陈春华等: "混合架构云资源池部署及管理关键技术研究", 《移动通信》 * |
Cited By (4)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| CN112506650A (en) * | 2020-11-27 | 2021-03-16 | 中国建设银行股份有限公司 | Resource allocation method, system, computer device and storage medium |
| CN113326129A (en) * | 2021-05-31 | 2021-08-31 | 广东轩辕网络科技股份有限公司 | Heterogeneous virtual resource management system and method |
| CN115567537A (en) * | 2022-09-20 | 2023-01-03 | 中国联合网络通信集团有限公司 | Resource scheduling method and equipment |
| CN117194023A (en) * | 2023-09-07 | 2023-12-08 | 上海利唐信息科技有限公司 | A resource isolation control method, device and storage medium |
Similar Documents
| Publication | Publication Date | Title |
|---|---|---|
| US10540212B2 (en) | Data-locality-aware task scheduling on hyper-converged computing infrastructures | |
| US10129333B2 (en) | Optimization of computer system logical partition migrations in a multiple computer system environment | |
| US10572292B2 (en) | Platform independent GPU profiles for more efficient utilization of GPU resources | |
| CN108885582B (en) | Multi-tenant memory services for memory pool architecture | |
| US9582221B2 (en) | Virtualization-aware data locality in distributed data processing | |
| US20150121371A1 (en) | Multi-tenant distributed computing and database | |
| JP6231207B2 (en) | Resource load balancing | |
| JP6488296B2 (en) | Scalable distributed storage architecture | |
| US9977618B2 (en) | Pooling of memory resources across multiple nodes | |
| US11307802B2 (en) | NVMe queue management multi-tier storage systems | |
| US9665154B2 (en) | Subsystem-level power management in a multi-node virtual machine environment | |
| US11068315B2 (en) | Hypervisor attached volume group load balancing | |
| US20140149475A1 (en) | Managing distributed storage quotas | |
| KR101430649B1 (en) | System and method for providing data analysis service in cloud environment | |
| CN110688214A (en) | Management method and system of heterogeneous resource pool | |
| EP3867753B1 (en) | Intelligent pooling of isolated hierarchical runtimes for cloud scale databases in multi-tenant environment | |
| US20140359050A1 (en) | Modular architecture for extreme-scale distributed processing applications | |
| US11048561B2 (en) | Avoiding power-on failures in virtualized GPUs | |
| US20230100484A1 (en) | Serverless function colocation with storage pools | |
| Aguilera et al. | Memory disaggregation: why now and what are the challenges | |
| US11886898B2 (en) | GPU-remoting latency aware virtual machine migration | |
| US20200387404A1 (en) | Deployment of virtual node clusters in a multi-tenant environment | |
| Ma et al. | Providing hybrid block storage for virtual machines using object-based storage | |
| Taifi et al. | Building a private HPC cloud for compute and data-intensive applications | |
| US12254220B2 (en) | Resource configuration based on energy expenditure |
Legal Events
| Date | Code | Title | Description |
|---|---|---|---|
| PB01 | Publication | ||
| PB01 | Publication | ||
| SE01 | Entry into force of request for substantive examination | ||
| SE01 | Entry into force of request for substantive examination | ||
| RJ01 | Rejection of invention patent application after publication | ||
| RJ01 | Rejection of invention patent application after publication |
Application publication date: 20200114 |