CN109542586A - A kind of node resource state update method and system - Google Patents
A kind of node resource state update method and system Download PDFInfo
- Publication number
- CN109542586A CN109542586A CN201811376424.2A CN201811376424A CN109542586A CN 109542586 A CN109542586 A CN 109542586A CN 201811376424 A CN201811376424 A CN 201811376424A CN 109542586 A CN109542586 A CN 109542586A
- Authority
- CN
- China
- Prior art keywords
- node
- increment
- resource state
- node resource
- main body
- 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
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
Landscapes
- Engineering & Computer Science (AREA)
- Software Systems (AREA)
- Theoretical Computer Science (AREA)
- Physics & Mathematics (AREA)
- General Engineering & Computer Science (AREA)
- General Physics & Mathematics (AREA)
- Management, Administration, Business Operations System, And Electronic Commerce (AREA)
Abstract
The present invention provides a kind of node resource state update method and system, includes the following steps: to carry out node resource state update；Within the period that node resource state updates, incremental update is carried out to node resource state；Wherein, including calibration increment and calculate node resource status.Step carries out node resource state to update including: the resource status dispatched main body and periodically obtain each node from Kube-apiserver；Node is ranked up according to node surplus resources situation；After dispatching main body and getting the creating Pod of the task, the node for selecting surplus resources most from the node to have sorted will need the Pod created to be dispatched on the node；After the completion of scheduling, main body is dispatched by the result of scheduling and is reported to Kube-apiserver.Calculate node resource status include: it is every once dispatched, then will dispatch the surplus resources of the node being scheduled for recorded in main body and subtract a value, i.e. increment K, make the resource status of the node close to actual resource status.
Description
Technical field
The present invention relates to computer resource management algorithmic technique fields, and in particular to a kind of node resource state update method
And system.
Background technique
Docker has seen dramatic change brought by it by vast software supplier immediately and has anticipated since 2013 are born
Justice, and therefore drawn close one after another to Docker, the ecosystem for meeting various demands has been built for it.To but also Docker
It is rapidly developed, one of topic most burning hot at field of cloud calculation.The advantage of Docker is that isolation, resource can
Control and portability can provide many conveniences for software development, deployment and maintenance, therefore just receive IT circles from being born
Greatly pay attention to.Current popular container cluster management instrument has the Kubernetes and distributed operating system of Google
CoreOS.Both, since Kubernetes has the function of perfect replica management and access agent, powerful development teams
And active open source community, the basic conception in Kubernetes have: Pod, Replication Controller,
Service, Label and Selector.
1)Pod.Pod is the minimum unit of Kubernetes management container, be may include in a Pod multiple
Container。
2) Replication Controller (hereinafter referred to as RC).RC is one group of Pod with same nature, main to use
All meet user-defined quantity in the Pod number of copies for ensuring the type at any time.
3)Service.Service is Kubernetes to the abstract of one group of Pod service provided, can by Service
To be the service externally provided by the port encapsulation of one group of Pod exposure.
4) Label and Selector: in front to substantially understood in the explanation of RC and Service Label and
The usage of Selector: Label and Selector is the form of Key-Value, and Label is used to add to some element and mark
Label, and Selector is then used to inquire the element for containing certain Label.
The scheduling of Pod has the component Kube-scheduler and Kube-apiserver of Kubernetes are unified to complete, such as
Fruit produces the request of a large amount of creation Pod within a node state update cycle, due to node resource during this period of time
There is no updates for state, therefore node listing is not resequenced, therefore Kube-scheduler can dispatch these Pod
Onto the same node, cause Pod on the node excessive, the situation of resource allocation unevenness.The problem can no doubt pass through reduction
The node resource state update cycle is realized, but increases the call number of Restful API again in this way, when affecting scheduling
Between.
Summary of the invention
In order to overcome the deficiencies in the prior art described above, the present invention provides a kind of node resource state update method and is
System, to solve the above technical problems.
The technical scheme is that
A kind of node resource state update method, includes the following steps:
Carry out node resource state update；
Within the period that node resource state updates, incremental update is carried out to node resource state；Wherein, including calibration increases
Amount and calculate node resource status.
Further, step progress node resource state, which updates, includes:
Scheduling main body periodically obtains the resource status of each node from Kube-apiserver；
Node is ranked up according to node surplus resources situation；
When dispatch main body get creation Pod task after, from the node to have sorted select surplus resources at most
Node will need the Pod created to be dispatched on the node；
After the completion of scheduling, main body is dispatched by the result of scheduling and is reported to Kube-apiserver.
Further, step carries out in incremental update node resource state within the period that node resource state updates,
Calculate node resource status includes:
It is every once to be dispatched, then the surplus resources for dispatching the node being scheduled for recorded in main body are subtracted one
Value, i.e. increment K make the resource status of the node close to actual resource status.
Further, step carries out in incremental update node resource state within the period that node resource state updates,
It calibrates increment and calibrates increment K, comprising:
After updating node resource state every time, according to the node resource shape got from Kube-apiserver
The error between resource status saved in state and scheduling main body, calibrates the value of increment K；So that the value of increment K by
Gradually approaching to reality value.
Further, step carries out in incremental update node resource state within the period that node resource state updates,
It calibrates increment and calibrates increment K, specifically include:
In conjunction with current increment K0And the increment K by being actually calculated in the update cycler, increment calibration is set
For new increment K', the process for calibrating increment K is expressed with formula (1-1)
K'=iK0+(1-i)Kr (1-1)
Wherein, the value of variable i influences the value of the increment after calibration: if i value is larger, new increment is closer to original
There is increment K0If i value is smaller, new increment is closer to the practical increment K in the update cycler。
Technical solution of the present invention also provides a kind of node resource state more new system, including node resource state update module
With incremental update module；
Node resource state update module, for carrying out node resource state update；
Incremental update module, for node resource state update module carry out node resource state update period in,
Incremental update is carried out to node resource state.
Further, node resource state update module includes scheduling main body and Kube-apiserver unit；
The scheduling main body, for periodically obtaining the resource status of each node from Kube-apiserver and according to node
Surplus resources situation is ranked up node；
The node that scheduling main body is also used to select surplus resources most from the node to have sorted, by need to create
Pod is dispatched on the node；
Main body is dispatched, is also used to after the completion of scheduling, the result of scheduling is reported to Kube-apiserver unit.
Further, incremental update module includes calibration increment unit and calculate node resource status unit；
Calculate node resource status unit, for it is every once dispatched when by dispatch main body in record be scheduled for
The surplus resources of node subtract a value, i.e. increment K, make the resource status of the node close to actual resource status.
Increment unit is calibrated, for calibrating increment K, i.e., after updating node resource state every time, according to from Kube-
Error between the node resource state got in apiserver unit and the resource status saved in scheduling main body, school
The value of quasi- increment K.
Kube-apiserver is responsible for providing Restful API Calls, and Kube-scheduler is then scheduling main body, scheduling
Body of work complete Kube-scheduler in Kube-scheudler and periodically obtain each section from Kube-apiserver
The resource status of point, and node is ranked up according to node surplus resources situation；When Kube-scheduler gets creation
, then can be from the node most with selection surplus resources in the node that has sorted after the task of Pod, the Pod scheduling that will need to create
Onto the node；After the completion of scheduling, the result of scheduling is reported to Kube-apiserver by Kube-scheduler, is completed entire
Scheduling flow is added to calibration two steps of increment K and calculate node resource status, i.e., on the basis of original scheduling flow
Calculate node resource status refers to every node being scheduled for once dispatched, then will recorded in Kube-scheduler
Surplus resources subtract a value, i.e. increment K so that the resource status of the node is close to actual resource status；Calibration
Increment is then after every time one updates node resource state, according to the actual resource status of the node (from Kube-
The resource status got in apiserver) with calculate the node resource status (Kube-scheduler save resource
State) between error, the value of increment K is calibrated, so that the value of increment K gradually approaching to reality value.
As can be seen from the above technical solutions, the invention has the following advantages that this programme proposes node state increment meter
Calculate algorithm, within the period of node resource state information update, the real-time analog node resource by way of incremental computations
State adjusts the sequence of node listing, in time so as to avoid the generation of problem.
In addition, design principle of the present invention is reliable, structure is simple, has very extensive application prospect.
It can be seen that compared with prior art, the present invention have substantive distinguishing features outstanding and it is significant ground it is progressive, implementation
Beneficial effect be also obvious.
Detailed description of the invention
Fig. 1 is a kind of node resource state update method schematic diagram.
Specific embodiment
It is resource pool that the sharpest edges of cloud platform, which are by individual physical host resource virtualizing one by one, and user makes
When with cloud platform, it is only necessary to from resource pool application resource, without being related to which physical host is the resource be particularly located on.But
As platform provider, then needs to consider the strategy that resource applied to user is scheduled, make physical host as far as possible
Resource is available to be made full use of.The major criterion evaluated scheduling strategy is exactly the balance of scheduling of resource, i.e.,
Whether the applied resource of user has balancedly been dispatched on different physical hosts.The node resource state that this programme proposes
Update method prevents from being dispatched to a large amount of Pod within the node resource state update cycle by real-time calculate node resource status
On same node, the harmony of Pod distribution is improved, is made full use of so that the resource of physical host is available.
To keep the purposes, technical schemes and advantages of the embodiment of the present application clearer, below in conjunction with the embodiment of the present application
In attached drawing, the technical scheme in the embodiment of the application is clearly and completely described, it is clear that described embodiment is
Some embodiments of the present application, instead of all the embodiments.Based on the embodiment in the application, those of ordinary skill in the art
Every other embodiment obtained without making creative work, shall fall in the protection scope of this application.
Embodiment one
As shown in Figure 1, the embodiment of the present invention provides a kind of node resource state update method, include the following steps:
S1: node resource state update is carried out；
In this step, the renewal process for carrying out node resource state includes: scheduling main body periodically from Kube-apiserver
The middle resource status for obtaining each node is simultaneously ranked up node according to node surplus resources situation；When scheduling main body gets wound
After building the task of Pod, the node for selecting surplus resources most from the node to have sorted will need the Pod created to be dispatched to
On the node；
After the completion of scheduling, main body is dispatched by the result of scheduling and is reported to Kube-apiserver.
S2: within the period that node resource state updates, incremental update is carried out to node resource state；Wherein, including school
Quasi- increment and calculate node resource status.
This step on the basis of original scheduling flow, is added to calibration increment K and calculate node resource status two really
Step, i.e. calculate node resource status refer to it is every once dispatched, then it is scheduled by what is recorded in Kube-scheduler
To the surplus resources of node subtract a value, i.e. increment K so that the resource status of the node is close to actual resource shape
State；Calibration increment is then after every time one updates node resource state, according to the actual resource status of the node (from Kube-
The resource status got in apiserver) with calculate the node resource status (Kube-scheduler save resource
State) between error, the value of increment K is calibrated, so that the value of increment K gradually approaching to reality value.
Wherein, calculate node resource status is relatively simple, it is only necessary to increment K is added on original node resource state
It as the node resource state after scheduling, and calibrates that increment K is then relatively complicated, needs to combine current increment K0With
And the increment K by being actually calculated in the update cycler, increment is calibrated to new increment K', therefore main right below
The implementation of calibration increment K is described.
The process for calibrating increment K is expressed with formula (1-1)
K'=iK0+(1-i)Kr (1-1)
Wherein, the value of variable i influences the value of the increment after calibration: if i value is larger, new increment is closer to original
There is increment K0If i value is smaller, new increment is closer to the practical increment K in the update cycler。
Embodiment two
Technical solution of the present invention also provides a kind of node resource state more new system, including node resource state update module
With incremental update module；
Node resource state update module, for carrying out node resource state update；
Incremental update module, for node resource state update module carry out node resource state update period in,
Incremental update is carried out to node resource state.
Node resource state update module includes scheduling main body and Kube-apiserver unit；
The scheduling main body, for periodically obtaining the resource status of each node from Kube-apiserver and according to node
Surplus resources situation is ranked up node；
The node that scheduling main body is also used to select surplus resources most from the node to have sorted, by need to create
Pod is dispatched on the node；
Main body is dispatched, is also used to after the completion of scheduling, the result of scheduling is reported to Kube-apiserver unit.
Incremental update module includes calibration increment unit and calculate node resource status unit；
Calculate node resource status unit, for it is every once dispatched when by dispatch main body in record be scheduled for
The surplus resources of node subtract a value, i.e. increment K, make the resource status of the node close to actual resource status.
Increment unit is calibrated, for calibrating increment K, i.e., after updating node resource state every time, according to from Kube-
Error between the node resource state got in apiserver unit and the resource status saved in scheduling main body, school
The value of quasi- increment K.
Kube-apiserver is responsible for providing Restful API Calls, and Kube-scheduler is then scheduling main body, scheduling
Body of work complete Kube-scheduler in Kube-scheudler and periodically obtain each section from Kube-apiserver
The resource status of point, and node is ranked up according to node surplus resources situation；When Kube-scheduler gets creation
, then can be from the node most with selection surplus resources in the node that has sorted after the task of Pod, the Pod scheduling that will need to create
Onto the node；After the completion of scheduling, the result of scheduling is reported to Kube-apiserver by Kube-scheduler, is completed entire
Scheduling flow is added to calibration two steps of increment K and calculate node resource status, i.e., on the basis of original scheduling flow
Calculate node resource status refers to every node being scheduled for once dispatched, then will recorded in Kube-scheduler
Surplus resources subtract a value, i.e. increment K so that the resource status of the node is close to actual resource status；Calibration
Increment is then after every time one updates node resource state, according to the actual resource status of the node (from Kube-
The resource status got in apiserver) with calculate the node resource status (Kube-scheduler save resource
State) between error, the value of increment K is calibrated, so that the value of increment K gradually approaching to reality value.
Node resource state update method provided by the invention is in analysis data basis, mainly creation Pod's
When negligible amounts, starting the container stage be whole flow process bottleneck, and create Pod quantity it is more when, container scheduling then by
Gradually become the bottleneck of whole flow process, this is because the time of container starting is limited by Docker, most short is 2s or so, therefore is being opened
When dynamic Pod negligible amounts, the time of this 2s or so just becomes the bottleneck of whole flow process, however when the quantity for starting Pod is more,
It is concurrently carried out since the task of starting Pod can be assigned on different nodes, the time for starting container, there is no substantially
Increase, and container scheduling is embodied as single thread sequential scheduling, the quantity of scheduling time and starting Pod in current Kubernetes
It is directly proportional, therefore when the quantity for starting Pod is more, container scheduling becomes the bottleneck of whole flow process.From container scheduling phase
Hand optimizes the process of creation Pod, improves deployment and the stretching speed of application.
Description and claims of this specification and term " first ", " second ", " third " " in above-mentioned attached drawing
The (if present)s such as four " are to be used to distinguish similar objects, without being used to describe a particular order or precedence order.It should manage
The data that solution uses in this way are interchangeable under appropriate circumstances, so as to the embodiment of the present invention described herein can in addition to
Here the sequence other than those of diagram or description is implemented.In addition, term " includes " and " having " and their any deformation,
It is intended to cover and non-exclusive includes.
The foregoing description of the disclosed embodiments enables those skilled in the art to implement or use the present invention.
Various modifications to these embodiments will be readily apparent to those skilled in the art, as defined herein
General Principle can be realized in other embodiments without departing from the spirit or scope of the present invention.Therefore, of the invention
It is not intended to be limited to the embodiments shown herein, and is to fit to and the principles and novel features disclosed herein phase one
The widest scope of cause.
Claims (8)
1. a kind of node resource state update method, which comprises the steps of:
Carry out node resource state update；
Within the period that node resource state updates, incremental update is carried out to node resource state；Wherein, including calibration increment and
Calculate node resource status.
2. a kind of node resource state update method according to claim 1, which is characterized in that step carries out node resource
State updates
Scheduling main body periodically obtains the resource status of each node from Kube-apiserver；
Node is ranked up according to node surplus resources situation；
After dispatching main body and getting the creating Pod of the task, the node for selecting surplus resources most from the node to have sorted,
The Pod created will be needed to be dispatched on the node；
After the completion of scheduling, main body is dispatched by the result of scheduling and is reported to Kube-apiserver.
3. a kind of node resource state update method according to claim 2, which is characterized in that step is in node resource shape
In the period that state updates, node resource state is carried out in incremental update, calculate node resource status includes:
It is every once to be dispatched, then the surplus resources for dispatching the node being scheduled for recorded in main body are subtracted into a value, i.e.,
Increment K makes the resource status of the node close to actual resource status.
4. a kind of node resource state update method according to claim 3, which is characterized in that step is in node resource shape
In the period that state updates, node resource state is carried out in incremental update, calibration increment calibrates increment K, comprising:
After updating node resource state every time, according to the node resource state that is got from Kube-apiserver with
The error between resource status saved in scheduling main body, calibrates the value of increment K.
5. a kind of node resource state update method according to claim 4, which is characterized in that step is in node resource shape
In the period that state updates, node resource state is carried out in incremental update, calibration increment calibrates increment K, it specifically includes:
In conjunction with current increment K0And the increment K by being actually calculated in the update cycler, increment calibration is set as new
Increment K', calibrate increment K process with formula (1-1) express
K'=iK0+(1-i)Kr (1-1)
Wherein, the value of variable i influences the value of the increment after calibration: if i value is larger, new increment is closer to original increasing
Measure K0If i value is smaller, new increment is closer to the practical increment K in the update cycler。
6. a kind of node resource state more new system, which is characterized in that including node resource state update module and incremental update
Module；
Node resource state update module, for carrying out node resource state update；
Incremental update module, for node resource state update module carry out node resource state update period in, to section
Point resource status carries out incremental update.
7. a kind of node resource state more new system according to claim 6, which is characterized in that node resource state updates
Module includes scheduling main body and Kube-apiserver unit；
The scheduling main body, for periodically obtaining the resource status of each node from Kube-apiserver and according to node residue
Resource situation is ranked up node；
The node that scheduling main body is also used to select surplus resources most from the node to have sorted, the Pod tune that needs are created
It spends on the node；
Main body is dispatched, is also used to after the completion of scheduling, the result of scheduling is reported to Kube-apiserver unit.
8. a kind of node resource state more new system according to claim 6, which is characterized in that incremental update module includes
Calibrate increment unit and calculate node resource status unit；
Calculate node resource status unit, for it is every once dispatched when will dispatch the section being scheduled for that records in main body
The surplus resources of point subtract a value, i.e. increment K, make the resource status of the node close to actual resource status；
Increment unit is calibrated, for calibrating increment K, i.e., after updating node resource state every time, according to from Kube-
Error between the node resource state got in apiserver unit and the resource status saved in scheduling main body, school
The value of quasi- increment K.
Priority Applications (1)
| Application Number | Priority Date | Filing Date | Title |
|---|---|---|---|
| CN201811376424.2A CN109542586B (en) | 2018-11-19 | 2018-11-19 | Node resource state updating method and system |
Applications Claiming Priority (1)
| Application Number | Priority Date | Filing Date | Title |
|---|---|---|---|
| CN201811376424.2A CN109542586B (en) | 2018-11-19 | 2018-11-19 | Node resource state updating method and system |
Publications (2)
| Publication Number | Publication Date |
|---|---|
| CN109542586A true CN109542586A (en) | 2019-03-29 |
| CN109542586B CN109542586B (en) | 2021-10-29 |
Family
ID=65848302
Family Applications (1)
| Application Number | Title | Priority Date | Filing Date |
|---|---|---|---|
| CN201811376424.2A Active CN109542586B (en) | 2018-11-19 | 2018-11-19 | Node resource state updating method and system |
Country Status (1)
| Country | Link |
|---|---|
| CN (1) | CN109542586B (en) |
Cited By (2)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| CN111459612A (en) * | 2020-03-27 | 2020-07-28 | 新浪网技术(中国)有限公司 | Updating method and device for Pod in Kubernetes system |
| CN112860387A (en) * | 2019-11-27 | 2021-05-28 | 上海哔哩哔哩科技有限公司 | Distributed task scheduling method and device, computer equipment and storage medium |
Citations (9)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| CN102043673A (en) * | 2009-10-21 | 2011-05-04 | Sap股份公司 | Calibration of resource allocation during parallel processing |
| CN103823714A (en) * | 2014-01-15 | 2014-05-28 | 浙江大学 | Virtualization-based method and device for adjusting QoS (quality of service) of node memory of NUMA (non uniform memory access architecture) |
| CN103885836A (en) * | 2014-01-14 | 2014-06-25 | 无锡城市云计算中心有限公司 | Intelligent cloud computing data center resource scheduling method |
| CN103986766A (en) * | 2014-05-19 | 2014-08-13 | 中国工商银行股份有限公司 | Self-adaptation load balancing job task scheduling method and device |
| US20140245321A1 (en) * | 2009-10-09 | 2014-08-28 | International Business Machines Corporation | Generating timing sequence for activating resources linked through time dependency relationships |
| CN104168332A (en) * | 2014-09-01 | 2014-11-26 | 广东电网公司信息中心 | Load balance and node state monitoring method in high performance computing |
| CN107045455A (en) * | 2017-06-19 | 2017-08-15 | 华中科技大学 | A kind of Docker Swarm cluster resource method for optimizing scheduling based on load estimation |
| CN107179945A (en) * | 2017-03-31 | 2017-09-19 | 北京奇艺世纪科技有限公司 | A kind of resource allocation methods and device |
| CN107908479A (en) * | 2017-12-11 | 2018-04-13 | 北京奇艺世纪科技有限公司 | A kind of node resource distribution method and device |
-
2018
- 2018-11-19 CN CN201811376424.2A patent/CN109542586B/en active Active
Patent Citations (9)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| US20140245321A1 (en) * | 2009-10-09 | 2014-08-28 | International Business Machines Corporation | Generating timing sequence for activating resources linked through time dependency relationships |
| CN102043673A (en) * | 2009-10-21 | 2011-05-04 | Sap股份公司 | Calibration of resource allocation during parallel processing |
| CN103885836A (en) * | 2014-01-14 | 2014-06-25 | 无锡城市云计算中心有限公司 | Intelligent cloud computing data center resource scheduling method |
| CN103823714A (en) * | 2014-01-15 | 2014-05-28 | 浙江大学 | Virtualization-based method and device for adjusting QoS (quality of service) of node memory of NUMA (non uniform memory access architecture) |
| CN103986766A (en) * | 2014-05-19 | 2014-08-13 | 中国工商银行股份有限公司 | Self-adaptation load balancing job task scheduling method and device |
| CN104168332A (en) * | 2014-09-01 | 2014-11-26 | 广东电网公司信息中心 | Load balance and node state monitoring method in high performance computing |
| CN107179945A (en) * | 2017-03-31 | 2017-09-19 | 北京奇艺世纪科技有限公司 | A kind of resource allocation methods and device |
| CN107045455A (en) * | 2017-06-19 | 2017-08-15 | 华中科技大学 | A kind of Docker Swarm cluster resource method for optimizing scheduling based on load estimation |
| CN107908479A (en) * | 2017-12-11 | 2018-04-13 | 北京奇艺世纪科技有限公司 | A kind of node resource distribution method and device |
Cited By (2)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| CN112860387A (en) * | 2019-11-27 | 2021-05-28 | 上海哔哩哔哩科技有限公司 | Distributed task scheduling method and device, computer equipment and storage medium |
| CN111459612A (en) * | 2020-03-27 | 2020-07-28 | 新浪网技术(中国)有限公司 | Updating method and device for Pod in Kubernetes system |
Also Published As
| Publication number | Publication date |
|---|---|
| CN109542586B (en) | 2021-10-29 |
Similar Documents
| Publication | Publication Date | Title |
|---|---|---|
| Athlur et al. | Varuna: scalable, low-cost training of massive deep learning models | |
| CN104067260B (en) | Dynamic construction is for undertaking the methods, devices and systems of one group of calculating node of amount of user effort | |
| CA3099664C (en) | Cloud-edge topologies | |
| US9716746B2 (en) | System and method using software defined continuity (SDC) and application defined continuity (ADC) for achieving business continuity and application continuity on massively scalable entities like entire datacenters, entire clouds etc. in a computing system environment | |
| CN102939594B (en) | The method and apparatus that migration with the virtual resource in customer resources to data center environment is relevant | |
| CN104050042B (en) | The resource allocation methods and device of ETL operations | |
| CN109791504A (en) | For the dynamic BTS configuration of application container | |
| CN103377407B (en) | Cloud method for processing business and relevant apparatus and system | |
| CN104270421B (en) | A kind of multi-tenant cloud platform method for scheduling task for supporting Bandwidth guaranteed | |
| CN101820428B (en) | Composite service optimizing method and device based on protocol composition mechanism | |
| US20100262559A1 (en) | Modelling Computer Based Business Process And Simulating Operation | |
| CN105531688A (en) | Providing services as resources for other services | |
| US8402119B2 (en) | Real-load tuning of database applications | |
| CN102103518A (en) | System for managing resources in virtual environment and implementation method thereof | |
| CN102880542B (en) | Cloud computing service evaluation system and evaluation method | |
| Gupta et al. | Elastic caching | |
| CN109471730A (en) | A kind of elastic calculation service management system | |
| CN109542586A (en) | A kind of node resource state update method and system | |
| CN103793255A (en) | Configurable multi-main-mode multi-OS-inner-core real-time operating system structure and starting method | |
| CN108536539A (en) | A kind of method for scheduling task in industrial allocation formula data collecting system | |
| Baur et al. | A provider-agnostic approach to multi-cloud orchestration using a constraint language | |
| CN104657164B (en) | Software upgrading treating method and apparatus | |
| CN108900435B (en) | Service deployment method, device and computer storage medium | |
| Ataie et al. | Modeling and evaluation of dispatching policies in IaaS cloud data centers using SANs | |
| CN107741874A (en) | A kind of GIS clouds virtual machine automatically creates method and system |
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 |