WO2014088397A1 - A system and method for dynamic scheduling and management of cloud resources based on roles and profiles - Google Patents

A system and method for dynamic scheduling and management of cloud resources based on roles and profiles Download PDF

Info

Publication number
WO2014088397A1
WO2014088397A1 PCT/MY2013/000217 MY2013000217W WO2014088397A1 WO 2014088397 A1 WO2014088397 A1 WO 2014088397A1 MY 2013000217 W MY2013000217 W MY 2013000217W WO 2014088397 A1 WO2014088397 A1 WO 2014088397A1
Authority
WO
WIPO (PCT)
Prior art keywords
physical
resource
virtual
physical resource
role
Prior art date
Application number
PCT/MY2013/000217
Other languages
French (fr)
Inventor
Jing Yuan Luke
Syafuan Salim Ahmad
Suet Hwa Lee
Kwang Ming Ng
Original Assignee
Mimos Berhad
Priority date (The priority date 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 date listed.)
Filing date
Publication date
Application filed by Mimos Berhad filed Critical Mimos Berhad
Publication of WO2014088397A1 publication Critical patent/WO2014088397A1/en

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
    • G06F9/46—Multiprogramming arrangements
    • G06F9/50—Allocation of resources, e.g. of the central processing unit [CPU]
    • G06F9/5061—Partitioning or combining of resources
    • G06F9/5072—Grid computing
    • 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]
    • G06F9/5094—Allocation of resources, e.g. of the central processing unit [CPU] where the allocation takes into account power or heat criteria
    • Y—GENERAL TAGGING OF NEW TECHNOLOGICAL DEVELOPMENTS; GENERAL TAGGING OF CROSS-SECTIONAL TECHNOLOGIES SPANNING OVER SEVERAL SECTIONS OF THE IPC; TECHNICAL SUBJECTS COVERED BY FORMER USPC CROSS-REFERENCE ART COLLECTIONS [XRACs] AND DIGESTS
    • Y02—TECHNOLOGIES OR APPLICATIONS FOR MITIGATION OR ADAPTATION AGAINST CLIMATE CHANGE
    • Y02D—CLIMATE CHANGE MITIGATION TECHNOLOGIES IN INFORMATION AND COMMUNICATION TECHNOLOGIES [ICT], I.E. INFORMATION AND COMMUNICATION TECHNOLOGIES AIMING AT THE REDUCTION OF THEIR OWN ENERGY USE
    • Y02D10/00—Energy efficient computing, e.g. low power processors, power management or thermal management

Definitions

  • the present invention relates to a system and method for dynamic scheduling and management of cloud resources, including physical and virtual resources, based on roles and profiles of those resources.
  • laaS cloud providers offer servers in physical or more often in virtual form, raw (block) storage, firewalls, load balancers, and networks.
  • laaS providers supply these resources on demand from large pools installed in data centers.
  • Local area networks including IP addresses are part of the offer.
  • the Internet can be used or, in carrier clouds, dedicated virtual private networks can be configured.
  • laaS refers not to a machine that does all the work, but simply to a facility given to businesses that offers users the leverage of extra storage space in servers and data centers. Whilst laaS is discussed briefly here, this should not be taken as limiting on the invention in any which, which may have much broader application.
  • the present invention provides a system and method for dynamic scheduling and management of cloud resources, including physical and virtual resources, based on roles and profiles of those resources.
  • One aspect of the present invention provides a system (100) for dynamic scheduling and management of cloud resources based on roles and profiles comprising:
  • a physical resources pool (101 ) including a plurality of physical resources
  • the physical resource manager (102) to dynamically manage and schedule powering of the physical resources based on physical resources roles (101a) and information on virtual resources profiles (103a) received from the virtual resource manager (104);
  • the physical resource manager (102) to counter offer a temporary resource that the virtual resource manager (104) can use when a physical resource is unavailable, power up a new physical resource and communicate details of the new physical resource to the virtual resource manager (104);
  • the virtual resource manager (104) to manage and place the virtual resources based on virtual resources profiles (103a) and information on physical resources roles (101a) received from the physical resources manager (102).
  • Another aspect of the present invention provides a system (100) wherein the physical resources manager (102) has information on which physical resources are powered up, information on remaining physical resources that are not powered up and physical resources roles (101a) assigned to the powered up physical resources.
  • a further aspect of the invention provides a system (100) wherein the physical resources roles (101a) describe how a physical resource will behave and resources available.
  • a further aspect of the invention provides a system (100) wherein the virtual resource manager (104) has information on virtual resources profiles (103a) including type of virtual resource, the application contained and/or resource requirements.
  • Another aspect of the invention provides a method for dynamic scheduling and management of cloud resources based on roles and profiles comprising:
  • a further aspect of the invention provides a method including calculating a role physical resource score for every physical resource role available and setting low and high thresholds for the role physical resource scores.
  • a further aspect of the invention provides a method including calculating a virtual resource score during or after processing the request from the virtual resource manager (104) relating to the physical resource role requirement and comparing the virtual resource score with the role physical resource score thresholds for that role.
  • Another aspect of the invention provides a method wherein, depending on the difference between the virtual resource score and the role physical resource score thresholds for that role, the physical resource that will satisfy the physical resource role requirement is allocated and the virtual resource manager (104) is informed of the allocation, or the counter offer of the temporary resource is made to the virtual resource manager (104).
  • a further aspect of the invention provides a method wherein:
  • the virtual resource manager (104) is informed of the allocation and a new role physical resource score is calculated and low and high thresholds for the role physical resource score are reset;
  • the virtual resource manager (104) is informed of the allocation, a new physical resource is powered up from the physical resource pool (101a) and a new role physical resource score is calculated and low and high thresholds for the role physical resource score are reset;
  • the counter offer is made while a new physical resource is powered up from the physical resource pool (101a), the virtual resource manager is informed of the new physical resource once powered up, and a new role physical resource score is calculated and low and high thresholds for the role physical resource score are reset.
  • a further aspect of the invention provides a method wherein if a request arrives from the virtual resource manager (104) for virtual resource termination, the physical resource 2013/000217
  • Another aspect of the invention provides a method including mapping virtual resource profiles to corresponding physical resource roles using a profile-to-role map.
  • a further aspect of the invention provides a method wherein, when the virtual resource manager receives a request to initiate a virtual resource, the virtual resource manager (104):
  • FIG. 1.0 illustrates the system of an embodiment of the invention.
  • FIG. 2.0 illustrates a block flow diagram for the physical resource manager 200.
  • FIG. 3.0 illustrates a block flow diagram for the virtual resource manager 300.
  • the present invention provides a system and method for dynamic scheduling and management of cloud resources, including physical and virtual resources, based on roles and profiles of those resources.
  • the system (100) includes Physical Resource Manager (PRM) (102) and Virtual Resource Manager (VRM) (104) branches that will assign physical resources roles (101a) and virtual resources profiles (103a) for both physical and virtual resources of a physical resource pool (101) and a virtual resource pool (103).
  • PRM Physical Resource Manager
  • VRM Virtual Resource Manager
  • the system (100) allows the PRM (102) to dynamically manage and schedule the powering of physical resources based on physical resources roles (101a) and information on virtual resources profiles (103a) from the VRM (104).
  • the PRM (102) can counter offer to the VRM (104) a temporary resource that the VRM (104) can use in case a physical resource with a predefined role is not available.
  • the PRM (102) Upon the right physical resource being powered up, the PRM (102) then informs the VRM (104) to migrate a virtual server that has been created to the new physical resource.
  • the system (100) also allows the VRM (104) to manage and place the virtual resources based on virtual resources profiles (103a) and information of physical resource roles (101a) received from the PRM (102).
  • FIG. 2.0 a block flow diagram for the physical resource manager (200) is illustrated.
  • admins decides a set of physical servers to power up and this information is set in the PRM (201a) together with information of remaining servers of the physical resource pool 101 that are not powered up (201 b).
  • Admins also generates physical resource roles (202) and assigns the physical resource roles the powered up servers and registers the information into the PRM (203).
  • a physical resource role (101a) as used herein describes how a physical server will behave and the resources that are available. The behaviours may include, for example, "Always On Extra Large”, “Always On Large”, On Demand Small”, On Demand Medium” and so on. It should be appreciated however that the invention is not limited to these specific examples ad other behaviours may be equally applicable.
  • the PRM For every physical resource role (101a) available, the PRM will calculate a Role Physical Resource Score (RPRS) per role (204). The score can be calculated based on usage of a servers usage (CPU load, RAM, disk, network, etc.) as well as other information such as cost, time to power up, and so on. Admins then sets low and high thresholds in percentages for each RPRS (205). The PRM then listens for request from VRM (206). When a request arrives from VRM with the physical resource role requirement, the PRM will calculate a Virtual Resource Score (VRS) (207) and compare with the existing RPRS thresholds for that role. Depending on the difference, the PRM decides the next course of action according to the following scenarios:
  • VRS Virtual Resource Score
  • the PRM If the new VRS is below the existing low threshold value, the PRM returns information of the free physical server to the VRM (208), recalculates a new RPRS (211) and resets the threshold values.
  • the PRM If the new VRS is above the low threshold value, but below the high threshold value, the PRM returns the information of the free physical server to VRM (209a), but then powers up a new physical server (109b) from the available pool, recalculates a new RPRS (211 ) and resets the threshold values.
  • the PRM can counter offer the VRM with a free physical server from another role first (210a) while powering up a new physical server (210b). Once the new physical server is powered up, the PRM will then send the information of the new server to the VRM (210c), recalculate a new RPRS (211 ) and reset the threshold values. When a request arrives from VRM on virtual server termination, PRM will recalculate a new VRS (212) and if it is below to low threshold of the RPRS for the role and if the is server has no virtual servers running, that server will be powered down (213). Turning to Figure 3.0, a block flow diagram for the virtual resource manager (300) is illustrated.
  • a virtual resource profile describes the kind of virtual server, the application it contains, its resource requirement and so on.
  • the profiles may include "Database Large”, “App Server Medium”, “Web Frontend Light” and so on, although it should be appreciated that the present invention is not so limited.
  • Each profile is then mapped to a corresponding role using a Profile-to-Role Map (302) and a role can be mapped to several profiles.
  • the VRM then communicates with the PRM and receives information on available roles (303) and waits for requests from admins as well as the PRM (304).
  • the VRM When the VRM receives a request from admin to start a virtual server, it will first determine the virtual server profile, then based on the profile-to-role mapping send a request to the PRM for available physical server with that role (305).
  • the VRM will start the virtual server depending on the kind of offer received according to the following scenarios:
  • the virtual server will be started (306).
  • the virtual server will be started on that server (307a) and the VRM will continue to listen to the PRM for a new server with the desired role (307b). When the information arrives, the virtual server will then be migrated (308). When the VRM receives a request from admin to terminate a virtual server, it will do so and then inform the PRM of its action (309). 2013/000217
  • Table 1.0 Admin defined roles and profiles.
  • RPRS w-L- CPU + w 2 Memory + w 3 . Network + w 4 . Storage
  • Table 2.0 Admin derived profile-to-role map.

Landscapes

  • Engineering & Computer Science (AREA)
  • Software Systems (AREA)
  • Theoretical Computer Science (AREA)
  • Physics & Mathematics (AREA)
  • General Engineering & Computer Science (AREA)
  • General Physics & Mathematics (AREA)
  • Mathematical Physics (AREA)
  • Power Sources (AREA)

Abstract

A system (100) for dynamic scheduling and management of cloud resources based on roles and profiles is provided. The system comprises: a physical resources pool (101) including a plurality of physical resources; a physical resource manager (102) associated with said physical resources pool (101); a virtual resources pool (103) including a plurality of virtual resources; and a virtual resource manager (104) associated with said virtual resources pool (103); characterized in that said physical resource manager (102) and said virtual resource manager (104) are in communication with one another whereby: means is provided for said physical resource manager (102) to dynamically manage and schedule powering of said physical resources based on physical resources roles (101a) and information on virtual resources profiles (103a) received from said virtual resource manager (104); means is provided for said physical resource manager (102) to counter offer a temporary resource that the virtual resource manager (104) can use when a physical resource is unavailable, power up a new physical resource and communicate details of said new physical resource to said virtual resource manager (104); and means is provided for said virtual resource manager (104) to manage and place said virtual resources based on virtual resources profiles (103a) and information on physical resources roles (101a) received from said physical resources manager (102).

Description

A SYSTEM AND METHOD FOR DYNAMIC SCHEDULING AND MANAGEMENT OF CLOUD RESOURCES BASED ON ROLES AND PROFILES
FIELD OF INVENTION
The present invention relates to a system and method for dynamic scheduling and management of cloud resources, including physical and virtual resources, based on roles and profiles of those resources. BACKGROUND ART
In most data centers, for example those involved in infrastructure as a service (laaS) implementation, most if not all equipment is powered up irrespective of whether or not it is required. With rising energy prices and increasing pressure to reduce energy costs, such practices may not be desirable or viable in the future.
Taking laaS as an example, cloud providers offer servers in physical or more often in virtual form, raw (block) storage, firewalls, load balancers, and networks. laaS providers supply these resources on demand from large pools installed in data centers. Local area networks including IP addresses are part of the offer. For wide area connectivity, the Internet can be used or, in carrier clouds, dedicated virtual private networks can be configured. As such, laaS refers not to a machine that does all the work, but simply to a facility given to businesses that offers users the leverage of extra storage space in servers and data centers. Whilst laaS is discussed briefly here, this should not be taken as limiting on the invention in any which, which may have much broader application.
In order to reduce energy consumption and costs, solutions are required that allow data centers to dynamically schedule and manage their servers such that they can be powered up or down as the need arises, for example when there is a spike in requests for new virtual servers to be initiated in the laaS. The subject matter claimed herein is not limited to embodiments that solve any disadvantages or that operate only in environments such as those described above. Rather, this background is only provided to illustrate one exemplary technology area where some embodiments described herein may be practice.
SUMMARY OF INVENTION
The present invention provides a system and method for dynamic scheduling and management of cloud resources, including physical and virtual resources, based on roles and profiles of those resources.
One aspect of the present invention provides a system (100) for dynamic scheduling and management of cloud resources based on roles and profiles comprising:
a physical resources pool (101 ) including a plurality of physical resources;
a physical resource manager (102) associated with the physical resources pool
(101 );
a virtual resources pool (103) including a plurality of virtual resources; and a virtual resource manager (104) associated with the virtual resources pool (103); characterized in that the physical resource manager (102) and the virtual resource manager (104) are in communication with one another whereby:
means is provided for the physical resource manager (102) to dynamically manage and schedule powering of the physical resources based on physical resources roles (101a) and information on virtual resources profiles (103a) received from the virtual resource manager (104);
means is provided for the physical resource manager (102) to counter offer a temporary resource that the virtual resource manager (104) can use when a physical resource is unavailable, power up a new physical resource and communicate details of the new physical resource to the virtual resource manager (104); and
means is provided for the virtual resource manager (104) to manage and place the virtual resources based on virtual resources profiles (103a) and information on physical resources roles (101a) received from the physical resources manager (102). Another aspect of the present invention provides a system (100) wherein the physical resources manager (102) has information on which physical resources are powered up, information on remaining physical resources that are not powered up and physical resources roles (101a) assigned to the powered up physical resources. A further aspect of the invention provides a system (100) wherein the physical resources roles (101a) describe how a physical resource will behave and resources available.
A further aspect of the invention provides a system (100) wherein the virtual resource manager (104) has information on virtual resources profiles (103a) including type of virtual resource, the application contained and/or resource requirements.
Another aspect of the invention provides a method for dynamic scheduling and management of cloud resources based on roles and profiles comprising:
powering up at least one physical resource of a physical resource pool (101); at a physical resource manager (102):
recording physical resource(s) of the physical resource pool (101) that are powered up, information on remaining physical resource(s) that are not powered up and physical resources roles (101a) assigned to the powered up physical resources;
processing a request from a virtual resource manager 104 relating to a physical resource role requirement; and
allocating a physical resource that will satisfy the physical resource role requirement and informing the virtual resource manager (104) of the allocation, or, if a physical resource that will satisfy the physical resource role requirement is not available, counter offering a temporary resource to the virtual resource manager (104);
if a temporary resource is counter offered:
powering up at least one other physical resource of the physical resource pool (101 ) to satisfy the physical resource role requirement requested by the virtual resource manager (104);
informing the virtual resource manager (104) of the other physical resource, through the physical resource manager (102); and migrating the temporary resource to the other physical resource.
A further aspect of the invention provides a method including calculating a role physical resource score for every physical resource role available and setting low and high thresholds for the role physical resource scores. A further aspect of the invention provides a method including calculating a virtual resource score during or after processing the request from the virtual resource manager (104) relating to the physical resource role requirement and comparing the virtual resource score with the role physical resource score thresholds for that role.
Another aspect of the invention provides a method wherein, depending on the difference between the virtual resource score and the role physical resource score thresholds for that role, the physical resource that will satisfy the physical resource role requirement is allocated and the virtual resource manager (104) is informed of the allocation, or the counter offer of the temporary resource is made to the virtual resource manager (104).
A further aspect of the invention provides a method wherein:
if the virtual resource score is below the low threshold value for the role physical resource scores, the physical resource that will satisfy the physical resource role requirement is allocated, the virtual resource manager (104) is informed of the allocation and a new role physical resource score is calculated and low and high thresholds for the role physical resource score are reset;
if the virtual resource score is above the low threshold value and below the high threshold value for the role physical resource scores, the physical resource that will satisfy the physical resource role requirement is allocated, the virtual resource manager (104) is informed of the allocation, a new physical resource is powered up from the physical resource pool (101a) and a new role physical resource score is calculated and low and high thresholds for the role physical resource score are reset; and
if the virtual resource score is above the high threshold value for the role physical resource scores, the counter offer is made while a new physical resource is powered up from the physical resource pool (101a), the virtual resource manager is informed of the new physical resource once powered up, and a new role physical resource score is calculated and low and high thresholds for the role physical resource score are reset.
A further aspect of the invention provides a method wherein if a request arrives from the virtual resource manager (104) for virtual resource termination, the physical resource 2013/000217
- 6 -
manager (102) recalculates a new virtual resource score and, if the recalculated virtual resource score is below said low threshold of the role physical resource score for that role and if the physical resource has no associated virtual resources running, that physical resource is powered down.
Another aspect of the invention provides a method including mapping virtual resource profiles to corresponding physical resource roles using a profile-to-role map.
A further aspect of the invention provides a method wherein, when the virtual resource manager receives a request to initiate a virtual resource, the virtual resource manager (104):
determines a virtual resource profile;
based on profile-to-role mapping, sends a request to the physical resource manager (102) for an available physical resource with the role required; and on receiving a reply from the physical resource manager (102), initiates a virtual resource.
The present invention consists of features and a combination of parts hereinafter fully described and illustrated in the accompanying drawings, it being understood that various changes in the details may be made without departing from the scope of the invention or sacrificing any of the advantages of the present invention.
BRIEF DESCRIPTION OF ACCOMPANYING DRAWINGS
To further clarify various aspects of some embodiments of the present invention, a more particular description of the invention will be rendered by references to specific embodiments thereof, which are illustrated in the appended drawings. It is appreciated that these drawings depict only typical embodiments of the invention and are therefore not to be considered limiting of its scope. The invention will be described and explained with additional specificity and detail through the accompanying drawings in which:
FIG. 1.0 illustrates the system of an embodiment of the invention.
FIG. 2.0 illustrates a block flow diagram for the physical resource manager 200.
FIG. 3.0 illustrates a block flow diagram for the virtual resource manager 300.
DET AILED DESCRIPTION OF THE PREFERRED EMBODIMENTS
The present invention provides a system and method for dynamic scheduling and management of cloud resources, including physical and virtual resources, based on roles and profiles of those resources.
Hereinafter, this specification will describe the present invention according to the preferred embodiments. It is to be understood that limiting the description to the preferred embodiments of the invention is merely to facilitate discussion of the present invention and it is envisioned without departing from the scope of the appended claims.
Referring to Figure 1.0, the system (100) includes Physical Resource Manager (PRM) (102) and Virtual Resource Manager (VRM) (104) branches that will assign physical resources roles (101a) and virtual resources profiles (103a) for both physical and virtual resources of a physical resource pool (101) and a virtual resource pool (103).
The system (100) allows the PRM (102) to dynamically manage and schedule the powering of physical resources based on physical resources roles (101a) and information on virtual resources profiles (103a) from the VRM (104). In addition, the PRM (102) can counter offer to the VRM (104) a temporary resource that the VRM (104) can use in case a physical resource with a predefined role is not available. Upon the right physical resource being powered up, the PRM (102) then informs the VRM (104) to migrate a virtual server that has been created to the new physical resource. The system (100) also allows the VRM (104) to manage and place the virtual resources based on virtual resources profiles (103a) and information of physical resource roles (101a) received from the PRM (102).
Referring to Figure 2.0 a block flow diagram for the physical resource manager (200) is illustrated. In the initial phase, admins decides a set of physical servers to power up and this information is set in the PRM (201a) together with information of remaining servers of the physical resource pool 101 that are not powered up (201 b). Admins also generates physical resource roles (202) and assigns the physical resource roles the powered up servers and registers the information into the PRM (203). A physical resource role (101a) as used herein describes how a physical server will behave and the resources that are available. The behaviours may include, for example, "Always On Extra Large", "Always On Large", On Demand Small", On Demand Medium" and so on. It should be appreciated however that the invention is not limited to these specific examples ad other behaviours may be equally applicable.
For every physical resource role (101a) available, the PRM will calculate a Role Physical Resource Score (RPRS) per role (204). The score can be calculated based on usage of a servers usage (CPU load, RAM, disk, network, etc.) as well as other information such as cost, time to power up, and so on. Admins then sets low and high thresholds in percentages for each RPRS (205). The PRM then listens for request from VRM (206). When a request arrives from VRM with the physical resource role requirement, the PRM will calculate a Virtual Resource Score (VRS) (207) and compare with the existing RPRS thresholds for that role. Depending on the difference, the PRM decides the next course of action according to the following scenarios:
1. If the new VRS is below the existing low threshold value, the PRM returns information of the free physical server to the VRM (208), recalculates a new RPRS (211) and resets the threshold values.
2. If the new VRS is above the low threshold value, but below the high threshold value, the PRM returns the information of the free physical server to VRM (209a), but then powers up a new physical server (109b) from the available pool, recalculates a new RPRS (211 ) and resets the threshold values.
3. If the new VRS is above the high threshold, the PRM can counter offer the VRM with a free physical server from another role first (210a) while powering up a new physical server (210b). Once the new physical server is powered up, the PRM will then send the information of the new server to the VRM (210c), recalculate a new RPRS (211 ) and reset the threshold values. When a request arrives from VRM on virtual server termination, PRM will recalculate a new VRS (212) and if it is below to low threshold of the RPRS for the role and if the is server has no virtual servers running, that server will be powered down (213). Turning to Figure 3.0, a block flow diagram for the virtual resource manager (300) is illustrated. In the initial phase, admins decides virtual resource profiles available for the VRM (301 ). As used herein, a virtual resource profile describes the kind of virtual server, the application it contains, its resource requirement and so on. For example, the profiles may include "Database Large", "App Server Medium", "Web Frontend Light" and so on, although it should be appreciated that the present invention is not so limited.
Each profile is then mapped to a corresponding role using a Profile-to-Role Map (302) and a role can be mapped to several profiles. The VRM then communicates with the PRM and receives information on available roles (303) and waits for requests from admins as well as the PRM (304).
When the VRM receives a request from admin to start a virtual server, it will first determine the virtual server profile, then based on the profile-to-role mapping send a request to the PRM for available physical server with that role (305).
Once a reply is received from the PRM, the VRM will start the virtual server depending on the kind of offer received according to the following scenarios:
1. If the reply is that a server with the required role is available, the virtual server will be started (306).
2. If the reply is a counter offer with a server from a different role, the virtual server will be started on that server (307a) and the VRM will continue to listen to the PRM for a new server with the desired role (307b). When the information arrives, the virtual server will then be migrated (308). When the VRM receives a request from admin to terminate a virtual server, it will do so and then inform the PRM of its action (309). 2013/000217
11
For exemplification only, samples of admin defined roles and profiles are provided in Table 1.0 below.
Figure imgf000013_0001
On Demand Small 2 CPUs, 2GB memory, small storage, minimal network port, low cost, quick to power up
On Demand Medium 2 CPUs, 4GB memory, small storage, minimal netw^ ort,
Figure imgf000013_0002
Table 1.0: Admin defined roles and profiles.
Also, for exemplification only, the following formulas, illustrate sample calculations for RPRS and VRS.
RPRS = w-L- CPU + w2Memory + w3. Network + w4. Storage
+ u¾. Cost + w6. TimeToPowerUp + w7. Other
VRS = w vCPU + w2vMemory + w3. vNetwork
+ w4. vStorage + w¾. vCost + w6. Other
In order to further exemplify the present invention, a sample of an Admin Derived Profile- to-Role Map is provided in Table 2.0 below. Role Profiles
Always On Extra Large .Database Extra Large, Critical Storage Server Extra fjge 1 '
Always On Large Critical App Server Large, Database Large
Figure imgf000014_0001
On Demand Small Web Small
Table 2.0: Admin derived profile-to-role map.
Unless the context requires otherwise or specifically stated to the contrary, integers, steps or elements of the invention recited herein as singular integers, steps or elements clearly encompass both singular and plural forms of the recited integers, steps or elements.
Throughout this specification, unless the context requires otherwise, the word "comprise", or variations such as "comprises" or "comprising", will be understood to imply the inclusion of a stated step or element or integer or group of steps or elements or integers, but not the exclusion of any other step or element or integer or group of steps, elements or integers. Thus, in the context of this specification, the term "comprising" is used in an inclusive sense and thus should be understood as meaning "including principally, but not necessarily solely".
It will be appreciated that the foregoing description has been given by way of illustrative example of the invention and that all such modifications and variations thereto as would be apparent to persons of skill in the art are deemed to fall within the broad scope and ambit of the invention as herein set forth.

Claims

1. A system (100) for dynamic scheduling and management of cloud resources based on roles and profiles comprising:
a physical resources pool (101 ) including a plurality of physical resources; a physical resource manager (102) associated with said physical resources pool (101 );
a virtual resources pool (103) including a plurality of virtual resources; and a virtual resource manager (104) associated with said virtual resources pool (103);
characterized in that said physical resource manager (102) and said virtual resource manager (104) are in communication with one another whereby:
means is provided for said physical resource manager (102) to dynamically manage and schedule powering of said physical resources based on physical resources roles (101a) and information on virtual resources profiles (103a) received from said virtual resource manager (104);
means is provided for said physical resource manager (102) to counter offer a temporary resource that the virtual resource manager (104) can use when a physical resource is unavailable, power up a new physical resource and communicate details of said new physical resource to said virtual resource manager (104); and
means is provided for said virtual resource manager (104) to receive a request to initiate a virtual resource, said virtual resource manager (104) further determines a virtual resource profile; based on profile-to-role mapping, sends a request to said physical resource manager (102) for an available physical resource with the role required (305); and on receiving a reply from said physical resource manager (102), initiates a virtual resource (306); said virtual resource manager (104) further manages and place said virtual resources based on virtual resources profiles (103a) and information on physical resources roles (101a) received from said physical resources manager (102).
2. A system (100) according to claim 1 , wherein said physical resources manager (102) has information on which physical resources are powered up, information on remaining physical resources that are not powered up and physical resources roles (101a) assigned to said powered up physical resources; said physical resources roles (101a) describe how a physical resource will behave and resources available.
3. A system (100) according to claim 1, wherein said virtual resource manager (104) has information on virtual resources profiles (103a) including type of virtual resource, the application contained and/or resource requirements.
4. A method for dynamic scheduling and management of cloud resources based on roles and profiles comprising:
powering up at least one physical resource of a physical resource pool (101 );
at a physical resource manager (102):
recording physical resource(s) of said physical resource pool (101) that are powered up (201a), information on remaining physical resource(s) that are not powered up (201 b) and physical resources roles (101a) assigned to said powered up physical resources (203);
processing a request from a virtual resource manager 104 relating to a physical resource role requirement; and allocating a physical resource that will satisfy the physical resource role requirement and informing the virtual resource manager (104) of the allocation (208, 209), or, if a physical resource that will satisfy the physical resource role requirement is not available, counter offering a temporary resource to the virtual resource manager (210a); and
if a temporary resource is counter offered:
powering up at least one other physical resource of said physical resource pool (210b) to satisfy the physical resource role requirement requested by said virtual resource manager (104); informing the virtual resource manager (104) of the other physical resource (210c), through said physical resource manager (102); and
migrating the temporary resource to said other physical resource.
A method according to claim 4, including calculating a role physical resource score for every physical resource role available (204) and setting low and high thresholds for said role physical resource scores (205).
A method according to claim 5, including calculating a virtual resource score during or after processing said request from said virtual resource manager (104) relating to said physical resource role requirement and comparing the virtual resource score with said role physical resource score thresholds for that role(207).
A method according to claim 6, wherein depending on the difference between said virtual resource score and said role physical resource score thresholds for that role, said physical resource that will satisfy the physical resource role requirement is allocated and said virtual resource manager (104) is informed of the allocation (208, 209), or said counter offer of said temporary resource is made to the virtual resource manager (210a).
A method according to claim 7, wherein:
if said virtual resource score is below said low threshold value for said role physical resource scores, said physical resource that will satisfy the physical resource role requirement is allocated, said virtual resource manager (104) is informed of the allocation (208) and a new role physical resource score is calculated (211 ) and low and high thresholds for said role physical resource score are reset;
if said virtual resource score is above said low threshold value and below said high threshold value for said role physical resource scores, said physical resource that will satisfy the physical resource role requirement is allocated, said virtual resource manager (104) is informed of the allocation (209a), a new physical resource is powered up from said physical resource pool (209b) and a new role physical resource score is calculated (211) and low and high thresholds for said role physical resource score are reset; and
if said virtual resource score is above said high threshold value for said role physical resource scores, said counter offer is made (210a) while a new physical resource is powered up from said physical resource pool (210b), said virtual resource manager (104) is informed of said new physical resource once powered up (210c), and a new role physical resource score is calculated (211 ) and low and high thresholds for said role physical resource score are reset.
A method according to any of claims 4 to 8, wherein if a request arrives from said virtual resource manager (104) for virtual resource termination, said physical resource manager (102) recalculates a new virtual resource score (212) and, if said recalculated virtual resource score is below said low threshold of the role physical resource score for that role and if said physical resource has no associated virtual resources running, that physical resource is powered down.
10. A method according to any of claims 4 to 9, including mapping virtual resource profiles to corresponding physical resource roles using a profile-to-role map (302).
PCT/MY2013/000217 2012-12-06 2013-11-29 A system and method for dynamic scheduling and management of cloud resources based on roles and profiles WO2014088397A1 (en)

Applications Claiming Priority (2)

Application Number Priority Date Filing Date Title
MYPI2012005291 2012-12-06
MYPI2012005291 2012-12-06

Publications (1)

Publication Number Publication Date
WO2014088397A1 true WO2014088397A1 (en) 2014-06-12

Family

ID=50029182

Family Applications (1)

Application Number Title Priority Date Filing Date
PCT/MY2013/000217 WO2014088397A1 (en) 2012-12-06 2013-11-29 A system and method for dynamic scheduling and management of cloud resources based on roles and profiles

Country Status (1)

Country Link
WO (1) WO2014088397A1 (en)

Cited By (3)

* Cited by examiner, † Cited by third party
Publication number Priority date Publication date Assignee Title
CN105335235A (en) * 2015-11-24 2016-02-17 浪潮电子信息产业股份有限公司 IaaS mode based resource management system and method
CN107135110A (en) * 2017-06-08 2017-09-05 成都安恒信息技术有限公司 The system and application method of pre- deployment cloud computing physical resource in a kind of private clound
CN108037993A (en) * 2017-11-07 2018-05-15 大国创新智能科技(东莞)有限公司 Cloud computing dispatching method and system based on big data and deep learning neutral net

Citations (4)

* Cited by examiner, † Cited by third party
Publication number Priority date Publication date Assignee Title
US20100070784A1 (en) * 2008-09-15 2010-03-18 Vmware, Inc. Reducing Power Consumption in a Server Cluster
US20100306382A1 (en) * 2009-06-01 2010-12-02 International Business Machines Corporation Server consolidation using virtual machine resource tradeoffs
US20100332658A1 (en) * 2009-06-29 2010-12-30 Red Hat Israel, Ltd. Selecting a host from a host cluster to run a virtual machine
US20120204176A1 (en) * 2010-10-29 2012-08-09 Huawei Technologies Co., Ltd. Method and device for implementing load balance of data center resources

Patent Citations (4)

* Cited by examiner, † Cited by third party
Publication number Priority date Publication date Assignee Title
US20100070784A1 (en) * 2008-09-15 2010-03-18 Vmware, Inc. Reducing Power Consumption in a Server Cluster
US20100306382A1 (en) * 2009-06-01 2010-12-02 International Business Machines Corporation Server consolidation using virtual machine resource tradeoffs
US20100332658A1 (en) * 2009-06-29 2010-12-30 Red Hat Israel, Ltd. Selecting a host from a host cluster to run a virtual machine
US20120204176A1 (en) * 2010-10-29 2012-08-09 Huawei Technologies Co., Ltd. Method and device for implementing load balance of data center resources

Non-Patent Citations (1)

* Cited by examiner, † Cited by third party
Title
VAN H N ET AL: "Autonomic virtual resource management for service hosting platforms", SOFTWARE ENGINEERING CHALLENGES OF CLOUD COMPUTING, 2009. CLOUD '09. ICSE WORKSHOP ON, IEEE, PISCATAWAY, NJ, USA, 23 May 2009 (2009-05-23), pages 1 - 8, XP031472844, ISBN: 978-1-4244-3713-9 *

Cited By (4)

* Cited by examiner, † Cited by third party
Publication number Priority date Publication date Assignee Title
CN105335235A (en) * 2015-11-24 2016-02-17 浪潮电子信息产业股份有限公司 IaaS mode based resource management system and method
CN107135110A (en) * 2017-06-08 2017-09-05 成都安恒信息技术有限公司 The system and application method of pre- deployment cloud computing physical resource in a kind of private clound
CN108037993A (en) * 2017-11-07 2018-05-15 大国创新智能科技(东莞)有限公司 Cloud computing dispatching method and system based on big data and deep learning neutral net
CN108037993B (en) * 2017-11-07 2020-08-04 大国创新智能科技(东莞)有限公司 Cloud computing scheduling method and system based on big data and deep learning neural network

Similar Documents

Publication Publication Date Title
US10810045B2 (en) Method and apparatus for allocating central processing unit (CPU) resources in a default resource pool
US11429449B2 (en) Method for fast scheduling for balanced resource allocation in distributed and collaborative container platform environment
US9154549B2 (en) Dynamic server farms
US9588789B2 (en) Management apparatus and workload distribution management method
CN106453457B (en) Multi-priority service instance allocation within a cloud computing platform
CN108924268B (en) Container cloud service system and pod creation method and device
US9733961B2 (en) Virtual machine allocation at physical resources
US9003002B2 (en) Efficient port management for a distributed network address translation
CN103051564B (en) The method and apparatus of dynamic resource allocation
US20130268672A1 (en) Multi-Objective Virtual Machine Placement Method and Apparatus
US8959367B2 (en) Energy based resource allocation across virtualized machines and data centers
CN109388488B (en) Power allocation in computer system
Mishra et al. Time efficient dynamic threshold-based load balancing technique for Cloud Computing
US9819626B1 (en) Placement-dependent communication channels in distributed systems
CA2533744A1 (en) Hierarchical management of the dynamic allocation of resources in a multi-node system
JP2015503158A (en) Role instance reachability in the data center
US11956308B2 (en) Dynamically computing load balancer subset size in a distributed computing system
WO2014088397A1 (en) A system and method for dynamic scheduling and management of cloud resources based on roles and profiles
KR101402367B1 (en) Efficient and cost-effective distributed call admission control
US9866496B2 (en) Methods and systems for allocating and de-allocating delivery groups across multiple server farms
TW201324129A (en) System and method for dynamically assigning resources
CN105872048B (en) Control method and electronic equipment
TW201712563A (en) Public cloud system and public resource allocation method
KR101972997B1 (en) Method of managing profile for drive of virtual desttop in heterogeneous server and apparatus using the same
Zhuang et al. Ocpa: An algorithm for fast and effective virtual machine placement and assignment in large scale cloud environments

Legal Events

Date Code Title Description
121 Ep: the epo has been informed by wipo that ep was designated in this application

Ref document number: 13824673

Country of ref document: EP

Kind code of ref document: A1

NENP Non-entry into the national phase

Ref country code: DE

122 Ep: pct application non-entry in european phase

Ref document number: 13824673

Country of ref document: EP

Kind code of ref document: A1