CN115660369A - Server migration policy determination method, electronic device and storage medium - Google Patents
Server migration policy determination method, electronic device and storage medium Download PDFInfo
- Publication number
- CN115660369A CN115660369A CN202211400931.1A CN202211400931A CN115660369A CN 115660369 A CN115660369 A CN 115660369A CN 202211400931 A CN202211400931 A CN 202211400931A CN 115660369 A CN115660369 A CN 115660369A
- Authority
- CN
- China
- Prior art keywords
- migration
- servers
- cabinet
- attribute information
- determining
- Prior art date
- Legal status (The legal status is an assumption and is not a legal conclusion. Google has not performed a legal analysis and makes no representation as to the accuracy of the status listed.)
- Pending
Links
Images
Classifications
-
- 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
Abstract
The application provides a server migration strategy determination method, electronic equipment and a storage medium, and relates to the technical field of cloud computing, wherein the method comprises the following steps: acquiring first attribute information respectively corresponding to a plurality of cabinets for placing servers in a to-be-migrated range and second attribute information respectively corresponding to a plurality of servers; determining migration target information and constraint conditions according to the plurality of first attribute information and the plurality of second attribute information; and determining a migration strategy according to the migration target information and the constraint condition. In the embodiment of the application, a server migration strategy is determined according to the attribute information of the cabinet and the attribute information of the servers, and at least one server in the plurality of servers is migrated from the source cabinet to the target cabinet, so that the use state of at least one cabinet in the plurality of cabinets is changed, the resource utilization rate is improved, and resource waste is avoided.
Description
Technical Field
The present application relates to the field of cloud computing technologies, and in particular, to a server migration policy determination method, an electronic device, and a storage medium.
Background
In recent years, with the development of network technology, internet Data Centers (IDCs) have entered a high-quality development period. With the development of IDC, there may be a problem of unreasonable resources, for example, for a part of old cabinets, due to a change in an operation strategy, a change in a new demand, and migration and adjustment of a server, there may be a problem of low resource utilization rate of a part of cabinets, such as power consumption, a placement position, a port, and the like, and a problem of resource waste.
Therefore, a solution for effectively improving the resource utilization of the internet data center is needed.
Disclosure of Invention
The embodiment of the application provides a server migration strategy determination method, electronic equipment and a storage medium, so that the resource utilization rate of an internet data center is improved, and resource waste is avoided.
In a first aspect, an embodiment of the present application provides a method for determining a server migration policy, where the method includes:
acquiring first attribute information respectively corresponding to a plurality of cabinets for placing servers in a to-be-migrated range and second attribute information respectively corresponding to a plurality of servers;
determining migration target information and constraint conditions according to the plurality of first attribute information and the plurality of second attribute information;
determining a migration strategy according to the migration target information and the constraint condition;
wherein the migration policy includes migrating at least one of the plurality of servers from the source enclosure to the target enclosure, thereby altering a usage status of the at least one of the plurality of enclosures.
In a second aspect, an embodiment of the present application provides an electronic device, including a memory, a processor, and a computer program stored on the memory, where the processor implements the method of any one of the above when executing the computer program.
In a third aspect, an embodiment of the present application provides a computer-readable storage medium, in which a computer program is stored, and when the computer program is executed by a processor, the computer program implements the method of any one of the foregoing items.
Compared with the prior art, the method has the following advantages:
the embodiment of the application provides a server migration strategy determination method, electronic equipment and a storage medium, and first attribute information corresponding to a plurality of cabinets for placing servers in a to-be-migrated range and second attribute information corresponding to a plurality of servers are obtained; determining migration target information and constraint conditions according to the plurality of first attribute information and the plurality of second attribute information; and determining a migration strategy according to the migration target information and the constraint condition. In the embodiment of the application, a migration strategy is determined according to the attribute information of the cabinet and the attribute information of the servers, and at least one server in the plurality of servers is migrated from the source cabinet to the target cabinet, so that the use state of at least one cabinet in the plurality of cabinets is changed, the resource utilization rate is improved, and resource waste is avoided.
The above description is only an overview of the technical solutions of the present application, and the present application may be implemented in accordance with the content of the description so as to make the technical means of the present application more clearly understood, and the detailed description of the present application will be given below in order to make the above and other objects, features, and advantages of the present application more clearly understood.
Drawings
In the drawings, like reference numerals refer to the same or similar parts or elements throughout the several views unless otherwise specified. The figures are not necessarily to scale. It is appreciated that these drawings depict only some embodiments in accordance with the disclosure and are not to be considered limiting of its scope.
Fig. 1 is a schematic view of a scenario of a server migration policy determination method provided in the present application;
fig. 2 is a flowchart of a method for determining a server migration policy according to an embodiment of the present application;
FIG. 3 is a flow chart of a server migration policy determination method according to another embodiment of the present application;
fig. 4 is a block diagram of a server migration policy determination apparatus according to another embodiment of the present application; and
FIG. 5 is a block diagram of an electronic device used to implement embodiments of the present application.
Detailed Description
In the following, only certain exemplary embodiments are briefly described. As those skilled in the art will recognize, the described embodiments may be modified in various different ways, without departing from the spirit or scope of the present application. Accordingly, the drawings and description are to be regarded as illustrative in nature, and not as restrictive.
To facilitate understanding of the technical solutions of the embodiments of the present application, the following describes related arts of the embodiments of the present application. The following related arts as alternatives can be arbitrarily combined with the technical solutions of the embodiments of the present application, and all of them belong to the scope of the embodiments of the present application.
In a cloud computing cost reduction and efficiency improvement scene, a cabinet and a server of an internet data center need to be subjected to resource optimization, and a plurality of internet data centers face a server migration requirement. In the related technology, two modes of natural filling or active regulation based on rules are adopted to realize server migration and improve the utilization rate of the cabinet so as to realize resource optimization. Wherein, natural filling refers to improving the utilization rate of the cabinet depending on the future server requirements. The scheme adopts the requirement of a newly added server to naturally fill the rest positions in the cabinet, and belongs to a passive utilization rate improving mode. The disadvantage of this solution is that when the server speed increase in a specific area is low, the utilization rate of the cabinet will be maintained at a low level for a long time, resulting in waste of resources. The active regulation based on the rules is based on a series of rules, screens out some cabinets with low resource utilization rate, called source cabinets, and tries to empty the source cabinets. And selecting some cabinets with higher resource utilization rate and still having residual space, and calling the cabinets as target cabinets. And adopting an algorithm to make a decision, migrating the server in the source cabinet to the target cabinet, and implementing the migration. The disadvantage of this solution is that global optimization cannot be achieved on the one hand, and on the other hand, the target cabinet cannot be found due to improper condition setting.
In order to solve the above problem, an embodiment of the present application provides a method for determining a server migration policy. The method may be deployed in a computing device, e.g., a server, a terminal device, etc. Determining a migration strategy according to the attribute information of the cabinet and the attribute information of the server, migrating the server from the source cabinet to the target cabinet according to the migration strategy, and stopping or starting the cabinet, so that the resource utilization rate of the internet data center is improved. The embodiment of the application can be applied to a plurality of operation scenes such as cabinet regulation, delivery unit regulation, inter-package arbitration and machine room arbitration of the internet data center, and is also suitable for the treatment of the super-electricity. The excessive power is that the power consumption upper limit is exceeded, which refers to a situation that the total power consumption of all internet devices on the cabinet or the train exceeds the power consumption upper limit of the cabinet or the train (that is, an excessive power threshold). The over-current has potential safety hazard and should be avoided as much as possible. The embodiment can be embedded into a server migration decision-making system as a functional module, provides technical support for the capacity regularity of the internet data center, and has the advantages of small development difficulty, high development efficiency and strong practicability. The capacity normalization refers to taking into account capacity-related constraints (e.g., power consumption constraints, placement bit (U bit) constraints, port constraints, and the like) of certain containers (e.g., cabinets, delivery units, bays, machine rooms, and the like) for accommodating servers in a data center architecture, so as to optimize capacity cost, migrate servers in a plurality of containers, and reduce the number of the containers used, thereby reducing the cost of the internet data center. The Delivery unit (POD) refers to a module composed of network, computing, storage, and application components, and cooperates to deliver the web service, and the Delivery unit may include a plurality of servers. The cubicle includes a plurality of cabinets and the machine room includes a plurality of cubicles.
Fig. 1 is a schematic diagram of an exemplary application scenario for implementing the method of the embodiment of the present application. As shown in fig. 1, the internet data center includes a plurality of cabinets: cabinet 1, cabinet 2 \8230andcabinet n; there are a plurality of places bits in every rack, and a plurality of servers are placed to rack 1: server 11, server 12, 8230and server 1m n (ii) a The cabinet 2 houses a plurality of servers: garmentServer 21, server 22 8230and server 2m 2 (ii) a Cabinet n houses multiple servers: server n1, server n2 \8230am, server nm n . Determining a range to be migrated in the cabinet and the servers, and acquiring first attribute information corresponding to the plurality of cabinets and second attribute information corresponding to the plurality of servers in the range to be migrated; determining migration target information and constraint conditions according to the plurality of first attribute information and the plurality of second attribute information; determining a migration policy by using an optimization model (e.g., mixed Integer Linear Programming (MILP) model, etc.) according to the migration target information and the constraint conditions, and migrating at least one server of the plurality of servers from the source cabinet to the target cabinet; or to change the status of use of at least one of the plurality of cabinets, for example, to enable or disable the cabinet. In the embodiment of the application, a server migration strategy is determined according to the attribute information of the cabinet and the attribute information of the servers, and at least one server in the plurality of servers is migrated from the source cabinet to the target cabinet, so that the use state of the at least one cabinet in the plurality of cabinets is changed, the resource utilization rate is improved, and resource waste is avoided.
An embodiment of the present application provides a method for determining a server migration policy, and as shown in fig. 2, a flowchart of the method for determining a server migration policy according to an embodiment of the present application is shown. The method comprises the following steps:
step S201, first attribute information corresponding to a plurality of cabinets for placing servers in a to-be-migrated range and second attribute information corresponding to a plurality of servers are obtained.
The range to be migrated is determined according to specific needs, and may be an internet data center including a plurality of cabinets and a plurality of servers. And acquiring first attribute information of the cabinet in the range to be migrated and second attribute information of the server. Wherein the first attribute information includes at least one of: the system comprises a cabinet identifier, a city, a machine room, a building, a compartment, a train, a security domain (a group of logic areas formed by systems with the same security protection requirements and mutually trusting), a service class, a logic area, a network type, a cluster, a capacity upper limit, a used capacity, a regular group name, an enabling cost, a disabling cost and the like of the cabinet. Wherein the capacity comprises at least one of: power consumption, placement bits (U bits), ports, etc. The second attribute information includes at least one of: the server identification, the cabinet, the machine room, the machine type, the department, the product line, the security domain, the service class, the logic area, the network type, the cluster and the like of the server, the capacity occupation of the server and the like.
Step S202, determining migration target information and constraint conditions according to the plurality of first attribute information and the plurality of second attribute information.
The migration target information is a target to be reached by the server migration, and the target may be determined according to specific needs, and may be to minimize the cost of the cabinet, or minimize the cost of the cabinet and the migration cost. The constraint condition may be a condition that constrains capacity, power consumption, number of servers, and the like of the cabinet in the server migration process, and the number of the constraint conditions may be one or multiple, and may be determined according to specific needs.
Step S203, determining a migration strategy according to the migration target information and the constraint condition; wherein the migration policy includes migrating at least one of the plurality of servers from the source enclosure to the target enclosure, thereby altering a usage status of the at least one of the plurality of enclosures.
Determining an objective function according to the migration target information, calculating an optimal solution by using an optimization model according to the objective function and constraint conditions, and taking the optimal solution as a migration strategy to migrate the server from the source cabinet to the target cabinet, so as to change the use state of the cabinets, for example, migrating the server from 1000 cabinets, and closing the vacant 800 cabinets after migration. The source cabinet and the target cabinet refer to a server which is transferred from a cabinet A to a cabinet B, and the cabinet A is called as a source cabinet, and the cabinet B is called as a target cabinet.
The migrating the server from the source cabinet to the target cabinet may include migrating the server entity device, or migrating data in the server, for example, migrating data of the server in the cabinet a to the server in the cabinet b according to the data migration instruction.
Optionally, in practical application, appropriate solving accuracy and solving time limit may be set as required, so as to obtain an optimal solution meeting engineering requirements through calculation in a short time.
The server migration strategy determining method provided by the embodiment of the application obtains first attribute information respectively corresponding to a plurality of cabinets for placing servers and second attribute information respectively corresponding to a plurality of servers in a to-be-migrated range; determining migration target information and constraint conditions according to the plurality of first attribute information and the plurality of second attribute information; and determining a migration strategy according to the migration target information and the constraint conditions. In the embodiment of the application, a migration strategy is determined according to the attribute information of the cabinet and the attribute information of the servers, and at least one server in the plurality of servers is migrated from the source cabinet to the target cabinet, so that the use state of at least one cabinet in the plurality of cabinets is changed, the resource utilization rate is improved, and the resource waste is avoided.
When the server migration is performed, in addition to the constraint condition, a migration condition may also be set, so as to further limit the migrated server, which is specifically seen in the following embodiments:
in one implementation, the method further comprises: acquiring migration conditions of a plurality of servers, wherein the migration conditions are used for representing the same attribute category of the migratable servers; determining a migration strategy according to the migration target information and the constraint conditions, wherein the migration strategy comprises the following steps: determining an initial migration strategy according to the migration target information and the constraint conditions; and adjusting the initial migration strategy by using the migration condition.
The migration conditions include which attribute classes of the servers are allowed to migrate within the same range, for example, the same machine room, the same service class, the same network type, the same security domain, the same logical area, and the like. For different measurement and calculation scenes, the migration conditions can be different.
After the initial migration strategy is determined according to the migration target information and the constraint condition, the initial migration strategy is adjusted by using the migration condition, for example, the migration condition is that the same machine room allows migration, if the initial migration strategy includes that a server is migrated from a cabinet of the machine room a to a cabinet of the machine room b, since the machine room a and the machine room b are different machine rooms, the migration strategy is filtered out, and the server is migrated according to the migration strategy meeting the migration condition.
In this embodiment, the initial migration policy is adjusted according to the migration condition, so that the obtained migration policy can better meet the actual requirements.
In addition, the migration target information and the constraint condition are determined as follows:
in one implementation, the method further comprises: acquiring starting states corresponding to a plurality of cabinets for placing servers, migration cost information corresponding to the plurality of servers and super power consumption cost corresponding to the plurality of cabinets; determining migration target information and constraint conditions according to the plurality of first attribute information and the plurality of second attribute information, including: determining a constraint condition according to the plurality of first attribute information and the plurality of second attribute information; and determining migration target information according to the multiple enabling states, the multiple migration cost information, the multiple first attribute information, the super power consumption cost corresponding to the multiple cabinets and the constraint conditions.
Wherein, for each cabinet, the starting state of the cabinet can be set to any one of the following states according to actual needs: must be on, advise on, must be off, advise off, no status specified. The super power consumption cost corresponding to the cabinet can be set, the super power consumption cost can also be called as super power penalty, and the cost is the cost required by exceeding the maximum power consumption of the cabinet. For each server, whether it can be migrated and migration cost information can be set according to the service running on it. At least one constraint condition of server migration can be determined according to the first attribute information of the cabinets and the second attribute information of the servers, an objective function of an optimization model is determined according to the starting states of the cabinets, the migration cost information of the servers, the first attribute information and the super power consumption cost corresponding to the cabinets under the condition that the constraint condition is met, and the optimal solution of the cabinet switching scheme and the server migration scheme is calculated.
Further, a specific implementation manner for determining migration target information is shown in the following embodiments:
in one implementation, the first attribute information includes an activation cost and a deactivation cost of the cabinet; determining migration target information according to the multiple enabling states, the multiple migration cost information, the multiple first attribute information, the excess power consumption cost corresponding to the multiple cabinets and the constraint conditions, wherein the determining comprises the following steps: and determining the minimum migration cost according to the plurality of starting states, the plurality of migration cost information, the starting cost, the stopping cost, the super power consumption cost and the constraint conditions of the plurality of cabinets, and taking the minimum migration cost as the migration target information.
In practical application, in order to save the cost of the internet data center, the target information can be migrated in view of cost minimization, so that the purpose of saving the cost is achieved. The first attribute information of the enclosure may include an activation cost and a deactivation cost of the enclosure. And determining the minimum migration cost according to the plurality of enabling states, the plurality of migration cost information, the enabling cost, the disabling cost, the super power consumption cost and the constraint condition of the plurality of cabinets, and taking the minimum migration cost as the migration target information.
In the embodiment, the cabinet cost and the migration cost are minimized as the migration target information, and the server migration scheme is decided, so that the use number and the use cost of the cabinets can be reduced, and the purpose of saving the cost of the internet data center is achieved.
In one example, an objective function of a mixed integer optimization model is determined according to the following equation (1):
wherein alpha is i Representing the enabled state of the cabinet i;
represents the cost of the activation of the cabinet i;
represents the cost of shutdown of cabinet i;
migration cost information representing a server class s (server class s includes at least one server);
representing the cost of excess power consumption of cabinet i;
the power consumption relaxation variable of the cabinet i is represented, and the data type can be a continuous type;
represents the super power consumption cost of the machine column j (comprising a plurality of cabinets);
the power consumption relaxation variable of the machine column j is represented, and the data type can be a continuous type; omega i Representing a set of servers in the cabinet i;
indicating the number of server classes s migrated from the cabinet i. For the cabinet with the starting state set as the state of opening and closing, the starting state alpha of the cabinet is limited i Can be of corresponding value, for example, 0 and 1,0 means must be off, 1 means must be on; for the cabinet enabled state alpha i And the value range can be set according to the number of the migratable servers. For cabinets without defined enablement states, the enablement states can be used as decision variables for the optimization model.
In addition, the constraint conditions may be determined from multiple dimensions according to specific needs, see the following embodiments:
in one implementation, the first attribute information includes a capacity of the cabinet; the second attribute information includes a capacity required by the server; determining a constraint condition according to the plurality of first attribute information and the plurality of second attribute information, further comprising: determining a capacity constraint condition according to the starting states, the capacities corresponding to the cabinets and the capacities required by the servers; the constraints include capacity constraints; the capacity includes the number of placement bits and the number of ports.
The capacity of the cabinet includes the number of placement bits (U bits) in the cabinet and the number of ports, and the capacity required by the server may include the number of placement bits occupied by the server and the required number of ports. From the perspective of the capacity of the cabinet and the capacity required by the server, capacity constraints are determined, including a placement bit number constraint and a port number constraint, constraints are performed from the dimension of the capacity, and then a migration strategy is determined.
In one example, the placement bit number constraint is determined according to the following equation (2):
wherein X i,s Representing the number of server classes s of the cabinet i; u shape s Representing the number of placement bits required by the server class s;
representing the placement capacity of the cabinet i; alpha is alpha i Representing the enabled state of the cabinet i; omega i Representing the collection of servers within the cabinet i.
Determining a port number constraint according to the following equation (3):
wherein X i,s The number of server classes s representing the cabinet i; p is a radical of s Indicating the number of ports required by the server class s;
representing the port capacity of the cabinet i; alpha is alpha i Representing the enabled state of the cabinet i; omega i Representing the collection of servers within the cabinet i.
In one implementation, the first attribute information includes a power consumption capacity of the cabinet; the second attribute information includes power consumption of the server; determining a constraint condition according to the plurality of first attribute information and the plurality of second attribute information, including: determining a power consumption constraint condition according to the power consumption capacities of the plurality of cabinets and the power consumption of the plurality of servers; the constraints include power consumption constraints; the power consumption capacity of the cabinet is determined based on a power consumption profile of a server placed in the cabinet; the power consumption of the server is determined based on the power consumption profile of the server.
In practical application, from the perspective of power consumption capacity of the cabinet and power consumption of the server, a power consumption constraint condition is determined, constraint is performed from the dimension of power consumption, and then a migration strategy is determined. The power consumption image of the server is a group of statistical data representing the power consumption fluctuation characteristics of the server, and comprises a power consumption mean value, a standard deviation, a quantile inference coefficient, a correlation coefficient and the like, wherein the quantile inference coefficient can be determined according to the power consumption mean value, the standard deviation and the like. The power consumption constraint conditions comprise cabinet power consumption mean value constraint conditions and power consumption peak value constraint conditions.
In one example, the cabinet power consumption mean constraint is determined according to the following equation (4):
wherein, X i,s The number of server classes s representing the cabinet i; mu.s s Representing the power consumption mean value of the server class s;
representing the power consumption mean capacity of the cabinet i; alpha (alpha) ("alpha") i Indicating the starting state of the cabinet i; omega i Representing the collection of servers within the cabinet i.
In one example, the cabinet power consumption peak constraint is determined according to the following equation (5):
wherein, f (X) i,s s∈Ω i ) Representing a power consumption peak value of a server class s of the cabinet i determined by the server power consumption figure; x i,s Representing the number of server classes s of the cabinet i; omega i Representing a set of servers in the cabinet i;
representing the power consumption capacity of the cabinet i;
representing the power consumption relaxation variable of cabinet i.
Determining a power consumption peak constraint condition of a machine column (the machine column comprises a plurality of cabinets) according to the following formula (6):
wherein, the first and the second end of the pipe are connected with each other,
a power consumption peak value of a server class s of a set j determined by the server power consumption figure; omega i Representing a set of servers in the cabinet i;
representing a set of cabinets in column j;
representing the power consumption capacity of the rank j;
representing the power consumption relaxation variable for rank j.
In one implementation, the method further comprises: determining a server migration logic constraint condition according to the number of servers placed in the cabinet after the server migration, the number of servers placed in the cabinet before the server migration, the number of servers migrated into the cabinet and the number of servers migrated out of the cabinet; the constraints include server migration logic constraints.
In one example, the server migration logic constraints are determined according to the following equation (7):
wherein Z is i,s Representing the number of server classes s placed in the cabinet i after the migration; n is a radical of i,s Representing the number of server classes s placed by the cabinet i before the migration;
representing the number of server classes s migrated into the cabinet i;
indicating the number of servers s migrating out of enclosure i.
In one implementation, the method further comprises: determining a logical constraint condition of the number of servers according to the number of the servers placed in the cabinet after the migration of the servers, the number of the servers placed in the cabinet before the migration of the servers, the number of offline servers and the number of newly added servers; the constraints include a number of servers logical constraint.
In one example, the number of servers logical constraint is determined according to the following equation (8):
wherein Z is i,s Representing the number of server classes s placed in the cabinet i after the migration;
the number of the server classes s which are off-line, scrapped or warehoused is represented; n is a radical of i,s Representing the number of servers s placed by the cabinet i before the migration;
representing the number of the newly added server classes s; s ∈ Ω i ，Ω i Representing the collection of servers within cabinet i.
In one implementation, the scope to be migrated includes a plurality of groups to be migrated, the method further includes: determining a state constraint condition of the group to be migrated according to the starting states of the cabinets in the group to be migrated; the constraints include state constraints.
Wherein the enabled state of the cabinet comprises enabled or disabled; the group to be migrated may include a plurality of cabinets.
In one example, the state constraints for the group to be migrated are determined according to equation (9) below:
wherein alpha is i Indicating the starting state of the cabinet i;
representing the starting states of all cabinets in the group g to be migrated, wherein the formula (9) represents that the starting states of all cabinets in the group g to be migrated are consistent;
representing the set of enclosures within the group g to be migrated.
In each of the above examples, the decision variables of the optimization model may be as shown in table 1:
TABLE 1
In one implementation, the method further comprises: when the constraint condition is a nonlinear constraint condition, carrying out linearization processing on the constraint condition to obtain a linear constraint condition; determining a migration strategy according to the migration target information and the constraint condition, wherein the migration strategy comprises the following steps: and determining a migration strategy according to the migration target information and the linear constraint condition.
In practical applications, the objective function and the constraint condition of the optimization model are linear functions. However, the peak power consumption of the server is probability superposition, direct summation is not suitable, and the server power consumption portrait is more accurate. The server power consumption image considers the volatility and the correlation characteristics of the power consumption of the server in the cabinet or the train, and when the power consumption image is adopted to represent the peak power consumption of the cabinet or the train, the constraint condition is nonlinear, and the optimal solution is not easy to obtain. And (3) carrying out linearization processing on the nonlinear function by using a Taylor first-order expansion to obtain a linearization approximate expression of the nonlinear function, and determining a migration strategy according to migration target information and a linearity constraint condition.
In order to more clearly describe the technical idea of the technical solution of the present application, the following detailed description is provided by specific embodiments. Fig. 3 is a flowchart of a method for determining a server migration policy according to another embodiment of the present application. As shown in fig. 3, the method includes:
step S301, determining a range to be migrated and migration conditions.
Specifically, the range to be migrated is determined according to specific needs, and the range to be migrated may be an internet data center, which includes multiple racks and multiple servers. The migration conditions include which attribute classes of the servers are allowed to be migrated within the same range, for example, the same machine room, the same service class, the same network type, the same security domain, the same logical area, and the like. For different measurement and calculation scenes, the migration conditions can be different.
Step S302, acquiring attribute information of the cabinets and the servers in the range to be migrated.
Specifically, first attribute information of the cabinet in the range to be migrated and second attribute information of the server are obtained. Wherein the first attribute information includes at least one of: the system comprises a cabinet identifier, a city, a machine room, a building, a compartment, a train, a security domain, a service class, a logic area, a network type and a cluster to which the cabinet belongs, and the upper limit of the capacity, the used capacity, the regular group name, the starting cost, the stopping cost and the like of the cabinet. Wherein the capacity comprises at least one of: power consumption, placement bits (U bits), ports, etc. The second attribute information includes at least one of: the server identification, the cabinet, the machine room, the machine type, the department, the product line, the security domain, the service class, the logic area, the network type, the cluster and the like of the server, the capacity occupation of the server and the like.
Step S303, setting the starting state of the cabinet, the information whether the server can be migrated and the migration cost.
Specifically, for each cabinet, the activation state of the cabinet can be set to any one of the following states according to actual needs: must be on, advise on, must be off, advise off, not specify a state. For each server, whether the server can be migrated or not and migration cost information can be set according to the service running on the server.
And S304, determining an objective function and a constraint condition, and constructing a mixed integer optimization model.
And determining the minimum migration cost according to the plurality of enabling states, the plurality of migration cost information, the enabling cost, the disabling cost, the super power consumption cost and the constraint condition of the plurality of cabinets, and taking the minimum migration cost as an objective function. Determining constraints from a plurality of dimensions according to specific needs, including at least one of: capacity constraints, power consumption constraints, server migration logic constraints, number of servers logic constraints, and state constraints for a migration group.
And S305, solving the optimal solution of the mixed integer linear programming model to obtain a migration strategy.
Specifically, the optimal solution of the mixed integer linear programming model is solved, and a migration strategy is obtained by combining migration conditions, whether the server can migrate or not and the like.
Step S306, evaluating the feasibility of the migration strategy, if the evaluation is passed, executing step S307; otherwise, the procedure returns to step S303 to adjust the parameters.
Server migration involves migration of the services running on it, and its mechanism is complex. Although whether each server is migratable or not has been preliminarily set in step S303, the consideration is not necessarily comprehensive, and whether migration is possible or not needs to be further evaluated in conjunction with the migration policy. And setting an evaluation passing standard according to the operation strategy, if the number of the servers which can not be migrated is less than or equal to the standard, the evaluation passing, and executing the step S307 to perform the server migration.
If the evaluation is not passed, the process returns to step S303 to adjust parameters such as the enabled status, whether the server is migratable, and the like.
And step S307, carrying out server migration according to the migration strategy.
And (4) determining a feasible server in the migration strategy passing the evaluation for migration, closing the vacated cabinet and finishing normalization.
Corresponding to the application scenario and the method of the method provided by the embodiment of the application, the embodiment of the application further provides a server migration policy determination device. Fig. 4 is a block diagram illustrating a structure of a server migration policy determining apparatus according to an embodiment of the present application, where the server migration policy determining apparatus may include:
the information obtaining module 401 is configured to obtain first attribute information corresponding to each of multiple racks where servers are placed in the range to be migrated, and second attribute information corresponding to each of the multiple servers.
A first determining module 402, configured to determine migration target information and a constraint condition according to the plurality of first attribute information and the plurality of second attribute information.
A second determining module 403, configured to determine a migration policy according to the migration target information and the constraint condition.
Wherein the migration policy includes migrating at least one of the plurality of servers from the source enclosure to the target enclosure, thereby altering a usage status of the at least one of the plurality of enclosures.
The server migration strategy determining method provided by the embodiment of the application obtains first attribute information respectively corresponding to a plurality of cabinets for placing servers and second attribute information respectively corresponding to a plurality of servers in a to-be-migrated range; determining migration target information and constraint conditions according to the plurality of first attribute information and the plurality of second attribute information; and determining a migration strategy according to the migration target information and the constraint conditions. In the embodiment of the application, a migration strategy is determined according to the attribute information of the cabinet and the attribute information of the servers, and at least one server in the plurality of servers is migrated from the source cabinet to the target cabinet, so that the use state of at least one cabinet in the plurality of cabinets is changed, the resource utilization rate is improved, and resource waste is avoided.
In one implementation, the apparatus is further configured to:
acquiring migration conditions of a plurality of servers, wherein the migration conditions are used for representing the same attribute category of the migratable servers;
a second determining module 403, configured to:
determining an initial migration strategy according to the migration target information and the constraint conditions;
and adjusting the initial migration strategy by using the migration condition.
In one implementation, the apparatus is further configured to:
acquiring starting states corresponding to a plurality of cabinets for placing servers, migration cost information corresponding to the plurality of servers and super power consumption cost corresponding to the plurality of cabinets;
a first determining module 402 for:
determining a constraint condition according to the plurality of first attribute information and the plurality of second attribute information;
and determining migration target information according to the multiple enabling states, the multiple migration cost information, the multiple first attribute information, the super power consumption cost corresponding to the multiple cabinets and the constraint conditions.
In one implementation, the first attribute information includes an activation cost and a deactivation cost of the cabinet; when determining the migration target information according to the multiple enabling states, the multiple migration cost information, the multiple first attribute information, the excess power consumption cost corresponding to the multiple cabinets, and the constraint condition, the first determining module 402 is configured to:
and determining the minimum migration cost according to the plurality of enabling states, the plurality of migration cost information, the enabling cost, the disabling cost, the super power consumption cost and the constraint condition of the plurality of cabinets, and taking the minimum migration cost as the migration target information.
In one implementation, the first attribute information includes a capacity of the cabinet; the second attribute information includes a capacity required by the server; a second determining module 403, further configured to:
determining a capacity constraint condition according to the starting states, the capacities corresponding to the cabinets and the capacities required by the servers; the constraints include capacity constraints; the capacity includes the number of placement bits and the number of ports.
In one implementation, the first attribute information includes a power consumption capacity of the cabinet; the second attribute information includes power consumption of the server; a second determining module 403, further configured to:
determining power consumption constraint conditions according to the power consumption capacities of the cabinets and the power consumption of the servers, wherein the constraint conditions comprise the power consumption constraint conditions; the power consumption capacity of the cabinet is determined based on a power consumption profile of a server placed in the cabinet; the power consumption of the server is determined based on the power consumption profile of the server.
In one implementation, the apparatus is further configured to:
determining a server migration logic constraint condition according to the number of servers placed in the cabinet after the server migration, the number of servers placed in the cabinet before the server migration, the number of servers migrated into the cabinet and the number of servers migrated out of the cabinet; the constraints include server migration logic constraints.
In one implementation, the apparatus is further configured to:
determining a logical constraint condition of the number of servers according to the number of the servers placed in the cabinet after the migration of the servers, the number of the servers placed in the cabinet before the migration of the servers, the number of offline servers and the number of newly added servers; the constraints include a number of servers logical constraint.
In one implementation, the scope to be migrated includes a plurality of groups to be migrated, and the apparatus is further configured to:
determining a state constraint condition of the group to be migrated according to the starting states of the cabinets in the group to be migrated; the constraints include state constraints.
In one implementation, the apparatus is further configured to:
when the constraint condition is a nonlinear constraint condition, carrying out linearization processing on the constraint condition to obtain a linear constraint condition;
a second determining module 403, further configured to:
and determining a migration strategy according to the migration target information and the linear constraint condition.
The functions of the modules in the apparatuses in the embodiment of the present application may refer to the corresponding descriptions in the above method, and have corresponding beneficial effects, which are not described herein again.
FIG. 5 is a block diagram of an electronic device used to implement embodiments of the present application. As shown in fig. 5, the electronic apparatus includes: a memory 510 and a processor 520, the memory 510 having stored therein computer programs that are executable on the processor 520. The processor 520, when executing the computer program, implements the method in the above embodiments. The number of the memory 510 and the processor 520 may be one or more.
The electronic device further includes:
the communication interface 530 is used for communicating with an external device to perform data interactive transmission.
If the memory 510, the processor 520, and the communication interface 530 are implemented independently, the memory 510, the processor 520, and the communication interface 530 may be connected to each other through a bus and perform communication with each other. The bus may be an Industry Standard Architecture (ISA) bus, a Peripheral Component Interconnect (PCI) bus, an Extended ISA (EISA) bus, or the like. The bus may be divided into an address bus, a data bus, a control bus, etc. For ease of illustration, only one thick line is shown in FIG. 5, but this is not intended to represent only one bus or type of bus.
Optionally, in an implementation, if the memory 510, the processor 520, and the communication interface 530 are integrated on a chip, the memory 510, the processor 520, and the communication interface 530 may complete communication with each other through an internal interface.
Embodiments of the present application provide a computer-readable storage medium, which stores a computer program, and when the program is executed by a processor, the computer program implements the method provided in the embodiments of the present application.
The embodiment of the present application further provides a chip, where the chip includes a processor, and is configured to call and run an instruction stored in a memory from the memory, so that a communication device in which the chip is installed executes the method provided in the embodiment of the present application.
An embodiment of the present application further provides a chip, including: the system comprises an input interface, an output interface, a processor and a memory, wherein the input interface, the output interface, the processor and the memory are connected through an internal connection path, the processor is used for executing codes in the memory, and when the codes are executed, the processor is used for executing the method provided by the embodiment of the application.
It should be understood that the Processor may be a Central Processing Unit (CPU), other general purpose Processor, a Digital Signal Processor (DSP), an Application Specific Integrated Circuit (ASIC), a Field Programmable Gate Array (FPGA) or other Programmable logic device, discrete Gate or transistor logic, discrete hardware components, etc. A general purpose processor may be a microprocessor or any conventional processor or the like. It is noted that the processor may be a processor supporting an Advanced reduced instruction set machine (ARM) architecture.
Further, optionally, the memory may include a read-only memory and a random access memory. The memory may be either volatile memory or nonvolatile memory, or may include both volatile and nonvolatile memory. The non-volatile Memory may include a Read-Only Memory (ROM), a Programmable ROM (PROM), an Erasable PROM (EPROM), an Electrically Erasable PROM (EEPROM), or a flash Memory. Volatile Memory can include Random Access Memory (RAM), which acts as external cache Memory. By way of example, and not limitation, many forms of RAM may be used. For example, static Random Access Memory (Static RAM, SRAM), dynamic Random Access Memory (DRAM), synchronous Dynamic Random Access Memory (SDRAM), double Data Rate Synchronous Dynamic Random Access Memory (DDR SDRAM), enhanced SDRAM (ESDRAM), SLDRAM (SLDRAM), and Direct Rambus RAM (DR RAM).
In the above embodiments, the implementation may be wholly or partially realized by software, hardware, firmware, or any combination thereof. When implemented in software, may be implemented in whole or in part in the form of a computer program product. The computer program product includes one or more computer instructions. The procedures or functions according to the present application are all or partially generated when the computer program instructions are loaded and executed on a computer. The computer may be a general purpose computer, a special purpose computer, a network of computers, or other programmable device. The computer instructions may be stored in a computer-readable storage medium or transmitted from one computer-readable storage medium to another computer-readable storage medium.
In the description of the present specification, reference to the description of "one embodiment," "some embodiments," "an example," "a specific example," or "some examples" or the like means that a particular feature, structure, material, or characteristic described in connection with the embodiment or example is included in at least one embodiment or example of the present application. Furthermore, the particular features, structures, materials, or characteristics described may be combined in any suitable manner in any one or more embodiments or examples. Furthermore, various embodiments or examples and features of different embodiments or examples described in this specification can be combined and combined by one skilled in the art without contradiction.
Furthermore, the terms "first", "second" and "first" are used for descriptive purposes only and are not to be construed as indicating or implying relative importance or implicitly indicating the number of technical features indicated. Thus, a feature defined as "first" or "second" may explicitly or implicitly include at least one of the feature. In the description of the present application, "a plurality" means two or more unless specifically limited otherwise.
Any process or method described in a flow diagram or otherwise herein may be understood as representing a module, segment, or portion of code, which includes one or more executable instructions for implementing specific logical functions or steps of the process. And the scope of the preferred embodiments of the present application includes other implementations in which functions may be performed out of the order shown or discussed, including substantially concurrently or in reverse order, depending on the functionality involved.
The logic and/or steps described in the flowcharts or otherwise described herein, such as an ordered listing of executable instructions that can be considered to implement logical functions, can be embodied in any computer-readable medium for use by or in connection with an instruction execution system, apparatus, or device, such as a computer-based system, processor-containing system, or other system that can fetch the instructions from the instruction execution system, apparatus, or device and execute the instructions.
It should be understood that portions of the present application may be implemented in hardware, software, firmware, or a combination thereof. In the above embodiments, the various steps or methods may be implemented in software or firmware stored in memory and executed by a suitable instruction execution system. All or part of the steps of the method of the above embodiments may be implemented by hardware that is configured to be instructed to perform the relevant steps by a program, which may be stored in a computer-readable storage medium, and which, when executed, includes one or a combination of the steps of the method embodiments.
In addition, functional units in the embodiments of the present application may be integrated into one processing module, or each unit may exist alone physically, or two or more units are integrated into one module. The integrated module can be realized in a hardware mode, and can also be realized in a software functional module mode. The above-described integrated module, if implemented in the form of a software functional module and sold or used as a separate product, may also be stored in a computer-readable storage medium. The storage medium may be a read-only memory, a magnetic or optical disk, or the like.
The above description is only an exemplary embodiment of the present application, but the scope of the present application is not limited thereto, and any person skilled in the art can easily conceive various changes or substitutions within the technical scope described in the present application, and these should be covered by the scope of the present application. Therefore, the protection scope of the present application shall be subject to the protection scope of the claims.
Claims (12)
1. A method for determining a server migration policy, the method comprising:
acquiring first attribute information respectively corresponding to a plurality of cabinets for placing servers in a to-be-migrated range and second attribute information respectively corresponding to a plurality of servers;
determining migration target information and constraint conditions according to the plurality of first attribute information and the plurality of second attribute information;
determining a migration strategy according to the migration target information and the constraint condition;
wherein the migration policy comprises migrating at least one of the plurality of servers from a source enclosure to a target enclosure, thereby altering a usage status of at least one of the plurality of enclosures.
2. The method of claim 1, further comprising:
acquiring migration conditions of the plurality of servers, wherein the migration conditions are used for representing the same attribute category of the migratable servers;
determining a migration policy according to the migration target information and the constraint condition, including:
determining an initial migration strategy according to the migration target information and the constraint condition;
and adjusting the initial migration strategy by utilizing the migration condition.
3. The method according to claim 1 or 2, characterized in that the method further comprises:
acquiring starting states corresponding to the cabinets for placing the servers, migration cost information corresponding to the servers and super power consumption cost corresponding to the cabinets;
the determining migration target information and constraint conditions according to the plurality of first attribute information and the plurality of second attribute information includes:
determining the constraint condition according to the plurality of first attribute information and the plurality of second attribute information;
and determining migration target information according to the plurality of enabling states, the plurality of migration cost information, the plurality of first attribute information, the super power consumption cost corresponding to the plurality of cabinets and the constraint condition.
4. The method of claim 3, wherein the first attribute information includes an activation cost and a deactivation cost of the cabinet; the determining migration target information according to the plurality of enabling states, the plurality of migration cost information, the plurality of first attribute information, the super power consumption cost corresponding to the plurality of cabinets, and the constraint condition includes:
determining a minimum migration cost according to the plurality of enabling states, the plurality of migration cost information, the enabling cost, the disabling cost, the super power consumption cost and the constraint condition of the plurality of cabinets, and taking the minimum migration cost as the migration target information.
5. The method of claim 3, wherein the first attribute information includes a capacity of the cabinet; the second attribute information includes a capacity required by the server; the determining the constraint condition according to the plurality of first attribute information and the plurality of second attribute information further includes:
determining a capacity constraint condition according to the starting states, the capacities corresponding to the cabinets and the capacities required by the servers; the constraints include the capacity constraints; the capacity includes the number of placement bits and the number of ports.
6. The method of claim 3, wherein the first attribute information comprises a power consumption capacity of the cabinet; the second attribute information includes power consumption of the server; the determining the constraint condition according to the plurality of first attribute information and the plurality of second attribute information includes:
determining a power consumption constraint condition according to the power consumption capacities of the cabinets and the power consumption of the servers, wherein the constraint condition comprises the power consumption constraint condition; the power consumption capacity of the cabinet is determined based on a power consumption profile of a server placed in the cabinet; the power consumption of the server is determined based on the power consumption profile of the server.
7. The method of claim 1, further comprising:
determining a server migration logic constraint condition according to the number of servers placed in the cabinet after the migration of the servers, the number of servers placed in the cabinet before the migration of the servers, the number of servers migrated into the cabinet and the number of servers migrated out of the cabinet; the constraints include the server migration logic constraints.
8. The method of claim 1, further comprising:
determining a logical constraint condition of the number of servers according to the number of the servers placed in the cabinet after the migration of the servers, the number of the servers placed in the cabinet before the migration of the servers, the number of offline servers and the number of newly added servers; the constraint includes the number of servers logical constraint.
9. The method of claim 1, wherein the scope to be migrated comprises a plurality of groups to be migrated, the method further comprising:
determining a state constraint condition of the group to be migrated according to the starting states of the cabinets in the group to be migrated; the constraints include the state constraints.
10. The method of claim 1, further comprising:
when the constraint condition is a nonlinear constraint condition, carrying out linearization processing on the constraint condition to obtain a linear constraint condition;
the determining a migration policy according to the migration target information and the constraint condition includes:
and determining a migration strategy according to the migration target information and the linear constraint condition.
11. An electronic device, comprising a memory, a processor and a computer program stored on the memory, the processor implementing the method of any one of claims 1-10 when executing the computer program.
12. A computer-readable storage medium, in which a computer program is stored which, when being executed by a processor, carries out the method of any one of claims 1-10.
Priority Applications (1)
| Application Number | Priority Date | Filing Date | Title |
|---|---|---|---|
| CN202211400931.1A CN115660369A (en) | 2022-11-09 | 2022-11-09 | Server migration policy determination method, electronic device and storage medium |
Applications Claiming Priority (1)
| Application Number | Priority Date | Filing Date | Title |
|---|---|---|---|
| CN202211400931.1A CN115660369A (en) | 2022-11-09 | 2022-11-09 | Server migration policy determination method, electronic device and storage medium |
Publications (1)
| Publication Number | Publication Date |
|---|---|
| CN115660369A true CN115660369A (en) | 2023-01-31 |
Family
ID=85016088
Family Applications (1)
| Application Number | Title | Priority Date | Filing Date |
|---|---|---|---|
| CN202211400931.1A Pending CN115660369A (en) | 2022-11-09 | 2022-11-09 | Server migration policy determination method, electronic device and storage medium |
Country Status (1)
| Country | Link |
|---|---|
| CN (1) | CN115660369A (en) |
Cited By (1)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| CN116028232A (en) * | 2023-02-27 | 2023-04-28 | 浪潮电子信息产业股份有限公司 | Cross-cabinet server memory pooling method, device, equipment, server and medium |
-
2022
- 2022-11-09 CN CN202211400931.1A patent/CN115660369A/en active Pending
Cited By (1)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| CN116028232A (en) * | 2023-02-27 | 2023-04-28 | 浪潮电子信息产业股份有限公司 | Cross-cabinet server memory pooling method, device, equipment, server and medium |
Similar Documents
| Publication | Publication Date | Title |
|---|---|---|
| CN109714395B (en) | Cloud platform resource use prediction method and terminal equipment | |
| TWI475365B (en) | Hierarchical power smoothing | |
| Vafamehr et al. | Energy-aware cloud computing | |
| US20030126475A1 (en) | Method and apparatus to manage use of system power within a given specification | |
| CN111324471B (en) | Service adjustment method, device, equipment and storage medium | |
| CN103634401A (en) | Data copy storage method and terminal unit, and server unit | |
| CN107491870B (en) | Power planning method, device and equipment for power distribution network and computer readable storage medium | |
| CN115660369A (en) | Server migration policy determination method, electronic device and storage medium | |
| CN112612607A (en) | Data processing method, device, computer equipment and medium based on message queue | |
| CN104641355A (en) | Adaptive service timeouts | |
| CN106936882A (en) | A kind of electronic article transaction system | |
| CN112727743B (en) | Control method and device for multi-water pump system, control terminal and storage medium | |
| Moradi et al. | Multi‐objective transmission expansion planning with allocation of fixed series compensation under uncertainties | |
| CN112488544A (en) | Voltage sag compensation equipment configuration method and device and computer equipment | |
| CN109888847B (en) | Optimized operation method, device and system for multi-feed-in alternating current-direct current hybrid power grid | |
| CN111967682B (en) | Equipment on-shelf scheme optimizing method and device and terminal equipment | |
| US20220283951A1 (en) | Apparatus and method for intelligent memory page management | |
| CN106919450A (en) | resource adjusting method and device | |
| CN112084089B (en) | Method, device and equipment for determining upper limit of power consumption of data center node and storage medium | |
| CN112492008B (en) | Node position determination method and device, computer equipment and storage medium | |
| CN115033551A (en) | Database migration method and device, electronic equipment and storage medium | |
| Wang et al. | A sequential game perspective and optimization of the smart grid with distributed data centers | |
| CN103685359A (en) | Data processing method and device | |
| CN113961302A (en) | Resource allocation method, device, electronic equipment and storage medium | |
| CN108092910B (en) | Data traffic scheduling method and device |
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 |