Method for managing a distributed architecture of data centres, and corresponding device and computer program

Abstract

The invention relates to a method for managing a distributed architecture of data centres hosting a plurality of servers (11-13, 31-33) within which virtualisation nodes (NV11, NV12) are intended to be deployed. In such a method, an item of equipment (GI10) for managing the distributed architecture: - obtains data relating to a maintenance operation involving at least one first item of equipment (CPT1-CPT3) of an electricity distribution network supplying a first data centre (CET1-CET3) of the distributed architecture with power, the data comprising at least one maintenance duration of the first item of equipment, and transmits, to an entity (UD1) for the deployment of the virtualisation nodes within the distributed architecture, a first list comprising at least one identifier of at least one second item of equipment of the electricity distribution network supplying the first data centre with power, which item of equipment has a maintenance duration that is shorter than or equal to the autonomy duration of the first item of electrical equipment.

Description

Method for managing a distributed architecture of data centers, corresponding device and computer program Field of invention

[0001] The field of the invention is that of cloud computing.

[0002] More particularly, the present invention relates to the management and protection of computer servers hosted in data centers of a distributed architecture and within which virtualization nodes are intended to be deployed, in order to protect the virtualized functions instantiated on these virtualization nodes in the event of failure of one or more devices of an electricity distribution network supplying the data centers. Prior art and its drawbacks

[0003] For several years, telecommunications networks have been using virtualized functions instantiated on virtualization nodes hosted in virtual machines or in servers grouped into clusters, or "clusters" within data centers, giving rise to cloud computing. In the remainder of the document, reference is made to virtualization nodes hosted in servers, but it is understood that the teaching of this document also applies to the case of virtualization nodes hosted in virtual machines.

[0004] An example of managing the instantiation of virtualized functions is known as Kubernetes. A "Kubernetes" architecture comprises at least one cluster of virtualization nodes. Such a cluster of virtualization nodes comprises at least a first node called a management node, or "Kubernetes master node", and a plurality of computing nodes, or "Kubernetes worker nodes" intended to instantiate virtualized functions.

[0005] The management node includes, among other things, a database called ETCD which consists of a dynamic configuration register of the computing nodes.

[0006] A compute node comprises a plurality of virtualization units or "pods". Each virtualization unit is provided with resources allowing the execution of one or more tasks. A task, when executed, contributes to the implementation of a virtualized service or function.

[0007] The ETCD database embedded in the management node stores in reference files a list of virtualization units to be instantiated as well as parameters to be taken into account when instantiating the virtualized functions.

[0008] The management node regularly reads the contents of these files, compares them with the virtualization units being instantiated and adds or removes virtualization units in order to adapt their quantity to that indicated in these reference files.

[0009] Since the ETCD database is also accessible by a virtualization node deployment entity, the latter regularly reads the contents of these files, compares the capacity of the deployed virtualization nodes with the capacity required by the virtualization units being instantiated and adds or removes virtualization nodes in order to adapt their quantity to needs.

[0010] Deploying a virtualization node on a computer server involves, for example, downloading a file containing an operating system and a set of applications necessary for deploying the virtualization node to a computer server, then starting the computer server using the downloaded file.

[0011] It is also possible to deploy multiple virtualization nodes on a single computer server using virtual machines. In this case, once the file is uploaded to the computer server, a virtual machine is started using the uploaded file.

[0012] In an effort to reduce operating costs and improve the flexibility of network infrastructures, cloud computing architectures are most often distributed or multi-site architectures in which the servers hosting the virtualization nodes belonging to the same cluster of nodes can be located on separate and distant geographical sites.

[0013] Some virtualized functions requiring, for example, low latency tend to be executed by virtualization units deployed in servers located at the edge of communications networks, i.e., as close as possible to the user terminals requiring a given service, while virtualized functions requiring less latency but processing large volumes of data are instead instantiated in centralized data centers, generally of larger size. It is also worth mentioning the MEC initiative (Mobile Edge Computing) consisting of instantiating application functions at the edge of the network, these functions being able to be virtualized.

[0014] Instantiating virtualized functions in data centers, whether centralized or distributed, requires computing, storage, memory, communication, and energy resources. Similarly, the proper functioning of virtualized functions requires that these resources not fail due to a power outage.

[0015] While centralized data centers can be powered by several different power distribution networks, this is more difficult for distributed data centers, which due to their smaller size and geographical location may only be powered by a single power distribution network without redundancy.

[0016] To protect against power grid outages, data centers are equipped with an uninterruptible power supply (UPS) that may have sufficient capacity to allow time to migrate virtualized functions that cannot withstand interruptions to servers in an alternative data center that is not affected by a power grid outage.

[0017] This migration solution in response to a failure of the electrical distribution network, however, assumes that at least one alternative data center compatible with the low latency requirements of some of the virtualized functions to be migrated, is supplied with electricity for a sufficient duration and has free and operational servers.

[0018] In addition, during maintenance operations of a data center, all or part of the servers hosted in this data center may be rendered inoperable, independently of events that may occur on the electricity distribution network supplying the data center.

[0019] In order to ensure that the resources necessary for the protection of virtualized functions are reserved efficiently, it is known to implement multi-site protection schemes for virtualized functions, particularly when there is a risk of failure of the power supply of a data center.

[0020] To achieve this, it is proposed to reserve resources in virtualization nodes deployed in servers hosted in data centers supplied with electricity by separate electricity distribution networks.

[0021] Such a solution does not offer truly guaranteed protection because it does not take into account the occurrence of maintenance operations occurring in the electricity distribution network and its impact on the instantiation and protection of virtualized functions executed within servers hosted in data centers affected by these electricity distribution network maintenance operations.

[0022] The present invention aims to resolve all or part of the drawbacks mentioned above.

[0023] The invention meets this need by proposing a method for managing a distributed architecture of data centers hosting a plurality of servers within which at least one virtualization node is intended to be deployed.

[0024] Such a method is particular in that it is implemented by a management device of said distributed architecture and that it comprises the following steps: - obtaining data relating to a maintenance operation impacting at least a first device of an electricity distribution network supplying a first data center of said distributed architecture, said data comprising at least one maintenance duration of said first device, - when the maintenance duration of the first device is greater than or equal to an autonomy duration of at least a first electrical device locally supplying said first data center, transmission, to an entity for deploying the virtualization nodes within the distributed architecture,of a first list comprising at least one identifier of at least one second piece of equipment of the electricity distribution network supplying said first data center having a maintenance duration less than or equal to the autonomy duration of the first piece of electrical equipment.,

[0025] Such a method ensures that the occurrence of a maintenance operation in an electricity distribution network does not have a negative impact on the execution of critical virtualized functions.

[0026] More specifically, such a solution makes it possible to anticipate the deployment of virtualization nodes based on a maintenance program for electricity distribution network equipment supplying the different sites housing the data centers of the same distributed architecture. Thus, the virtualized functions executed by a virtualization node hosted in a server, or a virtual machine, impacted by particularly sensitive maintenance of the electricity distribution network can be either migrated or duplicated in advance to servers for which the power supply is guaranteed. The advance deployment of a virtualization node makes it possible to guarantee the reservation of resources.

[0027] In some cases, migrating a virtualized function has a significant impact on the quality of the required service. It is therefore preferable to trigger such a migration only when there is a failure of the equipment supplying power to the server.

[0028] In other cases, it is better to duplicate the virtualized function as soon as the second virtualization node is created and migrate the service client to the second virtualized function when the equipment powering the server fails.

[0029] Such a solution also allows for rational server management because, knowing the maintenance schedule that must take place on an electricity distribution network, it is possible to reserve only the necessary resources and for a duration adjusted to needs. This makes it possible to optimize the management of the different pools of servers belonging to the same distributed architecture and to avoid reserving resources unnecessarily or for excessively long periods within one or more servers.

[0030] The implementation of such a solution is based on the obtaining by a management equipment of a distributed architecture of information relating to maintenance operations impacting the electricity distribution networks supplying the different data centers of the same distributed architecture. Such management equipment centralizes information such as the identity and geographical location of the server(s) on which the virtualization nodes are deployed but also the needs in terms of computing, storage, memory, communication and energy resources, but also information relating to a duration of unavailability of certain equipment of the electricity distribution network supplying the servers of the data centers of the distributed architecture.

[0031] Armed with this various information, the management equipment is able to anticipate the deployment of virtualization nodes to which to migrate the execution of virtualized functions in anticipation of a power outage of the servers on which these virtualized functions are running in order to provide continuity of service.

[0032] Such a method may further comprise, when said first list is empty, the following steps: - receiving, from said deployment entity, a request for identification of at least one server hosted in a second data center of said distributed architecture powered by at least one third piece of equipment of the electricity distribution network separate from the first piece of equipment and the second piece of equipment, - transmitting, to said deployment entity, an identifier of said at least one server and a second list comprising at least one identifier of said at least one third piece of equipment having a maintenance duration less than or equal to an autonomy duration of said at least one second piece of electrical equipment locally powering said second data center.

[0033] When informed that no local electrical equipment is capable of providing the level of electrical energy required for the execution of certain virtualized functions, the deployment entity queries the management equipment in order to obtain information on other servers having the resources necessary for the deployment of a virtualization node for the execution of the virtualized functions to be migrated.

[0034] According to a particularity of the method which is the subject of the invention, the step of obtaining data relating to the maintenance operation impacting the first equipment consists of receiving a message sent by a control module of said first data center comprising at least one identifier of the first equipment and the duration of maintenance of said first equipment.

[0035] Such a data center control module is a device capable of communicating with devices in the electrical distribution network(s) supplying the data center that it controls. Thus, the control module collects information relating to the electricity distribution network, in particular information relating to maintenance operations, and transmits it to the management equipment.

[0036] In one example, the message transmitted by the control module further comprises an autonomy duration of said at least one first electrical equipment locally supplying said first data center.

[0037] The transmission of the message by the control module is triggered by the reception, from said deployment entity, of a request for information relating to said maintenance operation impacting said first equipment.

[0038] The virtualization node deployment entity may query the manager equipment on a regular basis or as needed, for example when reserving resources near a server, in anticipation of deploying virtualization nodes for execution of virtualized functions.

[0039] The message sent by the control module of said first data center is transmitted repeatedly over time.

[0040] Such a message can be issued periodically or each time a maintenance operation is scheduled.

[0041] The invention also relates to a method for protecting at least one first server within which at least one virtualization node is intended to be deployed, said first server being hosted in a first data center of a distributed architecture of data centers, said first data center being powered by at least one first equipment of an electricity distribution network impacted by a maintenance operation.

[0042] Such a method for protecting at least one first server is implemented by an entity for deploying virtualization nodes within said distributed architecture and is particular in that it comprises the following steps implemented when a maintenance duration of the first equipment is greater than or equal to an autonomy duration of said first electrical equipment: - reception, from a management equipment of said distributed architecture, of a first list comprising at least one identifier of at least one second equipment of the electricity distribution network supplying said first data center having a maintenance duration less than or equal to the autonomy duration of said first electrical equipment, - deployment of said at least one virtualization node within said first server.

[0043] When deploying a virtualization node, the deployment entity can mark it with a label containing the identifiers of the electricity distribution network equipment contained in the list provided by the manager so that it is taken into account when executing the virtualized functions.

[0044] The method for protecting at least one first server may further comprise, when said first list is empty, the following steps: - sending, to said management equipment, a request for identification of at least one second server hosted in a second data center of said distributed architecture powered by at least one third piece of equipment of the electricity distribution network separate from the first piece of equipment and the second piece of equipment, - receiving, from said management equipment, an identifier of said second server and a second list comprising at least one identifier of said at least one third piece of equipment having a maintenance duration less than or equal to an autonomy duration of at least one second piece of electrical equipment locally powering said second data center.

[0045] By reserving the necessary resources on a second server independent of ongoing maintenance operations on the electricity distribution network, the virtualization node deployment entity can deploy a new virtualization node to ensure the migration of virtualized functions if a failure actually occurs during maintenance of the electricity distribution network on which the first server depends.

[0046] As with the first virtualization node, the deployment entity can mark the new virtualization node with a label containing electricity distribution network equipment identifiers different from the label of the first virtualization node. In this way, the virtualized functions can be duplicated if necessary on two virtualization nodes that do not depend on the same electricity distribution network equipment.

[0047] Another subject of the invention relates to a management equipment of a distributed architecture of data centers hosting a plurality of servers within which at least one virtualization node is intended to be deployed, said management equipment comprising at least one processor configured to:- obtain data relating to a maintenance operation impacting at least one first equipment of an electricity distribution network supplying a first data center of said distributed architecture, said data comprising at least one maintenance duration of said first equipment,- when the maintenance duration of the first equipment is greater than or equal to an autonomy duration of at least one first electrical equipment locally supplying said first data center, transmit, to a deployment entity of the virtualization nodes within the distributed architecture,a first list comprising at least one identifier of at least one second piece of equipment of the electricity distribution network supplying said first data center having a maintenance duration less than or equal to the autonomy duration of the first piece of electrical equipment.,

[0048] The invention also relates to an entity for deploying virtualization nodes within a distributed architecture, said deployment entity being capable of protecting at least one first server within which at least one virtualization node is intended to be deployed, said first server being hosted in a first data center of the distributed architecture of data centers, said first data center being powered by at least one first piece of equipment of an electricity distribution network impacted by a maintenance operation, said deployment entity comprising at least one processor configured to: - receive, from a piece of equipment managing said distributed architecture,a first list comprising at least one identifier of at least one second piece of equipment of the electricity distribution network supplying said first data center having a maintenance duration less than or equal to the autonomy duration of said first electrical equipment, when a maintenance duration of the first piece of equipment is greater than or equal to an autonomy duration of said first electrical equipment, - deploy said at least one virtualization node within said first server.,

[0049] The invention finally relates to computer program products comprising program code instructions for implementing the methods as described above, when executed by a processor.

[0050] The invention also relates to a computer-readable recording medium on which computer programs are recorded comprising program code instructions for executing the steps of the methods according to the invention as described above.

[0051] Such a recording medium may be any entity or device capable of storing programs. For example, the medium may include a storage medium, such as a ROM, for example a CD ROM or a microelectronic circuit ROM, or a magnetic recording medium, for example a USB key or a hard disk.

[0052] On the other hand, such a recording medium may be a transmissible medium such as an electrical or optical signal, which may be conveyed via an electrical or optical cable, by radio or by other means, so that the computer programs contained therein are remotely executable. The programs according to the invention may in particular be downloaded over a network, for example the Internet.

[0053] Alternatively, the recording medium may be an integrated circuit in which the programs are incorporated, the circuit being adapted to execute or to be used in the execution of the aforementioned methods which are the subject of the invention. List of figures

[0054] Other aims, characteristics and advantages of the invention will appear more clearly on reading the following description, given as a simple illustrative, and non-limiting, example, in relation to the figures, among which:

[0055] : this figure represents a system in which the invention is implemented,

[0056] : this figure represents the different steps implemented by the different components of the system described with reference to the implementation of the different methods which are the subject of the present invention.

[0057] Detailed description of embodiments of the invention

[0058] The general principle of the invention is based on the anticipation of the deployment of virtualization nodes within servers hosted in data centers according to a maintenance program for electricity distribution network equipment supplying the different sites housing the data centers of the same distributed architecture. Thus, the virtualized functions executed by a virtualization node hosted in a server impacted by particularly sensitive maintenance of the electricity distribution network can be either migrated or duplicated in advance to servers for which the power supply is guaranteed. The advance deployment of a virtualization node makes it possible to guarantee the reservation of resources.

[0059] The implementation of such a solution is based on the obtaining by a management equipment of a distributed architecture of information relating to maintenance operations impacting the electricity distribution networks supplying the different data centers of the same distributed architecture. Such management equipment centralizes information such as the identity and geographical location of the server(s) on which the virtualization nodes are deployed but also the needs in terms of computing, storage, memory, communication and energy resources, but also information relating to a duration of unavailability of certain equipment of the electricity distribution network supplying the servers of the data centers of the distributed architecture.

[0060] Armed with this various information, the management equipment is then able to anticipate the deployment of virtualization nodes to which to migrate the execution of virtualized functions in anticipation of a power outage of the servers on which these virtualized functions are running in order to provide continuity of service.

[0061] In the remainder of the description, an embodiment of the invention is presented implemented in a system such as that shown in.

[0062] Such a system includes on the one hand an electricity distribution network RDE and a distributed architecture of data centers AD.

[0063] The electricity distribution network RDE comprises several source substations PS1, PS3 ensuring the transformation of high voltage electricity HV into medium voltage electricity MV. Such source substations PS1, PS3 are controlled by source substation controllers (not shown in the figure). The electricity distribution network RDE also comprises a plurality of transformer substations PT1, PT2, PT3 ensuring the transformation of medium voltage electricity MV into low voltage electricity LV intended to supply neighboring distribution networks NAN1, NAN2 and NAN3.

[0064] The transformer stations PT1, PT2, PT3 are controlled by transformer station controllers CPT1, CPT2 (not shown on the) and CPT3. The electricity distribution network RDE further comprises signaling routing units (not shown on the) allowing the routing of signaling messages between portions of the electricity distribution network RDE having different voltages, and smart metering units SM1, SM2 (not shown on the) SM3, ensuring the demarcation between the electricity distribution network RDE and the distributed architecture AD supplied with electricity by the electricity distribution network RDE.

[0065] The distributed AD architecture includes multiple data centers DC1, DC3 (not shown in the figure), with each data center DC1, DC3 located in availability zones ZD1, ZD3 that may or may not be co-located. The data center DC1 comprises a plurality of computer servers 11, 12, 13 within which virtualization nodes NV11, NV12 can be deployed, as well as at least one so-called "uninterruptible" electrical equipment UPS1 powering the computer servers 11, 12, 13. The data center DC2 also comprises a plurality of computer servers 31, 32, 33 within which virtualization nodes NV11, NV12 can be deployed, as well as at least one so-called "uninterruptible" electrical equipment UPS3 powering the computer servers 31, 32, 33. The virtualization nodes NV11 and NV12 respectively comprise a virtualization unit UV11 and UV12.Of course, a server 11, 12, 13, 31, 32, 33 can simultaneously deploy several virtualization nodes and a single virtualization node can comprise a plurality of virtualization units.

[0066] The electrical equipment UPS1 and UPS3 are respectively controlled by a technical environment controller CET1 and by a technical environment controller CET3. Such technical environment controllers CET1, CET3 exchange service messages with the transformer substation controllers CPT1, CPT2, CPT3 of the RDE electricity distribution network. The technical environment controllers CET1, CET3 also exchange service messages with an infrastructure manager GI10 in charge of allocating and administering the computer servers 11, 12, 13, 31, 32, 33.

[0067] Finally, the distributed architecture AD comprises at least one deployment unit UD1, responsible for deploying the virtualization nodes NV11, NV12 within the computer servers 11, 12, 13, 31, 32, 33. In order to ensure the deployment of the virtualization nodes NV11, NV12, the deployment unit UD1 exchanges service messages with the infrastructure manager GI10.

[0068] In relation to the, we represent the different steps implemented by the different components of the system described with reference to the during the implementation of the different methods which are the subject of the present invention.

[0069] The context of implementation of the methods which are the subject of the present invention is that of a scheduled maintenance operation of the transformer station controller CPT1 which prohibits any remote intervention on the transformer station PT1 for the duration of the maintenance.

[0070] In the implementation example considered, no virtualization node is deployed in the computer servers 31, 32, 33 of the data center DC3 and a maintenance operation of the computer servers 31, 32 of the data center DC3 is in progress, prohibiting their use for several hours.

[0071] During maintenance of the CPT1 transformer station controller, a fault affects the PT1 transformer station and consequently interrupts the distribution of electricity to the UPS1 electrical equipment.

[0072] This interruption of the electricity supply is detected by the technical environment controller CET1 in a step E0.

[0073] In a first implementation, the transformer station controller CPT1 sends a message to the technical environment controller CET1 using techniques known as power line communication or PLC for "Power Line Communication". This message includes in particular an estimated maintenance duration MTTR1 of the transformer station PT1 as well as an identifier of the transformer station PT1, noted IDPT1.

[0074] In a second implementation, this message is relayed by the smart metering device SM1 to the technical environment controller CET1. In this implementation, the message can be transmitted using power lines to the electrical equipment UPS1, or through a direct interface, such as an Ethernet interface directly connected to the technical environment controller CET1.

[0075] Following the obtaining of this information relating to the maintenance of the technical environment controller CET1, the technical environment controller CET1 generates and transmits, during a step E1, a message MSG1 to the infrastructure manager GI10. Such a message MSG1 may comprise, among other things, an estimated maintenance duration MTTR1 of the transformer station PT1 as well as an identifier of the transformer station PT1, noted IDPT1. Such a message MSG1 further comprises an estimated autonomy duration MTBF1 of the electrical equipment UPS1. The message MSG1 may also comprise an identifier of the electrical equipment UPS1 as well as information relating to the availability zone ZD1 associated with the data center DC1.

[0076] Upon receipt of the message MSG1, the infrastructure manager GI10 updates, in a step E2, a first reference file stored in one of its memories. This first file indicates that the computer servers 11, 12, 13 hosted in the data center DC1 corresponding to the availability zone ZD1 are dependent, for their power supply, on the transformer station PT1 identified IDPT1. The first file also indicates the estimated maintenance duration MTTR1 of the transformer station PT1.

[0077] The infrastructure manager GI10 also stores in the first reference file that the electrical equipment UPS1 on which the computer servers 11, 12, 13 depend has an estimated autonomy duration MTBF1 during which the electrical equipment UPS1 is capable of electrically supplying the computer servers 11, 12, 13.

[0078] During a step E3, the deployment unit UD1 of the virtualization node NV11 transmits a request for DI information relating to a maintenance operation to the infrastructure manager GI10.

[0079] In a particular implementation, the DI information request includes an identifier of the computer server 11 as well as a request to obtain the estimated autonomy time of the electrical equipment UPS1.

[0080] In another implementation, the information request DI also includes a request to obtain the IDPT identifiers of transformer stations PT on which the computer server 11 depends and whose estimated maintenance durations MTTR are less than the autonomy duration of the electrical equipment UPS1.

[0081] Step E3 may, for example, be implemented periodically or each time the deployment unit UD1 is about to deploy one or more NV virtualization nodes.

[0082] In response to the information request DI, the management equipment GI10 identifies in the first reference file the IDPT identifier(s) of transformer stations PT on which the computer server 11 depends and whose estimated maintenance durations MTTR are less than the autonomy duration of the electrical equipment UPS1, during a step E4.

[0083] When the management equipment GI10 has identified at least one transformer station PT on which the computer server 11 depends and whose estimated maintenance duration MTTR is less than the autonomy duration of the electrical equipment UPS1, it transmits, to the deployment entity UD1, a first list L1 comprising the identifier of this transformer station PT in a step E5.

[0084] When the GI10 management equipment has not identified any PT transformer station whose estimated maintenance duration MTTR is less than the autonomy duration of the UPS1 electrical equipment, the first list L1 that it transmits to the UD1 deployment entity is an empty list.

[0085] Upon receipt of an empty list L1, the deployment unit UD1 sends, in a step E6, a request for identification RQT of at least one server hosted in a data center DC powered by a transformer station separate from that or those powering the data center DC1. Such a request RQT notably includes the estimated autonomy duration MTBF1 of the transformer station PT1. The request RQT may also include information relating to the computing, storage, memory, and communication resources required by the various virtualized functions executed by the virtualization node NV11 deployed on the computer server 11.

[0086] In response to receiving the RQT request, the management equipment GI10 transmits an identifier of at least one server 33 hosted in the second data center DC3 associated with the availability zone ZD3 as well as a second list L2 to the deployment unit UD1 in a step E7. This second list L2 comprises at least one identifier IDPT of at least one transformer station PT distinct from the transformer station PT1 having a maintenance duration MTTR less than or equal to an estimated autonomy duration MTBF of at least one electrical equipment UPS3 locally supplying the data center DC3. When the management equipment GI10 has received information relating to the required computing, storage, memory, and communication resources, it uses them to identify one or more computer servers having such resources.

[0087] Upon receipt of list L2, the deployment unit UD1 has all the information enabling it to deploy the virtualization node NV12 within the server 33 identified in list L2, in a step E8.

[0088] Thus, the virtualized functions executed by the NV11 virtualization node hosted in the server 11 impacted by maintenance of the RDE electricity distribution network can be either migrated or duplicated in advance to the NV12 virtualization node deployed for the occasion on the server 33.

[0089] Optionally, when the deployment unit UD1 deploys the virtualization node UV12 on the server 33, it proceeds to mark it using an availability zone label LBLZD3 comprising the IDPT identifiers of the transformer stations PT on which the computer server 33 depends for its electricity supply and whose maintenance durations MTTR are less than the autonomy duration of the electrical equipment UPS3 locally supplying the computer server 33.

[0090] Such LBLZD labels facilitate the deployment of UV virtualization units. Indeed, when migrating or duplicating a virtualized function whose description file contains a request to create at least two UV11 and UV12 virtualization units as well as an anti-affinity rule indicating that each UV11 and UV12 virtualization unit must be deployed in virtualization nodes hosted in IT servers located in different deployment zones, the existence of these LBLZD labels associated with each server belonging to the AD distributed architecture makes it possible to quickly and definitely identify the appropriate IT server(s).Thus, the virtualization unit UV12 is created in the virtualization node NV12 deployed on the second availability zone ZD3 independent of any failure of the transformer station PT1, which is not the case of the virtualization node NV11, which although supplied with electricity by the electrical equipment UPS1, is impacted by this failure of the transformer station PT1 since the autonomy duration of the electrical equipment UPS1 is less than the maintenance duration MTTR1 of the transformer station PT1.

[0091] In this way, the risk that the two virtualization nodes NV11 and NV12, each hosting a virtualization unit UV11, UV12 involved in the execution of the virtualized function, fail at the same time is reduced, thus providing increased availability of the service provided by the virtualized function.

[0092] When the CPT1 controller is put back into service at the end of the maintenance period, the transformer station controller CPT1 sends a new message to the technical environment controller CET1. This new message includes a new estimated maintenance duration MTTR1' of the transformer station. When the new estimated maintenance duration MTTR1' is less than or equal to the autonomy duration MTBF1, the deployment unit UD1 proceeds to delete the virtualization node NV12. The server 33 thus freed, manager GI10 can then carry out maintenance on the latter.

Claims

Method for managing a distributed architecture of data centers hosting a plurality of servers within which at least one virtualization node is intended to be deployed, said method being implemented by a management device of said distributed architecture and comprising the following steps: - obtaining data relating to a maintenance operation impacting at least one first device of an electricity distribution network supplying a first data center of said distributed architecture, said data comprising at least one maintenance duration of said first device, - when the maintenance duration of the first device is greater than or equal to an autonomy duration of at least one first electrical device locally supplying said first data center, transmission, intended for an entity for deploying virtualization nodes within the distributed architecture,of a first list comprising at least one identifier of at least one second piece of equipment of the electricity distribution network supplying said first data center having a maintenance duration less than or equal to the autonomy duration of the first piece of electrical equipment., Method for managing a distributed architecture of data centers according to claim 1 further comprising, when said first list is empty, the following steps: - reception, from said deployment entity, of a request for identification of at least one server hosted in a second data center of said distributed architecture powered by at least one third piece of equipment of the electricity distribution network separate from the first piece of equipment and the second piece of equipment, - transmission, to said deployment entity, of an identifier of said at least one server and a second list comprising at least one identifier of said at least one third piece of equipment having a maintenance duration less than or equal to an autonomy duration of said at least one second piece of electrical equipment locally powering said second data center. Method for managing a distributed data center architecture according to claim 1 or 2 wherein the step of obtaining data relating to the maintenance operation impacting the first equipment consists of receiving a message sent by a control module of said first data center comprising at least one identifier of the first equipment and the duration of maintenance of said first equipment. Method for managing a distributed data center architecture according to claim 3 wherein said message further comprises a duration of autonomy of said at least one first electrical equipment locally supplying said first data center. Method for managing a distributed data center architecture according to any one of the preceding claims, in which said transmission step is triggered by the reception, from said deployment entity, of a request for information relating to said maintenance operation impacting said first equipment. Method for managing a distributed architecture of data centers according to claims 3 to 5 wherein said message transmitted by the control module of said first data center is transmitted repeatedly over time. Method for protecting at least one first server within which at least one virtualization node is intended to be deployed, said first server being hosted in a first data center of a distributed architecture of data centers, said first data center being powered by at least one first piece of equipment of an electricity distribution network impacted by a maintenance operation, said method being implemented by an entity for deploying the virtualization nodes within said distributed architecture and comprising the following steps implemented when a maintenance duration of the first piece of equipment is greater than or equal to an autonomy duration of said first piece of electrical equipment: - reception, from a management equipment of said distributed architecture,of a first list comprising at least one identifier of at least one second piece of equipment of the electricity distribution network supplying said first data center having a maintenance duration less than or equal to the autonomy duration of said first electrical equipment, - deployment of said at least one virtualization node within said first server., Method for protecting at least one first server according to claim 7 further comprising, when said first list is empty, the following steps: - sending, to said management equipment, a request for identification of at least one second server hosted in a second data center of said distributed architecture powered by at least one third piece of equipment of the electricity distribution network separate from the first piece of equipment and the second piece of equipment, - receiving, from said management equipment, an identifier of said second server and a second list comprising at least one identifier of said at least one third piece of equipment having a maintenance duration less than or equal to an autonomy duration of at least one second piece of electrical equipment locally powering said second data center. Management equipment of a distributed architecture of data centers hosting a plurality of servers within which at least one virtualization node is intended to be deployed, said management equipment comprising at least one processor configured to:- obtain data relating to a maintenance operation impacting at least one first equipment of an electricity distribution network supplying a first data center of said distributed architecture, said data comprising at least one maintenance duration of said first equipment,- when the maintenance duration of the first equipment is greater than or equal to an autonomy duration of at least one first electrical equipment locally supplying said first data center, transmit, to a deployment entity of the virtualization nodes within the distributed architecture,a first list comprising at least one identifier of at least one second piece of equipment of the electricity distribution network supplying said first data center having a maintenance duration less than or equal to the autonomy duration of the first piece of electrical equipment., Entity for deploying virtualization nodes within a distributed architecture, said deployment entity being capable of protecting at least a first server within which at least one virtualization node is intended to be deployed, said first server being hosted in a first data center of the distributed architecture of data centers, said first data center being powered by at least a first piece of equipment of an electricity distribution network impacted by a maintenance operation, said deployment entity comprising at least one processor configured to: - receive, from a management equipment of said distributed architecture, a first list comprising at least one identifier of at least a second piece of equipment of the electricity distribution network supplying said first data center having a maintenance duration less than or equal to the autonomy duration of said first piece of electrical equipment,when a maintenance duration of the first equipment is greater than or equal to an autonomy duration of said first electrical equipment, - deploy said at least one virtualization node within said first server., Computer program product comprising program code instructions for implementing a method for managing a distributed data center architecture according to claims 1 to 6, when executed by a processor. Computer program product comprising program code instructions for implementing a method for protecting at least a first server according to claim 7 to 8, when executed by a processor.

Images