EP2559195A1 - Outil pour la gestion de ressources et d'infrastructures informatiques et de reseaux - Google Patents
Outil pour la gestion de ressources et d'infrastructures informatiques et de reseauxInfo
- Publication number
- EP2559195A1 EP2559195A1 EP11720150A EP11720150A EP2559195A1 EP 2559195 A1 EP2559195 A1 EP 2559195A1 EP 11720150 A EP11720150 A EP 11720150A EP 11720150 A EP11720150 A EP 11720150A EP 2559195 A1 EP2559195 A1 EP 2559195A1
- Authority
- EP
- European Patent Office
- Prior art keywords
- resource
- tool
- resources
- capacity
- infrastructure
- 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.)
- Withdrawn
Links
Classifications
-
- H—ELECTRICITY
- H04—ELECTRIC COMMUNICATION TECHNIQUE
- H04L—TRANSMISSION OF DIGITAL INFORMATION, e.g. TELEGRAPHIC COMMUNICATION
- H04L41/00—Arrangements for maintenance, administration or management of data switching networks, e.g. of packet switching networks
- H04L41/08—Configuration management of networks or network elements
- H04L41/0896—Bandwidth or capacity management, i.e. automatically increasing or decreasing capacities
-
- H—ELECTRICITY
- H04—ELECTRIC COMMUNICATION TECHNIQUE
- H04L—TRANSMISSION OF DIGITAL INFORMATION, e.g. TELEGRAPHIC COMMUNICATION
- H04L47/00—Traffic control in data switching networks
- H04L47/70—Admission control; Resource allocation
- H04L47/78—Architectures of resource allocation
- H04L47/781—Centralised allocation of resources
-
- H—ELECTRICITY
- H04—ELECTRIC COMMUNICATION TECHNIQUE
- H04L—TRANSMISSION OF DIGITAL INFORMATION, e.g. TELEGRAPHIC COMMUNICATION
- H04L41/00—Arrangements for maintenance, administration or management of data switching networks, e.g. of packet switching networks
- H04L41/08—Configuration management of networks or network elements
- H04L41/0893—Assignment of logical groups to network elements
-
- H—ELECTRICITY
- H04—ELECTRIC COMMUNICATION TECHNIQUE
- H04L—TRANSMISSION OF DIGITAL INFORMATION, e.g. TELEGRAPHIC COMMUNICATION
- H04L41/00—Arrangements for maintenance, administration or management of data switching networks, e.g. of packet switching networks
- H04L41/12—Discovery or management of network topologies
-
- H—ELECTRICITY
- H04—ELECTRIC COMMUNICATION TECHNIQUE
- H04L—TRANSMISSION OF DIGITAL INFORMATION, e.g. TELEGRAPHIC COMMUNICATION
- H04L47/00—Traffic control in data switching networks
- H04L47/70—Admission control; Resource allocation
- H04L47/80—Actions related to the user profile or the type of traffic
- H04L47/808—User-type aware
-
- H—ELECTRICITY
- H04—ELECTRIC COMMUNICATION TECHNIQUE
- H04L—TRANSMISSION OF DIGITAL INFORMATION, e.g. TELEGRAPHIC COMMUNICATION
- H04L47/00—Traffic control in data switching networks
- H04L47/70—Admission control; Resource allocation
- H04L47/82—Miscellaneous aspects
- H04L47/826—Involving periods of time
-
- H—ELECTRICITY
- H04—ELECTRIC COMMUNICATION TECHNIQUE
- H04L—TRANSMISSION OF DIGITAL INFORMATION, e.g. TELEGRAPHIC COMMUNICATION
- H04L67/00—Network arrangements or protocols for supporting network services or applications
- H04L67/01—Protocols
- H04L67/10—Protocols in which an application is distributed across nodes in the network
-
- H—ELECTRICITY
- H04—ELECTRIC COMMUNICATION TECHNIQUE
- H04W—WIRELESS COMMUNICATION NETWORKS
- H04W4/00—Services specially adapted for wireless communication networks; Facilities therefor
- H04W4/02—Services making use of location information
- H04W4/025—Services making use of location information using location based information parameters
-
- H—ELECTRICITY
- H04—ELECTRIC COMMUNICATION TECHNIQUE
- H04L—TRANSMISSION OF DIGITAL INFORMATION, e.g. TELEGRAPHIC COMMUNICATION
- H04L41/00—Arrangements for maintenance, administration or management of data switching networks, e.g. of packet switching networks
- H04L41/08—Configuration management of networks or network elements
- H04L41/0895—Configuration of virtualised networks or elements, e.g. virtualised network function or OpenFlow elements
-
- H—ELECTRICITY
- H04—ELECTRIC COMMUNICATION TECHNIQUE
- H04L—TRANSMISSION OF DIGITAL INFORMATION, e.g. TELEGRAPHIC COMMUNICATION
- H04L41/00—Arrangements for maintenance, administration or management of data switching networks, e.g. of packet switching networks
- H04L41/12—Discovery or management of network topologies
- H04L41/122—Discovery or management of network topologies of virtualised topologies, e.g. software-defined networks [SDN] or network function virtualisation [NFV]
-
- H—ELECTRICITY
- H04—ELECTRIC COMMUNICATION TECHNIQUE
- H04L—TRANSMISSION OF DIGITAL INFORMATION, e.g. TELEGRAPHIC COMMUNICATION
- H04L41/00—Arrangements for maintenance, administration or management of data switching networks, e.g. of packet switching networks
- H04L41/40—Arrangements for maintenance, administration or management of data switching networks, e.g. of packet switching networks using virtualisation of network functions or resources, e.g. SDN or NFV entities
-
- H—ELECTRICITY
- H04—ELECTRIC COMMUNICATION TECHNIQUE
- H04L—TRANSMISSION OF DIGITAL INFORMATION, e.g. TELEGRAPHIC COMMUNICATION
- H04L47/00—Traffic control in data switching networks
- H04L47/70—Admission control; Resource allocation
- H04L47/82—Miscellaneous aspects
- H04L47/822—Collecting or measuring resource availability data
Definitions
- the invention relates to networks and computer equipment for transmitting and / or processing digital information.
- the invention relates to extended networks exploited using the "EP" protocol (for "Internet Protocol” or “Internet protocol” in French).
- Networks and computer systems are designed and operated in a very different way from one another.
- Computer networks are usually shared simply, that is to say without any particular contract, or offer of guarantee, performance including computing or storage systems, and more generally so-called "end” systems, as for they remain private and physically isolated, at least as far as their own function is concerned.
- WANs primarily use the transmission of information in the form of packets formatted and routed according to the internet protocol.
- the service offered by the Internet protocol is of the type known as "best effort", or “we do our best” in French.
- the Internet protocol provides the best delivery of information (or “best effort delivery” in English), given the communication resources, particularly links and gateways, and computer resources available in the network.
- Some WAN applications require time and / or data arrival rate guarantees.
- the information is transmitted in the form of a signal sampled at a fixed frequency, and this signal must be reconstructed and returned to the receiver at this same frequency.
- these applications may accommodate to some extent variations in delay and / or routing speed, they nevertheless require a bounded routing delay (of the same order of magnitude as the sampling period of the transmitted signal) and a minimum routing rate for the receiver to benefit from the quality and the fluidity of the transmission.
- the information as broadcast (emitted).
- the transmission capacity can be dedicated to the virtual private network.
- the capacity thus mobilized for the virtual private network is generally greater than its real needs: the intrinsic capacities of the private network link, in particular its bandwidth, may be greater than the needs, and / or there are periods of time during which link virtual private is not used.
- the total transmission capacity of the WAN including its time dimension, is misused.
- the invention improves the situation in this respect by proposing a tool for assisting the operation of a network of communicating equipment each having transmission, storage and / or digital information processing capabilities, comprising:
- a resource manager associated with a resource situation data storage arranged according to a data structure in which an identifier is related to dated values of quantitative quantities; the resource manager being arranged to register at least some of the network equipment as resources in the situation data storage, with:
- a resource selector including:
- a first selection tool adapted to return a set of selected resource identifiers in the data storage according to functional identification data
- a planning tool adapted to evaluate an acceptance condition based on date comparison expressions that relate to a dated functional capacity! and the dated transmission capacity, storage and / or processing capacity continuations maintained relationship of one or more resource identifiers;
- a resource allocator arranged to receive an identified request for temporary functional capacity reservation, including a dated set of functional data, and to respond to it by:
- the data structure relates each resource identifier to geographic location data values
- the resource selector includes a second selection tool adapted to return a subset of selected resource identifiers in the data storage. according to geographical location data taken from the reservation request.
- the resource selector is arranged to respond to the reservation request by calling the second selection tool and then calling the first selection tool with the resource identifiers returned by the second selection tool.
- the data structure relates each resource identifier to non-functional resource attribute values, and the resource selector includes a third selection tool adapted to return a subset of selected resource identifiers in the storage. data according to non-functional attribute data derived from the query.
- the resource selector is arranged to respond to the reservation request by calling the third selection tool for a set of resource identifiers returned by the first selection tool.
- the resource manager is associated with a data storage link, arranged according to a data structure in which a link identifier is related to a datum of origin and datum of: destination of said link, and the datum manager; resources is adapted to record at least some of the network equipment forming a communication link with:
- link identifier a first resource identifier corresponding to the equipment in question in the situation data storage
- a second resource identifier corresponding to one of the equipment directly connected by the equipment in question to the situation data storage
- a third resource identifier corresponding to one of the other equipment directly connected by the equipment in question in the situation data storage.
- the resource selector includes a fourth selection tool adapted to receive a subset of resource identifiers and to return: on the one hand, only those received identifiers which are maintained in the binding data storage as the second or third resource identifier in relation to the first resource identifier,
- the resource selector is arranged to respond to the reservation request by calling the fourth selection tool for a set of resource identifiers returned by the first selection tool.
- the resource selector is arranged to respond to the reservation request by calling the fourth selection tool for a set of resource identifiers returned by the third selection tool.
- the resource selector is arranged to respond to the reservation request by invoking the fourth selection tool for a set of resource identifiers returned by the Resource Allocation Tool.
- FIG. 3 represents two nodes of an information manipulation infrastructure
- FIG. 4 represents the infrastructure of FIG. 2, modified according to one aspect of the invention
- FIG. 5A physically represents a set of information manipulation infrastructures, completed according to another aspect of the invention.
- FIG. 5B represents part of the infrastructure of FIG. 5A in virtualized form
- FIGS. 6A to 6E show information handling equipment used in the infrastructures of FIGS. 4, 5A or 5B for example;
- FIG. 7 represents a capacitive profile of a resource, of manipulation of information
- FIG. 8 is similar to FIG. 7 for another information manipulation resource
- FIG. 9 represents a functional diagram for part of the infrastructure manager of FIG. 4;
- FIG. 11 is a graph illustrating a profile of a resource of the infrastructure of FIG. 4 and a series of corresponding temporal events
- FIG. 12 is a flowchart illustrating the reservation processing of FIG. 9;
- Fig. 13 is a flow chart detailing operation 96 ⁇ of Fig. 12;
- Fig. 14 is a flow chart detailing operation 970 of Fig. 12;
- FIG. 15 is a flowchart illustrating the operation of a time series within an infrastructure resource of FIG. 4;
- FIG. 16 is a flowchart illustrating the operation of a virtual infrastructure manager
- FIG. 17 illustrates a request evaluation device
- FIG. 18 is a flowchart illustrating a function of a tool of the device of FIG. 17;
- FIG. 19 is a flowchart illustrating another function of the tool of FIG. 18;
- FIG. 20 is a flowchart illustrating the operation of another tool of the device of FIG. 1;
- FIGS. 21, 22 and 23 are flowcharts respectively illustrating different functions of yet another tool of the device of FIG. 17;
- FIGS. 24 to 27 are flow charts respectively illustrating functions of another tool still of the device of FIG. 17;
- FIG. 28 is a diagram of a conceptual data model for the tool of the invention.
- FIG. 29 is a diagram illustrating the initialization of the tool according to the invention.
- Appendix 2 defines a set of function for use in the invention.
- This document may contain elements that may be protected by copyright or copyright.
- the rights owner has no objection to the identical reproduction by anyone of this patent document as it appears in the files and / or publications of the patent offices. On the other hand, it reserves for the remainder the entirety of its copyrights and / or copyright.
- FIG. 1 shows three computers 100, 102 and 103, also denoted “COMP0", “CO P2” and “CO P3", interconnected via a router 101, also denoted "ROUT1".
- the computer COMP0 100 is interconnected with the router ROUT1 101 by a bidirectional link, the directions of which are decomposed into a forward link 111, from COMP0 to ROUT1, and a reverse link 1 12, from ROUT1 to COMP0.
- the router ROUT1 101 is interconnected with the computer COMP2 102 by a forward link 121, from ROUT1 to COMP2, and a return link 122, from CO P2 to ROUT1.
- the outbound and / or return links may be, at least in part, Internet links.
- Figure 1 is presented as a reduced system, in which the invention can begin to manifest itself. It is clear that an extended network will include many more resources. But they will remain, at least in part, treated as described in Figure 1.
- a node can be a computer, a router, a switch, a storage system, a modem or a visualization system, a data acquisition system or a sub-network of sensors.
- network links generally bidirectional, as seen above.
- Figure 2 schematically shows a simple example of what is now called an "extended physical infrastructure".
- This physical infrastructure hereinafter PI 200 infrastructure, shows a node 201, designated 1, interconnected to a node 202, designated N2, via a forward link 2012, designated L12, er of a link back 2021, designated L21.
- the node N2 202 is itself interconnected to a node 204, designated N4, via a forward link 2024, referenced L24, and a link back 2042, referenced L42.
- nodes N4204 are also interconnected nodes designated N3203, N5205, N6206 and N7207, respectively via links L342034, L542054, L642064, L74 2074 and return links L43 2043, L45 2045, L46 2046, L47 2047.
- the set of Ni nodes and Li links that connect them together constitute the infrastructure Pi 200.
- This infrastructure PI 200 is delimited by a thick dashed frame in Figure 2.
- the nodes are mostly computers.
- the node N4 can be a computer, a router or a server.
- a node N1 corresponds to a physical unit PI 200 (a computer or a router for example), the links being mainly network links, including Internet links, if any.
- a node and its links depends on the fineness of the decomposition of the physical infrastructure: in a finer representation, a node could consist of a functional unit of a computer (disk, processing unit ), while, in a coarser representation, a node could be a subnetwork, for example.
- the fineness of the decomposition can be different according to the nodes of the infrastructure: a particular node can consist of the whole of a sub-network whereas a different node of the same infrastructure can be only consisting of a personal computer from another subnet.
- Figure 3 is a generic and simplified example of the variety of devices that may constitute a node. This figure 3 shows an NI node 310 interconnected with an N2320 node.
- the NI node 310 may comprise a display device or DISP device 311, and / or a storage disk, or DSK disk 312, with its controller, and / or a central processing unit, or CPU 313.
- the N2 node 320 may include an MD 321 modem, and / or an S W 322 switch, which may also be a router.
- the resources included in a node are at least partially configurable, for example by means of a command received by the computing unit, or CPU, of the node in question.
- the term calculating unit must be taken here in a broad sense, and not be limited to the microprocessor fitted to the central unit of a personal computer, a workstation or a server.
- This article focuses on managing the movement of massive data sets within distributed resources, computations, or storage, associated with scientific instruments for capturing information.
- the proposed solution is based on a bandwidth profile implementation mechanism, associated with the traditional transport protocol.
- This article introduces the malleable resource allocation approach by capacity time profile represented by a step function. This profile is only used in the case of the allocation of bandwidth 1P to convey a volume of data in deterministic time.
- This article focuses on the management of bandwidth reservations in an optical network.
- the proposed solution is based on an optimization algorithm using linear programming and mixing rigid queries and malleable queries (with several levels of bandwidth).
- This article looks at security management in on-demand virtual infrastructures.
- the proposed solution is based on the use of a simplified public key infrastructure and delegation.
- VXDL Virtual Resources and Interconnection Networks Description Language
- This article proposes a description language of a "virtual infrastructure” entity combining network resources and computing resources.
- This article is a snapshot of network virtualization issues, it does not mention any combination of virtualized network resources and computing resources.
- CARRIOCAS prcject Towards Converged Internet Infrastructure Supporting High Performance Distributed Applications
- VEGAT-WHITE PRIM ⁇ T D. RODRIGUES, L. THUAL, D. VERCHERE, IEEE / OSA Journal of Lightwave Technology, 2009.
- This article presents in a very general way the approach of combined virtualization of the network and the computer equipments.
- virtualization that is to say a set of physical elements, such as a physical infrastructure, are collectively managed to form a virtual element of a virtual infrastructure. For example, several computing units, including those distant from one another, can be virtually associated to form a single computing unit of greater capacity.
- FIG. 4 shows a physical infrastructure manager, or PIM manager 401, assistant to the PI infrastructure 200.
- the PIM manager 401 is connected to each of the Ni nodes of this PI infrastructure 200 by means of a respective link 411-i. , shown in fine dashed line. Each link allows data exchange between the PIM manager 401 and the corresponding node N1.
- the PIM manager 401 can furthermore be connected to a user interface, or UI interface 05.
- This PIM manager 401 is capable of receiving an X request, possibly via the UI interface 405, on which a request will be made later. .
- the PIM manager 401 is adapted to maintain a dynamic representation of the PI infrastructure 200, that is to say mainly all the resources of this infrastructure PI 200, including the nodes Ni of this infrastructure and the links of communication between these nodes.
- the PIM manager 401 is further adapted to maintain a representation of the functional state of these resources.
- the PIM manager 401 maintains in particular a list of so-called “physical” attributes, as well as a list of control and control functions for the resource in question.
- These control functions are generically named “rt CTRL ⁇ functions and control functions," CMD0 functions. "The shape of CTRL0 AMCC and functions depends on the nature of the resource.
- the PIM manager 401 maintains for each of the resources of the infrastructure PI 200 a corresponding object of the "information manipulation resource" type, as defined in Appendix A.1.1.2, which is designated herein. after object of type R. It is understood that a "type" of object can correspond to what is generally called an "class” of object.
- Each type of object R includes, as physical attributes, a universal identifier of physical resource "URI” and a type of physical resource "type_r” s which type belongs to the extensible set of the types of resources described in Appendix A l .3.1.
- the PIM manager 401 can be connected to an organized data storage space to maintain this representation of the infrastructure PI 200.
- the storage space here takes for example at least partially the form of a database, designated base RDB 402 in Figure 4.
- the PIM manager 401 creates an instance of the class R for each resource of the infrastructure PI 200 in the form of what is called a "daemon", or a "daemon”. Each daemon can thus be invoked, for example by functions linked in the class R, or other functions.
- FIG. 28 shows that the PIM manager 401 maintains:
- object Substrate Router 2780 For each routing device, a corresponding object generically designated object Substrate Router 2780.
- Figure 4 shows two separate data exchange networks, it is possible to make a functionally equivalent device into a single network.
- the P3M manager 401 can exchange data with at least some of the nodes N1 via the network links between these nodes.
- manager PIM 401 has been shown here outside the PI 200 infrastructure, it should be understood that this manager can also belong to this infrastructure, or even be distributed on one or more of the nodes of the latter.
- FIG. 5A shows a plurality of physical infrastructures, namely the infrastructures PI1-200-1, PI2200-2,..., PLI 200-i, PIn200-n, controlled by respective physical infrastructure managers, namely the managers PIM1 401-1, PIM2401 * 2, ..., PIMi 401-i, ..., and PIMn 401-n.
- These ⁇ 400-i managers are connected to a virtual infrastructure manager, or VIM manager 500.
- the communication between the VIM manager 500 and the PIM managers 40 li can be established according to a standard protocol, for example of the MTOSI type. English "Multi-Technology Operations System Interface" or "Interface of multiple technology operating systems” in French), or a similar protocol, including proprietary.
- the VIM manager 500 is able to send X requests to each of the PIMi 40 l-i, which requests may include commands to be executed as will be seen later. This VIM manager 500 can receive requests ⁇ , which will be discussed later.
- Figure 5B shows in the lower part of the infrastructure of Figure 5A in a form called “virtualized”, which can be called virtual infrastructure, where infrastructure VI 510.
- each physical resource is seen by the VIM manager 500 as a functional element in terms of manipulation deformations.
- the VIM manager 500 thus sees each physical infrastructure PI as an aggregate of functional elements.
- FIG. 5B shows, for example, a physical infrastructure ⁇ , referenced 10-1, a physical infrastructure PI2, referenced 510-2, a physical infrastructure - referenced 510-3, a physical infrastructure P11, generic, referenced 510-i, and a Pin physical infrastructure, referenced 510-n, each time in a virtualized form.
- Each functional element is represented by a cube. Although this is not visible in FIG. 5B, each physical resource is divisible, as far as its own functional capacity is concerned, into several functional elements. In addition, the capacity of these functional elements may be variable over time.
- each functional element can be seen as a "virtual engine” running on a physical resource.
- the shape of a virtual machine, and the management capabilities it offers, depend on the nature of the physical resource it is run on and its function within the infrastructure.
- the notion of virtual machine as it is understood here can go beyond what the technique conventionally means by a virtual machine. For example, a partition of a data storage space can be viewed as a virtual machine "running" on that space. This has been done to aid the understanding of the present description.
- VM WARE registered trade name
- XEN registered trade name
- the virtualization of a physical resource consists of defining a plurality of virtual resources sharing, in capacity and / or time, the functional capacity of this physical resource. This involves running virtualization agents on the physical resource itself or at least on the PIM manager that is responsible for this resource. These agents can control, configure, and / or control the physical resource through the CMDO and CRTLO functions discussed above.
- each PIMi 401 "i manager decides which physical infrastructure resources will be virtualized. For some resources, one can choose to virtualize only part of the resources.
- FIG. 5B shows a virtual link Ll 550-1 connecting infrastructure P12, PI3, Ply and Pin, while virtual links L2550-2 and L3550-3 connect infrastructure ⁇ , PI2, PI3 and Pli.
- each node or link is seen as functionally homogeneous.
- each resource is endowed, at a given moment, with only one function, called, main, such as storage, calculation, communication link, or router for example.
- main such as storage, calculation, communication link, or router for example.
- main such as storage, calculation, communication link, or router for example.
- a physical resource constantly performs the same function, but this is not required.
- a personal computer in that it includes computing capacity through its processor and storage capacity offered by its hard disk, is likely, in a virtual infrastructure, to offer these functions two functions, but not simultaneously.
- FIG. 5A Although the lower part of the figure SB represents only part of the infrastructure of FIG. 5A, it is understood that the whole of this infrastructure is intended to be virtualized, in particular, each physical infrastructure ⁇ -i, by PI infrastructure example 1200-1, PI 200-2, Pl-i 200-i and Pin 200-n.
- all the nodes of the same physical sub-infrastructure offer permanently the same function. This is the case, for example, when the sub-infrastructure takes the form of what is called a "cluster" in English, or a cluster of servers in French. This is not required, however.
- the VIM manager 500 is adapted to define one or more virtual infrastructures, or VPXI infrastructures (of the English "Virtual Private eXecution Infracture", or “Virtual Private Execution Infrastructure” in French).
- Each VPXI infrastructure thus includes virtual nodes interconnected by virtual links.
- a VPXI infrastructure is composed of virtual resources defined from physical resources.
- each virtual node comprises part of the functional capacity of a physical node.
- a virtual link includes a portion of the bandwidth offered by the physical link (s) on which it is based.
- some virtual resources may correspond to the entire functional capacity of a physical resource, at least all of the functional capacity that one has decided to virtualize, also called “exposed capacity”.
- Figure 5B shows a first infrastructure virtual VPXI-1 570 * 1, consisting of virtual nodes represented by horizontally hatched cubes, and a second VPXI-2570-2 virtual infrastructure, including virtual nodes represented by obliquely hatched cubes Hatches differentiating between the first and second VPXT virtual infrastructures - 1 70-1 and VPXI-2 -570-2 have been included in the lower part of Figure SB, each time in relation to the corresponding physical nodes.
- a first infrastructure virtual VPXI-1 570 * consisting of virtual nodes represented by horizontally hatched cubes
- a second VPXI-2570-2 virtual infrastructure including virtual nodes represented by obliquely hatched cubes Hatches differentiating between the first and second VPXT virtual infrastructures - 1 70-1 and VPXI-2 -570-2 have been included in the lower part of Figure SB, each time in relation to the corresponding physical nodes.
- a virtual node can be defined from only a portion of the functional capacity of the same physical node.
- the same virtual sub-infrastructure can only collect resources of the same function (calculation, storage or printing for example), which allows, in a certain way, to add their respective capacity.
- complex virtual infrastructures for example comprising two computing elements interconnected by an Internet link, in addition to a set of storage elements connected to one of these two calculation elements. .
- the different virtual infrastructures are isolated from each other, allowing each infrastructure to benefit from a high level of security and management of capacity and performance.
- a VPXI infrastructure can be specifically assigned to a user.
- the VM 500 manager selects, allocates and manages virtual resources and links between virtual nodes.
- the VIM manager 500 For each VPXI virtual infrastructure, the VIM manager 500 maintains a computing object representing that infrastructure, generically referred to as VPXI object 2710 in Fig. 27.
- This VPXI object maintains in relation:
- PIM infrastructure 200 which requires the reservation of resources, a security constraint data, which defines the required security level for the resources, an allocation period data, which defines a period of existence of the sub-infrastructure in the time, for example in the form of a start date of reservation and a total time of execution or an end date of allocation;
- the virtual network topology including performance characteristics such as bandwidth and latency, as well as security, business cost and time attributes linking the virtual resources to each other;
- VIM manager 500 For each virtual node, the VIM manager 500 creates and maintains a corresponding computer object, generically referred to as VXnode object 2730 in FIG. 28; linking a list of so-called “virtual” attributes and a list of control functions of the corresponding physical resource. These control functions are generically referred to as PILOTO functions.
- VXnode 2730 object still contains a list of calendars, which will be discussed later.
- the virtual attributes include, among other things, a resource type, denoted "typej", which type belongs to the extensible set "of the information processing resource types" described in Appendix A.1.3.1, or together Rt, attributes of security, reliability, mobility, resizing autonomy and monitoring.
- the VIM manager 500 still maintains a virtual link object for each virtual link of a virtual sub-infrastructure, generically referred to as VXlink object 2740 in Fig. 28, and which relates analog entries to a VXnode object 2730.
- a VXlink object 2740 includes an identifier of the original virtual node and an identifier of the destination virtual node.
- VIM manager further maintains for each virtual router a data object, generically designated VXrouter object 2750 in FIG 28 "and has similar inputs to VXnode object.
- each VPXJ object includes pointers to each of the virtual resources that comprise it, namely one or more Vxn objects of 2730, Vxlirik 2740, and VXrouter 2750.
- Each VXnode object 2730 includes a pointer to a substrate object Node 2760 corresponding to the physical node on which the virtual node is defined. In general, several VXnode 2730 objects can point to the same substrate 2760 substrate object.
- each Vxiink object 2740 and each Vxrouter object 2750 points to a substrate link object 2770 and a substrate router object 2780, respectively.
- the manager VHvi 500 further maintains for each user of a VPXI infrastructure, a user object, GENERALLY represented USER 2720 in Figure 28, in relation to the object VPXI 2710 assigned to it.
- a USER 2720 object maintains in relation: a list of general attributes relating to the user, including user name data, user type data, user location data;
- BiiiingO functions a list of payment functions, or generically referred to as BiiiingO functions.
- the manager V 500 can be connected to an organized storage space of the database type, for example the VRDB database 502 of FIG. 5A.
- each VXnode object 2730, each VPXI object 2710, each VXl Rouk object 2740, each VXrouter object 2750 takes the form of a "daemon", or an agent, executed by the VIM manager 500.
- each USER 2720 object can also be made in this form.
- This VIM 500 can advantageously be implemented in the form of what is called a "framework" in English, or “framework of application” in French.
- the management of virtual infrastructures VPXI implies that one can intervene on each resource of the physical infrastructure P, considered individually. Examples of physical structures that permit it are described, by way of non-limiting example, with reference to FIGS. 6A to 6 ⁇ .
- FIG. 6A shows a data storage disk, or DSK disk 601, together with its capacity controller, or CTRLR controller 61 1, which allows the exchange of useful data, or U_DAT data, for reading and / or writing with the DSK 601 disk.
- the CTRLR 611 controller is capable of operating the DSK 601 disk according to a set of operating parameters.
- the CTRLR 610 controller has a unit that interconnects it with a PIM manager in charge of the DSK 601 disk. This unit, designated ACT unit 611, can be seen as an actuator responsible for executing instructions from the concerned PIM manager. , for example transmitted through the communication network shown in dashed line in Figure 4. These instructions can have a particular shape.
- Figs. 6B to 6E illustrate arrangements similar to those of Fig. 6A:
- a display device or DISP device 602 is connected to its respective controller CTRLR 612, itself connected to an ACT unit 622
- a central computing unit or CPU 603, is connected to an ACT unit 623 via its controller CTRLR 612;
- a switch and / or router, or RTR device 604 is connected to its controller CTRLR 614, which is connected to an ACT unit 624;
- a network access point or NAP point 605 is connected to an AC unit 25 via its CTRLR controller 615.
- the manager PIM sends instructions to the ACT actioners on call of the functions CTRL () and / or CMDQ.
- the use of an ACT actuator is not possible or not necessary.
- the data necessary for the control and / or control configuration of the resource is directly received by the controller CTRLR as useful data, referred to as U-DAT data in FIGS. 6A-6E.
- U-DAT data useful data
- the ACT actuator is capable of modifying at least some of the operating parameters of its respective controller.
- the actuator can be viewed as a management agent for a resource.
- Resource management in the PI 200 infrastructure requires management agents that can maintain control and command functions as well as a status register for each infrastructure resource.
- each management agent must be able to execute, ideally permanently, from which nature of the physical resource to manage, may depend on the execution environment of the agent.
- the agent for its management can be deported to a different location of the infrastructure, typically on the manager PIM200, as is the case. especially network links. It may then be advantageous to provide an agent common to all the resources to be managed at the level of the PIM manager 200.
- the controller is able to modify quantitative data of maximum capacity of the resource he is dealing with.
- FIG. 7 represents an example of what can be called a "capacity time profile" for a resource, which is noted as a C (t) profile.
- a time profile C (t) can be established for any physical resource of the PI 200 infrastructure. Such a profile can also be established for any virtual resource.
- the temporal profile C (t) of a resource consists of all the variations concerning the functional capacity C of this resource over time / or a period of time.
- Any profile C (t) first comprises a temporal sub-profile of total capacity, or profile Cmax (t), corresponding to the time evolution of the maximum functional capacity of the resource.
- profile Cmax corresponding to the time evolution of the maximum functional capacity of the resource.
- the total capacity Cmax of the resource is constant over time, but this is only one example.
- a profile C (t) may further comprise a set of temporal sub-profiles of capacity reserved, in each case, to an infrastructure t.
- the infrastructure / will take the form of a virtual sub-infrastructure, typically a VPXl infrastructure, but this is not mandatory.”
- the subprofile of capacity reserved for infrastructure / is noted Ci (t ).
- the FIG. 7 thus shows a reserved capacity sub-profile for a first infrastructure 1, denoted Cl (t), and a reserved capacity sub-profile for a second infrastructure 2, denoted C2 (t).
- a reserved capacity subprofile Ci (i) may include one or more reservation fragments, i.e., a quantity of the capacity of the resource reserved for the portion of the infrastructure in question between two dates.
- a reservation fragment may correspond to an integral capacity, defined as the sum between these two dates of the corresponding part of the reserved capacity subprofile.
- a profile C (t) may further comprise a "best effort" capability subprofile, or capacity profile at best, denoted by Cbe (t).
- the sub-profile Cbeft corresponds to the capacity of the resource which is public and dedicated to the so-called service ! * best effort.
- This best effort "capability is not allocated to a specific part of the PI 200 infrastructure. When considered between two dates, this" best effort “capability profile delineates a" best effort “fragment. effort ", representing an integral capacity, that is, any resource whose total capacity can be divided between an unsecured capacity and a guaranteed capacity includes a C (t) profile with a" best effort “capability Cbe (t). this is particularly the case of communication-type resources or which include an Internet link.
- the profile C (t) may further comprise a reserve capacity subprofile, or profile Crvn (t), corresponding to the capacity of the resource set aside.
- the Crvnft profile) may include spare capacity fragments.
- the C (t) profile includes a residual capacity subprofile, or Crslft profile, which corresponds to the temporal evolution of the capacity of the resource which is neither attributed to any part of the infrastructure nor set aside, nor allocated to the BE service.
- This residual capacity is available for the PI 200 infrastructure elements. It can be qualified as “bookable”, “available” or “exposed” capacity.
- the profile C (t) of a resource can be represented by a set of time functions in the form of a staircase.
- Each function can take positive values in all real numbers, rational numbers, integers or Boolean numbers, depending in particular on the possibilities of dividing the capacity of this resource.
- the function of a resource is understood as the function that this resource exercises within the infrastructure, for example a computer function or information processing function, a storage function, a communication function, a function routing, a visualization function, a data capture or acquisition function.
- the measurement of the functional capacity C of a resource depends on the function of this resource.
- the capacity associated with a communication function may be measured by a digital data transmission rate, for example, expressed in. bits
- the capacity associated with a storage function may be expressed as a quantity of digital data, for example in bytes.
- the sum of the allocated functional capacities of a resource is less than or at most equal to the maximum capacity of this resource.
- the residual capacity of a resource which is also expressed in the form of a profile, can be proposed to an infrastructure or kept in reserve.
- the total capacity of a resource can be seen as the nesting of all the allocated functional capacity profiles and the residual functional capacity profile.
- Each profile can be viewed as a set of dated values of quantitative capacity data.
- the allocation of a fragment of capacity to an infrastructure is broadly understood to mean that, during the corresponding time period, the resource operates on behalf of the infrastructure in question.
- the part of the corresponding capacity then constitutes a virtual resource of the infrastructure in question for the corresponding period of time.
- a fragment of capacity is allocated to an infrastructure or a resource of this infrastructure.
- the same physical resource can provide different functions within the infrastructure, physical or virtual, but in a given period of time, this resource provides only one and the same function, called "main”.
- Figure 8 shows that the maximum capacity Cmax of a resource can be modified over time.
- the total capacity of a resource can also be modified after a new distribution of network resources that is also called “reprovision” or “reprovisioning”.
- an increase in the maximum capacity may correspond to the illumination of an additional optical fiber of the network or to the activation of new wavelengths.
- this may correspond to a modification of the parameters of a virtual machine, such as a working memory size, an amount of bandwidth or calculation power.
- a temporal profile of capacity C (t) relative to a virtual resource a variation of the maximum capacity Cmax, which may be temporary, may result / imply a redefinition of this resource from the physical resource on which she relies.
- this may correspond to an increase in the size of a data storage partition of a physical device, attributed to the virtual resource in question.
- each profile can take the form of a daemon executed according to the case on a controller of the type of the PIM controller or the VIM controller, and / or be stored on one of the bases RDB402 and VRDB502.
- the list of calendars of a VXnode 2730, VXlink 2740, or VXrouter 2750 object may include a link to the profile of this virtual resource and / or a link to each physical resource involved in this virtual resource.
- this link can point to only part of a profile, such as a reserved capacity subprofile.
- the capacity profile C (t) of a virtual resource can be deduced from the capacity profiles of the physical resources * or in some virtual cases, which compose it.
- a physical resource object may include a link to the time profile of this resource, for example maintained as a physical attribute in one of the Substrate node 2760, Substrate link 2770 and Substrate router 2780 objects.
- the PtM manager 400 can maintain a capacity profile C (t) for each P infrastructure resource PI 200, particularly in the physical attributes of the Substrate Node, Substrate Link or Substrate Router objects.
- the capacity profile Cft) of a resource can also be stored in the resource itself, when the physical constitution of this resource allows it. In this case, Substrate Node, Substrate Link, or Substrate Router objects can point to this profile.
- the VIM manager 500 maintains a capacity profile C (t) for each virtual resource based on the infrastructure PI 200. This is what has been called “Calendar” in connection with FIG. 28. This makes it possible, in particular, to create infrastructures. VPXI by aggregating / binding capacity fragments of a virtual resource.
- a virtual node and / or a VPXI object can be created by aggregating functional capabilities of unassigned physical nodes (fragments). For example, we can, on the same principle, create "best effort" infrastructures by combining the "best effort" capacities of different physical resources.
- a temporal capacitive profile associates a value of time (date) with a value of capacity.
- temporal profiles for physical or virtual resources relating to other attributes of the resource than its capacity It is possible to establish security profiles allowing for example access to the resource only at certain times of the day, replication profiles according to which, for example, a resource (storage) is replicated during the day and not at night. ; or monitoring profiles where, for example, a resource is monitored on working days and not on holidays.
- a capacity profile can be defined for each virtual node because it can operate simultaneously, successively or alternately for different VPXI infrastructures.
- Time profiles can be established for other attributes, including values for security, performance, geographic location, monetary or energy cost of the resource in question.
- the request Y of the figure SA can be a so-called "reservation" request, by which the mobilization of at least part of the functional capacity of the physical infrastructure resources PI 200 is requested for a given period of time.
- the request Y can target a given quantity of this capacity, in agreement with the divisible nature of this capacity.
- the reservation of the resource can be limited in time, and in this case be expressed in absolute form, that is to say delimited by two universal dates PI physical infrastructure PI 200, or relative, for example by .adata a start and a reservation period.
- a reservation request is more exactly a "pre-reservation" request, since it aims at a future reservation of the functional resource capacity,
- the request Y may also be a so-called "reprovision" request, that is to say a request to modify the functional capacity of one or more infrastructure resources, or even all the resources thereof. Most often, a reprovision request aims at or involves adapting or distributing the resources of the physical infrastructure PI 200 in a different way.
- a reprovision request can be defined absolutely or relatively, and may or may not be limited in time.
- the request Y can target virtual elements, or virtualized physical resources.
- a query Y relates to a functional capacity and a period of time, dated or not, without aiming at a particular physical device or virtual node.
- FIG. 9 illustrates the processing of a request Y1, similar to the request Y of FIG. 5A, by the manager VIM 500.
- the request Y1 consists of a reservation request.
- the manager VIM 500 implements a reservation processing, designated Rsrvn processing, represented by the block 901.
- the srvn processing 901 interacts with a description of the resource state of the PI infrastructure 200 or the virtual infrastructure VL or description RStat, represented by block 902.
- the description RStat 902 can use the profiles maintained in the database RDB 402 and / or VRDB 502.
- the processing Rsrvn 901 results in a profile C (t) to pre-reservation, block 910.
- This profile C (t) to pre-reservation is stored, for example in replacement of the initial profile of the resource.
- the Rsrvn 902 processing may further involve Rprvn 903 processing, as illustrated by the fine dashed arrow in Figure 9. This may be the case, for example, when the capacity residual profile of the resource is insufficient in view of the ability to reserve the query Yl next.
- the profile C (i) can be applied to a converter Cnvtr 914 to obtain what is called here a "time series of capacitance events", or serial 916 .
- a series represents a chronologically ordered sequence of future dated events that trigger actions of configuration and / or management of the resource considered then variations in the profile C (t) of this resource.
- such a series is called “bounded horizon", that is, it contains only the capacity events between a start date BD and an end date ED, this end date ED being temporally remote from the start date of a fixed period, or time horizon h.
- This series is also called “sliding”, that is to say that the start date BD is regularly advanced as time passes.
- the converter 914 can be seen as interpreting the time capacity profiles.
- FIG. 11 shows a representation of a series Se corresponding to the profile C (t) of FIG. 7.
- the series Se comprises a set of computer triplets Ek, Ek + 1,..., Ek + 5, each comprising a universal date data, a capacity value data item and a pointer data item to a set of functions and / or parameters. configuration and / or management of the resource concerned.
- a triplet, or event is generated correspondingly.
- the event triplet Ek + J corresponds to the end of the capacity reserve Crsn (t)
- the time series 916 takes the form of a computer object as defined in Appendix A.1.1.4, in combination with the objects defined in Annexes A.1.1.3, A.1.1.5, A.1.1.1. More generally, an event Ek relates a date, one or more command identifiers for the resource and a set of parameters for these functions, based on a dated attribute value. In other words, it is possible to establish a time series Se for any profile describing the variation of a resource attribute over time.
- a time series Se that is to say the call of the converter with a time horizon indication and the chronological call of each function and parameter of this series, at the appropriate date, can be performed, in part and for some physical resources at least, by the PIM manager 200 in charge of this resource.
- step 950 the manager VM 500 receives a request Y.
- This request includes indications of functional capacity to be reserved, including the function itself and the "quantity" of this function which is referred to, of time period of time. reservation, or at least a start date of reservation, and possibly of targeted resource (individualized).
- the manager VBv1 500 consults the state of the resources of the infrastructure V1, as they appear for example in the resource description 901. This can be done using the resource profiles contained in the base VRDB 502 and / or RDB 402.
- step 954 the V1 driver 401 judges whether it is possible to satisfy the request Y, to what extent, and how.
- This step 954 includes a step in which the request Y is formatted, in accordance with the representation made of the resources in the VRDB database 502.
- the request Y is stored in the manner of functional nodes connected to each other by links of links. communication.
- the query Y can specify the capacity of each functional node and each link.
- the VIM manager 500 creates an object called "VPXF" in step 960.
- the creation of a VPXI object of step 960 notably comprises the definition of the VPXI object in question, its storage in an organized data structure, and its allocation to the user having generated the request Y.
- the request Y can be submitted to the VIM manager in the form of a VPXI object, for example using a markup language conforming to the XML standard.
- the physical infrastructure resources are virtually allocated according to this object, at step 970.
- the VIM manager 500 returns a success notice at step 999.
- the creation of a VPXI object starts at step 962 by the creation of a new entry in a VPXI table, as represented for example in FIG. 27.
- this table maintains a relationship, among other things. , an identifier datum of the VPXI object, a user identifier datum, a description of this object, or a link to such a description, in terms of resources (links, nodes and routers in particular), a list of functions management and topology of the VPXI object,
- Operation 968 then gives the user the access rights defined in the VPXI object that has just been created.
- the operation 968 further includes loading the newly created VPXI object as a daemon.
- Step 964 involves updating and / or creating a VPXI object 2710, and objects Vx node 2730, Vxlink 2740, Vxrouter 2750 and substrate node objects 2760, substrate Hnk 2770 and substrate router 2780.
- operation 968 is a response to the user, response that follows the request that this user has issued. There is also an answer in a reprovision request.
- step 972 all the resources concerned by the VPXI object are listed, and it will be necessary to configure. This involves consulting the list of resources maintained in relation to the VPXI object in question in the database RVDB 502.
- a loop structure is started by setting a first resource as a current resource, in a step 974.
- this current resource is a node or an arc (or link), during a step 976.
- the resource is a node, we will consider this node in step 979. If the resource is an arc, we will consider the source node of the arc in step 978.
- the source node of the arc is the one hence the communication made on the arc or link considered.
- this processing can be considered as a procedure relating to the node concerned, a procedure that is defined in the VPXI object, for example by pointing a particular procedure, with parameters, among a predefined set of procedures.
- This usually involves sending the control manager 4 200 commands. These commands can be seen as the result of pilot function calls, generically denoted PILOT (), having effect on the PIM manager 200, schematically represented by the X request described above.
- a particular procedure might be the dynamic deployment and startup of a VMi virtual machine image, with operating system and pre-compiled executable programs, on a particular machine Mk.
- This procedure might be referred to as "Mk depioy (VMi) tt , and is an example of a CMD () function.
- another particular procedure may correspond, for a transmission link, to the association of a virtual link indicator (VLi) with a guaranteed service capacity (GARANTEED) and a threshold value of flow (Mi) on the port Pk.
- VLi virtual link indicator
- GAANTEED guaranteed service capacity
- Mi threshold value of flow
- Each resource type has a set, or set, of predefined configuration procedures. These configuration procedures are transmitted to the physical node considered either directly or via the PIM manager.
- the processing of all the resources of a VPXI object can be done in parallel, by resources, since these resources can generally be configured independently of each other. This makes it possible to accelerate globally the processing of a request Y.
- Figure 15 illustrates how one can exploit a given "time series”.
- the step 1302 sets to 0 (for example) the value of an index k.
- step 1304 executes the event defined in the time series, for time T3 ⁇ 4 (T 0 for k ⁇ 0).
- T 0 for k ⁇ 0 the value of an index k.
- step 1304 executes the event defined in the time series, for time T3 ⁇ 4 (T 0 for k ⁇ 0).
- T 0 for k ⁇ 0 the next event, of rank k + 1, of the series. This is symbolized in 1306 by the fact that we go from k to k + 1. (at this stage from 0 to 1).
- Test 1308 determines if the end of the series has passed.
- step 1310 consists of waiting for a time equal to 3 ⁇ 4 -T k .
- the event of the series is executed for the new value of k, at 1304, and so on, until the test 1308 makes it possible to exit to the end step 1312 .
- the device responsible for operating a time series may be of different material depending on the capabilities of the physical resource considered. In some cases, for example when the resource involved includes a computer, the resource itself operates its time series. In other cases, the resource merely responds to the function calls corresponding to each of the events (receiving instructions only).
- the converter 914 is advantageously executed on the PIR manager 202.
- VPXI management daemon Upon initialization of the global system, a VPXI management daemon is loaded along with a set of blank tables.
- the VPXI manager embeds a resource allocation module which makes it possible to establish the virtual nodes responding to a VPXI request.
- a first parameterization which can be manual, is to fill in the information of general order, in the different tables.
- Each control daemon of a physical resource namely each Substrate Node, Substrate Link, and Substrate Router daemon in Figure 28, depending on the nature of the resource in question, is loaded and initialized during a save operation of that resource. physical with its respective PIM manager 400.
- This record which includes the information of the information necessary for the creation of an object of type R, can be automatic, for example resulting from the execution of a series of instructions in the form of a computer code, or manual , by intervention of the owner / manager of the resource.
- This record triggers the initialization of the configuration procedures specific to each resource, in particular the CTRL0 and CMD () functions.
- the VXnode, VXlink, and VXrouter daemons which act as virtual resource driver daemons, are loaded and initialized as soon as they are allocated to a VPXl infrastructure by the VPXL manager.
- a first step E 1 includes the recording, or the declaration, of resources in what could be called a "substrate" of resources. This registration is made with the respective PIM manager 400 of the resource.
- a second step E2 corresponds to the submission of a VPXI infrastructure request by a user.
- a third step corresponds to the allocation of ime OR several virtual resources by the VPXI manager of the VIM manager 500 to a VPXI object.
- a fourth step E4 corresponds to the activation of a VPXL infrastructure
- a fifth step E5 corresponds to the activation of a control function of the virtual resources according to their respective calendars.
- a sixth step E6 corresponds to the activation of a physical resource control function via the PIM manager, for example a configuration function.
- a seventh step E7 corresponds to the access and use of the fragment of the physical resource by the user.
- Figure 16 considers that this is treated by a main procedure. After its departure 1400, it establishes an initial configuration, which is generally predetermined, and sets that this initial configuration is the current configuration 1404. Then, we wait for a request 1406. When a request arrives, it is processed as in 1408. This results in a new configuration, which is established as the current configuration in 1410, after which it returns to 1406 to reach the next request.
- the creation of a VPXI object involves the reservation of fragments of capacity in the capacity profiles of each of the resources concerned by this VPXI object.
- any VPXI object can also present a time profile of capacity, corresponding to the aggregation of the resource capacity fragments that constitute it.
- the profile of the VPXI object can in particular comprise a reserved fragment of a VPXI object request, a fragment of available capacity, or to reserve a usable "best effort" capacity fragment, without any other guarantee by any user. infrastructure.
- This temporal profile, or at least a link to this profile can be maintained in the storage structure that stores the VPXI objects. And this time profile can be submitted to the converter to obtain a time series each time.
- the VIM manager 500 comprises a request evaluation device, designated RED device 1700, capable of interacting with the VRDB base 502 to determine whether a request Y that is submitted to it can be satisfied, and what measure.
- This device can take the form of a computer module at least partially executed on the VIM manager 500. In particular, this module can take the form of a daemon. This module can also be designated resource allocation module, or Vx module tolloc.
- the device R £ D 1700 comprises a geographic resource selection tool, or tool GEOCEL 1702j adapted to select a subset of resources of the VRDB database 502 according to one or more geographical criteria, taken from the request Y.
- the selection of the subset of resources may take into account political criteria (belonging to a nation, a country, a government, an institution or others).
- the device RED 1 00 further comprises a functional resource selection tool, or tool FCTSEL 1704, adapted to select some of the resources of the VRDB base 502 according to functional attributes maintained in the database in relation to the resources in question.
- the FCTSEL tool 1704 is arranged to establish this selection among a subset of resources selected by the tool GEOSEL 1702.
- the RED 1700 device further comprises an attribute-based resource selection tool, or tool ATTRSEL 1706, adapted to receive at least part of the request Y, and to output a subset of resources of the VRDB base 502, selected based on attributes maintained in this database VRDB 402 in relation to the resources in question.
- the tool ATTRSEL 1706 is arranged to establish this selection among a subset of resources selected by the tool FCTSEL 1704.
- the RED 1700 device further includes a link selection tool, or RLMK tool 1708, adapted to receive a set of links and input resources, and to output a subset of selected links.
- RLMK tool 1708 can work on a subset of links and resources selected by the ATTRSEL 1706 tool.
- the RED Î700 device includes a planning tool, or SCHDLR tool 1710, adapted to receive a set of resources and links, and to establish as an output an optimized subset of said resources and links, based on a minimizing costs based on selected criteria.
- the SCHDLR 1710 tool is designed to work on a subset of links and resources from tool RNLK 1708 and / or tool ATTRSEL 1706.
- the combination of the GEOSEL 1702 tool, the FCTSEL 1704 tool, the ATTRSEL 1706 tool and the ATTRSEL 1706 tool and the RLNK 1708 tool, among others, can be seen. globally as a resource selection tool, or "resource selection”.
- Figure 18 illustrates a first function of the GEOSEL tool 1702.
- the GEOSEL tool 1702 receives as input the request Y, or at least part of it, and a subset of resources, or set of input resources, or set 1RS, of the VRDB 502 base.
- the GEOSEL tool 1702 is called beforehand to the other selection tools of the RED 1700 device, so that the assembly 1RS substantially corresponds to the entire base VRDB 502.
- the number, denoted n, of the resources referred to by the request Y is determined, excluding the links. All of these resources, excluded links, are noted Y. for the query Y.
- step 1804 a loop is initiated on the dummy variable which changes from 1 to n in unit increments.
- step 1806 a location function is called for a particular resource, denoted Ri, of the request Y.
- This function defined in Appendix A-2.1, returns a location attribute maintained in the request Y in connection with the request. resource Ri.
- This location attribute can be explicit, that is to say, explicit by the user who issued the request Y.
- This location attribute can also be implicit, that is to say inferred from information about the location. the user, known to the system, and / or the knowledge of users or resources in the vicinity of the user / sender of the request Y.
- step 1806 it is tested whether the lease function has returned an empty set or not.
- step 1806 If the test of step 1806 is positive, that is, if no location attribute is associated with the resource Ri of the request Y, then the next resource Y.Ri is processed (the variable "i "is incremented).
- step 1806 If the test of step 1806 is negative, that is to say if there exists a location attribute in relation to the resource Y.Ri, then, in step 1808, a subassembly of resourcés- result for the resource Y.Ri, or subset RSSi, including all the resources Rj of the set 1RS whose location attribute, as returned by the location function, corresponds to the location attribute of the resource Ri of the request Y.
- a set of output resources, or ORS set is set up, each comprising RSSi subsets, as well as the links of the set 1RS noted in their together I SL
- step 1812 the GEOSEL tool 1702 returns the OSR set as a result.
- Figure 19 illustrates a second function of the GEOSEL 1702 tool.
- this second function of the GEOSEL tool 1702 receives a request Y, and a set of input resources, or set 1RS.
- the set 1RS of step 1 00 corresponds to the set OSR delivered at the output of the first function of the tool GEOSEL 1702.
- step 1 02 the number, denoted n of Li links contained in the request Y is determined.
- the set of links referred to in the request Y is denoted Y.L.
- a loop is started with the dummy variable which is incremented unitarily from 1 to n.
- a SQus-efis ⁇ mble-resultRSSi is determined for a particular link, denoted Li link.
- the subset RSSi includes links Lj of the set 1RS such as:
- the call of the Latencymin function for the link Li of the request Y is less than the result of the Latencymax function call for this link Lj.
- Latencymax and Latencymi functions are respectively defined in Annexes A.2.2 and A.2.3.
- Step 1 06 is restarted for the following link Li (the dummy variable i is incremented by
- OSR a result set of resources, denoted OSR.
- the OSR set comprises each of the RSSL subsets as well as the resources, apart from the links, of the SRI set, noted in their entirety ISR.R.
- step 1910 the ORS set is returned as a result of the second function of the GEOSEL tool 1702.
- Figure 20 illustrates the operation of the FCTSEL 1704 tool.
- step 2000 the FCTSEL tool 1704 receives a request Y and a set of input resources, denoted 1RS.
- the set 1RS received in step 2000 corresponds to the set ORS delivered at the output of the tool GEOSEL 1702, in particular the second function of this tool.
- step 2002 the number n of resources R referred to by the request Y, excluding links, is established. All of these resources are noted Y.R.
- step 2004 a loop is started on the dummy variable "i", which is incremented unitarily from 1 to n.
- the function function defined in Annex A2A is called. If the result of this call is the empty set (step 2006), then this step 2006 is restarted for the next object Ri.
- step 2008 the number, denoted m, of functions returned by the call of the function function is established.
- step 2010 we start a loop on the dummy variable j, which is incremented unitarily from 1 to m.
- the subset RSSij comprises the resources Rk of the set 1RS whose one of the associated functions, denoted FL corresponds to the function Fj in question. This constituted the 2012 stage.
- step 2014 we establish a subset of resource-results for resource Ri, noted RSSi.
- the subset RSSi includes each subset RSSij.
- step 2016, the OSR result set, comprising the RSSi subset of each resource Ri, and the set of links of the set SRI, denoted IRS.L, are established.
- step 2018 the OSR set is returned as a result.
- Figure 21 illustrates a first function of the ATTOSEL 1706 tool.
- the ATTRSEL tool 1706 receives the request Y and a set of resources: 1RS.
- the set 1RS received in step 2100 may be the set ORS issued by the function FCTSEL 1704, or not.
- step 2102 the number n of resources R, excluded links, are determined that are the subject of the request Y.
- step 2104 a loop is initiated on the dummy variable "i", which will be incremented unitarily from 1 to n.
- a first subset of resource-results RSSI i is determined for a particular resource, denoted Ri.
- This subset RSSli includes the resources Rj of the set 1RS such as:
- the result of the call of the function cpumin for the resource Ri of the request Y is less than the result of the call of the function cpumax for the resource Rj of the set 1RS.
- a second subset of resource-results RSS2i for the resource Ri is determined, comprising all the resources Rj of the set 1RS such that:
- step 21 10 a third subset of resources ⁇ results RSS3I is determined for the resource Ri comprising all the resources Rj of the set 1RS such that:
- the result of the call of the function hdmin on the resource Ri is less than the result of the call of the function hdmax for this resource Rj.
- a fourth subset of resources-results RSS4I for the resource Ri is determined, comprising the set of resources Rj of the set 1RS such that:
- a subset-result RSSi is defined for the resource Ri.
- This subset RSSi comprises ⁇ intersection of sets SRI i, SR2L SR3i, SR4i and SR5i for the resource Ri.
- a set of OSR resource-results is defined, each comprising RSSi subsets corresponding to the resources Ri of the request Y as well as the set of links from the set 1RS, denoted by IRS.L.
- step 2120 the OSR set is returned as a result
- Figure 22 illustrates a second function of the ATTRSEL tool 1706.
- this second function of the tool ATTRÉL 1706 receives the request Y and a set of resources 1RS.
- the set 1RS received at step 2200 corresponds to the OSR set resulting from calling the first function of the ATTRSEL tool 1706.
- step 2202 the number n of resources Ri concerned by the survey Y is established.
- step 2204 a loop is initiated on the dummy variable f, which varies from 1 to n in increments of "1" ("one").
- step 2206 a subset of RSSi result resources is established for a particular resource, denoted Ri.
- the subset RSSi includes all the resources Rj of the 1RS set such as:
- the result of the call of the start function for the resource Ri is less than the result of the call of the function end for the resource Rj.
- step 2206 is restarted for the next resource Ri.
- a subset of resource-results OSR is defined comprising the subset RSSi of each of the resources Ri of the request: Y, as well as the set of Links of the set 1RS, denoted by IRS. L.
- step 2210 or return the ORS set as a result
- Figure 23 illustrates a third function of the ATTRSEL tool 1706.
- step 2300 the third function of the ATTRSEL tool 1706 receives a request Y and a set of resources 1RS.
- the set of IRS resources received at step 2300 corresponds to the OSR set resulting from the call of the second function of the ATTRSEL tool 1706.
- step 2302 the number of links L referred to by the request Y is determined.
- step 2304 a loop is initiated on the dummy variable "i", which varies from 1 to n in increments of "1".
- a subset of resource-result RSSi for the link Li is determined, comprising all the links Lj of the set 1RS such that:
- the result of the call of the start function on the link Li is less than the result of the call of the function end on the link Lj of the set 1RS.
- Step 2306 is then restarted for the link Li of the next request Y.
- a set of OSR resource-results is defined comprising the subset SSi of each of the links Li of the request Y, as well as the set of resources of the set 1RS, denoted IRS.R.
- step 2310 the ORS set is returned as a result.
- Figure 24 illustrates a first function of tool RLNK 1708.
- step 2400 the RLNK function receives a set of 1RS resources.
- the set of resources 1RS received in step 2400 may result from the call one of the functions of the tool ATTRSEL 1706, in particular the third function of this tool.
- the number m of resources, excluding links, is determined in the 1RS set.
- a loop is initiated on the dummy variable "i", which varies from 1 to m.
- a first subset of resource-result RSSi 1 is determined comprising the links Lj of the set 1RS such that the call of the function to, as defined in appendix A.3,1, for this link Lj is equal to the resource Ri.
- step 2408 a test is made to find out whether the RSS set is empty or not.
- step 2410 aims to determine whether the set RSS2i is empty or not.
- step 2412 we define a subset of result resources RSSi for the resource Ri, which is the empty set. And we repeat steps 2406 and following for the next resource Ri of the set 1RS.
- step 2408 proceeds to step 2414 during which the set RSSi for the resource Ri is defined. and includes the resource Ri of the set 1RS in question. Then, steps 2406 and following are repeated for the next resource Ri of the set 1RS.
- the OSR resource-result set is defined, which comprises each RSSi subset as well as the set of links of the 1RS set, denoted by IRS.L.
- step 2418 the OSR object is delivered as a result.
- Figure 25 illustrates a second function of tool RLN 1708.
- this second function receives a set of ISR input resources.
- step 2502 the number, denoted m, of links included in the SIR set is determined.
- step 2504 a loop is initiated on the dummy variable which is individually incremented from 1 to m.
- RSS2i a second subset of resources, denoted RSS2i, for this link Li, comprising the resources Rj, apart from the links, of the set ISR corresponding to the result of the call of the function Jrom on the link Li.
- step 2508 it is checked whether the subset RSSIi is empty or not.
- step 2510 in which we create a subset of resources-results, denoted RSSi, for the link.
- the RSSi subset is set to empty.
- step 2510 If so, proceed to step 2510. Otherwise, proceed to step 2514, in which a subsetable RSSi is created which is established to include the Li link in question.
- the set OSR comprises the subset RSSi corresponding to each of the links Li of the set SRI, as well as all the resources, excluding the links, of this set ISR, globally noted ISR.R.
- step 2518 the OSR set is returned as a result.
- Figure 26 shows a third function of tool RLN 1708.
- step 2600 the function in question receives the request Y and a set of ISR input resources.
- step 2602 the number, denoted n, of the links referred to by the request Y is determined.
- step 2604 a loop is initiated on the dummy variable "i", which will be incremented from 1 to n.
- the result of calling the bandwidthmin function on the Li link of the request Y is less than the result of calling the bandwidthmax function on the link Lj in question.
- Step 2606 is then restarted for the following Li link of the request Y.
- step 2608 a set of OSR resource-results comprising I subset RSSi corresponding to each of the links Li of the request Y, as well as the set of resources, denoted ISR.R, excluding links, are defined. ISR set.
- Figure 27 illustrates the operation of the SCHDLR 1710 tool.
- step 2700 the request Y and a subset of virtual resources ISR are received.
- this subset ISR results from the successive call of the functions RNLK and ATTRSEL, so that the subset ISR comprises only nodes and links likely to respond, possibly in combination with each other, to the request Y,
- step 2702 we consider the capacitive profile of each of the resources of the subset SRI. This usually involves querying the VR.DB 502 database.
- step 2704 it is determined whether there exists in the ISR subsystem a solution to the request Y which is compatible with the respective capacitive profiles of the resources. In other words, for each of the resources of the subset SRI, it is determined whether its capacitive profile allows a suitable reservation in terms of date / duration and capacity. Finally, a subset of solutions for the query Y is determined.
- step 2706 an empty capacitive profile is returned.
- step 2710 a set of updated capacitive profiles, that is to say containing the necessary reservations, capacity and time. And we create the appropriate VPXI object in the VPXI table.
- an optimization procedure is launched to determine which of the solutions of the entire step 2704 best meet predetermined criteria. These criteria mainly concern the management of infrastructures as a whole.
- the SCHDLR module 1710 implements a request-by-request scheduling algorithm.
- This module SCHDLR 1710 can also be arranged to handle several requests of the type of the request Y. In other words, the module SCHDLR 1710 can work in batches.
- the optimization step 2712 may use a more complex scheduler, for example adapted to simultaneously optimize several criteria such as user satisfaction, resource utilization, energy consumption, monetary cost for the customer or the like. .
- the invention can not be limited to a particular scheduling algorithm. In practice, any scheduler capable of establishing resource reservation profiles from a set of resources can be used here.
- the optimal operation of the system requires that the different components of the virtual infrastructure 500 are synchronized with each other. At the very least, this requires that the VIM manager 500, each of the ⁇ -i 200-i handlers and each device running itself from the Se series be synchronized with each other. This can be done by means of a synchronization device, thus linking the modules responsible for the interpretation of the temporal profiles, the execution of time series and the controllers operating the changes within the equipment of the infrastructure.
- This device may comprise one or more GPS-type global clocks, an NTP server and NTP clients, a distributed global clock, for example made in the form of software; which is constructed and resynchronized from any physical time source.
- This tool includes a resource manager associated with a data storage describing the capabilities of the various equipment of the network, or data resource situation.
- This storage is arranged according to a data structure in which an identifier was related to dated values of quantitative quantities.
- the resource manager registers at least some of the equipment of the network as resources in the situation data storage with, as identifier, an equipment identifier, and as a dated value of quantitative quantities, a first series of dated values of capabilities.
- transmission, storage and / or processing device defining an overall operable capacity of the resource, and one or more series of dated transmission, storage and / or processing capacity values defining temporarily allocated resource capabilities.
- a resource selector has also been described, for use, for example, in this tool for assisting the operation of a network, comprising a first selection tool adapted to return a subset of selected resource identifiers in the storage. data according to functional identification data, a second selection tool adapted to return a subset of selected resource identifiers in a data storage according to geographic location data derived from the reservation request, a third selection tool adapted to return a subset of selected resource identifiers in the data storage according to non-functional attribute data derived from this query, a fourth selection tool adapted to receive a subset of resource identifiers and to return, on the one hand, only those received identifiers which are maintained in a binding data storage as a second or third resource identifier in relation to a first resource identifier and, on the other hand, each of the first identifiers in question.
- the resource selector comprising a set of selection functions operating on different criteria from each other.
- the resource selector may include only some of these selection functions.
- a planning tool adapted to evaluate an acceptance condition from date comparison expressions relating to a dated functional capability and the dated data storage and / or processing transmission capacity continuations maintained has also been described. relationship of one or more resource identifiers. This planning tool is thus able to verify if a resource can be reserved, in other words, if its capacity profile authorizes a reservation and under which conditions.
- a resource allocator has also been described arranged to receive an identified request for temporary functional capacity reservation including a dated set of functional data and to respond by calling the resource selector for each functional data item of the request, by calling the resource selector a scheduling tool for at least some of the subset identifiers returned by the resource selector, and ultimately returning a set of resource identifiers as a response to the reservation request.
- a virtual infrastructure manager has also been described which is associated with a second storage of situation data and virtual infrastructures.
- This second data storage is arranged according to a second data structure in which an identifier is related to dated values of quantitative quantities.
- the virtual infrastructure manager is adapted to register virtual units in the second data storage, with, as identifier, an identifier of the unit and, as a date value of quantitative quantity, a second series of dated values of processing capabilities. , storage and / or transmission of the virtual unit defining a global exploitable capacity of the unit, in the form of a capacity profile.
- This virtual infrastructure manager is further associated with a third data structure, in which a virtual unit identifier is associated with a group of resource identifiers and thereby with dated value sequences of corresponding capabilities.
- the first, second and third data structures thus jointly define an object of virtual infrastructures corresponding to a virtual unit identifier, for at least some of these identifiers while maintaining a correspondence between the first and second series of dated values.
- processing, storage and / or transmission capacity that is to say, in particular between the capacity profiles of elements of the virtual infrastructure, those of the infrastructure itself and especially those of the network equipment, or resources physical.
- a network manager is responsible for maintaining rights and capabilities for users over time.
- the virtual infrastructure manager is arranged to dynamically reconfigure virtual infrastructure objects according to the requested rights and capabilities, for example a request for replenishment or reservation.
- Any reconfiguration operation of a virtual infrastructure includes reconfiguring the content of the third data structure associated with the virtual infrastructure object and / or reconfiguring the content of the first data structure referred to in the object of virtual infrastructures. This makes it possible to manage the virtual infrastructure in correspondence with a plurality of temporal graphs of processing capacity and or transmission of the physical equipment constituting the exploited network.
- An equipment controller capable of operating a physical device in accordance with a set of operating parameters and a data storage arranged according to a structure which relates an identifier for this physical equipment and, on the one hand, a set of dated values of attributes, and, on the other hand, a list of command functions capable of modifying at least some of the operating parameters of the controller.
- An interpreter is adapted to receive at the same time an equipment identifier data and a time horizon parameter, and to respond thereto establish a sequence of respective events from the data storage information concerned with the horizon. a series of events from the data storage information concerned with the time horizon, each event or more control function identifiers and a set of parameters for these functions based on a dated attribute value.
- the controller, interpreter, and sequencer work together to implement an "infinite" process, at least at the system life scale, which, at least for parts of these elements, run on resources, such as 'run in the background.
- Each physical infrastructure manager in combination with one or more actuators, arranged on the equipment itself or remotely, if necessary partially, acts as a sequencer that calls the interpreter and realizes chronologically the calls of the functions of each Event of the sequel as returned by the interpreter.
- the call of the interpreter can nevertheless be done in a programmed manner, at predefined time intervals, or in a systematic way, as soon as a change has occurred in the temporal profile of a physical device.
- the operation assistance tool may contain any combination of the functional elements described above between them, when these elements are compatible with each other.
- the proposed tool uses a logical representation of the physical functional capacity of any technical device comprising a network, in particular a wide area network such as the Internet.
- a technical device is considered a "resource" of the network.
- this resource can be virtualized, that is to say, to host several resources, generally presenting an identical main function by giving the impression to any user that the virtual resource that he uses is a physical resource of his own.
- a model of logical and dynamic segmentation of the individual physical functional capacity of each of these resources has been proposed. It has also been proposed to establish sliding and bounded time series of management, configuration and control events for physical resources for all types of resources. These time profiles and event series help resource management, in particular by facilitating the computations generated by the resource allocation operations following a request from a user.
- the proposed tool allows any owner of computer equipment with processing, communication or storage capabilities to dynamically, flexibly and reversibly insert this equipment into a large, global resource pool of the Internet. dynamically segment the functional capabilities of this resource, and choose which uses are intended for isolated functional sub-capabilities.
- Any operator of a resource or collection of resources such as a network, a cluster of computers, or a data center can dynamically and flexibly manage and configure its resources remotely, or transmit them threshold values allowing a autonomous management and configuration. It allows rigorous monitoring, simple accounting and precise statistical analyzes of the use of resources in two sizes, namely time and capacity, and more generally, time and any attribute that can be associated with physical equipment. This makes it possible to establish efficient cost and sizing calculations of individual capacities.
- the proposed tool still allows equitable valuation of infrastructure investments by adding value to the entire container, such as storage space or routing capabilities, and not just processing and routing. content as is the case in the current interest.
- This tool can enable a gradual transformation of the current Internet into a future Internet by providing a universal connectivity service, more service capabilities, and on-demand, high-capacity and guaranteed-quality infrastructure services.
- the tool uses a temporal representation model that can be described as "fine-grained" network capabilities. This provides dynamic control, management and valuation of network resources in general, and the Internet in particular, to ensure global adjustment of these resources to environmental conditions and real needs.
- the proposed tool is suitable for any equipment implementing any network abstraction layer (1, 2 and 3) of the current Internet as well as modern mechanisms for virtualization of computing resources. It is possible to reuse all existing protocols and software, but also to use new network, transport and application protocols that could be more efficient and better adapted to new applications.
- Any manufacturer of computer or communication components can provide a logical representation of the capacity of the equipment it manufactures and thus enable its dynamic and flexible remote management and configuration, using standard protocols such as Netconf or even autonomous.
- the tool thus makes it possible to advantageously exploit dynamic configuration mechanisms and control plans developed in recent years in optical networks and packet networks such as GMPLS / ASON, MEF and MTOSI.
- the tool especially allows the sharing of resources between different users with constraints and interests different from each other. Some users need guarantees in real time or in advance, while others are unable to foresee such needs or do not use them. This is done by offering the operator or the owner of the physical resource the opportunity to value the resources of its infrastructure at best.
- the proposed tool is based on a representation of the continuous time (universal time) which differentiates it greatly from other propositions in the field of which one manipulates a time said in "slots" or “slices of time” in French.
- the tool is not required to use discrete values of capacity. This makes it possible to obtain solutions that can be computed in polynomial time, which proves to be very advantageous, in particular during resource allocation calculations and subsequent user requests.
- the tool also makes it possible to logically and dynamically divide a distributed physical computing infrastructure into independently controlled and potentially isolated infrastrucfures. It diversifies and increases the value of distributed infrastructures by offering a solution of quality, service and security to users willing to pay the price.
- the proposed tool makes it possible to decide on the location and timing of rooting of a virtual private computing infrastructure within a public physical infrastructure and distributed geographically. It speeds up the resource allocation decision process by making successive restrictions of the solution space.
- the invention is not limited to the embodiments described above, by way of example only March encompasses all the variants that may be envisaged by the man in particular. It has been described a system operating optimally. In practice, for this If the system runs at a minimum, the VIM500 manager and each PIM200-I manager must maintain one VPXI object for each virtual sub-infrastructure, one VXNOD type object for each virtual node and one "substrate node" object for each physical device in the network. . The system then operates in a degraded mode without managing its network.
- VXlink object In order for the system to work with a managed network, a VXlink object must also be maintained for each virtual link between virtual nodes and a "stubstrate link" object for each physical link in the network.
- a physical resource, node or link could serve as a basis for one or more virtual resources depending on the nature of the physical equipment in question. It is to be understood that a plurality of physical resources may also be assembled to form a single virtual node and that likewise several virtual nodes may be assembled to form a single, uniquely managed virtual node.
- VIM500 and P1M200-I drivers have been described for their functional properties within the system. It should be understood that any implementation of these functions, in whatever form, is within the scope of this application. These managers can be completely or partially centralized or distributed, in particular according to the configurations and the possibilities of the equipment available within the infastructures.
- the proposed tool makes it possible to manage in a unified, generalized and combined way all the resources of the network. All these resources, whatever their nature, a computer, a router and / or links interconnecting these resources, at all levels of control and management are treated in a homogeneous way. Finally, the physical elements are ignored to remove all boundaries between them.
- the present invention also aims at the software code that can be used, especially when it is made available on any support readable on a computer.
- computer-readable medium covers a storage medium, for example magnetic or optical, as well as a m on, such as a digital or analog signal, passing through a physical link or by wave.
- the tool for assisting the operation of an equipment network is adapted to coordinate and optimize the computer resources, for example heterogeneous, of a network.
- the properties and capacities are thus allocated, then possibly modified, according to the requests of the client and / or according to the properties / capacities available of the provider / network manager.
- the allocation of resources is furthermore carried out and / or modified further according to criteria ordered in order of priority.
- Such an arrangement will thus give rise to the reassignment programmed during a time period, to respond to a second request, capacity and / or properties previously reserved for this period following receipt of a first request, if the second request has higher priority criteria than the first request, and the second request can not be completed without this arbitration.
- the priority criteria may relate to the clients that are the origin of the requests, and / or various characteristics, for example depending on the services required or the equipment requested. For example, for two customers who have requested a fast service, the customer having agreed to paying the most expensive will get resources as closely as possible, if the supplier's decision criterion is income. On the other hand, if the criterion is energy expenditure, it is the customer whose energy credit is the most important that will be preferred.
- tk date expressed in universal time and included in your window
- F t pe_ type of event among ⁇ cap_provisioning, cap_renting)
- ck capacity expressed in unit unit: of the resource
- action_ ⁇ k (r) ⁇ list of actions and parameters associated with the event Ek (r) activated on the date tk according to the type of event
- the date tk serves as an index for searching and performing events.
- n is bounded by nb_evt_max (r)
- i is a value integer in [0, Ne-Î].
- RESA_PROFJL (t, r, F) ⁇ Cj (t, r F), j integer in [0, ml] ⁇ where is bounded by nb jprof
- the manipulation of information includes the transmission and processing of information.
Landscapes
- Engineering & Computer Science (AREA)
- Computer Networks & Wireless Communication (AREA)
- Signal Processing (AREA)
- Data Exchanges In Wide-Area Networks (AREA)
- Computer And Data Communications (AREA)
Abstract
Description
Claims
Applications Claiming Priority (2)
Application Number | Priority Date | Filing Date | Title |
---|---|---|---|
FR1001626A FR2959091B1 (fr) | 2010-04-16 | 2010-04-16 | Outil de gestion de ressources et d'infrastructures informatiques et reseaux |
PCT/FR2011/050859 WO2011128595A1 (fr) | 2010-04-16 | 2011-04-14 | Outil pour la gestion de ressources et d'infrastructures informatiques et de reseaux |
Publications (1)
Publication Number | Publication Date |
---|---|
EP2559195A1 true EP2559195A1 (fr) | 2013-02-20 |
Family
ID=43126989
Family Applications (1)
Application Number | Title | Priority Date | Filing Date |
---|---|---|---|
EP11720150A Withdrawn EP2559195A1 (fr) | 2010-04-16 | 2011-04-14 | Outil pour la gestion de ressources et d'infrastructures informatiques et de reseaux |
Country Status (5)
Country | Link |
---|---|
US (2) | US20130073732A1 (fr) |
EP (1) | EP2559195A1 (fr) |
CA (1) | CA2796550A1 (fr) |
FR (1) | FR2959091B1 (fr) |
WO (1) | WO2011128595A1 (fr) |
Families Citing this family (11)
Publication number | Priority date | Publication date | Assignee | Title |
---|---|---|---|---|
US9721086B2 (en) | 2013-03-15 | 2017-08-01 | Advanced Elemental Technologies, Inc. | Methods and systems for secure and reliable identity-based computing |
US9378065B2 (en) * | 2013-03-15 | 2016-06-28 | Advanced Elemental Technologies, Inc. | Purposeful computing |
US9344336B2 (en) * | 2013-10-15 | 2016-05-17 | Dell Products L.P. | System and method for managing virtual link state |
US9621439B2 (en) * | 2014-02-28 | 2017-04-11 | International Business Machines Corporation | Dynamic and adaptive quota shares |
US10200486B2 (en) * | 2015-02-26 | 2019-02-05 | Urban Airship, Inc. | Mobile event notifications for network enabled objects |
US9992072B1 (en) * | 2015-05-04 | 2018-06-05 | VCE IP Holding Company LLC | System, method, apparatus, and computer program product for enabling management of a plurality of computer components using a software framework |
CN106528287B (zh) | 2015-09-09 | 2019-10-29 | 阿里巴巴集团控股有限公司 | 计算机系统资源分配方法和装置 |
CN108028806B (zh) * | 2015-11-06 | 2020-06-16 | 华为技术有限公司 | 网络功能虚拟化nfv网络中分配虚拟资源的方法和装置 |
US10411969B2 (en) * | 2016-10-03 | 2019-09-10 | Microsoft Technology Licensing, Llc | Backend resource costs for online service offerings |
US11042405B2 (en) * | 2019-01-10 | 2021-06-22 | Vmware, Inc. | Scheduling and executing functions across different functions-as-a-service (FAAS) infrastructures |
WO2023225078A1 (fr) | 2022-05-20 | 2023-11-23 | Advanced Elemental Technologies, Inc. | Systèmes et procédés associés à une infrastructure d'informations d'identification de ressource informatique et d'événement/activité connectée à l'aide d'une identification biométrique quasi existentielle ou existentielle d'êtres humains |
Family Cites Families (14)
Publication number | Priority date | Publication date | Assignee | Title |
---|---|---|---|---|
MY147018A (en) * | 2001-01-04 | 2012-10-15 | Thomson Licensing Sa | A method and apparatus for acquiring media services available from content aggregators |
US7085242B2 (en) * | 2002-03-22 | 2006-08-01 | Telcordia Technologies, Inc. | Virtual IP topology reconfiguration migration |
KR20040105804A (ko) * | 2002-03-28 | 2004-12-16 | 오페락스 아베 | 아이피 네트워크 내의 자원예약 방법 및 시스템 |
JP4062071B2 (ja) * | 2002-11-26 | 2008-03-19 | 日本電気株式会社 | Gmplsラベル管理装置 |
FR2858900B1 (fr) * | 2003-08-12 | 2006-01-06 | Cit Alcatel | Fourniture de services par reservation de ressources au sein d'un reseau de communications a gestion de ressources par des regles de politique |
WO2006031157A1 (fr) * | 2004-09-16 | 2006-03-23 | Telefonaktiebolaget Lm Ericsson (Publ) | Routage base sur l'utilisation d'une transmission |
US7818010B2 (en) * | 2005-05-31 | 2010-10-19 | Avaya Inc. | Methods and apparatus for allocating resources in a distributed environment |
US8539481B2 (en) * | 2005-12-12 | 2013-09-17 | Microsoft Corporation | Using virtual hierarchies to build alternative namespaces |
EE05523B1 (et) * | 2005-12-30 | 2012-02-15 | Priit@Vimberg | Meetod ja süsteem ühtseks ressursside haldamiseksning juhtimiseks |
US8209695B1 (en) * | 2006-07-28 | 2012-06-26 | Hewlett-Packard Development Company, L.P. | Reserving resources in a resource-on-demand system for user desktop utility demand |
US8239487B1 (en) * | 2007-05-30 | 2012-08-07 | Rocketon, Inc. | Method and apparatus for promoting desired on-line activities using on-line games |
WO2009007620A2 (fr) * | 2007-06-29 | 2009-01-15 | France Telecom | Systeme de gestion automatique des reseaux sur une grille informatique |
EP2309432A1 (fr) * | 2009-09-07 | 2011-04-13 | Siemens Aktiengesellschaft | Procédé et système de propagation d'un mode de mise à l'échelle dans un procédé de production |
US8434088B2 (en) * | 2010-02-18 | 2013-04-30 | International Business Machines Corporation | Optimized capacity planning |
-
2010
- 2010-04-16 FR FR1001626A patent/FR2959091B1/fr not_active Expired - Fee Related
-
2011
- 2011-04-14 CA CA2796550A patent/CA2796550A1/fr not_active Abandoned
- 2011-04-14 WO PCT/FR2011/050859 patent/WO2011128595A1/fr active Application Filing
- 2011-04-14 US US13/641,634 patent/US20130073732A1/en not_active Abandoned
- 2011-04-14 EP EP11720150A patent/EP2559195A1/fr not_active Withdrawn
-
2016
- 2016-06-30 US US15/199,816 patent/US20160315817A1/en not_active Abandoned
Non-Patent Citations (1)
Title |
---|
See references of WO2011128595A1 * |
Also Published As
Publication number | Publication date |
---|---|
WO2011128595A1 (fr) | 2011-10-20 |
US20160315817A1 (en) | 2016-10-27 |
US20130073732A1 (en) | 2013-03-21 |
FR2959091A1 (fr) | 2011-10-21 |
FR2959091B1 (fr) | 2014-06-20 |
CA2796550A1 (fr) | 2011-10-20 |
Similar Documents
Publication | Publication Date | Title |
---|---|---|
EP2559196B1 (fr) | Outil de gestion de ressources et d'infrastructures informatiques et réseaux | |
WO2011128595A1 (fr) | Outil pour la gestion de ressources et d'infrastructures informatiques et de reseaux | |
EP2559224B1 (fr) | Outil de gestion de ressources et d'infrastructures informatiques et de réseaux | |
US9716746B2 (en) | System and method using software defined continuity (SDC) and application defined continuity (ADC) for achieving business continuity and application continuity on massively scalable entities like entire datacenters, entire clouds etc. in a computing system environment | |
US9306868B2 (en) | Cross-cloud computing resource usage tracking | |
US8364819B2 (en) | Systems and methods for cross-vendor mapping service in cloud networks | |
US20190173666A1 (en) | Hierarchical blockchain consensus optimazation scheme | |
US20120137002A1 (en) | Systems and methods for brokering optimized resource supply costs in host cloud-based network using predictive workloads | |
US20140040343A1 (en) | Globally Distributed Utility Computing Cloud | |
US20110296000A1 (en) | Systems and methods for exporting usage history data as input to a management platform of a target cloud-based network | |
US20120130873A1 (en) | Systems and methods for generating multi-cloud incremental billing capture and administration | |
US20120311153A1 (en) | Systems and methods for detecting resource consumption events over sliding intervals in cloud-based network | |
US20120078915A1 (en) | Systems and methods for cloud-based directory system based on hashed values of parent and child storage locations | |
EP2353256A1 (fr) | Determination et gestion de reseaux virtuels | |
JP2011129117A (ja) | サービスとしてのクラウドフェデレーション | |
EP2727319B1 (fr) | Procédé d'affectation d'adresses logiques aux ports de connexion d'équipements d'une grappe de serveurs, programme d'ordinateur et grappe de serveurs correspondants | |
FR3037417A1 (fr) | Procede et systeme de determination d'une configuration de serveurs cible pour un deploiement d'une application logicielle | |
US11663048B2 (en) | On-premises to cloud workload migration through cyclic deployment and evaluation | |
Grigoras et al. | MonALISA-based Grid monitoring and control | |
WO2009007620A2 (fr) | Systeme de gestion automatique des reseaux sur une grille informatique | |
Cannarella | Multi-Tenant federated approach to resources brokering between Kubernetes clusters | |
EP3228070B1 (fr) | Procédé de gestion de contenus dans un réseau de distribution de contenus | |
CA3213594A1 (fr) | Serveur, systeme et procede de configuration pour la generation d'informations de configuration pour une plateforme multi-systemes | |
Ucan | Data storage, transfers and communication in personal clouds | |
FR2913293A1 (fr) | Systeme d'informations en environnement de diffusion audio/video comportant des moyens pour la gestion de sites distants. |
Legal Events
Date | Code | Title | Description |
---|---|---|---|
PUAI | Public reference made under article 153(3) epc to a published international application that has entered the european phase |
Free format text: ORIGINAL CODE: 0009012 |
|
17P | Request for examination filed |
Effective date: 20121012 |
|
AK | Designated contracting states |
Kind code of ref document: A1 Designated state(s): AL AT BE BG CH CY CZ DE DK EE ES FI FR GB GR HR HU IE IS IT LI LT LU LV MC MK MT NL NO PL PT RO RS SE SI SK SM TR |
|
DAX | Request for extension of the european patent (deleted) | ||
RAP1 | Party data changed (applicant data changed or rights of an application transferred) |
Owner name: LYATISS |
|
RAP1 | Party data changed (applicant data changed or rights of an application transferred) |
Owner name: LYATISS |
|
RAP1 | Party data changed (applicant data changed or rights of an application transferred) |
Owner name: F5 NETWORKS, INC |
|
17Q | First examination report despatched |
Effective date: 20161202 |
|
STAA | Information on the status of an ep patent application or granted ep patent |
Free format text: STATUS: THE APPLICATION IS DEEMED TO BE WITHDRAWN |
|
18D | Application deemed to be withdrawn |
Effective date: 20170413 |