Telefonaktiebolaget Lm Ericsson (publ)

Daniel Turull

Vinay Yadhav

Joao Monteiro Soares

Amir Roozbeh

Lars Westberg

Chakri Padala

Ganapathy Raman Madanagopal

Mozhgan Mahloo

Mina Sedaghat

Pontus Sköldström

Raquel Vigolvino Lopes

Marcus Carvalho

Francisco Vilar Brasileiro

Giovanni Farias Da Silva

Erik Halen

A method by a user plane breakout function in a mobile core network for providing dynamic distributed local breakout. The method includes receiving, from one or more neighboring user plane breakout functions, service instance information of one or more instances of a service, processing capacity information of one or more edge clouds, and link quality information of one or more links between other user plane breakout functions. The method further includes, calculating, for each of the one or more instances of the service, a service instance access score for that instance of the service based on the service instance information, the processing capacity information, and the link quality information.

Dynamic distributed local breakout determination

A method performed by a computer to update a runtime environment of an application of the computer via a communications network, wherein a filesystem of the runtime environment comprises one or more layers, wherein at least one layer of the one or more layers comprises a link layer formed by a plurality of packages and wherein the link layer comprises symbolic links indicative of the packages forming an updated layer. The method comprising receiving, from a user device or from a scheduling unit, a first signal indicative of a command to use the updated layer of the one or more layers, obtaining the updated layer, obtaining packages forming the updated layer, from a local cache or from a shared storage or from an image repository node, and updating the runtime environment by replacing a layer of the one or more layers with the updated layer using the obtained packages.

Method for updating applications in cloud environments

A method for forming a cluster of nodes. The method includes obtaining first information associated with a predetermined number of nodes in the cluster. The method also includes determining an administrative role of the first node based on the obtained first information. The method also includes, as a result of determining that the administrative role of the first node is a first role, broadcasting a first broadcast message, thereby enabling a plurality of nodes that are not in the cluster to receive the first broadcast message, wherein the plurality of nodes that are not in the cluster includes at least a second node, the first broadcast message comprising second information for controlling the timing at which each node within the plurality of nodes transmits to the first node a response message responsive to the broadcast message. The method also includes receiving a first response message responsive to the first broadcast message, wherein the first response message was transmitted by the second node. The method also includes, after receiving the first response message, adding the second node to the cluster.

Methods and nodes for cluster formation

It is disclosed a resource sharing manager, RSM, operative to provide efficient utilization of central processing units, CPUs, within virtual servers, each virtual server having an operating system, OS. The RSM dynamically obtains () information about ownership and sharable status of said CPUs, and dynamically determines () which CPUs are sharable to which virtual servers. The RSM obtains () information about that one or more sharable CPUs are available; and obtains () information about that one or more virtual servers require more processing resources. The RSM also assigns () a first CPU of said sharable CPUs when available, to a first virtual server of said virtual servers. Information about ownership and sharable status of the first CPU, is hence provided to the OS of the first virtual server. Overhead is reduced by circumventing a hypervisor when sharing CPUs in virtual servers. An increase in efficiency of task execution is provided.

Management of dynamic sharing of central processing units

A method and a reallocation component for managing a reallocation of information from a source memory sled to a target memory sled. The source and target memory sleds comprise a respective table indicating source status for each page of the source and target memory sleds, respectively. The reallocation component initiates, for each respective source page whose status indicates that the respective source page is initialized, reallocation of the respective content allocated on each respective source page of the source memory sled to a respective target page of the target memory sled. The reallocation component sets for each respective source page whose status indicates that the respective source page is uninitialized, the respective target status for the respective target page to indicate uninitialized, while refraining from reallocating the respective content allocated on each respective source page whose status indicates that the respective source page is uninitialized.

Method and reallocation component for managing reallocation of information from source to target memory sled

To manage memory, a computer system, responsive to receiving a message indicating an availability of a memory page of the computer system, generates a mapping between a logical address of the memory page and at least two physical memory addresses at which respective copies of the memory page are available. The computer system provides one of the at least two physical memory addresses in response to a request for access to the memory page.

Managing availability of memory pages

Migrating an application executing in a source compute sled to a target compute sled. The migration component selects a first sub-set of source pages. A respective source status of each source page of the first sub-set is modified according to a source table. A target table of the target compute sled is set to indicate that a first sub-set of target pages are modified. The migration component migrates the respective content stored in the first sub-set of source pages to target pages and selects a second sub-set of source pages, wherein the respective source status of each source page of the second sub-set is modified according to the source table. The migration component sets the target table to indicate that a second sub-set of target pages is allocated in the memory and then moves the respective content stored in the second sub-set of source pages to the memory.

Method and a migration component for migrating an application

A method is discussed for balancing processing loads to at least a first and a second VM instances associated with the same processing circuitry. Information about first and second applications respectively running on the first and second VM instances is obtained. Incoming data corresponding to a first and second pluralities of jobs to be performed respectively by the first and second VM instances is received. Based on the obtained information and on the received data, a first number of the first plurality of jobs which the first VM instance is allowed to perform is determined by means of the processing circuitry, and a second number of the second plurality of jobs which the second VM instance is allowed to perform is determined by means of the processing circuitry. The first VM instance is instructed to release the processing circuitry after having performed the determined first number of jobs to allow the second VM instance to use the processing circuitry for performing the second number of jobs.

Balancing processing loads of virtual machines

Methods, computer-readable media, and systems are included for generating information about latency ratings corresponding to a memory pool and a CPU pool. An example method includes for each CPU of the CPU pool, estimating a first latency rating for said each CPU towards the memory pool, and for each memory unit of the memory pool, estimating a second latency rating for said each memory unit towards the CPU pool. The CPUs are organized into a first plurality of groups of CPUs based on the estimated first latency rating, where each CPU of each group of the first plurality of groups has a first common latency rating towards the memory pool. The memory units are organized into a second plurality of groups of memory units based on the estimated second latency rating, where each memory unit of each group of the second plurality of groups has a second common latency rating towards the CPU pool.

Methods and modules relating to allocation of host machines

A method, a resource manager, and a computer program are described for scheduling instances in a logical server, where each instance belongs to a class of instances, where each class is associated with a required service level objective (SLO). Based on determined margins between current SLOs and required SLOs, instances are sorted. If resources are not enough, an instance having a large margin may be pre-empted irrespective of the class. If available resources are sufficient for an instance having a small margin, this instance can be allocated resources. If the available resources do not suffice, it may be decided to pre-empt another instance to which resource are allocated, in order to free resources sufficient for the instance having the small margin. Accordingly, scheduling is performed for instances having various classes without violating the SLOs of the instances and such that resources are more efficiently used.

Method and resource manager for scheduling of instances in a data centre

A method and a defragmentation module for defragmenting resources of a hardware system. The defragmentation module identifies a set of structures. Each structure of the set of structures partially hosts a respective set of host machines. Respective resources of each host machine of the respective set of host machines are allocated in at least two structures of the set of structures. The defragmentation module selects, from the respective resources of a host machine of the respective set of host machine, a remote resource of a first structure being different from a second structure partially hosting the host machine. A remote amount of the remote resource is less than an amount of available resources of the second structure. The defragmentation module assigns the remote amount of the available resources of the second structure to the host machine instead of the remote resource.

Method and defragmentation module for defragmenting resources

There is provided a method for coordinated scheduling between real-time processes. The method is performed by a central scheduler. The method comprises acquiring information on runtimes and deadlines for real-time processes of tasks for local schedulers to be executed on shared computing resources. The method comprises scheduling the real-time processes based on the runtimes and deadlines so as to keep the deadlines during execution of the real-time processes. There is also provided a central scheduler configured to perform such a method. There is also provided a computer program comprising computer program code which, when run on a processing unit of a central scheduler causes the processing unit to execute such a method.

Coordinated scheduling between real-time processes

A method and a Memory Availability Managing Module () 'MAMM' for managing availability of memory pages () are disclosed. A disaggregated hardware system () comprises sets of memory blades () and computing pools (). The MAMM () receives (A) a message relating to allocation of at least one memory page to at least one operating system (). The message comprises an indication about availability for said at least one memory page. The MAMM () translates (A) the indication about availability to a set of memory blade parameters, identifying at least one memory blade (). The MAMM () generates (A) address mapping information for said at least one memory page, including a logical address of said at least one memory page mapped to at least two physical memory addresses of said at least one memory blade (). The MAMM () provides (A) at least some of the address mapping information for use when access to said at least one memory page is requested. A corresponding computer program and a carrier therefor are also disclosed.

Method and memory availability managing module for managing availability of memory pages

A Weight Generating Module for generating a respective set of weights representing a respective policy of a plurality of policies. The respective set of weights defines a respective host machine. The Module calculates a respective user-defined number of pairs for each collection of a number of collections by distributing a total number of pairs among the number of collections for each respective policy based on a respective set of user-defined weights and a respective allocation weight. The Module selects, for said each collection, the respective user-defined number of pairs in increasing order with respect to the latencies to obtain a respective sub-set of collection weights relating to latencies associated with said each collection. The Module determines, for said each respective policy, the respective set of weights representing the respective policy based on a set of collection weights. The Module provides, for said each respective policy, the respective set of weights.

A Memory Merging Function 'MMF' for merging memory pages. A hardware system comprises a set of memory blades and a set of computing pools. At least one instance of an operating system executes on the hardware system. The MMF is independent of the operating system. The MMF finds a first and a second memory page. The first and second memory pages include identical information. The first and second memory pages are associated with at least one computing unit of the computing units. The MMF obtains a respective memory blade parameter relating to memory blade of the first and second memory pages and a respective latency parameter relating to latency for accessing the first and second memory pages. The MMF releases at least one of the first and second memory pages based on the respective memory blade and latency parameters.

Growing community of inventors

Sundbyberg, Sweden

Daniel Turull