Abstract:
Methods and systems allocate storage costs to virtual machines (“VMs”) in a virtual data center. Methods calculate a datastore-base rate based on datastore utilized-storage capacity in each LD and each LD-base rate when the datastore utilized-storage capacity and each LD-base rate are available. Datastore total cost is calculated by multiplying the datastore-base rate by the datastore utilized-storage capacity. Methods also use graph based methods to calculate datastore-base rates when the datastore utilized-storage capacity is unknown for each LD. The datastore-base rate associated with each datastore may then be used to calculate a VM storage cost of each VM hosted by a datastore.
Abstract:
This disclosure presents computational systems and methods that allocate cost of resources of a cluster of server computers used by virtual machines in a virtual data center. In one aspect, a fair unit rate is computed based on the larger of a measured average utilization or an expected utilization of a cluster resource of server computers within a physical data center by virtual machines. The fair unit rate is a cost per unit of resource used over a period of time and is used to compute an allocated cost of the virtual machine usage of the cluster resource.
Abstract:
Techniques for performing dynamic cost per unit resource usage in a virtual data center are described. In one example embodiment, an initial unit resource usage price is received for the virtual data center for a first cycle. Further, capital expenditure (CAPEX) and operating expenditure (OPEX) information of the virtual data center of the first cycle is obtained. Furthermore, a target return on investment (ROI) for the virtual data center for a second cycle is received. A unit resource usage price is then computed for the second cycle using the received initial unit resource usage price for the first cycle and the CAPEX and OPEX information of the first cycle. The unit resource usage price is then dynamically calibrated for the second cycle using the computed unit resource usage price and the target ROI.
Abstract:
The disclosure provides a method for diagnosing remote sites of a distributed container orchestration system. The method generally includes receiving a test suite custom resource defining an image to be used for a diagnosis of components of a workload cluster deployed at the remote sites, wherein the image comprises a diagnosis module and/or a user-provided plugin to be used for the diagnosis; identifying a failed component in the workload cluster; obtaining infrastructure information about the workload cluster; identifying the components of the workload cluster for diagnosis based on the failed component, the infrastructure information, and the test suite custom resource; identifying at least one diagnosis site of the remote sites where the components are running using the infrastructure information; and deploying a first pod at the at least one diagnosis site to execute the diagnosis of the one or more components.
Abstract:
System and computer-implemented method for migrating partial tree structures of virtual disks for virtual computing instances between sites in a computer system uses a compressed trie, which is created from target tree structures of virtual disks at a plurality of target sites in the computer system. For a virtual computing instance selected, the compressed trie is used to find candidate target sites based on a disk chain string of the virtual computing instance. For each candidate target site, a cost value for migrating the virtual computing instance along with a partial source tree structure of virtual disks corresponding to the virtual computing instance from the source site to the candidate target site is calculated to select a target site with a lowest cost value as a migration option to reduce storage resource usage in the computer system.
Abstract:
Some embodiments of the invention provide a method for defining a telecommunications network deployment for a particular geographic region, the telecommunications network including an access network, an edge network, and a core network. The method determines population density of UEs (user equipment) for the particular geographic region. Based on the determined population density, the method divides the particular geographic region into a set of sub-regions. For each sub-region in the set of sub-regions, the method simulates performance of the telecommunications network to explore multiple configurations for access nodes that connect UEs in the sub-region to the telecommunications network. Each configuration in the multiple configurations is defined based on population density of the sub-region. The method selects a particular configuration for access nodes from the multiple configurations for use in defining a deployment of the telecommunications network.
Abstract:
A computer-implemented method, medium, and system for upgrade of telco node cluster running cloud-native network functions are disclosed. In one computer-implemented method, a worker node group that includes a plurality of worker nodes is determined in a container orchestration platform. A first node to upgrade is determined within the worker node group. All pods in the first node are deactivated by a high availability as a service (HAaaS) module. Standby pods in a second node are activated by the HAaaS module and as active pods. All network traffic associated with all the pods in the first node is migrated to the active pods. The first node is deleted from the worker node group. Hardware resources associated with running the first node are released. A third node is generated as a new worker node in the worker node group and uses the released hardware resources.
Abstract:
System and method for performing diagnostics in a multi-cloud system triggers a diagnostic workflow in a first cloud computing environment of the multi-cloud system in response to an event in the multi-cloud system and execute the diagnostic workflow in the first cloud computing environment by identifying components in the multi-cloud system that are affected by the event and obtaining probes for the identified components. For each component of the identified components, a sub-flow of the diagnostic workflow is started to run at least one probe of the obtained probes to generate a diagnostic result of the component. A diagnostic report is generated based on the diagnostic result of each component of the identified components.
Abstract:
System and computer-implemented method for migrating partial tree structures of virtual disks for virtual computing instances between sites in a computer system uses a compressed trie, which is created from target tree structures of virtual disks at a plurality of target sites in the computer system. For a virtual computing instance selected, the compressed trie is used to find candidate target sites based on a disk chain string of the virtual computing instance. For each candidate target site, a cost value for migrating the virtual computing instance along with a partial source tree structure of virtual disks corresponding to the virtual computing instance from the source site to the candidate target site is calculated to select a target site with a lowest cost value as a migration option to reduce storage resource usage in the computer system.
Abstract:
One or more embodiments provide techniques for migrating virtual machines (VMs) from a private data center to a cloud data center. A hybrid cloud manager determines a scope of migration from the private data center to the cloud data center. The hybrid cloud manager groups each VM included in the scope of migration into one or more clusters. The hybrid cloud manager defines one or more migration phases. Each migration phase comprises a subset of the one or more clusters. The hybrid cloud manager generates a migration schedule based on at least the one or more migration phases. The hybrid cloud manager migrates the VMs from the private data center to the cloud data center in accordance with the migration schedule.