Abstract: An algorithm for efficiently maintaining a globally uniform-in-time execution schedule for a dynamically changing set of periodic workload instances is provided. At a high level, the algorithm operates by gradually adjusting execution start times in the schedule until they converge to a globally uniform state. In certain embodiments, the algorithm exhibits the property of “quick convergence,” which means that regardless of the number of periodic workload instances added or removed, the execution start times for all workload instances in the schedule will typically converge to a globally uniform state within a single cycle length from the time of the addition/removal event(s) (subject to a tunable “aggressiveness” parameter).

Abstract: One or more virtual machines are launched at an application platform. At each of the one or more virtual machines, a machine learning model execution environment is instantiated for an instance of a machine learning model. A respective instance of the machine learning model is loaded to each machine learning model execution environment. Each loaded instance of the machine learning model is associated with an application programming interface (API) endpoint which can receive input data for the loaded instance of the machine learning model from a client device and return output data produced by the loaded instance of the machine learning model based on the input data.

Abstract: Techniques for allocating functionality of a block device driver are described. The described techniques utilize a hybrid architecture including a block device kernel driver that operates at a kernel space layer of the OS and a block device user space component that operates at a user space layer of the OS. Generally, the block device kernel driver performs input/output (I/O) operations on backing files of a block device and the block device user space component performs other operations such as management operations on the backing files of the block device.

Abstract: A time series forecasting system is disclosed that receives a forecast request identifying a forecast to be made for a future time point and a time series dataset to be used for making the requested forecast. The system selects a model to be used for making the requested forecast and determines a set of one or more attributes of the time series dataset. Based on the set of attributes, the system selects a compute instance either from a shared node pool or a dedicated instance having a shape to be used for training the selected model and generating a forecast. The system then generates a forecast result for the future time point using the trained model and provides the forecast result as a response to the forecast request.

Abstract: The subject matter of this specification can be implemented in, among other things, a method that includes accessing a plurality of target tasks for a computing system, the computing system comprising a plurality of resources, wherein the plurality of resources comprises a first server and a second server, accessing a plurality of configurations of the computing system, wherein each of the plurality of configurations identifies one or more resources of the plurality of resources to perform the respective target task of the plurality of target tasks, and performing, for each of the plurality of configurations, a simulation to determine a plurality of performance metrics, wherein each of the plurality of performance metrics predicts performance of at least one of the plurality of resources executing the plurality of target tasks on the computing system.

Abstract: A scalable Internet of Things (IoT) system may include multiple instances of an IoT manager, each instance respectively configured to connect to a respective edge system of multiple edge systems. The IoT system may further include a containerized system configured to allow any instance of the IoT manager to deploy data pipelines to any edge system of the multiple edge systems in delta communications. Any instance of the IoT manager may send a change message to any edge system via a publish/subscribe notification method. In some examples, a centralized IoT manager may form a secure communication with an edge system, synchronize an object model with an edge object model for the edge system, and maintain the edge system using delta change communications. The IoT system may facilitate any instance of the IoT manager to subscribe a communication channel with an associated edge system for receiving update notification.

Abstract: A method of scheduling an operating system of a vehicle control unit includes determining a runnable function according to a first task requested from an application for a vehicle; executing the first task by operating with any one of a first thread and a second thread according to the determined runnable function for a first period in the first core; and when operating with the second thread in the first core, executing a first backup task corresponding to the first task in a second core that is different from the first core for the first period.

Abstract: Methods, systems, and apparatus, including computer programs encoded on computer storage media for performing preflight checks of a distributed computing system, are described. In one aspect, a method includes assigning a computing workload to a first subset of hardware accelerator machines each having one or more hardware accelerators. A preflight check on the first subset is performed before performing the computing workload to verify the functionality of each machine in the first subset. For each hardware accelerator machine of the first subset, a program code package is installed, including a task action based at least in part on characteristics of the computing workload. The task action including a sequence of operations is performed on the hardware accelerator machine to determine whether the task action fails. Whenever the task action fails, the computing workload is re-assigned to a second subset of hardware accelerator machines different from the first subset.

Abstract: This application discloses a VNF service instantiation method and apparatus. The method is performed by a network functions virtualization orchestrator NFVO or a virtualized network function manager VNFM. The method includes: receiving a virtualized network function VNF instantiation request message; obtaining deployment information of a container service instance that needs to be invoked for VNF instantiation; determining one or more container as service clusters CaaS clusters based on the deployment information of the container service instance, and sending a container service instance creation request to a container as service manager CaaS manager in each of the one or more CaaS clusters; and receiving a container service instance creation success message from the CaaS manager. According to the foregoing solution, problems of cross-site deployment and management of a container service in an NFV scenario are resolved.

Abstract: A monitor process identifies a first container executing on a worker node of a container orchestration system comprising a plurality of worker nodes, each worker node including a control plane component configured to execute a container in response to a request from a scheduler. The monitor process identifies a control group (cgroup) that corresponds to the first container. The monitor process generates a first resource utilization structure that corresponds to the first container. The monitor process, for each respective time of a plurality of successive times, obtains, by the monitor process, from the cgroup, one or more computer resource utilization values that identify real-time memory utilization of the first container at the respective time of the plurality of successive times. The monitor process stores, in the first resource utilization structure, computer resource utilization information based on the one or more computer resource utilization values.

Abstract: Computer-implemented methods and systems for integrating computer applications are disclosed. One method includes querying a primary computer application for current state of a newly created object; receiving the current state of the object, and generating object data for a secondary computer application based on the current state of the object. The method further includes communicating an object creation request to a secondary computer application, the object creation request including the generated object data, receiving a secondary computer application object identifier from the secondary computer application upon creation of the object at the secondary computer application, and communicating the secondary computer application object identifier to the primary computer application for storing in a record of the object created at the primary computer application.

Abstract: One example described herein include a system that can detect an event associated with executing a software operation using a quantum service of a quantum computing system. Based on detecting the event, the system can identify a classical service (of a classical computing system) that corresponds to the quantum service. The system can then cause the software operation to be executed using the classical service.

Abstract: Techniques are disclosed relating to filtering messages. A computer system may detect an occurrence of an event of a particular type. The computer system may determine whether to enqueue, in a message queue, a message that identifies a set of tasks to be performed in relation to the event. The determination may be based on a response received from a cache that stores a subset of filter rules of a filter rules table. Based on the response indicating a cache miss, the computer system may enqueue the message in the message queue. A process that processes the message may be operable to resolve the cache miss by 1) accessing a filter rule from the filter rules table that indicates whether messages for events of the particular type should be enqueued in the message queue and 2) updating the cache to store the filter rule.

Abstract: An apparatus comprises at least one processing device configured to monitor, by a first service in a service chain, a first set of processing queues comprising two or more different processing queues associated with two or more different priority levels. The processing device is also configured to process, by the first service, a given portion of data stored in at least one of the two or more different processing queues in the first set of processing queues. The processing device is further configured to determine prioritization information associated with the given portion of the data and to select, based on the prioritization information, a given one of two or more different processing queues in a second set of processing queues associated with a second service in the service chain, and to store the given portion of the data in the given processing queue in the second set of processing queues.

Abstract: Some implementations described herein relate to a system that is configured to obtain one or more event logs associated with a tenant of the system. The system may be configured to determine, based on the one or more event logs, an event rate associated with the tenant and thereby determine, based on the event rate, a rotation interval. The system may be configured to cause, based on the rotation interval, a data structure to be generated for storing event logs associated with the tenant that are obtained during a time window. The system may be configured to obtain, within the time window, one or more additional event logs associated with the tenant and to cause, based on obtaining the one or more additional event logs within the time window, the one or more additional event logs to be stored in the data structure.

Abstract: An example method of virtualizing a hardware accelerator in a host cluster of a virtualized computing system includes: commanding, at an initiator host in the host cluster, a programmable expansion bus device to reconfigure as a virtual accelerator based on specifications of a hardware accelerator in a target host of the host cluster; executing, in the programmable expansion bus device, software to emulate the virtual accelerator as connected to an expansion bus of the initiator host; receiving, at the programmable expansion bus device, compute tasks from an application executing in the initiator host; and sending, to the target host, the compute tasks for processing by the hardware accelerator.

Abstract: Disclosed embodiments are directed at systems, methods, and architecture for configuring event hooks in a microservice architecture-based system. The control plane links a plurality of APIs for a microservice architecture application. Each API includes a data plane proxy that serves traffic for the API from the control plane. The control plane receives an event hook including an event, a source, and a handler. The control plane configures a component of the microservice-architecture-based system to run the handler when the event occurs at the source. When the event occurred at the source, the component runs the handler.

Abstract: Systems and methods for processing and/or presenting data are disclosed. In an aspect, one method can comprise receiving a request for information and detecting a type of data representing the information requested. The data can be processed via a type-dependent agent and the processed data can be provided via an agnostic data engine.

Abstract: Examples described herein relate to migrating a virtualized execution environment from a first platform to a second platform while retaining use of namespace identifiers and permitting issuance of storage transactions by the virtualized execution environment. The first platform can include a first central processing unit or a first network interface. The second platform can include a central processing unit that is different that the first central processing unit and a network interface that is the same or different than the first network interface. The second platform can retain access permissions and target media format independent of one or more identifiers associated with the migrated virtualized execution environment at the second platform. Unperformed storage transactions can be migrated to the second platform for execution.

Abstract: In asynchronous processing, processing of a low-order system is checked. A high-order system 1 includes a high-order workflow advancing unit 21 that transmits a processing command for asynchronous processing to a low-order system 2, and a notice processing unit 23 that receives, from the low-order system 2, a notice related to a device command to be executed by a device 3 in the asynchronous processing, and updates progress data 13. The low-order system 2 includes a low-order workflow advancing unit 61 that, upon receiving the processing command from the high-order system 1, transmits a device command to the device, and a notification unit 62 that, when transmission of the device command to the device 3 is detected, notifies the high-order system 1 of the identifier of the device to which the device command was transmitted and the device command.