58results about How to "Avoid resource competition" patented technology

The invention discloses a monitoring device for a server cluster. The device comprises a control node, wherein the control node comprises at least one task allocation node; each task allocation node comprises at least one acquiring node; each task allocation node is used for allocating a plurality of servers to be acquired to each acquiring node in the at least one acquiring node; and each acquiring node is used for acquiring the running state information of a server from the plurality of servers to be acquired, and forwarding the running state information of the server to the control node for saving through the belonging task allocation node. According to the monitoring device, each acquiring node is responsible for acquiring the information of the plurality of servers, a relation of one point to multiple points exists between each node and each server, and the plurality of acquiring nodes are not required to communicate with one another. Along with the expansion in the scale of the server luster, monitoring of a large-scale server luster can be realized only by increasing the quantity of the acquiring nodes or the quantity of business allocation nodes.

Embodiments of the invention disclose a data updating method, and a data query method and apparatus. The data updating method comprises the steps of storing to-be-updated data corresponding to a received data updating request in a preset number of data fragmentation queues based on a preset fragmentation rule; traversing each data fragmentation queue in response to a preset fragmented data summarization triggering instruction, and updating fragment summarization data in a fragment summarization data cache corresponding to the data fragmentation queue based on the to-be-updated data in the data fragmentation queue when each data fragmentation queue is traversed; and obtaining the fragment summarization data from the fragment summarization data cache in response to a preset data summarization triggering instruction, and updating the summarization data in the summarization data cache based on the fragment summarization data. By utilizing the data updating method, the system performance can be improved on the basis of ensuring data consistency, and the system availability in a high-concurrency scene is greatly improved.

The invention provides a shared data updating device. The device comprises a storage unit, a discrepant data computing unit, a data persistence unit and a data verification unit, wherein the storage unit is used for saving a basic data base table and a cache data base table; the basic data base table is used for saving summarized data of shared data; the cache data base table is used for saving discrepant data of the shared data; the discrepant data calculating unit is used for computing discrepant data of the shared data caused by updating operation; the data persistence unit adopts isolated transaction to insert the discrepant data into the cache data base table; and the data verification unit is used for inquiring the discrepant data of the basic data base table and the cache data base table and determining whether to submit isolated transaction according to a verification result. The invention further provides a shared data updating method. According to the technical scheme, locking process can be eliminated during data updating and verification processes on the basis that the data updating correctness is guaranteed, so that the concurrency supported by a system is improved.

The invention relates to a resource scheduling method and device, and a filter type scheduler. The method comprises the following steps: a first filter type scheduler acquires a scheduling request message carrying a service demand, converts the scheduling request message to a scheduling task message, and notifies each filter type scheduler in a scheduling system through an asynchronous communication way, wherein the scheduling task message is used for indicating the filter type scheduler to determine a scheduling result in a virtual group associated with the filter type scheduler according tothe service demand, and the scheduling result is sent to the first filter type scheduler; the scheduling result determined according to the scheduling task message by the filter type scheduler in thescheduling system is acquired; the final scheduling result is determined in the acquired scheduling result according to a preset algorithm, and the final scheduling result comprises one or multiple servers satisfying the service demand. The scheduling processing capacity and the scheduling efficiency of the whole scheduling system are improved.

The invention relates to the field of artificial intelligence, and discloses an intelligent task scheduling method and device, an equipment and a storage medium. The method comprises the steps of obtaining a plurality of to-be-scheduled tasks needing to be scheduled and the correlation degrees among the to-be-scheduled tasks; determining a plurality of front tasks with front dependence in each to-be-scheduled task according to the correlation degree; obtaining the dependence degree of each front-end task, and finding the front-end task with the highest dependence degree; acquiring the prioritylevels of the target tasks except the front task in the to-be-scheduled tasks, and constructing a preset task execution sequence according to the dependency degree and the priority levels; schedulingeach to-be-scheduled task according to a preset task execution sequence until all to-be-scheduled tasks are scheduled. According to the present invention, the resource competition between other non-important tasks and the important tasks can be avoided, the important tasks can obtain the optimal execution right, the priority execution of the important tasks is ensured, the development of the subsequent tasks is facilitated, and the working speed and efficiencyand the user experience are improved.

The invention discloses a file access method. The method comprises the following steps of: receiving an access request of a target client for accessing a target file, wherein the access request comprises an access mode of requesting to access the target file; acquiring access information corresponding to the target file, and determining a current state of a metadata lock of the target file by utilizing the access information; by utilizing the current state, according to a corresponding relationship of each state of the metadata lock and the access mode, determining whether to give corresponding access permission to the target client; and if yes, allowing the target client to access the target file. In a permission management mode, a resource competition problem is avoided in advance, consistency of data is ensured, and system stability is promoted. The invention further discloses a file access device and equipment and a readable storage medium, which have the corresponding technical effects.

The invention discloses a mapping method between virtual CPUs (Central Processing Unit) and physical CPUs, and electronic equipment. The method comprises the following steps: in a current time period, a virtual machine manager obtains a first virtual CPU set to be mapped and a first physical CPU with least tasks to be operated in a next time period; the virtual machine manager obtains a first characteristic value of each first virtual CPU in the first virtual CPU set and a second characteristic value of the first physical CPU; and the virtual machine manager obtains a target characteristic value matched with the second characteristic value from all first characteristic values and maps the target virtual CPU corresponding to the target characteristic value to the first physical CPU to operate. The technical scheme solves the technical problems of the resource competition and the integral performance decrease of a system in the prior art when the virtual CPU is mapped to the physical CPU.

The invention provides an alarm processing system and method. The alarm processing system comprises: at least one first server, at least two second servers connected with the at least one first server, and at least two clients connected with any second server. Each client is used for sending a first target instruction to the second server connected with the client, receiving first alarm information sent by the second server and carrying out corresponding process. Each second server is used for sending a second target instruction to the at least one first server according to the received at least one target instruction, receiving second alarm information sent by the at least one first server and sending the first alarm information respectively to the corresponding at least one client. The at least one first server is used for sending corresponding second alarm information respectively to the at least two second server. According to the technical scheme provided by the invention, the usability of the alarm processing system is improved.

Since managed copy requires consumption of a plenty of resources, there is a problem that if managed copy controlled by the reproduction device side and BD-J application execution on a recording medium are simultaneously operated, resource shortage is caused. Provided is a reproduction device in which during a managed copy, a disc is virtually removed for the BD-J application so as to limit access to the disc, thereby avoiding the resource conflict between the managed copy and the BD-J application execution, which enables simultaneous operation of the managed copy and the BD-J application execution.

The embodiment of the invention provides a Zookeeper cluster system and a connection method and device thereof. The Zookeeper cluster system comprises a proxy device, wherein the proxy device is deployed on a machine in which Zookeeper clients are located; each Zookeeper client is connected with a server through the proxy device; and the proxy device is used for maintaining server lists of a Zookeeper cluster, carrying out connection on the Zookeeper clients and specific machines of the server according to requests of the Zookeeper clients and forwarding the requests of the Zookeeper clients to the specific machines. The proxy device is deployed on the machine in which Zookeeper clients are located and maintains the server lists, so the Zookeeper clients can obtain the server lists in theneighborhood and update own server lists. The Zookeeper clients do not obtain the server lists from the server for updating, so the resource competition problem is avoided, and the problem that the server lists cannot be timely updated due to resource competition can be avoided.

The invention discloses a distributed version management method, device and system, and relates to the technical field of computers. A specific embodiment of the method comprises the following steps: acquiring a message from a message queue; wherein the message comprises a node identifier of the current service node and a local message version; according to the node identifier, intercepting a version field corresponding to the node identifier from unified version information stored in a memory to obtain a global message version; wherein the unified version information comprises version fields corresponding to messages of a plurality of service nodes, and the plurality of service nodes are used for completing the same service; and comparing the local message version with the global message version, if the local message version is higher than the global message version, updating the unified version information, and writing the message into a database. According to the method, the message queue is introduced under the distributed architecture, so that the consumption message can be serialized, the de-locking and unified management of the message version are realized, the database pressure is reduced to the greatest extent, and the concurrent processing capability is improved.

A method and a system for managing applications are provided. Further, the method includes: deploying an application container engine in an edge node; receiving, by the edge node, application deployment information sent by a central node; according to the application deployment information, downloading, by the edge node, an image containing a corresponding application from the central node; calling, by the edge node, the application container engine to load the image, and running, by the edge node, the application in the application container engine; and allocating, by the edge node, available resources for the application container engine.

The invention relates to a GPU (Graphics Processing Unit) time-sharing sharing method and system based on a Kubernetes cluster. The method comprises the steps that a front-end module is arranged in a working node of a Kubernetes cluster, the front-end module is a GPU equipment library installed in a container, and the GPU equipment library schedules use of a GPU in a task by intercepting all APIs related to memory and calculation in a CUDA library; a back-end module is arranged in a working node of a Kubernetes cluster, the back-end module manages tokens between containers and time quotas of the tokens, and time sharing of the GPU is achieved through the tokens and the time quotas of the tokens. According to the method, a GPU time-sharing rule is provided, a GPU equipment library is added into a mirror image to serve as a front end, and a rear-end module is added into a node for control, so that the security and fairness of task execution among a plurality of containers in the node can be ensured.

The invention discloses a method for remotely upgrading GPS vehicle-mounted terminals in a batch mode, which comprises the steps that a monitoring terminal selects GPS vehicle-mounted terminals which need to be upgraded and sends an upgrading request to an upgrading server; the upgrading server sorts the GPS vehicle-mounted terminals to be upgraded according to certain rules and authorizes the GPS vehicle-mounted terminals according to a sorted sequence; and the authorized GPS vehicle-mounted terminals are connected to the upgrading server to download upgrading software to carry out upgrading. According to the invention, upgrading can be carried out on large batches of vehicle-mounted terminals, thereby solving a problem of resource competition, and improving the upgrading efficiency. In addition, sorting information is displayed on the monitoring terminal, thereby being helpful for the monitoring personnel to know upgrading conditions.

The invention discloses a VOIP communication method, a VOIP communication device, VOIP communication equipment and a home gateway system, and relates to the technical field of voice calls in order tosolve the problem that the transmission quality of the voice data stream cannot be guaranteed caused by that the voice data stream and the Internet data stream use a PDN connection together. The VOIPcommunication method comprises: determining a working mode configured by the home gateway system; determining a network registration status of the home gateway system when the working mode is a wireless mode; determining a network registration type of the home gateway system when the network registration state is a successful state; establishing the first dedicated PDN connection when the networkregistration type is the first network type; performing account registration on the external network by the home gateway system according to the established first dedicated PDN connection, and recording the result of the account registration. The VOIP communication method provided by the invention is used for transmitting a voice data stream.

The invention provides a data transmission method, a terminal and a network device, relates to the field of communication, and solves the problems that in the prior art, when a network side WLAN device and a terminal working in an unlicensed frequency band are accessed to a channel, the CMSA must pass through, the realization complexity is high, and the interference elimination effect is poor. Themethod is applied to a terminal and comprises the following steps: acquiring first data which needs to be sent to network equipment through a first wireless access network; wherein the first wirelessaccess network works in an unlicensed frequency band or a shared frequency band; and sending the first data to the network equipment through the second wireless access network. According to the scheme provided by the invention, the second wireless access network is used for sending the data which should be sent through the first wireless access network. According to the embodiment of the invention, the resource competition between the terminal and the network equipment is avoided, so that the network equipment does not need to depend on CSMA and other channel sharing technologies to access the channel or the complexity of the channel sharing technology is reduced, the equipment realization complexity is reduced, the same-frequency interference can be effectively removed, and the channel utilization rate is improved.