105results about How to "Reduce performance overhead" patented technology

The invention relates to the technical field of computer application, and discloses a file read-write event monitoring method under an eBPF, which comprises the following steps: initializing an eBPF program, generating a kernel mode byte code and a user mode byte code, loading the kernel mode byte code into a kernel, and carrying out instrumentation in a file operation function to monitor file operation; initializing a preset buffer area for communication between a kernel mode and a user mode, and storing a file identifier of a to-be-monitored file in an eBPF mapping table; and when a file operation function is called, reading kernel structure body information, obtaining an identifier of an operated file, matching the identifier with the identifier in the mapping table, if the matching fails, discarding an event, and if the matching succeeds, judging that the file is in a monitoring range. Therefore, the monitoring of the file read-write event under the eBPF is realized.

The embodiment of the invention discloses a taint analysis method and device, computer equipment and a storage medium, and belongs to the technical field of information security. In the application, the coprocessor of the computer equipment comprises a plurality of registers, and the plurality of registers not only can be used for storing stain information corresponding to a plurality of general registers in a main processor of the computer equipment, but also can be used for storing stain information corresponding to a program memory space of a target program currently executed by the main processor. Therefore, when the coprocessor performs taint propagation on the first instruction, the taint information of the operand of the first instruction can be accessed by accessing the plurality of registers, and compared with the mode of accessing the taint information by accessing a memory, the operation is simpler, the speed is faster, and the performance overhead is smaller.

The invention aims to provide an efficient memory allocation and recovery method for an Android device, and relates to the technical field of memory processing, the method comprises the following steps: step 1: obtaining running data of the Android device, and calculating a memory state entropy based on the running data; calculating a memory fragment risk degree in combination with the priority matrix and the operation data; 2, calculating a memory allocation dynamic threshold according to the memory fragmentation risk degree; calculating a self-adaptive memory compression rate; step 3, using a self-adaptive memory compression rate to compress memory data which is not used by the Android device at present; the page number of the activity process is lower than the set minimum page threshold value; 4, if the memory fragmentation risk degree exceeds a set fragmentation threshold value, the Android device executes memory fragmentation; and averagely distributing the residual memory capacity to all the active processes. According to the invention, accurate allocation and efficient recovery of memory resources are realized.

The invention discloses a storage and calculation integrated architecture data layering method and system oriented to a calculation-intensive system, and the method comprises the steps: setting a control module, and carrying out the redirection of a part of file data corresponding to a concurrent read-write task based on the control module; a file pre-retrieval module is set, data attributes of the file data are distinguished according to file types on the basis of the file pre-retrieval module, and the data attributes comprise cold data and hot data; and migrating and storing the file data based on the determined data attributes. According to the method, the overall performance of the mixed medium storage system under the compute-intensive task can be optimized, cold and hot data can be dynamically identified, and the performance overhead caused by data migration is reduced.

The invention discloses a federated learning contribution degree evaluation method and device, electronic equipment, a medium and a product, and relates to the technical field of federated learning, and the federated learning contribution degree evaluation method comprises the steps: obtaining an initial global model, and sending the initial global model to each client in a preset client set; performing federal iteration training on the initial global model based on a received local model uploaded by each client in a preset client set, and determining an overall global model; performing federal iteration training on the initial global model based on received local models uploaded by clients except the to-be-evaluated client in a preset client set, and determining partial global models; and determining the contribution degree of the to-be-evaluated client according to a performance difference value between the overall global model and the partial global model. According to the federal learning contribution degree evaluation method provided by the invention, the calculation complexity of the contribution degree is reduced, and the time consumption and the calculation resource demand are reduced.

The invention belongs to the technical field of cloud computing, and discloses a lightweight multi-domain hyper-fusion platform construction method compatible with heterogeneous hardware resources, which adopts a lightweight hyper-fusion platform architecture compatible with the heterogeneous hardware resources, converts physical resources into virtual resources on a virtual machine based on a KVM (Kernel-based Virtual Machine), shields the difference of underlying hardware, and improves the performance of the platform. According to the method, heterogeneous storage resources are integrated based on Ceph, and storage devices of different manufacturers are integrated into a unified storage pool through a distributed storage technology without being limited by types of bottom hardware devices. Through the SDN technology, the OpenStack network service can decouple a network control plane and hardware, and unified management of different network devices is realized. Through a virtualization technology and an automatic management tool, a simplified elastic expansion solution is provided, and changes of resource demands are easily coped with.

The invention provides a zero-copy rapid transceiving device, a data sending method and a data receiving method, and relates to the technical field of network communication, the zero-copy rapid transceiving device comprises a network card in which a direct memory access controller and an associated annular cache region are configured; the kernel protocol stack is configured with a data cache structure body, and a data pointer of the data cache structure body and a packet descriptor of the annular cache region are configured to point to the same memory region; when the network card receives external data, the direct memory access controller copies the data to the memory area according to the direction of the packet descriptor so that the data can be processed by the kernel protocol stack, and when the kernel protocol stack sends the data, the data is copied to the memory area according to the direction of the data pointer so that the data can be sent by the direct memory access controller. The method has the beneficial effects that data copying is not needed in a driving layer message data processing process, so that storage resources are effectively saved, the load of a CPU (Central Processing Unit) is reduced, and the network bandwidth and the system performance are effectively improved.

The invention relates to the field of network page updating, and discloses an efficient front-end code real-time updating method and device and a storage medium, and the method comprises the following steps: initializing a front-end item; a partition recognition method is adopted for front-end items, and the dependency relationship between the items is divided into a plurality of sub-graphs; performing code operation identification on the front-end items by adopting a code analysis tool, and performing operation classification; selecting corresponding updating mechanisms according to different operation classifications; in combination with an incremental compiling method of Webpack and Vite, code incremental compiling is realized through module dependency graph optimization and enhanced analysis; carrying out real-time hot updating on the codes by adopting a multi-level differential hot updating method; and a cache control mechanism is introduced, so that front-end resources are updated in time when codes are subjected to real-time hot update. According to the method and the device, the front-end page updating efficiency and accuracy are improved.

The invention discloses an RISC-V context switching optimization method and device and a medium, and belongs to the technical field of processors. The method comprises the steps of executing a current task based on the computing core; when a context switching operation is triggered, determining the residual space of the register stack based on the numerical value of the stack top register; judging whether the register stack can store the current task or not based on the residual space and the current task; if not, storing the current task based on the memory; if yes, storing the current task based on the register stack; and executing a replacement task based on the computing core, and switching back to the current task through the stack top register when the replacement task is completed. According to the method, the effect of improving the context switching speed in the RISC-V is achieved.

The embodiment of the invention discloses a video coding information extraction method and device, electronic equipment and a storage medium, and the method comprises the steps: obtaining a video file generated by carrying out the image collection coding of a display change target through a camera, and enabling the image change frequency of the display change target to be greater than or equal to the image collection frequency of the camera; target area extraction is carried out on image frames of the video file frame by frame, image comparison is carried out on target areas of two adjacent image frames in sequence, and the target areas are imaging areas of display change targets in the image frames; and counting parameter information of the image frames in the video file in the preset range, wherein the counting dimension of the parameter information at least comprises the number of the image comparison results which are the same. The camera sends the generated video file to the external device for detection, and the detection process is completed on the basis of local comparison of the adjacent image frames of the video file, so that the performance overhead of the camera is reduced, and the accuracy of coding quality detection is improved.

The invention relates to the technical field of Internet of Vehicles, and discloses a vehicle end data processing method, a monitoring system, a domain controller, a medium and a product. The method comprises the following steps: acquiring a data packet monitoring program corresponding to a vehicle end network and an original socket; loading the data packet monitoring program to a kernel mode space, and binding the data packet monitoring program with the original socket to obtain a target socket; and monitoring each network data packet passing through the target socket, filtering out the target data packet from each network data packet by using the data packet monitoring program, and reading data in the target data packet to the user mode space. By implementing the technical scheme of the invention, memory resources are saved, the performance overhead is saved, the flexibility of data packet filtering is improved, the running stability and running safety of the vehicle-side operating system are improved, and the running effect of the vehicle-side operating system is ensured.

The present invention provides a data encryption storage method based on the national secret algorithm, which belongs to the field of data security. The present invention includes four parts: the issuance of the agreed key, the generation of the master key, the generation of the data key, and the data encryption; the key management service is the key life cycle management center, which is responsible for the centralized management of the key. The key cannot be obtained from the outside, and the data key can be derived from the master key for use; the encryption and decryption of the data is realized locally by securely transmitting the data key. The risk of data storage is reduced and the security of the encryption key is improved.

The invention discloses a compiling method for compiling a C language source code into an RISC-V assembly code. The method comprises the following steps: acquiring a C language source code; performing lexical analysis on the C language source code to generate a mark flow; performing syntactic analysis on the mark flow, and constructing an abstract syntax tree; performing semantic analysis on the abstract syntax tree to generate a target abstract syntax tree; constructing a runtime environment of the RISC-V assembly code; generating an intermediate code and a control flow diagram corresponding to the intermediate code according to a rule in the runtime environment and the target abstract syntax tree; generating a target code by using the intermediate code and the control flow diagram corresponding to the intermediate code; according to the technical scheme, the intermediate representation more adaptive to RISC-V custom instruction mapping can be generated, so that the execution efficiency of assembly codes is improved; and meanwhile, by designing a lightweight runtime environment, the performance overhead is further reduced.

The invention provides a virtual object control method and device, electronic equipment and a readable storage medium, and the method comprises the steps: providing a game scene corresponding to a game match in response to a match start instruction, and the game scene comprises a first game role and a second game role which respectively play a first game identity; in response to the situation that the first game role in the game scene is corrupted by the second game role, the first game role is controlled to be converted into the second game identity from the first game identity, so that the first game role continues the current game with the second game identity. Therefore, the data processing amount of the server can be reduced, and the performance overhead of the game server can be reduced. Meanwhile, for the player controlling the first game role which is corrupted, the player cannot quit the current game immediately after being corrupted, the chance that the player continuously participates in the current game to corrupt the second game role to pick up falling materials can be obtained again, and the game experience of the player is further improved.

The embodiment of the invention provides a memory leak detection method and device, equipment and a storage medium, and relates to the technical field of operating systems and performance tuning. The method comprises the following steps: monitoring memory allocation and release operation of a process by adopting a probe program; collecting memory use information of a stack of the process on memory allocation and release operation; through a collaborative caching mechanism of a kernel mode and a user mode, sharing memory use information to the user mode, and analyzing the memory use information in the user mode to obtain a comprehensive hotspot score representing a memory occupation growth trend of a stack; and determining whether the stack has memory leak according to the comprehensive hotspot score. Based on the method, whether the memory leaks or not can be accurately detected under the condition of low performance overhead.

According to the method for automatically acquiring the map tag of the AGV chassis, the solution of automatically acquiring the map tag and updating the map routing information is provided, so that the AGV positioning and navigation efficiency is improved on the premise of ensuring no error, and relatively high compatibility is realized. Comprising the following implementation steps: step 1), receiving an instruction; step 2), performing initialization; step 3), traversing routing points and planning a moving trajectory; step 4) calculating a chassis pose and updating positioning information; 5) updating the map; and step 6), judging whether the routing point information is updated or not.

The present application discloses a rendering method, device, electronic device and readable storage medium, the method comprising: receiving a terrain prosthesis generated according to real terrain, and generating the material and texture of the terrain prosthesis, wherein the terrain prosthesis is a static grid; dividing the scene to be rendered into near-view terrain and far-view terrain according to the position information of the target virtual character in the scene to be rendered; generating a level model according to the real terrain corresponding to the near-view terrain; merging the level model with the terrain prosthesis to achieve the rendering of the scene to be rendered. The present application uses less memory, reduces the frequency of IO, and achieves a balance between effect and performance overhead while ensuring far-view effect and terrain effect; for players, based on the different performance of players' mobile devices, the memory and performance overhead are reduced as much as possible while ensuring a relatively ideal effect, which greatly improves the gaming experience.

The invention discloses a digital content object generation method and device, relates to the technical field of game development, and mainly aims to solve the problem that the existing digital content object generation efficiency is low. Comprising the steps that under the condition of a visual game development environment, in response to a target digital content object creation instruction at a development node, the development node is determined; target digital content object information is obtained, a digital content object pool corresponding to the target digital content object information is obtained based on a digital content object pool manager, and the digital content object pool manager is used for conducting at least one management operation of creating, obtaining and recycling on the digital content object pool. The digital content object pool is used for performing at least one management operation of creating, using and destroying on a digital content object data container, and the digital content object data container comprises a digital content object and a script code associated with the digital content object; and determining a target digital content object data container from the digital content object pool, and generating a target digital content object at the development node based on the target digital content object data container.

The invention relates to a self-adaptive management method and system for a database plan cache, and the method comprises the steps: firstly judging whether the plan cache is hit or not after a database receives an SQL statement, and triggering a hard analysis generation plan and caching the plan when the plan cache is not hit; if the cache is hit, further judging whether a corresponding multi-execution plan exists or not; and when only a single execution plan exists, analyzing the relationship between the number distribution of execution tuples and the number of execution times by adopting an execution efficiency algorithm to dynamically judge whether the data is inclined. And when a plurality of execution plans exist, entering a multi-plan cache management stage, selecting the execution plans according to a matching result of the current binding variable predicate selection rate and the cache plan historical selection rate, and generating and caching a new plan when the matching fails. According to the method, the data skew is accurately identified by executing the efficiency algorithm, intelligent matching and multiplexing of plans are realized by means of a multi-plan cache management mechanism, and the overall performance of the database in a data skew scene is improved.

The invention discloses a method for preventing a user helper privilege lifting attack based on a Linux Capability mechanism, and belongs to the field of system security. According to the method, under the root permission, starting from a calling function of a user helper, a key position is found, permission check is added to the key position, a new capabilistic is defined in a header file, meanwhile, the new capabilistic is granted to the trusted user helper, and finally whether an executed program has the permission or not is checked. According to the defending method for the privilege lifting attack, extra hardware support is not needed, only a Linux kernel code needs to be slightly changed, the existing capability permission is ingeniously utilized, and the currently popular novel privilege lifting attack which is carried out by utilizing a user helper is effectively blocked.

The disclosed embodiments relate to a text processing method, apparatus, device and medium, wherein the method comprises: obtaining at least two display attribute sets corresponding to the text to be displayed; each display attribute set corresponds to characters with the same display effect; segmenting the text to be displayed according to the characters corresponding to each display attribute set to obtain at least two text segments; wherein the characters in each text segment correspond to the same display attribute set; based on the display attribute set corresponding to the characters in each text segment, drawing processing is performed on each text segment to obtain a drawing processing result corresponding to each text segment; according to the position of each character in each text segment in the text to be displayed, each drawing processing result is spliced ​​to obtain a text drawing result. The disclosed embodiments can reduce the consumption of device resources in the text drawing process and reduce the performance overhead of text display in the device.

This invention discloses a fuzz testing method based on program termination points, comprising: inserting breakpoint instructions at the entry point of each basic block of the module under test; constructing a set of mutation seed files based on an initial seed file set, and providing each mutation seed in the set to the program under test for testing; loading an auxiliary tracing module in the debugger, recording the sequence of basic blocks executed by the program under test through a breakpoint tracing mechanism, and determining the termination basic block; triggering potential vulnerabilities in the program under test through continuous testing; simultaneously optimizing the seed mutation strategy based on coverage; during test execution, when the program under test triggers a debugging exception or a crash signal by executing a breakpoint instruction, the debugger pauses the execution of the program under test and resumes the original instructions; after the breakpoint handling is completed, the execution of the program under test is resumed, allowing it to continue running until the next breakpoint is encountered or execution ends; the test is completed when the test process reaches the preset termination conditions, and a test report is generated.

The embodiment of the invention provides a debugging method and device, electronic equipment, a storage medium and a computer program product, the debugging method is applied to a processor, the debugging method comprises the steps that an insertion enable signal is acquired, and the insertion enable signal is used for indicating an instruction fetching position of the processor; under the condition that the insertion enable signal is the first enable signal, taking out an original instruction from a target buffer area of the processor, and executing the original instruction; wherein the first enable signal represents that the processor fetches an instruction from a target buffer area, and the target buffer area is used for storing an original instruction at a target address where the breakpoint instruction is inserted.

The invention provides a video playing method and device, electronic equipment and a storage medium, and relates to the technical field of video playing. The method comprises the following steps: after a video player is started by a client, creating a shared memory block based on configuration information of a to-be-played video from the client; the video player obtains a video stream of the video to be played according to the configuration information, decodes the video stream to obtain a decoded video stream, and writes the decoded video stream into a shared memory block; and the client accesses the shared memory block and renders the decoded video stream to play the to-be-played video, so that additional IO operation or memory copying is not needed, time delay and performance overhead are reduced, and the performance and stability of the PC end video player are improved.

The invention provides a GPU access data tracking method and system based on kernel parameter analysis and instrumentation verification, and the method comprises the steps: carrying out the kernel instrumentation step: carrying out the instrumentation of target kernels one by one, and generating the kernels after the instrumentation; an access data prediction step: analyzing parameters of the kernel to be started, predicting a video memory range modified by the kernel, and calling the kernel after instrumentation to verify a prediction result; an access data updating step: updating an access data tracking result according to the verification result; if the verification is passed, adding the prediction range to the access data range; and if the verification is not passed, updating the access data to be the whole allocated video memory range. According to the invention, the method does not depend on hardware support provided by a GPU manufacturer, such as a hardware access bit and a matched drive program; and a prediction and verification method is adopted, so that the performance overhead caused by instrumentation during operation is reduced, and the method has a wide application prospect.

A method comprises detecting execution of a fork() operation in a cryptographic computing system that generates a parent process and a child process, assigning a parent kernel data structure to the parent process and a child kernel data structure to the child process, detecting, in the child process, a write operation comprising write data and a cryptographic target address, and in response to the write operation blocking access to a corresponding page in the parent process, allocating a new physical page in memory for the child process, encrypting the write data with a cryptographic key unique to the child process, and filling the new physical page in memory with magic marker data.

The application relates to a data packet processing method and device, computer equipment, a storage medium and a computer program product. The method comprises the following steps: obtaining a storage unit identifier from an idle address index, storing a data packet in a storage unit corresponding to the storage unit identifier in a data buffer, recording a channel identifier of the data packet, and storing the storage unit identifier in a channel index corresponding to each target sending channel according to the channel identifier; obtaining the storage unit identifier from the channel index corresponding to a current sending channel, reading the data packet from the corresponding storage unit according to the storage unit identifier and sending the data packet through the current sending channel, deleting the current sending channel from the channel identifier, and recycling the corresponding storage unit identifier to the idle address index when the target sending channel does not exist in the channel identifier. The method can improve the buffer utilization rate in the multi-channel data packet forwarding process and avoid storage space waste.

The invention relates to an image processing method and device, a medium and electronic equipment, belongs to the technical field of computers, and can realize regional color change at low cost. The image processing method comprises the steps that a to-be-processed image is received, and the to-be-processed image comprises a target area of which the color needs to be changed; converting an original color channel sequence of the to-be-processed image into a target color channel sequence to obtain a first intermediate image; an image processing model is adopted to carry out stylization processing on an area, corresponding to the target area, in the first intermediate image, a second intermediate image is obtained, and the color of the area, corresponding to the target area, in the second intermediate image is different from the color corresponding to the target color channel sequence; the color channel sequence of the second intermediate image is restored to the original color channel sequence, a target image is obtained, and the color of an area corresponding to the target area in the target image is different from the color of the target area in the to-be-processed image.

The invention discloses a high-modulus grid surface reduction optimization method and application thereof in cruise ship decoration engineering modeling, a point cloud grid high modulus is obtained through three-dimensional laser scanning reverse modeling, surface reduction is implemented through an edge folding algorithm based on geometric errors, the algorithm execution efficiency is high, and the method is suitable for large-scale popularization and application. The number of grids is greatly reduced while details are reserved, and the polygonal broken line feeling of the grids in the visual effect after surface reduction is effectively solved through unique grouping rendering. In addition, a parameter setting and grouping rendering method of three-dimensional laser scanning reverse modeling on the cruise ship is combined, and a set of model high-quality and light-weight solution is provided for cruise ship decoration engineering modeling based on high-modulus grid reduction optimization.

The application discloses a service request processing method and device, electronic equipment and a storage medium. The method creates an independent counting unit for each time window, and destroys the counting unit associated with the target time window if the life cycle of the time window ends. In this way, the service requests of a preset type in each time window can be counted independently, and only the number of service requests of the preset type needs to be accumulated, without performing the complex and error-prone deduction operation in the conventional technology. On the one hand, since the data deduction operation is saved, the implementation complexity and performance overhead of the system are reduced, and the stability and reliability of the system are enhanced. On the other hand, in a high-concurrency environment, the system only needs to process the number accumulation process of the service requests of the preset type, reduces the competition for resources of the data accumulation and data deduction processes, and improves the accuracy of the counting result and the system state determination.