29 results about "Readers–writer lock" patented technology

The invention relates to the technical field of file storage, and discloses a method and a system for storing multiple concurrent large files. According to the method and the system, the format and the size of a file are verified, a unique file name is generated and used for identifying metadata of a storage file and outputting the file, each small block of the file is divided into a fixed size and is divided into small blocks, a unique identifier is generated for each small block, a database is connected, and the metadata of the file is stored in the database. Then traversing each small block, selecting a storage node for each small block, uploading the small blocks by using multiple threads, setting a request queue, processing file uploading and downloading requests in sequence, avoiding concurrent write-in conflicts of the same file by using a lock mechanism for file uploading, and reading and controlling a read request through a read-write lock; and acquiring the information of the storage file from the database, acquiring each small block by utilizing a concurrent downloading mode, recombining the small blocks into an original file in sequence after downloading is completed, and performing integrity verification after file recombining.

Provided in the present invention are a high-concurrency read-write optimization system for a distributed file system, and a medium and a device. The high-concurrency read-write optimization system comprises: a data read-write concurrency control module, which uses a fine-grained read-write lock to ensure data consistency and high concurrency; a file data cache module, which controls a client system to cache data of a server-side file system; a read-write request delay prediction module, which predicts a running delay of a file read-write request from a client, so as to provide a path optimization scheme; and a read-write task execution module, which ensures read-write performance under a high-concurrency condition by means of simultaneously executing local and remote data read-write operations. The present invention mainly provides a new data read-write optimization system for solving the problem of the performance of a distributed file system constructed on the basis of a non-volatile memory and RDMA technology having a bottleneck regarding a high-concurrency read-write task. The present invention improves the bandwidth utilization rate of a distributed file system for a storage device and a network device, thereby improving the overall performance of a system read-write file.

The invention relates to a hybrid architecture dynamic cache synchronization method based on a high-concurrency scene, and belongs to the technical field of computer Web application development. According to the method, a C + + dynamic link library is loaded when a JavaWeb application is started, and a cross-process cache storage space is constructed by utilizing a shared memory mechanism, so that data sharing among multiple instances is realized. And data interaction between Java and a C + + layer is completed by adopting a JNI interface, so that the Java garbage collection pressure is effectively reduced. Data consistency is guaranteed through an exclusive lock and read-write lock optimization mechanism, cross-instance update notification is realized in combination with event driving or message queues, and transaction type batch update is supported to ensure operation atomicity. A memory mapping file and an efficient data structure are innovatively adopted, the access efficiency is improved and the data copy overhead is reduced by combining a pre-allocation memory pool technology, the system throughput and the response speed are remarkably improved, the performance loss caused by memory fragments and lock competition is reduced, and the method is suitable for mainstream JavaWeb environments such as Spring frames and Tomcat servers.

The invention relates to a directory tree locking method and related equipment thereof, and the method comprises the steps that a locking operation request for a directory tree is acquired, the operation request comprises an operation type and an application node identifier, each layer in the directory tree corresponds to a sequence lock table, the sequence lock table comprises a preset number of read-write lock objects, and the read-write lock objects correspond to the operation type and the application node identifier; the read-write lock object comprises a read-write lock for recording an owner of a writer and a target node identifier corresponding to a node protected by the writer; and based on the operation type, the application node identifier and the target node identifier, executing a locking operation on a read-write lock object corresponding to each layer of nodes in an operation path. Based on the method, resource consumption can be reduced under the condition that memory use is controllable; and releasing the performance of read operation and concurrent write operation.

The invention provides a parasitic parameter extraction method and system for Socket interface multi-task coordination, and belongs to the technical field of parasitic parameter extraction. The method comprises the following steps: acquiring and analyzing an initial configuration file, and creating a read-write lock mechanism of a process pool and a global task coordination table; establishing non-blocking transmission control protocol monitoring, and mapping a Socket connection handle established by the sub-process and the host process to a global task coordination table; executing parasitic parameter extraction by utilizing the screened sub-processes, and generating a parasitic parameter result data packet after the extraction is completed; and performing Hash abstract verification, and if the Hash abstract verification is passed, marking the task corresponding to the parasitic parameter result data packet as completion and recording the extracted parasitic parameter. According to the method, a traditional file synchronization mechanism is replaced based on non-blocking Socket communication and an event-driven model, so that the inter-process communication efficiency is remarkably improved; and by adopting read-write lock hierarchical control and atomic operation, the utilization rate of hardware resources is effectively improved.

A hot upgrade method for a kernel module includes: when a hot upgrade request for a kernel module is triggered, calling a hot upgrade thread in a newly inserted hot upgrade updating module, and obtaining, by using the hot upgrade thread, a read-write lock that is pre-inserted into a basic module in the kernel module, to block first interface address information of a hot-upgradable module in the kernel module from being called, where the hot upgrade updating module includes second interface address information corresponding to each of a plurality of function call interfaces; and calling each function to be hot-upgraded by using the hot upgrade thread, and replacing, for a function call interface corresponding to each function, the first interface address information corresponding to the function call interface with the second interface address information by using the hot upgrade thread, to complete hot upgrade for the kernel module.

The application discloses a configurable read-write priority strategy read-write lock implementation method of an MMU-free embedded real-time operating system, and comprises the following steps: S1, performing strategy binding in a read-write lock creation stage; S2, realizing atomic operation in a middle-off mode; S3, actively eliminating writer starvation in a write priority mode; S4, performing priority inheritance when a write lock is applied; S5, adopting a double-waiting queue separation design; S6, adopting static memory pool zero dynamic allocation; and S7, adopting single-field tri-state encoding to mark a lock state. The configurable read-write priority strategy read-write lock implementation method of the MMU-free embedded real-time operating system realizes lightweight configurable read-write locks of the MMU-free embedded real-time operating system, can support flexible configuration of read / write priority strategies and has zero runtime switching overhead in the whole process, does not need special hardware instructions and MMU context support, and is perfectly compatible with low-end MCUs without exclusive access capability, such as Cortex-M0 / M0+.

The embodiment of the invention discloses a distributed transaction processing system transaction processing method and a computer readable storage medium. According to the method, a lock-free conflict detection mechanism is introduced, on the premise that any read-write lock is not used, writing-writing conflicts, writing-reading conflicts or read-writing conflicts of data item granularity between concurrent transactions are detected, and the three data inconsistency problems of dirty reading, unrepeatable reading and magical reading are avoided. Meanwhile, transactions with reading conflicts are allowed to be executed concurrently, and the concurrency of transaction processing is improved. When a timeout problem occurs, the coordinator and the participants respectively execute different protocol termination processes, so that the coordinator and the participants can be timely and properly processed when faults occur, and the 2PC protocol is optimized. Besides, after the participants enter the submission stage of the transaction submission step, the multi-copy mechanism of the system ensures that the sub-transactions undertaken by the participants are not influenced to execute correct submission or rollback operation even if the participants fail, so that the fault tolerance of the system is ensured.

The present invention discloses a distributed file system renaming operation method based on a read-write lock ring detection mechanism. A central node uniformly processes all ring detection tasks of renaming operations. After receiving a renaming operation request, the central node performs ring detection in a read-write lock manner. The present invention uses a lightweight distributed file system renaming operation ring detection mechanism, which can effectively avoid the occurrence of orphan ring data loss, and effectively improves the concurrency and throughput of the renaming operation through a more fine-grained locking scheme mechanism.

The invention discloses a read-write lock control method and device for an intelligent card and a medium. The method comprises the steps that a global lock manager is created through an application; creating the lock object through an application; the application locks the lock object through the global lock manager to obtain a locked object; under the condition that the application calls the locked object, the locked object is unlocked through the global lock manager to obtain an unlocked object, and the unlocked object represents the object instance in the unlocked state. The global lock manager directly manages the object instance and the read-write lock so as to perform access control on the whole object instance, and the control can be effectively performed no matter the variable is inside or outside the method, or the access is performed through the object instance, so that the application range of the read-write lock in the intelligent card is expanded, and the method can be widely applied to the technical field of data processing.

The present application relates to a locking method for a directory tree, and a related device. The method comprises: acquiring a locking operation request for a directory tree, wherein the operation request comprises an operation type and an application node identifier, each layer in the directory tree corresponds to a sequence lock table, each sequence lock table comprises a preset number of read-write lock objects, and each read-write lock object comprises a read-write lock used for recording a writer owner and a corresponding target node identifier used for recording a node protected by the writer; and on the basis of the operation type, the application node identifier and the target node identifier, executing a locking operation on the read-write lock objects corresponding to each layer of nodes in an operation path.

A processing device maintains locking data including a first portion indicating whether a write operation is updating a data item or awaiting to update the data item, and a second portion indicating a number of read operations accessing the data item. A first read operation to the read the data item is received. a first locking condition is determined to be satisfied using the locking data, representing that no write operations are updating the data item or awaiting to update the data item. Responsive to the determination the first locking condition is satisfied, the second portion of the locking data is atomically incremented to reflect the number of read operations reading the data, and the first read operation to read the data is executed.

The invention discloses a business data caching and reporting method suitable for an internet of things remote terminal, which comprises the following steps of: constructing a persistent cache architecture and initializing: adopting local file mapping as a cache carrier to realize data persistence; circular caching and data adding: managing a plurality of service cache blocks by adopting a circular queue; multi-concurrent sending queue and service routing: designing a multi-concurrent sending queue adaptive to the bandwidth and the processing capability of the Internet of Things terminal, and adaptively selecting a reporting channel according to the service data type; timed scheduling and dynamic timeout processing: realizing real-time maintenance of a sending queue through a timed polling and dynamic timeout mechanism; dual-mode data deletion and cache self-arrangement: realizing automatic arrangement of cache blocks through two deletion modes of temporary recovery and thorough deletion, and hierarchical concurrency control: adopting hierarchical control of a mutual exclusion lock and a read-write lock to distinguish write operation and read operation; the problems of cache data loss, low sending efficiency, resource competition and the like after the terminal is powered off and restarted are solved.

The invention provides a PaaS platform business document number generation method and system based on a lock mechanism, and the method comprises the steps: S1, judging whether a serial number counter in a PaaS platform needs to be reset or not, and selecting to execute a step S2 or a step S3 according to a judgment result; s2, using a numbering model ID as a lock key, applying for a write lock based on the judgment result, and selecting to execute the step S3 or re-execute the step S1 according to a write lock locking result; and S3, taking the number model ID as a lock key, applying for lock reading based on the judgment result, and generating a PaaS platform business document number according to a lock reading and locking result, or re-executing the step S1. Through a read-write lock mechanism, flexible numbering rule configuration and an efficient serial number generation strategy, the problem of service document number generation in a high-concurrency scene is effectively solved, the concurrent processing capacity, accuracy and maintainability of a system are improved, and the method is suitable for various service scenes needing to automatically generate unique numbers.

The embodiment of the invention provides a thread processing method and device, relates to the technical field of computers, and can solve the problem of priority inversion in a read-write lock scene and improve the execution efficiency of threads. The method is applied to the electronic equipment, the electronic equipment comprises a target processor, the target processor comprises a target operation queue, the target operation queue comprises a first thread, a second thread and a third thread, and the method comprises the steps that under the condition that the first thread holds a read lock of a target resource, the second thread enters a sleep state and is not cleared from the target operation queue; under the condition that the first thread releases the read lock of the target resource, the second thread is awakened and holds the write lock of the target resource; after the second thread runs, the third thread runs, and the priority of the third thread is lower than that of the second thread and higher than that of the first thread.

The invention discloses a read-write lock method and system with enhanced read performance, a storage medium and a product, relates to the technical field of high-performance concurrency control, and aims to solve the problem that the read performance of a read-write lock is delayed due to high-frequency atomic operation in related technologies. The method comprises the following steps: constructing a thread read-write lock containing a non-atomic read control word and an atomic write control word for each read-write thread, and storing all the thread read-write locks into a global lock queue for unified management. When the read lock is obtained, the thread only needs to operate the own thread read-write lock, and atomic operation competition between read threads is avoided by checking the atomic write control word and setting the read state in a non-atomic manner. When the write lock is obtained, all thread read-write locks in the global lock queue need to be traversed and locked, so that the data consistency is ensured. According to the method and the device, the read-write lock which is independently written through the non-atomic read operation is constructed, so that the multi-thread read-write lock is constructed, and the delay of read operation performance in a high-concurrency scene is reduced.

The present application discloses a method and device for obtaining thread read-write blocking information, which relates to the field of computing devices, and reduces the professional technical requirements for users while efficiently and accurately obtaining thread blocking information. The specific solution is as follows: obtain the time point when the thread that calls the read-write lock successfully obtains the read-write lock through the probe point registered at the application interface of the read-write lock; determine the holding time of the thread currently holding the read-write lock; if the holding time of the first thread is greater than or equal to the first threshold, output the blocking information of the first thread.

The invention is suitable for the technical field of terminals, and particularly relates to a thread scheduling method, electronic equipment and a computer readable storage medium. According to the method, when it is detected that a first thread requests a target read-write lock in a write mode, a second thread is determined, the second thread is a thread with the target read-write lock in a read mode, and the scheduling attribute of the first thread and the scheduling attribute of the second thread are determined. When the scheduling attribute of the first thread is higher than the scheduling attribute of the second thread, the scheduling attribute of the second thread is set as the scheduling attribute of the first thread, namely, the scheduling attribute of the second thread is improved, so that the second thread can obtain more CPU resources and the like for scheduling, the scheduling speed of the second thread is improved, and the scheduling efficiency of the second thread is improved. Therefore, the second thread can quickly release the target read-write lock, the waiting time for the first thread to obtain the target read-write lock is shortened, the problems that the first thread is blocked for a long time, the electronic equipment is blocked and the like are solved, and the user experience is improved.

The application provides a PaaS platform business document number generation method and system based on a lock mechanism. The method according to the application comprises the following steps: S1: judging whether a serial number counter in a PaaS platform needs to be reset, and selecting to execute step S2 or step S3 according to a judgment result; S2: taking a number model ID as a lock key and applying for a write lock based on the judgment result, and selecting to execute step S3 or re-execute step S1 according to a write lock locking result; S3: taking the number model ID as the lock key and applying for a read lock based on the judgment result, and generating a PaaS platform business document number according to a read lock locking result, or re-executing step S1. The application effectively solves the problem of business document number generation in a high-concurrency scenario by using a read-write lock mechanism, flexible number rule configuration and an efficient serial number generation strategy, improves the concurrent processing capacity, accuracy and maintainability of the system, and is suitable for various business scenarios that need to automatically generate unique numbers.

The invention relates to the field of data processing, and discloses a self-adaptive read-write lock partition optimization method, device and equipment and a storage medium, and the method is used for dynamically adapting to data segmentation cold and hot adjustment and guaranteeing cross-segment writing safety. The method comprises the following steps: continuously collecting real-time access indexes of each data segment protected by a read-write lock; dynamically analyzing and identifying a hot data segment and a cold data segment based on the change trend of the real-time access index in a plurality of continuous acquisition periods; local structure adjustment strategies corresponding to the hot data segments and the cold data segments are generated respectively; adjusting the hot data segment and the cold data segment based on a local structure adjustment strategy, and in the adjustment process, when a cross-segment write operation related to a plurality of data segments is triggered, identifying a target data segment related to the cross-segment write operation, obtaining global locking based on a sequence coordination and failure retry mechanism of a write intention lock, and obtaining a target data segment related to the target data segment; and temporarily freezing the structure adjustment of the target data segment, and uniformly releasing the resources and updating the state after writing is completed.

The present invention discloses an instruction execution method, a computing device, and a storage medium based on a read-write lock. The method includes the steps of: submitting a first storage instruction for storing data in an internal memory to a processor; when the processor cannot normally execute the first storage instruction, generating a second storage instruction according to a data storage exception message; acquiring a write lock and locking the process of executing the storage instruction; storing data in the internal memory by executing the second storage instruction through the processor; when receiving a first read instruction for reading data in the internal memory, acquiring a read lock; if the write lock is occupied and the read lock cannot be acquired, then acquiring the read lock again; if the read lock is acquired, locking the process of executing the read instruction; and reading data from the internal memory by executing the first read instruction through the processor. The present invention can prevent the atomicity of data access from being lost, thereby avoiding abnormal operation problems of certain special application programs.

The present invention provides a high-concurrency read-write optimization system, medium and device for a distributed file system, including: a data read-write concurrency control module that uses fine-grained read-write locks to ensure data consistency and high concurrency; a file data caching module that controls data caching of the client system for the server-side file system; a read-write request latency prediction module that predicts the runtime latency of file read-write requests of the client to provide a path optimization scheme; and a read-write task execution module that ensures read-write performance under high-concurrency conditions by simultaneously executing local and remote data read-write operations. The present invention mainly addresses the performance bottleneck problem of a distributed file system built based on non-volatile memory and RDMA technology when facing high-concurrency read-write tasks, and proposes a novel data read-write optimization system. The present invention improves the bandwidth utilization rate of the distributed file system for storage devices and network devices, thereby enhancing the overall performance of the system for reading and writing files.

This invention provides a file read / write method, apparatus, and device in a distributed file system to solve the technical problem of low file read / write performance caused by snapshot lock mutual exclusion contention in distributed systems. Without snapshot processing, this invention allows ordinary read / write IO to acquire only the read / write lock of the parent directory of the file being read / written, effectively reducing mutual exclusion lock contention and IO latency involved in snapshot processing. Furthermore, to ensure the reliability of snapshot services, a pre-check process is added to the snapshot configuration process. This pre-check process ensures that no read / write requests acquiring non-full path snapshot locks begin snapshot processing. This invention reduces mutual exclusion contention for snapshot locks in MDS, improves file read / write performance in distributed file systems, and guarantees the reliability of snapshot configuration.

The present invention provides a read-write lock implementation method, device, electronic device and storage medium, which relates to the field of communication technology. The read-write lock implementation method includes: pre-defining a data structure of the read-write lock, wherein the data structure at least includes a counter, wherein the count value of the counter is used to characterize the number of processes holding the read lock; in the case of receiving a read lock operation request, judging whether the current process has a write lock operation, and obtaining a write lock operation judgment result; based on the write lock operation judgment result and the atomic logic processing of the counter in the data structure, completing the read lock operation. The performance consumption in the process of read lock adding operation and read lock releasing operation is reduced, and the read concurrency capability is improved.

The application relates to the computer field and discloses a process lock holding detection method, an electronic device and a readable medium. The process lock holding detection method comprises the following steps: determining that a first process of the electronic device is in a process state satisfying a system protection triggering condition, and the first process is waiting for using a read-write lock of shared memory of the electronic device; selecting a plurality of second processes from a thread group in which the first process is located, wherein the second processes are not waiting for the read-write lock and are in a lock holding process state; and saving process information of the plurality of second processes. Therefore, by using the process lock holding detection method, the number of process stacks printed by the final kernel is greatly reduced, the workload of the developer for troubleshooting is greatly reduced, and the lock holding process can be accurately positioned.

The invention provides a system operation parameter safety management method which specifically comprises the following steps: S1, parameter modular design: system operation parameters are split into independent sub-parameters according to functions, each sub-parameter is managed by an exclusive internal class, and an external module needs to be accessed through an interface function; and S2, intelligent pointer memory management: using std:: sharedptr to allocate parameter memory, and automatically managing the memory through reference counting. When parameters are updated, new memories are allocated by creating new intelligent pointers, and old parameter memories are automatically released only after reference counts return to zero; s3, design of a read-write lock mechanism: adopting a read-write lock, allowing multi-thread concurrent reading, exclusively locking during writing, and balancing performance and safety; and the like. According to the system operation parameter security management method, the data stability and the memory security can be improved, and the system performance in a multi-thread environment can be improved.

This application discloses a read-write lock control method, apparatus, electronic device, and storage medium. The method includes: receiving a write lock request from a first thread, where the first thread is in a lock-waiting state; receiving a read lock request from a second thread, where the second thread is also in a lock-waiting state; if the importance of the second thread is higher than that of the first thread, processing the read lock request to ensure the second thread successfully acquires the read lock. By responding first to read lock requests from threads with higher priority, the throughput of read locks can be improved, effectively reducing thread read lock stalling issues.

The application relates to the technical field of vehicles and discloses a vehicle-mounted display control method and device, electronic equipment and a storage medium. The method comprises the following steps: in response to the initialization of a read-write lock, a global context and a flow state, starting a data flow of a corresponding device after registering a callback thread of at least one vehicle-mounted image acquisition device; in response to the callback thread of any vehicle-mounted image acquisition device being triggered, generating a local snapshot of a global device handle to obtain a local copy, then acquiring a read lock and holding the read lock within an update period of a global flow state identifier; in response to the update of the global flow state identifier being completed, releasing the read lock and performing a callback exit operation or a whole-process lock-free vehicle-mounted display operation based on the validity of the local copy; and in response to the execution of the callback exit operation or the vehicle-mounted display operation being completed, entering the second step after the next callback thread is triggered until an anti-initialization thread is triggered. The application optimizes the lock mechanism and can improve the stability of mass-produced vehicles.

The invention provides a method and a device for realizing a read-write lock based on ETCD and a storage medium. The method comprises the following steps: under the condition that a request of a read lock or a write lock sent by a target client to an ETCD cluster in an ETCD transaction mode is received, starting an ETCD transaction, and creating a read-write lock lockKey; under the condition that the read-write lock lockKey is successfully created, whether the version number of the read-write lock lockKey is 1 or not is determined, under the condition that the version number of the read-write lock lockKey is determined to be 1, an auxiliary key is created, and if the version number of the read-write lock lockKey is 1, it is represented that the target client successfully obtains the read lock or the write lock; and setting the mode of the auxiliary key as a target mode so as to realize a read lock operation or a write lock operation of the target client. A read lock request and a write lock request of the client are realized by utilizing the ETCD transaction and the double-key value, so that the process of acquiring the read lock and the write lock by the existing client related to the ETCD is simplified.