124 results about "Page fault" patented technology

Provided in the present application are a memory pre-loading processing method, and a device and a storage medium. The method comprises: a virtual machine manager collecting a plurality of pieces of historical page fault information that are generated by a target application program in a client; on the basis of a plurality of client virtual addresses that are included in the plurality of pieces of historical page fault information, determining a target client virtual address to be accessed when a page fault occurs in the target application program next time; on the basis of the target client virtual address and a storage address of a target client system page table corresponding to the target application program, determining a target host machine virtual address corresponding to the target client virtual address; and controlling a host machine operating system to allocate a target host machine physical address corresponding to the target host machine virtual address, and loading data, which corresponds to the target host machine virtual address, into the target host machine physical address. By means of loading, into a memory in advance, data corresponding to a target client virtual address in which a page fault may occur in the future, an access delay duration caused by the page fault is shortened.

The invention relates to a multi-back-end separated memory system and an optimization control method thereof, the multi-back-end separated memory system comprises an intelligent far memory multi-back-end management control module and a multi-back-end far memory switch, the intelligent far memory multi-back-end management control module analyzes and processes calling of page errors and page switching triggering, and the multi-back-end far memory switch is used for switching the multi-back-end far memory switch. Switching instruction information and parameter regulation and control instruction information are obtained; and the multi-rear-end remote memory exchanger receives and executes the switching instruction information and the parameter regulation and control instruction information, runs applications on the separated memory architecture and the multi-rear-end remote memory software system, and releases resources after running is finished. By supporting a memory exchange strategy and a system architecture of a plurality of heterogeneous far-end separated memory rear ends, parallel access of a plurality of paths of far memories is realized to improve data throughput, application characteristics are analyzed, and intelligent rear end switching and data exchange parameter adjustment are realized; parallel access of a plurality of memory exchange back-end devices, fine-grained parameter configuration of a remote memory data access path, real-time switching of a plurality of memory exchange back-ends and an intelligent control and management method of the remote memory access path can be realized.

A method for performing a remote direct memory access (RDMA) read command includes reserving a memory space in a buffer to receive data associated with an address range, sending a RDMA read instruction to a remote module to request the data, and receiving the data from the remote module. A method for performing a RDMA write command includes receiving from a remote module a request to send command requesting to send data associated with an address range, reserving a memory space in a buffer to receive data associated with the address range, sending a RDMA read instruction to the remote module, and receiving the data from the remote module.

The invention discloses a heterogeneous memory page migration device and method and a readable storage medium, and relates to the technical field of data processing, the heterogeneous memory page migration device comprises a first computing unit, a migration unit and a memory unit, and the migration unit comprises a communicator and a processor; a communicator configured to receive an address translation request; the processor is configured to transmit page contents of a remote page to a local memory frame according to a remote physical frame number in a first page table item when determining that the target page in the address conversion request is the remote page, and replace the remote physical frame number in the first page table item with a local physical frame number; and the communicator is further configured to return the second page table item to the first computing unit, so that the problem of relatively long time consumption when the computing unit accesses a remote page and triggers a page error in the related technology is solved, and the time consumption for migrating the heterogeneous memory page is saved.

The invention discloses a thread scheduling method and device, electronic equipment and a storage medium, and belongs to the technical field of operating systems. The method comprises the steps that a DSM PF event of a virtual machine is monitored, and the DSM PF event is triggered when a plurality of threads access the same shared memory page in a cross-node mode; according to the DSM PF events, an inter-thread incidence matrix is constructed, and the inter-thread incidence matrix is used for quantifying the number of times of triggering the DSM PF events between any two threads; the thread graph structure is divided to generate a thread grouping scheme with the aim of minimizing the number of DSM PF events between different grouping threads, the vertex of the thread graph structure represents the threads, and the adjacency matrix of the thread graph structure is the incidence matrix between the threads.

Embodiments of the present application relate to the technical field of memory management, and in particular to a memory management method, a terminal device, a chip, and a computer-readable storage medium. The method comprises: when a first process is started, applying for a process virtual memory for the first process; when a first thread of the first process is created, determining a memory estimation value of the first thread during running, wherein the first thread is a first thread created for the first process; on the basis of the memory estimation value, determining a first virtual memory for the first thread from the process virtual memory; and establishing a mapping relationship between the first virtual memory and a first physical memory, wherein the first physical memory comprises K physical huge pages, and K is greater than or equal to 1 and is an integer. The technical solution provided in the embodiments of the present application can reduce page faults occurring during running of the first process, reducing the number of times an electronic device applies for a physical memory when trapping to a kernel mode from a user mode, thereby reducing the memory allocation latency, and improving user experience.

The present application discloses a memory management method and an electronic device. The method is executed by an electronic device. In the method, a hardware accelerator detects a first event, the first event indicating that the probability of a page fault occurring in a first DMA memory used by a first application is greater than a first threshold; in response to the first event, the hardware accelerator performs one or more of the following operations: checking and killing a first process of the first application; and writing first data of the first application in a disk into the first DMA memory, and updating a first memory page table, the first memory page table comprising a mapping of a virtual address on the hardware accelerator side to a physical address on the first DMA memory side. During implementation of the present application, the hardware accelerator can handle a page fault that may occur in the DMA memory, thereby improving efficiency of memory management.

The present disclosure relates to systems, apparatuses, methods, and non-transitory computer-readable media including a non-volatile memory and a controller operatively coupled to the non-volatile memory. The controller is to determine information on a number of errors for a page for reading data stored in the page of the non-volatile memory, and the data is read using a first read threshold. The controller is to determine a second read threshold based at least in part on the first read threshold and the number of page errors for the page and apply the second read threshold for subsequently reading data stored on the page according to a decision rule.

A hypercall method and apparatus for a kernel-mode program of an enhanced Berkeley packet filter are disclosed. The method is applied to a virtual machine monitor, comprises: acquiring, in response to a virtualization page fault triggered by the kernel-mode program, a memory address where the virtualization page fault is triggered; determining whether the memory address of the virtualization page fault is consistent with a memory address corresponding to a page fault key in a mapping table; reading, from the mapping table, a page fault value mapped by the page fault key if the memory address of the virtualization page fault is consistent with the memory address corresponding to the page fault key, wherein the page fault value comprises a function type of a hypercall written by the kernel-mode program; and executing, based on the function type indicated by the page fault value, the hypercall of the function type.

A memory management method and module, a chip, an electronic device, and a storage medium. The memory management method comprises: scanning memory pages to which virtual addresses of a discontinuous memory mapping space are mapped to acquire a compressible memory page as a first memory page; compressing memory data in the first memory page to acquire corresponding memory compressed data; storing the memory compressed data in a data storage module, the data storage module being located in memory space outside the discontinuous memory mapping space; after storing the memory compressed data in the data storage module, releasing the first memory page; and setting the corresponding virtual address as a page fault address. The memory utilization is improved.

A memory management unit comprises an interface to receive an address translation request from a device, specifying a first address to be translated, and translation circuitry to translate the first address into a second address, wherein the translation is based on page table information corresponding to the first address. In response to the translation circuitry performing the translation without identifying a page fault associated with the first address, the interface is configured to send an address translation response to the device, the address translation response comprising the second address. The memory management unit comprises page request issuing circuitry responsive to the translation circuitry, in response to the address translation request, identifying a page fault associated with the first address, to issue a page request requesting that the page table information corresponding to the first address is updated to correct the page fault.

Embodiments of the present disclosure provide a data transmission method, a device, a storage medium, and a program product. The embodiments of the present disclosure provide a software-implemented RDMA memory page fault solution: when acquiring data from a remote memory, a remote end maps a page-faulted virtual memory into a specific physical memory region, allows for the occurrence of a memory page fault in an RDMA process, and adds a memory page fault processing flow between a local end and the remote end to implement memory page fault processing; and when writing data into the remote memory, the remote end provides a shared virtual memory and a private virtual memory and exposes the shared virtual memory to the local end, the local end writes data into the shared virtual memory, and then a remote control object migrates the data to the private virtual memory, wherein memory page faults are allowed to occur and be processed during the migration. Since memory page faults are allowed to occur and page fault processing is supported, dynamic allocation of physical memory resources is supported during the RDMA process, thereby improving the utilization of memory resources while leveraging the advantages of RDMA.

The invention discloses a virtual data lake remote file mapping method and system, which are applied to the technical field of data processing, and the method comprises the following steps: creating a proxy file with the same size as a remote file in a local system, and establishing a mapping directory table of the proxy file and the remote file; when a computing node accesses the memory space mapped by the proxy file to trigger missing page interruption, reading corresponding remote data from a remote host according to the mapping directory table and a remote direct memory access technology, and storing the remote data in a memory missing page; two files to be fused are mapped into the same process space at the same time, and data fusion is carried out; through core technologies such as proxy file mapping, missing page drive loading and RDMA transmission, efficient access and zero copy fusion of remote data are realized, and frequent network requests are reduced.

The invention relates to a method for processing a missing page exception, which comprises the following steps of: creating a plurality of processing modules for processing the missing page exception, and enabling the plurality of processing modules to be in a dormant state; when at least one missing page exception occurs in the memory access operation of the computing device, awakening at least one processing module in the plurality of processing modules based on the number of the missing page exceptions in the at least one missing page exception; wherein the number of the missing page exceptions in the at least one missing page exception is greater than or equal to the number of the processing modules in the at least one processing module; the processing modules except at least one processing module in the multiple processing modules continue to be in the dormant state; the at least one processing module is used for processing at least one missing page exception. According to the method, the missing page exception processing efficiency can be improved.

An adaptive, large graph-oriented unified memory management method is proposed; according to the order of priorities of different types of graph data structure in a graph computing application, whether the current GPU memory is full is sequentially determined by means of GPU memory checking; whether the size of current graph data exceeds the available memory capacity of the GPU is determined by means of data overflow checking; and then a unified memory management policy is configured; the method uses different graph algorithms based on the characteristics of graph data structure and the size of the available GPU memory; the method can significantly improve the performance of processing large graphs, which exceed the video memory capacity under a unified memory architecture, including improving GPU bandwidth utilization, reducing the number of page faults and the overhead of processing page faults, and speeding up the execution of graph computing programs.

According to a memory page processing method, after a memory page is allocated to a virtual address that causes a page fault, the allocated memory page is pre-padded with first data, and then the memory page padded with the first data is accessed. Subsequently, if data in the memory page is migrated to a cache, the first data padded in the memory page is also migrated to the cache. If the data in the memory page is evicted from the cache to a memory, the evicted cache data may also include the first data.

A method for processing a page fault in memory access includes: sending a first access request, where the first access request is used to access memory, and the first access request includes a first virtual address; receiving the first access request, and sending a first response, where the first response carries page fault information, and the page fault information indicates a fault type of a page fault corresponding to the first virtual address; and receiving the first response, to process a related access request based on the fault type indicated by the page fault information carried in the first response.

Embodiments of the present specification provide a page table sharing method and a page fault exception processing method, wherein the page table sharing method comprises: in response to an access request of a first process accessing memory, allocating a plurality of virtual memory areas for the first process; for a target virtual memory area in the plurality of virtual memory areas, allocating a shadow virtual memory area, wherein the shadow virtual memory area is used to share a virtual memory area of a second process having the same attribute as the target virtual memory area; and determining a target shared page table corresponding to the shadow virtual memory area. By introducing the design of page table sharing for common shared memory, the process can use the page table sharing function without reserving memory in advance, thereby improving the universality of page table sharing. By allocating a plurality of virtual memory areas for the first process, the coverage of page table sharing is improved, and the introduction of the shadow virtual memory area simplifies the positioning of the shared page table and reduces the page table overhead of the shared memory.

The present application relates to devices and components, including apparatus, systems, and methods for scheduling delivery and execution of page fault or permission fault exceptions. A memory management unit may receive a virtual address associated with an execution mode and initiate a virtual-to-physical translation operation. The MMU may detect a first condition associated with a search of the virtual address in a translation lookaside buffer (TLB). In response to the detection of the first condition, MMU may start a timer. MMU may detect a fault exception associated with the translation operation of the virtual address and determine that a second condition is satisfied. In response to detecting the second condition, the MMU or the reorder buffer exception monitor may deliver the fault exception based on the timer.

Embodiments of the present disclosure are directed to apparatuses, systems, and techniques for a fault resilient transactional processing device for a virtualized system. A request is received at a device connected to a computing system hosting one or more clients to initiate a transaction involving a direct memory access (DMA) operation for accessing data associated with the one or more clients. A page fault associated with execution of a DMA operation of a transaction is detected. A transaction fault handling protocol is selected from a set of transaction fault handling protocols to initiate to address the detected page fault. The selected transactional fault handling protocol is caused to be executed to address the detected page fault.

The invention provides an intelligent freezing method and device for memory repeated and missing pages. The device comprises three components, namely a daemon process, process freezing based on repeated and missing page driving and memory sensing dynamic unfreezing. And the daemon process is responsible for communicating with the system module. And freezing a process to which the background application program causing the repeated missing page belongs based on the process freezing of the repeated missing page drive. Memory aware dynamic thawing maintains a heartbeat in the system. Each heartbeat cycle is divided into two stages, namely a freezing stage and an unfreezing stage. When each period starts, the selected application program is frozen and then unfrozen. And monitoring a memory pressure state. And when the memory pressure is increased, the freezing period is prolonged. Otherwise, shortening. It does not require invasive modifications to mobile applications and hardware infrastructure. The result of experimental evaluation by using real equipment shows that the user experience can be remarkably improved. Specifically, compared with the prior art, the method has the advantage that the frame rate per second is averagely improved by 1.57 times.

The embodiment of the present application provides a computing system, a memory page fault processing method and a storage medium. In the embodiment of the present application, a page fault request service component is added to the pass-through device side, and a page fault request driver is added to the virtual machine management node. The page fault request service component and the page fault request driver cooperate with each other to realize the asynchronous recovery of large-block IO memory page faults corresponding to large-block data, and the pass-through device can asynchronously access the recovered memory pages. Compared with the existing synchronous page fault request recovery method, there is no need to wait for all memory pages corresponding to large-block data to be recovered, which helps to reduce the IO memory page fault recovery time, thereby reducing the delay of the pass-through device accessing memory.

The invention discloses a front-end resource disaster recovery method, electronic equipment, a storage medium and a program product, and relates to the technical field of Internet, comprising the steps of uniformly gathering disaster recovery decision logic from a client to a server, solving the inherent problems of'black box ', difficulty in operation and maintenance and poor consistency of a client scheme, and improving the disaster recovery efficiency. A foundation is laid for constructing an observable and manageable disaster recovery infrastructure; the'health state information 'is combined with the'network address scheduling strategy', so that the failover occurs before the user request is processed; the resource link in the hypertext markup language document is available, so that the performance loss and the experience lagging caused by waiting for overtime loading of the front-end script are eliminated; the uniform resource locators of all the static resources are uniformly replaced in one-time server rendering, so that all the static resources in the page are ensured to be from the same content distribution network address, and page errors caused by mismatching of resource versions are avoided.

The application belongs to the technical field of computer memory management, and discloses an active page replacement method and system based on regional reuse mode identification, which comprises the following steps: working set identification based on memory access sample clustering, obtaining memory access samples by sampling the memory access instructions of a process, and clustering the samples to obtain the working set in the current monitoring window in real time; adaptive memory region division based on working set integration, dividing the address space into regions according to virtual address continuity and adaptively splitting / merging; reuse mode identification based on state transition, determining the reuse mode of each region according to the switching between hot and cold states of each region and the state duration; active page replacement and prefetching method based on the reuse mode, prefeteching the regions that will reach the reuse time, and triggering the replacement of the regions that are in the cooling state for a long time. Compared with the existing passive page fault triggering method, the application can reduce the page fault and jitter, reduce the replacement traffic, and improve the application execution efficiency and system throughput.

The application discloses a memory data management method, an electronic device, a storage medium and a program product, relates to the technical field of storage, and comprises the following steps: realizing memory data management based on a native memory management mechanism and a page fault exception mechanism, processing the physical address of to-be-encrypted data by using a first key through step-by-step encryption, performing exclusive or operation on the obtained first ciphertext and the to-be-encrypted data, and storing the obtained second ciphertext into a red-black tree in a memory space, so that the encryption range is expanded, the data security is improved, the memory space and the red-black tree are fully utilized, and the addition, deletion and modification performance is improved. The target second ciphertext to be migrated is further encrypted and written into a swap area file. The method is realized by using pure software and does not depend on specific hardware devices. The technical problems of poor compatibility, high cost, being not conducive to large-scale application and great influence on system performance are solved, the technical effects of good compatibility, reduced cost, convenience for large-scale application and reduced influence on system performance are achieved.

The present application discloses a page fault handling method, apparatus, device, and storage medium, relating to the field of computer technologies, including: during the startup process of a target process in a target virtual machine, determining whether a page fault is currently triggered; if a page fault is currently triggered, obtaining a free memory page from different storage spaces according to whether the target virtual machine uses standard large pages, and determining whether a cleared flag is set for the free memory page; if the cleared flag is set for the free memory page, skipping the memory page clearing operation, and using the free memory page to map physical memory for the virtual memory of the target process. By clearing the free memory page in advance and setting the relevant cleared flag, the present application determines whether the obtained free memory page has the cleared flag set when a page fault occurs. If so, it indicates that the free memory page has been cleared, thereby reducing the page fault execution time triggered during the startup process of the virtual machine and improving the startup speed of the virtual machine.

The application provides a NUMA system page cache copy management method and system. The application first generates a read-only copy page in the local memory of an access node through the linkage of target file page cache identification, access subject NUMA node information acquisition and policy copy judgment, thereby avoiding cross-node remote memory access. Then, in combination with local copy priority mapping and page fault triggered by unmapping when process node scheduling is changed, the dynamic adaptation of process scheduling behavior and page mapping relationship is realized. Finally, in the read page fault interrupt process, the page mapping update is completed based on the copy strategy, and the association relationship between the node and the access task is recorded. Without damaging the file page cache semantics, the remote access overhead of the multi-NUMA node system file page cache can be greatly reduced, the problem of continuous remote access caused by process node drift can be solved, and the overall file access performance and running stability in the concurrent scenario can be significantly improved.

The invention discloses a page migration method and device, equipment and a medium, and relates to the technical field of computers. A NUMA automatic balancing mechanism optimization scheme is provided, when the access of a target process to a target page triggers a page error, page migration is not directly carried out, and whether the target process is allowed to access the target page or not is judged according to memory page table information, context information, processor information and a preset rule; the migration strategy is dynamically judged and optimized according to a preset rule, so that various different performance requirement scenes can be better adapted; according to the page table item migration method and device, page table item migration of the target page is carried out only when it is confirmed that the target process is allowed to access the target page through the information and the preset rule, additional performance overhead caused by frequent page migration is avoided, and the overall performance and efficiency of a system are improved.

A method for performing a remote direct memory access (RDMA) read command includes reserving a memory space in a buffer to receive data associated with an address range, sending a RDMA read instruction to a remote module to request the data, and receiving the data from the remote module. A method for performing a RDMA write command includes receiving from a remote module a request to send command requesting to send data associated with an address range, reserving a memory space in a buffer to receive data associated with the address range, sending a RDMA read instruction to the remote module, and receiving the data from the remote module.