39results about How to "Guaranteed read and write performance" patented technology

The invention discloses a hybrid main storage architecture based efficient dynamic page scheduling method applied to a memory controller of a horizontal storage architecture which comprises a first storage medium and a second storage medium. The hybrid main storage architecture based efficient dynamic page scheduling method comprises the steps of configuring an access list respectively in each storage medium; configuring a stack respectively for each storage medium in the memory controller; carrying out dynamic management fore recently accessed pages in the storage medium based on the page state records recorded in the stack and the reading-writing access time recorded in the access list, placing the pages with high writing hot-degree in the first storage medium, storing the frequently read pages in the second storage medium, wherein the first storage medium is a DRAM, and the second storage medium is NVM. The hybrid main storage architecture based efficient dynamic page scheduling method can master the historical access information more precisely to adapt to the application scenes with relatively weak locality, can greatly reduce frequent and ineffective page migration quantity between the hybrid memory mediums, and can improve the utilization rate and the access hit rate of a main memory.

The invention is applicable to the field of data security, and provides a solid state hard disk data encryption and decryption method and a solid state hard disk system. The data encryption and decryption method comprises the following steps that a host computer generates a public key and private key pair (k1, k2) based on the asymmetrical encryption algorithm; the private key k2 is stored into a solid state hard disk, and the public key k1 is stored into the host computer; a secret key k3 based on the symmetrical encryption algorithm is generated at the host computer, and the secret key k3 is stored into the solid state hard disk after being signed and encrypted through the private key k2; during the system initialization, the host computer decrypts the secret key k3 encrypted by the private key k2 in the solid state hard disk through the public key k1, a plaintext secret key k3 is obtained, and the solid state hard disk realizes the encryption / decryption on data in the solid state disk through the plaintext secret key k3; when the system is powered off or the computer is powered off, the plaintext secret key k3 is deleted, and in addition, the plaintext secret key k3 cannot be accessed by other programs during the system operation. Therefore, the solid state hard disk data encryption and decryption method and the solid state hard disk system have the advantages that the data encryption intensity and the data security of the solid state hard disk can be improved, and in addition, the reading and writing performance of the solid state hard disk is ensured.

The invention discloses a secure storage platform for data. The secure storage platform for data comprises an authentication server, a secure key management server, an application server and a distributed cluster, wherein the authentication server is connected to a client and used for performing security verification on an access request after the access request is sent to the distributed cluster by the client; the secure key management server is connected to the authentication server and used for managing a file key so as to assign a private key of the file key to the designated client; the application server is connected between the distributed cluster and the client and is taken as an access agent of the client to access the distributed cluster; the distributed cluster is connected to the application server and is used for storing cloud data, and the application server is allowed to access the distributed cluster after the authentication server judges that the client is the designated server according to the private key and the access request. According to the technical scheme, the security of the storage platform is improved on the premise that expansibility, economic efficiency and effectiveness of the platform are guaranteed.

The embodiment of the present invention discloses a data buffer device, a data storage system and a method. The data buffer device is connected to a data processing apparatus through a data interface. The data buffer device includes: a controller, and a memory connected with the controller. The memory is used for caching the hotspot data in a hard disk connected to the data buffer device, and the controller is used to read and write data into the memory according to the requestsof the data processing apparatus. By using the present invention, not only the data read and write performance can be enhanced, and also the waste of system resources can be prevented.

The invention relates to a data storage method which includes the steps of merging and storing data written at random in an SSD; writing the data written in the SSD into an array RAID set. After the embodiment is applied, the data written at random are recorded through the SSD, the data are then written into the array RAID set at a time, and the reading-writing performance of an RAID5 is further guaranteed.

The embodiment of the invention provides a database routing method which is applied to a database. The database comprises multiple database nodes. A database routing device is introduced to the method to provide route scheduling of the database, and the method comprises the steps that the database routing device receives a data routing information query request sent by an application, wherein the data routing information query request contains data types; the database routing device determines database nodes corresponding to the data types according to the data types; the database routing device sends data routing information query response to the application, wherein the data routing information query response contains identifier information of the database nodes. The database routing method performs route scheduling of the database by introducing the database routing device so that the relational database can be expanded in a distributed mode. Accordingly, the reading-writing performance of the database is ensured under the situation of increase of a large amount of data.

The invention discloses a data storage method, device and system, computer equipment and a storage medium, and the method comprises the steps: processing a write-in request of to-be-stored data in a memory, and caching the to-be-stored data in the memory; when the data cached in the memory reaches a first preset threshold value, converting the to-be-stored data in the memory into a multi-layer matrix array with an index, and storing the multi-layer matrix array in a storage layer of a matrix storage structure preset in the nonvolatile storage equipment; and when the data in the nonvolatile storage device reaches a second preset threshold value, performing merging processing on the data stored in the nonvolatile storage device, and writing the data into the next layer of the merging tree structure. According to the inventionmethod, the read-write performance of the system can be ensured, and the space size of each layer is increased, so that the write-amplification performance cost of the system caused by the multilayer log structure tree structure is solved, and the system fluctuation and the pause delay are reduced.

It is an RFID testing method, using the determined coding instructions to modulate the RF signal generator carrier, assuring that under the rated output power, in accordance with RFID working frequency range to scan, and meanwhile modulating the carrier signal according to the RFID protocol, the oscillograph sends the time-domain signal peak received by its sensing antenna to PC, and PC converts the time-domain signal frequency into the frequency-domain signal, and thus it can detect RFID dynamic resonance peak and bandwidth, ensuring the reading and writing performance after RFID mass-production.

The invention provides a video file processing method and a device, and relates to the technical field of information processing, and the method comprises the steps: determining idle data blocks in adisk of a file system according to file attributes stored in a memory; determining the number of data blocks required by the to-be-stored video file according to the size of the to-be-stored video file; determining a target data block from the idle data blocks according to the number of data blocks required by the to-be-stored video file; and storing the to-be-stored video file into the target data block, and updating the file attributes recorded by the file index unit of the block group where the target data block is located and the file attributes loaded from the file index unit of the blockgroup where the target data block is located in the memory. A disk of the file system is divided into a plurality of block groups, and each block group comprises an index area and a data area, so that segmented storage of the index area and the data area of the file system is realized, the access performance of the data area in the whole file system is prevented from being influenced by damage ofa certain index area, and the use performance of the file system is effectively improved.

The present invention provides a data storage apparatus. The data storage apparatus comprises a host interface, a main control chip, one or more NAND chip used for storing data and an MRAM. The NAND chip and the MRAM are separately connected to the main control chip. The MRAM comprises a write cache or a read / write cache, and the MRAM further comprises an erasure time table and an unavailable page table, wherein the erasure time table is used for storing the number of times of erasing each block in the NAND chip, and the unavailable page table comprises a page in a bad block that appears when the NAND chip leaves a factory, a page in a bad block that appears in a subsequent read / write usage process and alternative pages of the foregoing pages. According to the data storage apparatus and the read / write method using the unavailable page table / unavailable block table, which is provided by the present invention, the MRAM comprises the write cache or the read / write cache, which not only ensures read / write performance, but also reduces the number of times of erasing the NAND and prolonging the service life of the data storage apparatus; the erasure time table and unavailable page table / unavailable block table of each block are maintained, and an NAND management technology of remote writing will not be adopted any more, and a logic address and physical address contrast table that occupies a large amount of space does not need to be stored, so that not only storage space is saved, but also complex processing is not required, thereby further improving read / write performance.

The invention discloses a storage method and device of mirror image documents of virtual machines. The storage method includes that the rate of reading and writing operation of the virtual machines is detected, and according to the detected rate and the reading and writing performance of a plurality of storers, the storer where the mirror image documents of the virtual machines are located is adjusted. The storer where the mirror image documents of the virtual machines are located is adjusted according to the rate of the reading and writing operation of the virtual machines and the reading and writing performance of the storers, so that different storers can play the maximum performance, and when the multiple virtual machines are virtualized on the basis of one physical machine, the requirement for intensively and randomly reading and writing small documents based on a virtualized platform can still be met, and the reading and writing performance of the storers can be ensured.

The embodiment of the invention provides a video pre-recording method and a cloud storage system. The method comprises the following steps: receiving video stream data collected by target monitoring equipment; according to the identifier of the target monitoring device, determining a pre-recorded storage area in a specified disk corresponding to the target monitoring device to obtain a target pre-recorded storage area; storing the currently received video stream data of the target monitoring device in a target pre-recording storage area in a periodic covering manner; and storing the data in the target pre-recording storage area into a long-period storage area of a video pool of the cloud storage system. According to the method, the pre-recording storage area, corresponding to the monitoring equipment, in the specified disk is used for caching the video of the monitoring equipment, the storage space of the disk is far larger than that of the annular memory, video pre-recording can be carried out according to the actually required time, the data volume of the pre-recorded video is greatly increased, and therefore the duration of the pre-recorded video is prolonged.

The invention discloses a method for adjusting bus timing, a storage medium and a terminal. The method comprises the steps of obtaining a plurality of delay threshold values corresponding to a preset storage card; on the condition that a preset operation fails, detecting whether one delay threshold value capable of completing the preset operation exists in the multiple delay threshold values or not under the current first bus frequency, wherein the preset operation includes a read operation and / or a write operation of the preset storage card; on the condition that the delay threshold value capable of completing the preset operation exists, setting the delay threshold value as a delay threshold value under the first bus frequency, and according to the delay threshold value, adjusting a deviation between a clock signal and a two-way instruction or a response signal or a data signal so as to achieve data transmission. According to the method for adjusting bus timing, the function of traversing all delay threshold values under the bus frequency can be achieved, the read-write performance of the preset storage card is kept, and the problems in the prior art are solved.

The invention provides a distributed system multi-target cluster mounting strategy automatic matching method and system. The method comprises the following steps: a distributed system client submits afile writing request to a router; after the request is received, the router queries mounting strategy information of a distributed system client path from the state storage module, analyzes an optimal mounting strategy according to the queried mounting strategy information and sends the optimal mounting strategy to the distributed system client; when the distributed system client receives the optimal mounting strategy, whether the strategy needs to be modified or not is determined; if so, a strategy modification command is executed; the modified path strategy is stored into a state storage module; the router queries the sub-clusters meeting the requirements from the state storage module, forwards the request to a running management node, and starts to execute file writing operation; if not, the request is forwarded to the running management node, and execution of the file writing operation is started. Load balance can be guaranteed, cluster resources are reasonably used, and file read-write performance is improved.

The invention discloses a method for data interaction of a host and a storage device and a storage controller. The method comprises a method for the host to read data from the storage device and a method for the host to write the data into the storage device, the storage controller receives a data operation command sent by the host, whether the data operation command is a writing command or a reading command is judged by the storage controller, and a command response is sent to the host; when the data operation command is the writing command, the data operation command is received and sent to the storage device, when the data operation command is the reading command, the data operation command is received and sent to the host, after data transmission is completed, the storage controller sends a command completing state to the host, and transmission is carried out based on a USB Bulk transmission protocol. When a data stream transmission mode is adopted in the host, data overflowing and loss are effectively avoided, and on the premise of guaranteeing read-write performance, the compatibility of the device and the host is improved to the maximum degree.

An embodiment of the invention provides a magnetic disk remapping method, a magnetic disk remapping device and electronic equipment. The magnetic disk remapping method includes: when a bad track exists in a hot data area of a magnetic disk, adopting a redundancy mechanism of RAID (redundant array of independent disk) to recover data of the area with the bad track to a reserved area of the magnetic disk by means of remapping, and then determining a cold data area as a target area; exchanging stored data in the reserved area and the target area to enable the hot data to be accessed through a physical address of the target area. Hot data access is realized by directly accessing to the original cold data area, so that read-write performances of the magnetic disk are guaranteed; further, possibility of bad track diffusion is lowered, and reliability of a storage system is improved.

The present invention relates to a PHP (Professional Hypertext Preprocessor) based log collection and storage method and system. The method comprises the steps of: S1, reporting log data by a client; S2, collecting the log data and sending the log data to a Redis cache server by a log collection module; S3, storing the log data by the Redis cache server. S4, reading the log data line by line from the Redis cache server and sending the log data to a MongoDB database by a log asynchronous writing module; and S5, writing and storing the log data in the MongoDB database. According to the PHP based log collection and storage method and system, an effective log can be conveniently collected, reading and writing performances of the database are ensured to operate in a low-concurrency and low-IO-load range, and writing pressure of the storage database is reduced, so that the system can operate healthily and stably.

Embodiments of the present application provide a data processing method and apparatus, and relates to the field of communication technology, which can solve the problem of poor service quality of important services due to insufficient memory resources of OSD used for reading and writing important service data. The method includes: receiving a write request message sent by the terminal, wherein thewrite request message carries a service priority and data to be written; mapping The data to be written to the target PG matched with the service priority, mapping the target PG to the target OSD matched with the priority of the target PG, and writing the data to be written to the target OSD by using the memory resources corresponding to the target OSD, wherein the priority of the OSD is directlyproportional to the amount of memory resources corresponding to the OSD.

The invention discloses an adjustable wind guide and noise reduction device. The adjustable wind guide and noise reduction device is arranged between a fan module and a hard disk module, and comprisesa fixed framework fixedly connected with a chassis; an upper sliding groove and a lower sliding groove are respectively arranged on the upper side plate and the lower side plate of the fixed framework; a centre shaft is arranged between the upper side plate and the lower side plate; furthermore, the upper end and the lower end of the centre shaft respectively protrude out of the outside of the fixed framework; a wind guide strip sleeves the centre shaft, and is inside the fixed framework; a limiting block is arranged on the lower end of the centre shaft; and a first locking nut is arranged onthe upper end of the centre shaft. The wind guide and noise reduction device is arranged between the fan module and the hard disk module; furthermore, the position and the angle of the wind guide mechanism on the wind guide and noise reduction device can be flexibly adjusted according to the performance of a hard disk; therefore, the heat dissipation effect is ensured; furthermore, influence on ahard disk, which is not good in reading and writing performance, also can be avoided; and thus, guarantee is provided for normal running of a server.

The invention is applicable to the field of data security, and provides a solid state hard disk data encryption and decryption method and a solid state hard disk system. The data encryption and decryption method comprises the following steps that a host computer generates a public key and private key pair (k1, k2) based on the asymmetrical encryption algorithm; the private key k2 is stored into a solid state hard disk, and the public key k1 is stored into the host computer; a secret key k3 based on the symmetrical encryption algorithm is generated at the host computer, and the secret key k3 is stored into the solid state hard disk after being signed and encrypted through the private key k2; during the system initialization, the host computer decrypts the secret key k3 encrypted by the private key k2 in the solid state hard disk through the public key k1, a plaintext secret key k3 is obtained, and the solid state hard disk realizes the encryption / decryption on data in the solid state disk through the plaintext secret key k3; when the system is powered off or the computer is powered off, the plaintext secret key k3 is deleted, and in addition, the plaintext secret key k3 cannot be accessed by other programs during the system operation. Therefore, the solid state hard disk data encryption and decryption method and the solid state hard disk system have the advantages that the data encryption intensity and the data security of the solid state hard disk can be improved, and in addition, the reading and writing performance of the solid state hard disk is ensured.

The invention discloses a construction method and an operation method of a DRAM-NVM hybrid index structure. The constructed index structure comprises an index layer, a middle layer and a data layer; the index layer is stored in the DRAM; the middle layer comprises metadata nodes which are stored in the DRAM, and backup exists in the NVM; the data layer comprises LogTree, the LogTree is of a tree structure, the number of the LogTree is the same as that of the metadata nodes, and the LogTree is in one-to-one correspondence with the metadata nodes; in an initial state, the LogTree is stored in an NVM (Non-Volatile Memory) and is recorded as NvmTree; in the read-write process, backing up the LogTree with the access heat greater than a preset access heat threshold and caching the LogTree in a DRAM to create a Cache Tree; at the moment, the LogTree comprises an NvmTree initially stored in an NVM, a Cache Tree cached in a DRAM and a log stored in the NVM; the log is used for storing a record for carrying out write operation on the Cache; and a LogTree in the data layer is used for storing a target keyword key in a key value pair written by a user and a pointer pointing to a value. The fault recovery process can be greatly accelerated on the premise of ensuring the read-write performance.

The embodiment of the invention discloses a partition creation method and device, a storage medium and computer equipment. The method comprises the following steps: determining an aligned sector position between adjacent partitions existing in a memory, and then determining a first storage capacity from the aligned sector position to a next partition in the adjacent partitions, and creating a target partition based on a first storage capacity from each aligned sector position to the next partition in each adjacent partition and a preset partition capacity. By adopting the embodiment of the invention, the new target partition can be established by utilizing the unused first partition capacity between the existing adjacent partitions, the waste of resources is reduced, and the read-write performance of the memory is ensured by the first storage capacity determined on the basis of the aligned sector position of the memory.

The invention provides a method for prolonging the service life of a mechanical hard disk, a storage device and a system.The method comprises the steps that the state of each sector in each mechanical hard disk is obtained, and whether a fault sector exists in the mechanical hard disk or not is determined according to the state of each sector; if the number of the faulty sectors in the mechanical hard disk is smaller than a set value, fault identifiers are set for the faulty sectors, and the faulty sectors are isolated from other sectors in the same mechanical hard disk; when a data read-write request is received, determining whether data corresponding to the data read-write request is located in the fault sector; if the data corresponding to the data read-write request is located in the fault sector, error reminding information is sent out. According to the scheme, the data read-write performance is guaranteed. Meanwhile, the probability that the mechanical hard disk is removed is reduced, and the service life of the mechanical hard disk is prolonged.

A disk remapping method and apparatus, and an electronic device. The disk remapping method comprises: when a bad track exists in a thermal data area of a disk, determining a cold data area as a target area after data of an area in which the bad track is located are recovered to a reserved area of the disk in a manner of remapping using a redundant mechanism of redundant arrays of inexpensive disks (RAID) (S101); and exchanging the stored data in the reserved area and the target area to realize the accessing of the thermal data through a physical address of the target area (S102). The thermal data access is realized by directly accessing an original cold data area, thereby guaranteeing the read-write performance of a disk; and at the same time, the probability of bad track diffusion is reduced, and the reliability of a storage system is increased.

The invention discloses a data storage method, device, system, computer equipment and storage medium, wherein the method includes: processing a write request of data to be stored in memory, and caching the data to be stored in memory; When the data reaches the first preset threshold, the data to be stored in the memory is converted into a multi-layer matrix array with indexes, and stored in the storage layer of the matrix storage structure preset in the non-volatile storage device; when the non-volatile When the data in the volatile storage device reaches the second preset threshold, the data stored in the non-volatile storage device is merged and written into the next layer of the merged tree structure. The invention can ensure the read and write performance of the system, increase the space size of each layer, and thereby solve the write amplification performance overhead brought by the multi-layer log structure tree structure to the system, thereby reducing system fluctuations and pause delays.

The invention discloses a dual-active disaster recovery method and device and electronic equipment, and is applied to a first server, the method comprises the following steps: obtaining a file operation request corresponding to a target file; when the file operation request is an update type operation request, packaging the update type operation request into an update message; and sending an update message to the message queue, so that the second server executes the file operation request on the target file based on the update message in the message queue. Under the condition of ensuring the read-write performance of the distributed file system, the remote disaster recovery effect can be realized, the data security of the distributed file system can be improved, and the distributed file system can still be used normally and the data cannot be damaged and lost under the condition that a certain data center is damaged.

The embodiment of the invention discloses a metadata performance optimization method and a metadata performance optimization system based on system disk sharing, which are applied to a video monitoring scene, and comprise the following steps of automatically filling a node OS on a system disk, and reserving a GPT partition on the system disk as a metadata partition; traversing all drive charactersin a video monitoring scene, and identifying whether a system drive is an SSD or not; if the system disk is the SSD, deploying metadata on the metadata partition, and if the system disk is not the SSD, deploying the metadata on the data disk; and automatically separating metadata. In the invention, after a node OS is automatically filled on an SSD system disk, the partitions of the SSD system disk serve as metadata pools, metadata services are deployed on the system disk to be specially used as a video monitoring scene, and due to the fact that the read-write performance of the SSD is much higher than that of a mechanical disk, the metadata are deployed on the system disk, the requirement for cost can be met, and the read-write performance of the metadata can be guaranteed.

The invention discloses an SAS (Serial Attached SCSI) / SATA (Serial Advanced Technology Attachment) expander information self-adaption method and system. A self-adaptive SASSATA3.0 Expander system converts the uplink PCIE (Peripheral Component Interconnect Express) signal into into a downlink SAS / SATA signal, is connected with a plurality of paths of SAS / SATA Receivers; and the oscilloscope scanning period is adjusted at an output terminal of the downlink, the horizontal scanning period of the oscilloscope is synchronized with the period of receiving the code element; an eye pattern is formedby utilizing the afterglow function of the oscilloscope; indexes of the eye pattern template are determined through an SAS / SATA _ Tx protocol; de-emphasis and pre-emphasis of the output end of the expander chip are dynamically adjusted through a UART link to balance a high-frequency component and a low-frequency component; the influence of the transmission link on the final eye pattern result whenthe high-frequency component attenuation is greater than the low-frequency component attenuation is reduced; the weighted value is written into the FW of the Expander chip through the UART signal link to form a feedback loop, and the inter-symbol interference is reduced; and the transmission performance of the system is improved. The invention provides a self-adaptive circuit design, and by dynamically adjusting pre-emphasis and de-emphasis of a sending end and compensating a telling signal, the read-write performance and the data security of the hard disk are ensured.