551results about How to "Improve read and write performance" patented technology

The invention relates to a method and a system for storing mass data of the Internet of Things (IoT). The system comprises a plurality of data receiving nodes, a master node server and a database cluster. The method comprises the following steps of: (1) carrying out preprocessing on IoT data, and putting the preprocessed data in the database cluster consisting of a master node, slave nodes and the data receiving nodes; (2) creating sample records, which take sample elements as storage units, on the master node according to the static and dynamic information of the data in the database cluster; (3) after the sample records are encapsulated, sending the encapsulated sample records to all the slave nodes by the master node so as to be subjected to fragmentation processing and / or separated storage; and (4) after the slave nodes complete storage, uploading results to the master node, and updating the data in the database cluster by the master node, thereby completing storage. According to the method and the system, the cluster is extended by fully utilizing the existing storage technologies so as to store the mass data, the IoT data are divided into lightweight data and multimedia data, and particularly, a fragmentation strategy is adopted aiming at a large-scale amount of data, so that the time expenditure caused by the extension of a storage space is avoided.

Reading and verify operations are performed on non-volatile storage elements using temperature-compensated read voltages for unselected word lines, and / or for select gates such as drain or source side select gates of a NAND string. In one approach, while a read or verify voltage is applied to a selected word line, temperature-compensated read voltages are applied to unselected word lines and select gates. Word lines which directly neighbor the selected word line can receive a voltage which is not temperature compensated, or which is temperature-compensated to a reduced degree. The read or verify voltage applied to the selected word line can also be temperature-compensated. The temperature compensation may also account for word line position.

The present invention that partitions a memory array in N segments by switchably partitioning the bit lines in the array. In the exemplary embodiment, a top set of sense amps control the even bit lines and a bottom set of sense amps control the odd bit lines. The segmentation transistors turn on or off depending on the selected word line location in the array. Since bit line capacitance is mainly from the metal bit line to bit line coupling to their immediate neighbors, the bit line neighbors in the partitioned array are floating in some segments of the bit lines. The overall bit line capacitance is significantly reduced with a negligible increase in die size, resulting in reduced sensing times and enhanced read and write performance.

Method, system, and computer program product embodiments for facilitating data transfer from a write cache and NVS via a device adapter to a pool of storage devices by a processor or processors are provided. The processor(s) adaptively varies the destage rate based on the current occupancy of the NVS for a particular storage device and stage activity related to that storage device. The stage activity includes one or more of the storage device stage activity, device adapter stage activity, device adapter utilized bandwidth and the read / write speed of the storage device. These factors are generally associated with read response time in the event of a cache miss and not ordinarily associated with dynamic management of the destage rate. This combination maintains the desired overall occupancy of the NVS while improving response time performance.

A cache-based storage architecture has primary and secondary storage subsystems that are controlled by first and second data layout engines to provide a high-performance storage system. The primary storage subsystem illustratively comprises non-volatile electronic storage media configured as a cache, while the secondary storage subsystem comprises magnetic storage media configured as a disk array. The data layout engines illustratively implement data layout techniques that improve read and write performance to the primary and secondary storage subsystems. To that end, the data layout engines cooperate to optimize the use of the non-volatile cache as a primary storage stage that efficiently serves random data access operations prior to substantially transposing them into sequential data access operations for permanent (or archival) storage on the disk array.

The invention discloses a flash memory wear balance method, which comprises the following steps of: (1) dividing a flash memory storage area into a plurality of storage subareas; (2) determining the wear degree of various storage subareas at intervals, numbering seriously worn storage subareas, and interposing the seriously worn storage subareas into a seriously worn storage subarea queue; and (3) performing a dynamic wear balance operation to achieve flash memory wear balance when a logic block requires a newly allocated physical block. The wear balance method is suitable for performing the wear balance on memory devices such as flash memories, is not affected by the extensibility problem, is also suitable for large-capacity flash memory devices, and can greatly improve the read-write performance and the service life of memory systems.

A system and method for enabling flash memory systems to support flash devices with pages that are larger than operating system data sector sizes, while not violating the device's specifications, and also optimizing performance. According to the present invention, the writing logic of a flash memory system must take into account the PPP limitations and page size of the device during sector write operations. The PPP influences the decision when to simply write the new data, and when to allocate a new page and copy previously existing data to the new page. According to the present invention, when a page contains more than one sector, the software makes the standard translation into physical address, but after finding the address, it examines the page containing that address, and counts the number of other sectors within the same page already containing data. Then a decision is taken whether to write the sector into the calculated physical address, or write the sector into a fresh page, while at the same time, optionally copying the existing neighboring sectors into this fresh page.

A method and system for increasing read and write performance of flash-based storage systems, by using RAM buffers with multiple accesses. The increase of read and write performance of flash-based storage system is achieved by performing "from RAM" and "to RAM" transfer operations simultaneously. According to the preferred embodiment of the present invention, the invention provides a system for enabling simultaneous data transfer from a host interface to flash media and from flash media to a host interface. It also provides for a system for synchronizing memory-to-host and flash-to-memory transfers, during the host read operation. There is further provided a system of synchronizing host-to-memory and memory-to-flash transfers, during the host write operation.

A method and system are disclosed for handling logical-to-physical mapping in a storage device. The method includes the storage device storing in fast access memory, such as DRAM, only a fixed-size subset of the primary mapping table in non-volatile memory, along with contiguity information of physical addresses for logical address not in the subset that are adjacent to the logical addresses in the subset. The system includes a storage device having volatile memory, non-volatile memory and a controller in communication with the volatile and non-volatile memory that is configured to carry out the method noted above.

The embodiment of the invention discloses a data distribution method, which is used for improving the performance of a distribution storage system. The embodiment of the invention comprises the following steps: a data distribution device receives a storage instruction of a user; to-be-stored data which is indicated to be stored by the storage instruction is divided into P data segments; a storage node group corresponding to each data segment is determined; and finally, each data segment is distributed to the main node of the corresponding storage node group. The embodiment of the invention also provides a relevant data storage method and a relevant device and system.

The invention relates to a video detecting data storage method and relative system, which uses network to connect the data processor and the storage device. Wherein, said method comprises: dividing the video data into several data blocks and sending the data blocks to the storage device to be stored; reading stored data block to recover the video data; the data processor divides the stored data into several data blocks in same size, and assembles several data blocks into the data units in the same size; building index for each data unit; according to the index, reading the data block of storage device to recover the video data. The inventive video detecting data processor will directly process block operation on the storage device, to realize high-efficiency access to the video data of video detecting network, to improve the reliability and application flexibility of video data.

The invention provides a data read-write method of a disk array, comprising the following steps: distributing a plurality of ribbon structures in a memory and establishing a disk ribbon state bitmap to record the state attribute of all disk ribbons; initializing the disk ribbon state bitmap; receiving a read-write request of the user and updating the disk ribbon state bitmap; executing the read-write request of the user, executing a write target data block if the request is a write request, and updating a check block or updating the check block in a delaying mode according to the state attribute of the disk ribbon of the target data block; and executing a read-request processing flow if the request is a read request. The data read-write method uses the disk ribbon state bitmap for checking the written operation frequency in an automatic-adaptation way, and for the disk ribbon with high write-operation frequency, the check block is updated in a delaying mode to accelerate the read-write processing efficiency of the disk array.

The invention discloses a magnetic disk cache system based on a solid-state disk and belongs to the technical field of cache systems in computer data storage systems. The magnetic disk cache system based on the solid-state disk comprises a data block metadata maintenance module, a solid-state disk data replacement module and a dirty data block writing-back disk module. According to the magnetic disk cache system based on the solid-state disk, the reading and writing performance of disk data in a large-scale storage environment is improved through the solid-state disk, and the data block reading and writing hit rate and the cache space utilization rate are high; meanwhile, it is guaranteed that data blocks cached under the condition that a computer is restarted due to faults can not be lost easily, the cold-to-hot convergence time of solid-state disk equipment is shortened, and the problems that according to a computer data storage system in the prior art, the cache space is limited, cached data can be lost easily, and the cache space can not be fully utilized can be solved.

A method and system for increasing read and write performance of flash-based storage systems, by using RAM buffers with multiple accesses. The increase of read and write performance of flash-based storage system is achieved by performing "from RAM" and "to RAM" transfer operations simultaneously. According to the preferred embodiment of the present invention, the invention provides a system for enabling simultaneous data transfer from a host interface to flash media and from flash media to a host interface. It also provides for a system for synchronizing memory-to-host and flash-to-memory transfers, during the host read operation. There is further provided a system of synchronizing host-to-memory and memory-to-flash transfers, during the host write operation.

Reading and verify operations are performed on non-volatile storage elements using temperature-compensated read voltages for unselected word lines, and / or for select gates such as drain or source side select gates of a NAND string. In one approach, while a read or verify voltage is applied to a selected word line, temperature-compensated read voltages are applied to unselected word lines and select gates. Word lines which directly neighbor the selected word line can receive a voltage which is not temperature compensated, or which is temperature-compensated to a reduced degree. The read or verify voltage applied to the selected word line can also be temperature-compensated. The temperature compensation may also account for word line position.

The invention discloses a consistent hash-based hierarchical mixed storage system and method, and belongs to the field of computer storage. The characteristics of various storage mediums can be utilized to the maximum extent; and storage policies are reasonably adopted, so that the system performance is improved. The method comprises the steps of designing a hierarchical consistent hash ring according to difference of the storage mediums and the storage policies; performing hierarchical storage in the hierarchical consistent hash ring through indexes such as access frequencies, capacity and the like by storage objects; introducing a monitoring module for determining data collection frequencies and data migration thresholds in different time periods; introducing a scheduling module for performing reasonable upgrading and downgrading data migration scheduling for cold and hot changes, with time, of data; and managing SSD cluster data information by adopting a forest data structure. The hierarchical storage is performed for load characteristics; different storage mediums and storage policies are provided according to the characteristics of the storage objects; the system flexibility is enhanced and the system read-write performance is improved; and the system stability is ensured.

The present invention provides a method, system and device for multi-channel data processing on a storage device, wherein the system includes: a drive and a read-write management device, and more than one storage controller, wherein each storage channel has an independent storage The controller; the drive and read-write management device is used to receive the access requests provided by each thread, schedule the received access requests and send them to the storage controller responsible for the storage channel of the corresponding thread, wherein each thread is responsible for One or more storage channels; the storage controller is configured to perform data processing corresponding to the received access request according to the mapping relationship between the logical address and the physical address in the storage channel. The invention can make the concurrent scheduling between multiple channels determined by the upper-layer software, which is more suitable for the requirements of the application layer and achieves the best reading and writing performance.

The invention discloses a flash translation layer (FTL) with a data compression function and an implementation method. The FTL with the data compression function mainly comprises a compressor, a decompressor, a buffer, an address mapping management module, a trash recycling module and a loss balancing module. An LZ77 (Lempel-Ziv 77) algorithm based single-page compression strategy is adopted for the compression of written-in data and the decompression of readout data. A data compression technology is used for decompressing / compressing the readout / written-in data, a soft buffer is implemented in the FTL, and the data volume written-in and read-out from a flash memory solid state disk each time is reduced, thereby improving the integral reading and writing performance of the flash memory solid state disk.

The embodiment of the invention provides a method, device and equipment for synthesizing voice and music. The method comprises the steps that input voice data and background music data are obtained; one or more words or phrases are identified in the voice data and tones and lasting time of the words or the phrases are obtained, wherein the voice data are composed of the words or the phrases; tone and lasting time of the background music data are obtained; according to the tone and the lasting time of the background music data, speed change processing and / or tone modification processing are / is conducted on the tones and the lasting time of the words or the phrases; the processed voice data and the background music data are synthesized so that a new audio file can be formed. According to the method, device and equipment for synthesizing voice and music, independent voice data and music data can be perfectly combined together, a music attribute is offered to the monotonous voice data, so that the quality of an whole voice stream is improved, and the gradually improved and changed requirements for voice and music synthesis of users are satisfied.

A management method of large scale storage resource includes maintaining a set of storage resouce disposal information by node machine of special processor to manage different storage device resource in storage network so as to provide virtual storage service for front end host by carrying out process of command analysis with interface middle layer of small computer interface. The node machine with information list and software target machine can convert virtual access to be access of physical device.

Method, system, and computer program product embodiments for facilitating data transfer from a write cache and NVS via a device adapter to a pool of storage devices by a processor or processors are provided. The processor(s) adaptively varies the destage rate based on the current occupancy of the NVS for a particular storage device and stage activity related to that storage device. The stage activity includes one or more of the storage device stage activity, device adapter stage activity, device adapter utilized bandwidth and the read / write speed of the storage device. These factors are generally associated with read response time in the event of a cache miss and not ordinarily associated with dynamic management of the destage rate. This combination maintains the desired overall occupancy of the NVS while improving response time performance.

Reading and verify operations are performed on non-volatile storage elements using temperature-compensated read voltages for unselected word lines, and / or for select gates such as drain or source side select gates of a NAND string. In one approach, while a read or verify voltage is applied to a selected word line, temperature-compensated read voltages are applied to unselected word lines and select gates. Word lines which directly neighbor the selected word line can receive a voltage which is not temperature compensated, or which is temperature-compensated to a reduced degree. The read or verify voltage applied to the selected word line can also be temperature-compensated. The temperature compensation may also account for word line position.

The invention discloses a disk storage system and a method for controlling disk storage and a device thereof. In the invention, both a first disk with relatively high I / O rate and a second disk with relatively low I / O rate are taken as physical disks of the disk storage system; when a processor receives relatively high frequency of write command, write data in the write command are written into the first disk with higher I / O rate to ensure that read-write performance of the disk storage system is not reduced due to the influence of the I / O rate of the physical disks; when the processor receives relatively low frequency of the write command, the I / O rate of the second disk can meet the need for normal read-write; at the moment, write data in the write command are written into the second disk with relatively low I / O rate, thereby not only improving read-write performance of the disk storage system but also saving cost of the disk storage system.

The invention discloses a distributed storage system which comprises a storage pool, a file blocking module and a plurality of storage nodes, wherein the storage pool establishes network connection with an external client and is used for receiving a stored file uploaded by the external client by a network; the file blocking module establishes communication connection with the storage pool and is used for performing stripping processing on the stored file to obtain a plurality of file blocks; the storage nodes respectively establish communication connection with the file blocking module and are used for respectively storing the file blocks generated by blocking the stored file. According to the distributed storage system disclosed by the invention, the stored file is divided into the file blocks which are respectively stored in a plurality of different storage nodes; the storage nodes commonly perform read-write operation, so that the pressure of one storage node is dispersed, and the read-write performance is improved.

The invention discloses a distributed cache architecture with a task distribution function, which comprises a distributed task scheduling system, a relational database Mysql and a redis distributed cache system. The dynamic distributed cache architecture solves the situation that the traditional database can not process and access a large amount of data. The invention discloses another cache method adopting the distributed cache architecture, can achieve automatic task distribution and fault tolerance for scenes in which computation is required, and guarantees the reliability during processing.

The invention discloses a method used for the document reading / writing operation of multi-copy data grid system, which belongs to the operational field of high speed document writing. The invention is characterized in that the following steps are sequentially included: the user puts forward a writing document request to the copy access client terminal; after the identity is successfully authenticated by a metadata server, a server distance comparison module selects a copy storage server that is nearest to the user in logic distance, and selects the corresponding copy view information, and after confirmed by a view analytical module of the copy access client side as effectiveness, a reading and writing execution module of the copy access client sends data writing request to the copy storage server; after the copy storage server successfully executes writing operation, a copy view updating module of the metadata updates the copy view. The invention leads the user to select the nearest copy storage server to execute writing operation, meanwhile, the normal reading operation of the user is guaranteed.

The invention discloses a massive fragment data aggregation system for two kinds of massive fragment data. The system comprises a fragment uploading module of a client, and a cache module, a verification library module, a document storage module, a fragment receiving module, a fragment processing module, a fragment combination module and a fragment aggregation module of a server. Correspondingly, the invention also discloses a massive fragment data aggregation method. By the system and the method, a plurality of technologies such as message queuing services, memory banks, document databases, daemon processes and the like are adopted, so that the massive fragment data can be highly efficiently processed and combined; and a strict combination strategy is adopted, so that combination accuracy is ensured.

The invention discloses an information processing method and electronic equipment. The information processing method comprises the following steps: detecting to acquire a current temperature of a storage unit in the electronic equipment; acquiring a current environment temperature of an environment where the storage unit is located; acquiring a temperature control strategy of the storage unit corresponding to the current environment temperature when the current temperature reaches a first temperature threshold; adjusting a current working state of the storage unit from a first working state to a second working state matched with the current environment temperature on the basis of the temperature control strategy, wherein the second working state is different from the first working state.

The invention discloses a snapshot method for distributed storage. For a distributed storage system, original volumes and snapshot volumes are described by using independent virtual view objects, andthe snapshot volumes have complete physical copies, so that the dependency of the snapshot volumes on the existence of the original volumes is released. All the virtual view objects, namely VDIs, andsnapshots thereof share the whole distributed storage resource pool, and the snapshot volumes do not need independent reserved storage space any more, so that the dependency of the snapshot volumes onthe original volumes is released. On the basis of the copy-on-write (COW) and redirection-on-write (ROW) mechanisms, a log mode is introduced, the problems, caused by the snapshots, of great reduction of the read and write performance of the original volumes and the consistence of performance are solved, and meanwhile, the bottleneck that the number of the snapshots is limited is broken through.The efficiency and the availability of the snapshots in the distributed storage system are obviously improved, and therefore, the availability of the system is enhanced.