46results about How to "Reduce read volume" patented technology

The invention discloses a distributed lock realization method and device. It involves cloud computing technology, which solves the problem of resource waste caused by reading all shared storage space every time. The method includes: obtaining the surviving nodes in the current lock space; and reading the I / O blocks corresponding to the surviving nodes in the shared storage. The technical scheme provided by the invention is suitable for a large-scale cluster computing platform, and realizes a distributed lock with high efficiency and high resource utilization.

The invention provides a time series data storage method based on a multilayer column-type storage structure. The method comprises the steps that all time series data to be stored is stored in a file,wherein the file comprises a first part and a second part; acquisition time of each piece of time series data to be stored and a data value of each piece of time series data to be stored are stored in the first part; the first part is divided into multiple row sets; each row set is divided into multiple column sets; the number of all the row sets, the offset amount of each row set in the file, the number of all the column sets in each row set, an attribute value of each piece of time series data and the offset amount of each column set in the file are used as the second part. According to thetime series data storage method, the time series data is organized according to the columns, the data of the same column in the same row set is continuously stored in the file, queried data is located at the close positions in the file accordingly, the amount of reading the time series data during query can be reduced, the query speed is increased, and the IO performance of a disk is improved.

The invention discloses a retrieval device, a terminal and a retrieval method. The retrieval device comprises an acquiring unit, a screening unit and a retrieval result confirming unit, wherein the acquiring unit is used for receiving an input retrieval item and acquiring documents which comprise the retrieval item, the screening unit is used for counting a predicted weight value of each document, screening a preset number of primary documents from the documents with the retrieval item according to the predicted weight values, and the retrieval result confirming unit is used for reading position data of the retrieval item in each primary document, calculating a position relevancy according to the position data, and using the primary document of which the position relevancy satisfies the preset condition as a retrieval result. The retrieval device, the terminal and the retrieval method predicate the intermediate retrieval result according to the document characteristics and only read the position data and calculate the position relevancy of the part with good predicated result, and accordingly the position data reading amount and calculating amount are greatly reduced, and the retrieval speed is improved.

The invention provides a serial port caching control method, a controller and a microcontroller system thereof. The serial port caching controller comprises L label address rows, wherein each label address row comprises a block label of an M bit and an effective bit zone label of an N bit; the block label of the M bit is used for recording an address zone of T byte data stored in an internal caching memory, the effective bit zone label of the N bit is used for recording effective bit zones in the address zone, wherein the size of each effective bit zone is T / N byte. The serial port caching controller needs to read T / N byte data from an external memory to the internal caching memory every time without reading the T byte data of the whole address zone. Because the T byte data of the whole address zone can not necessarily be read by a microcontroller, the waiting time of the microcontroller can be shortened so that the executing speed is raised.

The invention relates to a map information quick display method which comprises: storing layering and vacuate classification gauge according to the map information, determining a lamination where a display proportional scale is, reading and displaying corresponding map display elements; storing a bilayer net index information based on the map information according to a range to be displayed by the map, and reading corresponding map information from one layer of net index to the corresponding next layer net. When the information is quickly read according to the corresponding method, required map information is rapidly read according to a corresponding method; meanwhile, displaying cache is adopted, such that the map can be displayed with a high efficiency by the system. The method is especially suitable for a navigating system of a navigator.

The present invention is applicable to the improvement field of distributed storage technology, and provides a binary-based node repair method. The node repair method includes the following steps: S1. Group the system nodes and group the (n, k) codes on the piggyback coding framework Define the system vector and encoding matrix; S2. Substitute the defined encoding matrix into the encoding structure to obtain the corresponding encoding method; S3. Repair the damaged nodes through zigzag decoding according to the encoding method. In the distributed storage system, according to its special encoding method, the designed code satisfies the (n, k) property; and in the process of node repair, it can effectively reduce the amount of data read and downloaded, thereby improving Repair efficiency.

The invention provides a rapid data recovery method and system based on crossed code correction and deletion. The method comprises the steps that calculation is performed according to an LRC encoding mode when data is written in, global encoding blocks are grouped in pairs, the global encoding blocks in each group are divided into two parts, after being subjected to exclusive-or operation, the second half part of one global encoding block and the first half part of the other global encoding block are written into the second half part of the current global encoding block, when the first global encoding block is lost, the second half part of the data block is read, the two second half parts, obtained before the exclusive-or operation is performed, of the lost data block are obtained, the first half part of the lost data block is obtained after the second half part, obtained after exclusive-or operation is performed, of the other global encoding block is subjected to exclusive-or operation, the data obtained before exclusive-or operation of the lost data block and the first half part of the other global encoding block are subjected to exclusive-or operation to obtain the second half part of the lost data block; the data is brushed back to a corresponding magnetic disk in a stripe mode to be stored, and after the data is written into a storage server, asynchronization longitudinal encoding calculation is performed.

The invention discloses a cloud computing method for high-performance scientific computing, including local computing users, the local computing users are connected to a service terminal, the service terminal is connected to a cloud platform, and the local computing users include local storage, computing A terminal, a computing cache and a computing node, the local storage is connected to the computing terminal, the computing terminal is connected to the computing cache, the computing cache is generated with a computing node, the service terminal includes an encryption module and an authentication module, and the encryption module Connected to the authentication module, the cloud platform includes a cloud sharing terminal and cloud storage, the cloud sharing terminal is connected to the cloud storage, by producing computing nodes in the calculation, and then encrypting and transmitting them to the cloud platform for storage, both data upload and storage can be reduced. The amount of reading can effectively increase the rate, while reducing redundant data, which is conducive to shared management, can increase the calculation rate, and greatly improve cloud computing and high performance and efficiency.