1550results about "Input/output to record carriers" patented technology

Methods, devices, and executable instructions are provided for allocating external memory. A request to allocate a portion of memory may be received at a first device. A memory appliance and the first client device are connected by a network. A region of memory of the memory appliance may be allocated as external memory prior to receipt of the request to allocate the portion of memory at the first client device. A subset of the region of memory for the portion of memory allocated may be selected at the first client device and in coordination with a second client device on the network, wherein the portion of memory allocated is external to the first client device and yet is primary memory to the first client device. At least the subset of the region of memory may be mapped at the first client device to a virtual address space.

Apparatuses and techniques are described implementing power-efficient monitoring for usage-based-disturbance mitigation. In a first aspect, a memory device takes a less strict approach for monitoring worse-case conditions associated with usage-based disturbance. In particular, the memory device conserves power by foregoing updating a list of rows associated with worse-case conditions until an unlisted row has a substantially worse condition than any one of the listed rows. This decreases how often the memory device expends power to update the list. In an optional second aspect, the memory device performs a partial bit-width comparison operation to evaluate the “substantially worse” criterion. The partial bit-width comparison enables a comparator to be implemented with a smaller footprint and operate with less power as compared to a comparator that is capable of performing a full bit-width comparison operation.

Systems and methods for selectively bypassing an external cache (EC) of a storage system are provided. In one example, when the EC backing storage device is saturated, reads bypass the EC and are completed via a redundant array of independent disks (RAID) subsystem of the storage system. One or more performance metrics for the EC backing storage device may be monitored to predict one or more saturation thresholds (e.g., in terms of latency and / or throughput). Based on this monitoring, tuning may be performed to drive utilization of the EC into a “knee region” of a performance (or response) curve of the EC backing storage device. For example, the depth of one or more request queues at the front-end of an EC lookup may be manipulated based on a current measure of saturation relating to the EC backing storage device to limit the number of in-flight reads pending for the EC.

This invention discloses a method and apparatus for storing log files. The method includes: obtaining a preset storage location for storing the log files and application parameters of an application, wherein the log files are generated by the application; filtering the log files based on the log pattern in the application parameters to obtain a target log file; and storing the target log file based on the application type and the preset storage location in the application parameters. This invention solves the technical problems of complex processes and low storage efficiency in storing log files in related technologies.

The present application relates to the technical field of product warehouse dynamic cleaning, and particularly relates to a product warehouse customized dynamic cleaning implementation method and system.The implementation method comprises the following steps: a business layer is responsible for scene logic implementation, and has a system type, an environment and a time range set by a user;S2: setting a cleaning rule, adopting a time priority scheduling algorithm, arranging a cleaning task execution order according to a task execution priority and a current product warehouse load state;S3: an execution layer is responsible for screening out products needing to be cleaned in a logic layer, and performing product cleaning by calling a system level command.The present application realizes accurate product warehouse cleaning, maximizes storage space release, reduces operation and maintenance costs, and improves product warehouse storage efficiency and service stability on the premise of guaranteeing core product safety.

Embodiments of the present disclosure provide a traffic control method, a device, a storage medium, and a program product. In the embodiments of the present disclosure, in a storage space recycling and unloading scenario, by means of either of a first thread and a second thread, a target zone resource is accessed, and a target write speed threshold of a write operation and a target recycling speed threshold of a storage space recycling operation are calculated, wherein the first thread can perform traffic control on a foreground write operation on the basis of the target write speed threshold, and the second thread can perform traffic control on the storage space recycling operation on the basis of the target recycling speed threshold, thereby implementing traffic control on the foreground write operation and the storage space recycling operation in the storage space recycling and unloading scenario. In addition, because only one thread accesses the target zone resource and data such as the target write speed threshold and the target recycling speed threshold, additional mutually exclusive logic does not need to be provided, thereby reducing code complexity of traffic control, and improving traffic control efficiency.

A system and technique for buffering data locally within a memory device to allow access to data associated with a plurality of different rows within the memory device. The memory device includes a storage bank circuit having memory cells and a sense amplifier circuit coupled to the storage bank circuit. The memory device also includes a buffer circuit coupled to an output of the sense amplifier circuit. In addition, the memory device includes a selection circuit. The selection circuit receives a first data signal from the sense amplifier circuit and a second data signal from the buffer circuit and outputs a selected one of the first data signal and the second data signal.

A data compression method and a related device, used for reducing I / O overhead. The data compression method comprises: acquiring attribute information of a logic block, wherein the logic block comprises a plurality of data pages, and the attribute information indicates data sizes of data contained in the plurality of data pages across a plurality of time periods; if the attribute information indicates that the total data size of the data contained in the plurality of data pages during a target time period is greater than or equal to a first threshold, compressing the data contained in the logic block, and storing the result obtained by compression, wherein the target time period includes at least time period among the plurality of time periods, and the time interval between the target time period and the current moment is greater than or equal to a time threshold; and if the attribute information indicates that the total data size of the data contained in the plurality of data pages during the target time period is less than the first threshold, determining not to compress the data contained in the logic block.

The application relates to the technical field of solid-state storage, in particular to a method for expanding the capacity of a storage chip, a chip and an access device, which comprises the following steps: S1, detecting the running parameters of the current state of the storage chip; S2, judging the use state of the storage chip according to the detected running parameters; S3, expanding the reserved storage area according to the judgment result; when the value of the running parameters is greater than a preset value in the judgment result, the reserved storage area is set to a read-write state, so that the storage capacity of the storage chip is expanded. In summary, the storage capacity of the storage chip can be expanded according to the use state after long-time use, more available capacity is provided for the user, the service life of the electronic device is prolonged, and the use experience of the user is optimized.

The application provides a read cache layer creation method and device and a storage medium, relates to the technical field of computers, and can solve the problem of high power consumption of an HDD storage disk. The method comprises the following steps: acquiring the idle rate of the memory space of each server in a cloud pool, the operating system of the server having the capability of creating a memory-optimized ZRAM virtual device; the cloud pool comprising a plurality of servers and a traditional hard disk HDD storage hard disk; for a target server with an idle rate greater than or equal to a preset threshold, creating at least one ZRAM virtual device in a target region of the memory space of the target server; and setting the at least one ZRAM virtual device as a read cache layer of the HDD storage hard disk. The application can effectively reduce the power consumption of the HDD storage disk.

Embodiments of the present application provide a processing method and device of an internal object, a storage medium, an electronic device and a program product, wherein the method comprises: in response to an initial service object changing into a target service object, determining initial metadata corresponding to the initial service object from at least one first metadata stored in a memory, wherein the first metadata is used to at least represent a storage state of data in a historical internal object associated with the initial service object, and the historical internal object is used to store service data of the initial service object; changing the initial metadata to obtain target metadata; and determining a recycling strategy of the historical internal object based on the target metadata, wherein the recycling strategy is used to represent a rule of whether to perform recycling processing on the historical internal object. Through the present application, the technical problem of low efficiency of recycling processing on the internal object is solved, and the technical effect of improving the efficiency of recycling the internal object is achieved.

The application provides a device storage control method, a device and a storage medium, and applies to the field of computer science. The method comprises the following steps: collecting storage information of a target device, determining a storage state of the target device based on the storage information; judging whether the storage state meets a preset condition; if yes, controlling a cache mode of the target device to be a first preset mode; and if no, controlling the cache mode of the target device to be a second preset mode. The method of the application achieves the technical effect of improving data consistency and accelerating effect.

Devices and techniques are disclosed herein for more efficiently exchanging large amounts of data between a host and a storage system. In an example, a large read operation can include receiving a pre-fetch command, a parameter list and a read command at a storage system. In certain examples, the pre-fetch command can provide an indication of the length of the parameter list, and the parameter list can provide location identifiers of the storage system from which the read command can sense the read data.

In a method of operating a storage device including a first storage device and a second storage device connected to each other via a host device, a data migration request for a first namespace included in the first storage device is received. A second namespace is generated in the second storage device. The second namespace corresponds to the first namespace. A pointer table for performing a data migration operation corresponding to the data migration request is set. First data and second data are migrated to the second namespace based on the pointer table. The first data is stored in the first namespace. The second data is stored in a first buffer memory included in the first storage device and corresponds to the first namespace. Based on the data migration operation being performed, the second data is directly sent from the first buffer memory to the second namespace.

Systems, apparatuses, and methods for a non-target command in a multi-rank memory system are disclosed. A command is received by a first memory rank and a second memory rank. The first memory rank may be a target rank for the command, and the second memory rank may be a non-target rank for the command. The first memory rank performs a first operation responsive to the command, and the second memory rank performs a second operation different from the first operation responsive to the command. In some embodiments, the first memory rank receives an active pulse of a first chip select signal for the command and the second memory rank receives at least two active pulses of a second chip select signal for the command. In some embodiments, the command includes at least one rank encoding bit used to specify a target rank. The command may be an activate command.

The present disclosure relates to the technical field of computer cloud platform software, and particularly relates to a server, a shared storage mounting method and a computer readable storage medium. The method comprises the following steps: receiving mounting information for mounting a file system; wherein the mounting information at least comprises a target mounting path determined based on a specified storage path of a service instance and first configuration parameters of the file system, the target mounting path is a first directory path in the server, and the first configuration parameters at least comprise a first mounting identifier for indicating whether to use shared mounting; determining a first mounting path based on the first mounting identifier; wherein the same first configuration parameters correspond to the same first mounting path, the first mounting path is a second directory path in the server, and the first directory path is different from the second directory path; mounting the file system to the first mounting path, and / or mounting the first mounting path to the target mounting path.

An apparatus includes at least one processing device configured to, for a given data portion of a layered-aware snapshot to be restored to a target storage system comprising a set of two or more storage tiers, determine tiering information characterizing a given storage tier in which the given data portion was stored when the layered-aware snapshot was taken. The at least one processing device is further configured to select one of the storage tiers of the target storage system based at least in part on the determined tiering information and a storage tier mapping policy that maps the given storage tier to the set of two or more storage tiers of the target storage system. The at least one processing device is further configured to restore the layered-aware snapshot to the target storage system by storing the given data portion in the selected storage tier.

The application discloses a Tensor data processing method and device and related equipment. The method comprises the following steps: acquiring prior information of Tensor data, wherein the prior information comprises a dimension parameter and a storage address mapping rule of the Tensor data; determining each target element based on the dimension parameter of the Tensor data; converting the virtual storage address of each target element into a physical storage address by using the storage address mapping rule, wherein the physical storage addresses are continuous; storing each target element into the corresponding physical storage address; and performing a preset operation on each target element stored in the physical storage address by using a preset algorithm to obtain a processing result. Thus, the cache hit rate is improved.

This application relates to a memory device having multiple input / output interfaces. A memory device includes: a first plane group including a first plane; a second plane group including a second plane; a first input / output (I / O) interface configured to access the first plane group; and a second I / O interface configured to access the second plane group. The memory device further includes a controller operatively coupled to the first I / O interface via a first channel and operatively coupled to the second I / O interface via a second channel. The controller can transmit a first command via the first channel to the first I / O interface to perform a first memory access operation associated with the first plane. The controller can transmit a second command via the second channel to the second I / O interface to perform a second memory access operation associated with the second plane.

The application discloses a kind of access control methods, devices, equipment, medium and product of heterogeneous storage system. Method includes: when key-value cache access request meets data prefetch condition and / or self-cleaning condition, data prefetch request and / or self-cleaning handling request are generated and joined to matching queue;Data prefetch request and / or self-cleaning handling request obtained from queue concurrently are joined in request processing queue after being jointly decided with key-value cache access request;Request is obtained from request processing queue, and it is determined whether data handling operation needs to be triggered;At least one of the following is executed: routing request to first type of memory or second type of memory, routing and scheduling data that needs to be handled between first type of memory and second type of memory, and routing response result to upper layer application, to provide a kind of key-value cache access control method which does not depend on special interconnection hardware, does not sacrifice model inference accuracy, can effectively utilize "hot-warm" heterogeneous storage capacity.

This invention provides a storage system and data placement method that can improve the performance of a storage system by efficiently operating multiple backend drives. [Solution] The storage system is constructed by having multiple storage nodes, each of which includes a storage control unit and is allocated multiple drives. The storage control unit reads and writes data to physical chunks in response to I / O requests from the host device. A drive has multiple physical chunks that are divided to store data. The storage control unit monitors the drive utilization rate for each of the multiple drives and, based on the drive utilization rates of the multiple drives, performs data relocation, moving data located in the physical chunks of the source drive to the physical chunks of the destination drive in order to equalize the drive utilization rates of the multiple drives.

Example implementations relate to deduplication operations in a storage system. An example includes receiving a set of data units to be stored in persistent storage of a deduplication storage system, and recording the arrival order of the set of data units in a manifest. The example also includes, in response to determining that an average unit size of the set of data units is smaller than a minimum size threshold, identifying a first data unit that is smaller than the minimum size threshold. The example also includes generating an aggregated data unit including the first data unit and a second data unit, and, in response to determining that the size of the aggregated data unit is larger than a target size threshold, replacing, in the manifest, the first data unit and the second data unit with the aggregated data unit.

The application relates to a parallel tensor cache system based on conflict-free computation and a data processing method. The system comprises: creating and maintaining two four-dimensional tensors in the memory, simultaneously constructing multiple groups of independent and uniform hash function groups, and providing a basic structure for key-value storage and mapping. For each position of the input sequence, multiple bucket indexes are generated through the hash function group, corresponding key and value vectors are accumulated into the corresponding bucket of the tensor, distributed storage of the key-value state is realized, and conflicts are avoided. A view interface is constructed, when querying, the bucket index is obtained through the hash function group, the bucket content is extracted and the approximate key-value vector is reconstructed; when performing calculation, if there is an attention mask, only the key-value to be calculated is reconstructed and sparse operation is performed, and if an unsupported operation is encountered, the key-value is automatically completely reconstructed into a dense tensor. By using the method, efficient storage of dynamic sparse tensor data and conflict-robust reconstruction can be realized under a constant memory budget.

Embodiments of the present application provide a flow control method, device, storage medium and program product. In the embodiments of the present application, in a storage space recycling offloading scenario, the target partition resource is accessed by any one of a first thread and a second thread, the target write speed threshold of the write operation and the target recycling speed threshold of the storage space recycling operation are calculated, the first thread can control the flow of the foreground write operation according to the target write speed threshold, the second thread can control the flow of the storage space recycling operation according to the target recycling speed threshold, and the flow control of the foreground write operation and the storage space recycling operation is realized in the storage space recycling offloading scenario. On the other hand, because only one thread accesses the target partition resource and data such as the target write speed threshold and the target recycling speed threshold, there is no need to increase additional mutual exclusion logic, the code complexity of the flow control can be reduced, and the flow control efficiency can be improved.

The application provides a resource management method, device and equipment. The method comprises: for each resource object, the resource object comprising at least one resource identification point, acquiring load data of each resource identification point, the load data representing resource usage of the resource identification point; determining a load level of the resource object based on the load data of each resource identification point; determining an overload control object based on the load level, the overload control object comprising at least one of a background task of the resource object, a foreground service object of the resource object and a token bucket object for counter-pressing host IO; and controlling resources occupied by the overload control object. Through the technical solution of the application, the current load can be prevented from exceeding the maximum processing capacity of the distributed storage system, and the operation stability and service reliability of the distributed storage system can be effectively improved.

The invention provides a storage space allocation method and device, equipment, a medium and a program product, and relates to the computer technology. Determining relationships between the first intermediate result and an intermediate result before the first intermediate result, between the first intermediate result and an intermediate result in synchronous operation with the first intermediate result, and between the first intermediate result and an intermediate result after the first intermediate result; based on the relationship, a storage space is allocated to the first intermediate result. Therefore, multiplexing of the storage space can be carried out based on the relations, and the purpose of saving the storage space is achieved.

Embodiments of the present application provide a hard disk space management method and device, electronic equipment and readable medium, applied to a hard disk, the hard disk includes at least one logical storage area, empty the logical storage area of the hard disk, and store the storage usage state and / or storage data state of the logical storage area by using a preset database; The metadata of the logical storage area is a data block; In the process of writing the preset to-be-written data block into the hard disk, it is judged whether there is a target logical storage area in the hard disk; The target logical storage area stores data related to the to-be-written data block; If there is, the to-be-written data block is written into the target logical storage area, and the storage usage state and / or storage data state of the target logical storage area in the database is updated; Based on the database, the garbage data block in any logical storage area in the hard disk is cleared, and the automatic implementation of the FTL implementation strategy and the function of GC of the zns disk is realized.