13 results about "Reference counting" patented technology

In some implementations, a memory apparatus may receive a command to write data to volatile memory of the memory system. The memory apparatus may compare the data to one or more data patterns to identify whether the data matches a data pattern of the one or more data patterns. The memory apparatus may increment a reference counter associated with the data pattern based on identifying that the data matches the data pattern. The memory apparatus may write, based on identifying that a measure flag associated with the data pattern is set, the data to the volatile memory.

The present disclosure relates to a request-level consistency control method and system for dynamic configuration hot update. The method comprises: organizing configuration content into multiple versioned configuration snapshots, establishing a corresponding reference count for each versioned configuration snapshot, and setting a candidate version; enhancing a configuration reading path in a service node by plugging so as to be able to perform a configuration reading operation according to a bound version; in response to receiving a service request, creating an activation token for the service request, obtaining a current candidate version as the bound version, writing the bound version into the activation token, and increasing the reference count of the bound version; during processing of the service request, when configuration needs to be read, reading a configuration value from a corresponding versioned configuration snapshot according to the bound version in the activation token; and in response to the processing of the service request being completed, decreasing the reference count of the bound version by one.

Embodiments of the present application disclose a reference counting method and a related apparatus. The method comprises: acquiring an idle target data block from a storage space; establishing a plurality of counters in the target data block, the number of the plurality of counters corresponding to the grouping situation of a plurality of cores of a central processing unit (CPU); in response to a Pin / Unpin operation performed on the target data block, determining a target core corresponding to the Pin / Unpin operation, the target core belonging to the plurality of cores; on the basis of the target core, determining a corresponding target counter, the target counter belonging to the plurality of counters; and performing, by means of the target counter, reference counting corresponding to the Pin / Unpin operation. The method can be used for increasing the speed of Pin / Unpin on a multi-core CPU, thereby improving the overall performance of a system.

This application discloses a reference counting method and related apparatus. The method includes: acquiring a free target data block in storage space; establishing multiple counters in the target data block, the number of counters corresponding to the grouping of multiple cores of a central processing unit (CPU); determining the target core corresponding to the pin / unpin operation in response to a pin / unpin operation on the target data block, wherein the target core belongs to multiple cores; determining the corresponding target counter based on the target core, wherein the target counter belongs to multiple counters; and performing reference counting corresponding to the pin / unpin operation using the target counter. This method can be used to improve the speed of pin / unpin on multi-core CPUs, thereby improving the overall system performance.

An apparatus includes a processing means configured to maintain a deduplicated data structure including sub-sections of data block identifiers associated with different compression ratio ranges and having different numbers of data block identifiers. The processing means is further configured to identify a given data block identifier and a given compression ratio for a given data block to be stored, and to determine whether the given data block identifier is in a given sub-section having a given compression ratio range including the given compression ratio. The processing means is further configured to write the given data block to a physical space block of a storage system in response to determining that the given data block identifier is not in the given sub-section, and to increment a deduplication reference count of the given data block identifier in response to determining that the given data block identifier is in the given sub-section.

The application discloses a method for volume priority reconstruction, comprising: creating at least two priority containers and associating storage volumes to direct data storage; scanning gc objects and associating storage objects by GC to record garbage amount and garbage bitmap of the storage objects for triggering garbage collection of the storage objects and identifying valid data; calculating target disks of the storage objects and their states by a layout algorithm and marking objects with target disk failure as to-be-reconstructed objects; periodically iterating the gc objects by a GC producer to add the to-be-reconstructed objects to a failure hash bucket and increase reference counts; extracting the to-be-reconstructed objects by a GC consumer to move valid data of the to-be-reconstructed objects to new storage objects with healthy target disks through an aggregation module; reducing counts and removing the objects after the moving is completed; and reporting reconstruction progress based on hash bucket count states of each node. The application realizes specified data priority reconstruction and guarantees important business data priority recovery safety through priority container association and GC directed moving.

The application discloses a kind of application data reference management and garbage collection.The application data reference management method includes: when detecting that target application data is referenced by target variable, and target variable belongs to target variable type, the logical address of the target application data is written into the physical address of the target variable;The logical address corresponding to the physical address of target variable is written into the reference address table as a reference address.The technical scheme of the embodiment of the application uses the reference address table to manage the application data reference not recorded in the reference array, avoids mistaking such application data as garbage data and being deleted, thereby avoiding the empty exception caused by referencing non-existent application data, the reference address table records reference address instead of the logical address of application data, avoids the need to modify application data reference counter or the content in reference address table when reference relationship is cleared, and ensures application execution efficiency.

This application provides a method for processing internal snapshots in qcow2 format, a cloud platform for implementing the method, and a computer-readable medium. This solution shifts the update processing of COW tags and reference counts from the internal snapshot creation stage to the data writing stage triggered by the COW mechanism. It no longer needs to traverse the index table to update the COW tags and index counts of all clusters in real time when creating an internal snapshot. Instead, it uses the additionally set global snapshot ID in this solution to determine whether the COW mechanism has been triggered, and updates the COW tags and reference counts asynchronously when triggered. This can significantly improve the performance of creating internal snapshots and reduce the impact on virtual machine services.

A hierarchical scheduling method and system for key-value caches aware of inconsistent memory access, relating to the field of large model inference technology. This application achieves reference counting and countdown mode switching by reusing a single byte metadata field. The key-value cache block status is updated when a request hits or ends its use. During eviction, a score is calculated for reference-counted blocks based on the normalized value of the most recent access timestamp, the affinity coefficient of the inconsistent memory access node, and the reference count. Blocks whose countdown has not reached zero are not included in the eviction candidate. Blocks with zero countdowns are scored based on access time and affinity coefficient, with high-scoring blocks prioritized for eviction and written to the next level of storage. This application solves the problems of existing technologies that fail to distinguish between the shared value of cache blocks and the eviction cost of inconsistent memory access, and are prone to intermittently eviction of high-value blocks due to requests. It improves cache hit rate with low metadata overhead, reduces cross-node recalculation, and increases system throughput.

The application provides a pointer recycling method, system and device, the method comprising: scanning source code or an abstract syntax tree through a compile-time automatic instrumentation module, identifying a resource reference entry and a target variable to be managed, inserting a cleanup attribute and ownership transfer semantics for the target variable, and generating a resource description table; the resource reference entry comprises a naked pointer; the naked pointer is wrapped using a lightweight proxy structure, and metadata is associated through the lightweight proxy structure; a resource in the resource description table is registered, reference count management is performed, cross-function transfer migration is performed, and a unified cleaning operation is performed through a runtime resource manager, to obtain a pointer life cycle state; system memory occupation information is collected in real time at runtime, memory recycling frequency and strategy are dynamically adjusted according to the memory occupation information, and resource recycling is performed according to the pointer life cycle state. The scheme improves the stability of long-term system operation, and improves the stability, reliability and development efficiency of C language software development.

This specification provides a binary translation method. After obtaining the intermediate representation sequence corresponding to the basic block to be translated, a Pass optimization process is added to remove redundant instructions and reduce the performance loss of binary translation. Specifically, the optimization process may include: replacing the operand of the first intermediate representation with the target source operand of the first second intermediate representation preceding the first intermediate representation, so that the reference count of the second intermediate representation is zero. Based on the above optimization process, during the translation of multiple first instructions that read and write to the same destination register, the second instructions obtained based on multiple first intermediate representations can be processed continuously in the same register (e.g., a temporary register) without copying data to the destination register midway, which helps to reduce the number of second instructions obtained in the final translation, thereby reducing performance loss.

A system can store data in a filesystem as blocks. The system can select a similarity hash type for a first block of the blocks from a group of similarity hash types based on a file type associated with data of the first block. The system can perform a corresponding similarity hash on the first block according to the similarity hash type, to produce a first hash. The system can identify a second block of the blocks that satisfies a similarity criterion relative to the first block based on the first hash and respective second hashes in a hash database that stores respective virtual mapping pointers to respective blocks that have a same similarity hash type. The system can perform deduplication on the first block using a dictionary associated with the second block, and incrementing a reference count of the dictionary.

The application provides a data recovery method and device, which are used in the technical field of computers. The method comprises the following steps: determining first data, wherein the first data is application data when an application program is normally running; saving the first data to a handle record, wherein the handle record is managed by using a reference counting mechanism; obtaining the handle record when the application program is abnormally restarted; and restoring the application program to a state before the abnormality according to the handle record. By the method, the application data when the application program is normally running is persistently saved, and the application program is restored after the abnormal restart, so that the state and the data of the application program are consistent with those before the abnormal restart, and the user experience is improved.