Lemon Inc.

Beijing Volcano Engine Technology Co., Ltd.

Douyin Vision Co., Ltd.

Hui Zhang

Ping Zhou

Fei Liu

Kan Frankie Fan

Chaohong Hu

Longxiao Li

Yi Wang

Bo Li

Ming Zhao

Hao Wang

Peng Xu

Jiaxin Ou

Jingwei Zhang

Zhengyu Yang

Chul Lee

Shan Xiao

Yang Liu

Sheng Qiu

Jianyang Hu

Huan Sun

Yizheng Jiao

Kuankuan Guo

Yinlin Zhang

Di Xu

A key-value store and a file system are integrated together to provide improved operations. The key-value store can include a log engine, a hash engine, a sorting engine, and a garbage collection manager. The features of the key-value store can be configured to reduce the number of I/O operations involving the file system, thereby improving read efficiency, reducing write latency, and reducing write amplification issues inherent in the combined key-value store and file system.

Key-value store and file system

Methods and systems for performing a hardware acceleration process that includes a hardware offloading engine. The hardware offloading engine includes an interface for communicating with a host device and a hardware accelerator for performing the acceleration process. The hardware accelerator has a processor configured to: receive from the interface a hardware offloading command from the host device, the hardware offloading command including an operation code, an input pointer, a total input size, and a first input size, parse the operation code, the input pointer, the total input size, and the first input size from the hardware offloading command, retrieve input data based on the input pointer and the total input size, separate the input data into a first data stream and a second data stream based on the first input size, and execute an offloaded operation on the first data stream and the second data stream.

Method and system for acceleration or offloading utilizing a multiple input data stream

A system includes a host device, a hardware offload engine, and a non-volatile storage to store on-disk data. The hardware offload engine is represented to the host device as being a storage having a virtual storage capacity, and the host device transmits an offload command to the hardware offload engine as a data write command without requiring kernel changes or special drivers.

Offload command execution for data processing acceleration

Systems and methods for accessing block storage devices are provided. In particular, a computing device may receive a write request including an uncompressed data and an uncompressed block address associated with the uncompressed data, generate compressed data by compressing the uncompressed data, determine a plurality of mapping candidates of compressed data blocks in the block storage devices based on the uncompressed block address, select a compressed data block from the plurality of mapping candidates that has sufficient capacity to store the compressed data, write the compressed data to the selected compressed data block, update metadata of the selected compressed data block to link the uncompressed block address to a compressed block address of the selected compressed data block, and write the selected compressed data block back to a respective block storage device of the block storage devices.

Transparent block device compression using hash-table

Methods, systems, and devices for performing an acceleration process by offloading an operation. The system includes a hardware offloading engine that includes a hardware accelerator for performing the acceleration process. The hardware accelerator has a processor configured to receive a hardware offloading command, the hardware offloading command including an operation code, an input pointer, and an output pointer, in which at least one of the input pointer or the output pointer includes a unified data pointer that includes one or more bits of memory for identifying the source location for the input data or the destination location of the output data, parse the operation code, the input pointer, and the output pointer from the hardware offloading command, retrieve the input data based on the input pointer, and execute an offloaded operation on the input data based on the operation code.

Method and system for acceleration or offloading utilizing a unified data pointer

A method for adaptive mapping for data compression includes determining an input/output (I/O) request pattern, dynamically switching between a segment mapping mode and a flat hash table mapping mode based on the determined I/O request pattern, updating a shared mapping table for the segment mapping mode and the flat hash table mapping mode, and adjusting an entry of the mapping table based on the determined I/O request pattern and a status of the entry.

Adaptive mapping for transparent block device level compression

A method for accessing blocks of a solid state drive is described. A starting position is received, where the starting position identifies a first block of a contiguous block region within a namespace of the solid state drive. The contiguous block region is to be accessed according to a single input/output operation and the namespace comprises two dimensions of logical address space with respective indices for indexing blocks within a corresponding dimension of the logical address space. A first dimensional identifier that identifies a size of the contiguous block region in a first dimension of the namespace is received. A second dimensional identifier that identifies a size of the contiguous block region in a second dimension of the namespace is received. Blocks of the contiguous block region are accessed in response to the single input/output operation according to the starting position, the first dimensional identifier, and the second dimensional identifier.

Multi-dimensional solid state drive block access

Systems and methods are provided for improved point querying of a database. The index values are separated from data and retained in cache memory to allow access without requiring a disk input/output (I/O) operation and thereby having less latency resulting from such disk I/O operations. The index values can be compressed using an algorithm such as Crit-Bit-Trie to allow storage of the index values in limited cache memory space. The index values can be selected for storage according to a least recently used approach when cache memory is insufficient to store all index values to maintain a hit rate for the cached portion and reduce the disk I/O operations.

Hash engine for conducting point queries

The present disclosure describes techniques of metadata management for transparent block level compression. A first area may be created in a backend solid state drive. The first area may comprise a plurality of entries. The plurality of entries may be indexed by addresses of a plurality of blocks of uncompressed data. Each of the plurality of entries comprises a first part configured to store metadata and a second part configured to store compressed data. Each of the plurality blocks of uncompressed data may be compressed individually to generate a plurality of compressed blocks. Metadata and at least a portion of compressed data associated with each of the plurality of compressed blocks may be stored in one of the plurality of entries based on an address of a corresponding block of uncompressed data. A second area may be created in the backend solid state drive for storing the rest of the compressed data.

Metadata management for transparent block level compression

Systems and methods for space allocation for block device compression are provided. In particular, a computing device may receive an allocation request to write the compressed data, select a range list adequate for serving the allocation request from a plurality of range list, dequeue a range entry from the selected range list to allocate free space for the compressed data, and allocate the free space corresponding to the range entry to the compressed data to serve the allocation request.

Space manager for transparent block device compression

A system and method are described to efficiently allocate memory space with low latency overhead by allocating blocks of non-volatile memory on a storage device according to a tree data structure comprising a plurality of counter sets, each counter set including one or a plurality of counters indicating numbers of unallocated blocks of memory space within the non-volatile memory.

Growing community of inventors

Los Angeles, CA, United States of America

Hui Zhang