Emc IP Holding Company LLC

Shuo Lv

Ming Lei Zhang

Chen Gong

Huan Chen

Qiaosheng Zhou

Wilson Guoyu Hu

Leihu Zhang

Lester Zhang

Bean Bin Zhao

Deric Wang

Jun Wu

Wenjun Wang

Chao Han

Guoyu Hu

Congyue Gu

Lei Gao

Zhiqiang Li

Jian Qiang Liu

Qingyun Liu

Zan Liu

Quanhong Wang

Eileen Gu

Embodiments of the present disclosure provide a method, a device, and a computer program product for storage management. The method for storage management includes: acquiring a reading request for a first target file, the reading request including a first target file name of the first target file. The method further includes: determining a first target characteristic value for the first target file based on the first target file name. The method further includes: determining first target index information for the first target file from a mapping from characteristic values to index information based on the first target characteristic value, wherein the first target index information is used to index the first target file from a merged file. The method further includes: reading the first target file included in the merged file from a storage system based on the first target index information. As a result, access to a large number of small files can be converted into access to large files, thereby improving the overall file access efficiency.

Method, device, and computer program product for storage management

Techniques for tracking a lock involve creating an event comprising object information, and extracting the object information in the event through a thread in a thread pool. Such techniques further involve recording lock information comprising the object information according to a determination that the thread executes a lock operation. Such a lock tracking technique for a threading model can record lock information of an object when a thread performs locking and unlocking, and realize tracking of a lock operation and generating a lock analysis report.

Method, device and computer program product for tracking lock

Storage management techniques involve determining, if it is determined that lock information associated with a lock operation performed on an object is to be inserted into a storage device, a target digest for representing the lock information; determining whether an idle index not associated with a historical digest exists in an index array for indicating a plurality of storage positions in the storage device; and inserting, if it is determined that an idle index exists in the index array, the lock information into a target storage position in the plurality of storage positions by associating the target digest with the idle index. Accordingly, lock information can be quickly inserted and cleared, thereby improving the system performance.

Managing lock information associated with a lock operation

Techniques provide for data deduplication. Such techniques involve: allocating a storage area in a storage device, the storage area including a first storage segment for storing an incompressible data block and a second storage segment for storing a compressed data block, a first size of the first storage segment being greater than a second size of the second storage segment; in response to receiving a write request, determining whether data block to which the write request is related is compressible; in response to determining that the data block is incompressible, adding header information to the data block to generate a first data segment of the first size; and storing the first data segment in the first storage segment through a deduplication operation. Accordingly, such techniques can increase the flexibility and efficiency of data deduplication.

Method, device, and computer readable medium for data deduplication

Techniques involve: selecting a stream from a plurality of streams having respective update frequencies, the update frequency of the selected stream matching an update frequency of to-be-written data; determining a label of the data based on a label of the selected stream; and sending a write request for the data to a storage system, the write request comprising the label of the data, so that the storage system performs a write operation for the data based on the stream identified by the label. Accordingly, a write amplification factor can be reduced, thereby increasing the effective life of a storage device and improving read and write performance of the storage system.

Method, device and computer program for data storage

Techniques involve implementing a file system. According to such techniques, a storage system creates a plurality of files in advance, each of which maintains a continuous space to simplify the process of processing read/write requests in the file system. When there is data to be written, an appropriate pre-created file is selected. Further, according to such techniques, a file system address is mapped to a physical address using a memory management unit. In this way, the file system performance is improved greatly.

Method, device and computer program product for implementing file system

Techniques to process metadata involve: in response to receiving a modification transaction for metadata on a computing device, acquiring information related to a busyness degree of the computing device; and according to at least a determination that the busyness degree is greater than a threshold degree, modifying the metadata in a metadata storage apparatus of the computing device directly without generating a log related to the modification transaction in a log storage apparatus of the computing device. Accordingly, such techniques can achieve good processing performance irrespective of a busy state or non-busy state of a computing device. In particular, when the computing device is in a busy state, a newly triggered modification transaction can still be timely executed, thereby improving IOPS performance of the computing device in a busy state.

Method, device and computer program product for processing metadata

Techniques for cache management involve accessing, when a first data block to be accessed is missing in a first cache, the first data block from a storage device storing the first data block; selecting, when the first cache is full and based on a plurality of parameters associated with a plurality of eviction policies, an eviction policy for evicting a data block in the first cache from the plurality of eviction policies, the plurality of parameters indicating corresponding possibilities that the plurality of eviction policies are selected; evicting a second data block in the first cache to a second cache based on the selected eviction policy, the second cache being configured to record the data block evicted from the first cache; and caching the accessed first data block in the first cache. Such techniques can improve the cache hit rate, thereby improving the access performance of a system.

Method, electronic device and computer program product for managing cache

Techniques for storage management involve: in accordance with a determination that an input/output (I/O) request of a storage system is received, determining a target storage device to which the I/O request is directed. The techniques further involve: in accordance with a determination that the target storage device is a storage device of a first type, processing the I/O request by accessing a memory of the storage system. The techniques further involve: in accordance with a determination that the target storage device is a storage device of a second type different from the first type, processing the I/O request without accessing the memory, the storage device of the second type having an access speed higher than that of the storage device of the first type. Accordingly, such techniques can improve performance of a storage system.

Optimized access to high-speed storage device

Techniques for storing data involve estimating a hit ratio of a digest cache associated with a target storage device, the digest cache recording a digest of data that is stored in the target storage device after preprocessing; generating, according to a determination that the hit ratio is lower than a predetermined threshold, a digest for target data to be stored and performing the preprocessing; and storing, according to a determination that the digest of the target data is missing in the digest cache, the preprocessed target data in the target storage device, and recording the digest of the target data in the digest cache. Such techniques can achieve good system performance in both cases of high data repetition and low data repetition.

Method, electronic device and computer program product for storing data

Techniques for data writing involve: determining an unavailable storage zone in multiple storage zones of a storage area, wherein each storage zone is used to store a zip header and compressed data corresponding to the zip header; acquiring a reference zip header for the unavailable storage zone, wherein the reference zip header includes metadata indicating a zone length of the unavailable storage zone; and generating consecutive write requests for the storage area based at least on target data to be written to the storage area and the reference zip header, so as to write the target data to available storage zones in the multiple storage zones. Accordingly, rewriting of data can be implemented by constructing large consecutive write requests, thus improving the write performance of the storage device.

Method, device and computer program product for data writing

Techniques for managing threads involve acquiring respective runtime addresses and call information of a plurality of lock objects in a plurality of threads, and determining, from the plurality of lock objects, a first group of lock objects associated with first call information and a second group of lock objects associated with second call information different from the first call information. The techniques further involve providing an indication that a deadlock exists in the plurality of threads if it is determined that a first group of runtime addresses of the first group of lock objects overlaps with a second group of runtime addresses of the second group of lock objects. Accordingly, potential deadlocks in a plurality of threads can be analyzed, thereby avoiding the inability of the threads to proceed normally due to the deadlocks.

Method, device and computer program product for thread management

A data compression technique involves: selecting, from a data block, a plurality of bit strings as sample data. The technique further involves: determining a set of characters included in the sample data. Each character in the set of characters is represented by at least one bit string among the plurality of bit strings. The technique further involves: compressing the data block if statistical characteristics of the set of characters match predetermined statistical characteristics. Accordingly, incompressible data can be filtered out efficiently and accurately, so as to utilize computing resources more efficiently.

Data compression method, electronic device and computer program product

Techniques involve receiving a write request for writing metadata of a file system into a solid state disk having a multi-level cell, and then caching the to-be-written metadata into a memory. The techniques further involve sequentially writing the cached metadata into the solid state disk by redirect-on-write. Accordingly, there is a file system implemented for properties of a solid state disk having a multi-level cell. Such techniques are able to provide completely sequential write of metadata of the file system by supporting redirect-on-write, thereby reducing the write amplification of the solid state disk and improving the performance of the file system.

Sequentially writing metadata into a solid state disk by redirect-on-write

Techniques delete snapshot data. In accordance with certain techniques, a first sub-process of a snapshot deletion process on a first data block of the snapshot data is performed with a first thread. The snapshot deletion process includes at least the first sub-process and a second sub-process, the first and second sub-processes being performed sequentially. In response to an end of the first sub-process performed with the first thread, the second sub-process on the first data block is performed with the first thread. In parallel with performing, with the first thread, the second sub-process on the first data block, the first sub-process on a second data block of the snapshot data is performed with a second thread different from the first thread, the second data block being different from the first data block. Such techniques improve IO lock contention, system resource utilization rate and parallelism, response time and system overhead.

Growing community of inventors

Beijing, China

Shuo Lv