Electronics and Telecommunications Research Institute

Hong Yeon Kim

Young Kyun Kim

Myung Hoon Cha

Wan Gyun Choi

Sang Min Lee

Han Namgoong

Young Chang Kim

June Hwan Kim

Ki Sung Jin

Hun Soon Lee

Sang-Min Lee

Myung-Joon Kim

Myung Joon Kim

Jeong Sook Park

Chei Yol Kim

Dong Oh Kim

A distributed storage server includes a plurality of data server devices and a plurality of metadata server devices. The metadata server devices store metadata associated with data which is distributively stored in the data server devices. A selected metadata server device checks whether a dangling directory occurs by performing a rename operation, based on information associated with a full path of a parent directory of a source and a full path of a parent directory of a target included in a request of the rename operation. When it is determined that the dangling directory does not occur, the selected metadata server device processes transactions directed to the metadata such that the rename operation is performed. The checking whether the dangling directory occurs is performed before a transaction period for processing the transactions.

Distributed storage server, server device included therein, and method of operating server device

A distributed file system includes metadata servers and data servers. The metadata server includes a selecting unit to select a data server from the data servers, a chunk allocation requesting unit to request that the selected data server perform chunk allocation, a chunk list managing unit to insert a list of chunks transmitted from the data server into a chunk list pool and determine an arrangement method of the chunk list pool, and a chunk fetching unit to fetch available chunk information from the chunk list pool. The data server includes a receiving unit to receive request for chunk allocation from the metadata server, a chunk allocating unit to allocate chunks in response to the request for chunk allocation and write a list of chunks based on information about the allocated chunk, and a transmitting unit to transmit the list of chunks to the metadata server.

Distributed file system and method of creating files effectively

Provided herein is a filing system creating and deleting apparatus, comprising an available inode pool in which inodes are to be stored, a file system object creating processor creating an inode allocating request signal in response to a file system creating request from an external resource, an inode allocating processor allocating at least one of inodes stored in the available inode pool in response to the inode allocating request signal, a file system object deleting processor creating an inode deallocating request signal in response to a file system deleting request from the external resource, an inode deleting thread collecting inodes requested to be deleted corresponding to the file system deleting request, and an inode deallocating processor deallocating the inode requested to be deleted from the inode deleting thread, wherein a number of inodes stored in the available inode pool is limited to no more than a maximum inode number in the available inode pool, and the inode requested to be deleted creates and deletes a file system stored in the available inode pool when the number of inodes stored in the available inode pool is smaller than the maximum inode number in the available inode pool.

File system creating and deleting apparatus and driving method thereof

Provided herein is a shuffle embedded distributed storage system and method supporting virtual merge, the system and method including a distributed shared storage configured to store a virtual merged file; a plurality of map servers connected to the distributed shared storage via a network, and configured to perform a map function and record a map result data computed as a result of the map function in the distributed shared storage by means of a map result file; and a plurality of reduce servers connected to the distributed shared storage and the map servers via the network, wherein the virtual merged file includes a list of the map result files recorded by the plurality of map servers, and an identifier of a reduce server to which the virtual merged file is to be transmitted.

Shuffle embedded distributed storage system supporting virtual merge and method thereof

A distributed file system, based on a torus network, includes a center node and one or more storage nodes. The center node encodes data when the data is received from a client. The one or more storage nodes receive data blocks or parity blocks from the center node and store the data blocks or parity blocks.

Distributed file system based on torus network

A distributed file system based on a torus network includes a plurality of metadata servers configured to store metadata of files, a plurality of data servers configured to divide data and store the divided data in a distributed manner, and at least one management server configured to manage the metadata servers and the data servers. The plurality of metadata servers, the plurality of data servers, and the at least one management server are disposed on first to nplanes each of which consists of a plurality of nodes, and the first plane is connected to a plurality of clients through a switch.

Distributed file system and operating method of the same

A virtual machine host server includes a virtual machine in which a guest operating system is installed and operated, a cache manager for processing at least one of an open request, a close request, and an input/output request for a disk image file of the virtual machine, which is stored in a storage system, and managing a boot workload map and a boot segment, a cache device for caching the boot segment, and a prefetch manager for prefetching the boot segment from the cache device.

Virtual machine host server apparatus and method for operating the same

Disclosed is a method of calculating parity. The method dividing, by a client system, a file which is to be stored into chunks of a preset size and distributively storing the chunks in a plurality of data servers; sending, by the client system, a data write complete notification message to a metadata server; storing, by the metadata server, a file sent through the data write complete notification message in a recovery queue; and sending, by the metadata server, a random data server a parity calculation request for the file stored in the recovery queue.

Method of calculating parity in asymetric clustering file system

Disclosed are an apparatus, a system, and a method for recovering meta data using fragmentary information. The system for recovering meta data includes: a data server storing recovery information for recovering at least one data file and meta data related to each of the data file; and a meta data server storing the meta data related to the data files and receiving the recovery information from the data server when the meta data are lost to recover the lost meta data. By this configuration, the exemplary embodiment of the present invention stably can the lost meta data of the meta data server by using the recovery the meta data and prevent the phenomenon that the meta data collides with each other on the same directory hierarchical structure.

Apparatus, system and method for recovering meta data using fragmentary information

Provided is a hot data management method based on hit counter, which prevents loads from being concentrated on a specific data server due to hot data by efficiently managing the hot data in the asymmetric storage system. Each of data servers of an asymmetric storage system checks hit counter for data stored in the corresponding data server to maintain hit counter information on the data in a latest state. The data server transmits the hit counter information to a metadata server at predetermined intervals. The data server makes or deletes a copy of the data according to the determination of the metadata server whether the data is hot data.

Hot data management method based on hit counter

A file storage system, a file storing method, and a file searching method. In the file storing method, a single file to be stored is classified into at least one or more objects, and the classified objects are classified into pages with a serial number. One storage device to record the file is selected among a plurality of storage devices connected through a network. One object is allocated to the selected storage device. Pages configuring the file of the object allocated to the selected storage device are stored. When all pages of the file are not stored, the remaining pages are stored by allocating new object to a new storage device. Metadata for managing information about the storage of the file is set. Accordingly, the file can be stored over several disks. In addition, the overall system performance can be increased by setting the file information in the object metadata simply using the least resources.

File storage system, file storing method and file searching method therein

A cache consistency maintenance procedure to select one of a detection-based cache consistency maintenance procedure optimized for record-based locking and an avoidance-based consistency-based maintenance procedure optimized for table and block-based locking. To support the characteristic of DBMS in which table locking and record locking are consistent to access the same table, the two kinds of the consistency maintenance policies for the same block are processed by a single buffer load process and the two kinds of the consistency maintenance policies are consistent with each other to provide better configuration and performance.

Buffer allocation method supporting detection-based and avoidance-based consistency maintenance policies in a shared disk-based multi-database management system

Growing community of inventors

Daejeon, South Korea

Hong Yeon Kim