Electronics and Telecommunications Research Institute

Hong-Yeon Kim

Sang-Min Lee

Young-Kyun Kim

Myung-Hoon Cha

Baik-Song An

Myung-Joon Kim

Chei-Yol Kim

Young-Chang Kim

Jeong-Sook Park

June Hwan Kim

Kwang-Won Koh

Kang-Ho Kim

Soo-Young Kim

Joon-Young Park

Dong-Oh Kim

Young-Chul Kim

Jongho Won

Ki-Dong Kang

Ki-Sung Jin

Disclosed herein is a method for distributed training of an AI model in a channel-sharing network environment. The method includes determining whether data parallel processing is applied, calculating a computation time and a communication time when input data is evenly distributed across multiple computation devices, and unevenly distributing the input data across the multiple computation devices based on the computation time and the communication time.

Method and apparatus for distributed training of artificial intelligence model in channel-sharing network environment

Disclosed herein are an apparatus and method for page allocation in a many-to-one virtualization environment. The method may include determining whether a page fault interrupt is caused by page initialization for page allocation, sending an ownership change message to a node having ownership of the corresponding page when the page fault interrupt is determined to be caused by page initialization, and initializing the corresponding page upon receiving an ownership-change-processing-complete message.

Apparatus and method for page allocation in many-to-one virtualization environment

Disclosed herein are an apparatus and method for processing fast persistent writing to nonvolatile memory. A method for processing fast persistent writing to a nonvolatile memory includes writing log data from a last storage position in a data block created in a certain size, reflecting the entire data block in a storage medium, increasing the last storage position by a size of the written log data, and reflecting the entire data block in a storage medium, wherein the data block is linearly linked to an additional data block in a creation order, and wherein the data block includes a log data storage region, information about a last storage position where the log data is stored in the log data storage region, and information about a linked next data block.

Apparatus and method for fast persistent writing to nonvolatile memory

Disclosed herein are a hybrid memory management apparatus and method for an many-to-one virtualization environment. The hybrid memory management apparatus is implemented in an inverse-virtualization-based multi-node computing system including multiple physical nodes, each containing hybrid memory in which DRAM and NVRAM coexist, a virtual machine, and hypervisors, and includes memory for storing at least one program, and a processor for executing the program, wherein the program includes a remote request service module for processing a page-related request with reference to the hybrid memory and responding to the page-related request by transmitting a result of processing, an internal request service module for processing an internal page fault request with reference to a hybrid memory and responding to the internal page fault request, and a data arrangement module for responding to an inquiry request for a location at which a newly added page is to be arranged in the hybrid memory.

Hybrid memory management apparatus and method for many-to-one virtualization environment

Disclosed herein are a distributed system and a method for operating the distributed system. The method for operating a distributed system including a server and multiple clients includes acquiring, by a first client of the multiple clients, a lock on a shared resource using a first table of the server and a second table of the client, and releasing, by the first client, a lock on the shared resource using the first table and the second table, wherein the first table is a lock (DSLock) table for storing information about a distributed shared resource, and the second table is a data structure (DSLock_node) table for a lock request.

Distributed system for distributed lock management and method for operating the same

Disclosed herein are a metadata server and a method for distributing metadata in units of directories using the metadata server. The method includes receiving a request for at least one of creation, deletion and retrieval from a user file system; acquiring an inode corresponding to an identifier of a parent inode, which is included in the request; searching the parent inode for a dentry corresponding to the request when the request is a request to create a directory; selecting a secondary metadata server in which a new directory is to be created in order to distribute metadata in units of directories; requesting the selected secondary metadata server to create an inode; receiving an identifier of the created inode from the secondary metadata server; and adding a new dentry to the parent inode using the identifier of the inode.

Metadata server and method for distributing metadata in directories using the same

Disclosed herein is a distributed file system using a torus network. The distributed file system includes multiple servers. The location of a master server may be determined to shorten the latency of data input/output. The location of the master server may be determined such that the distance between the master server and a node farthest away from the master server, among nodes, is minimized. When the location of the master server is determined, the characteristics of the torus network and the features of a propagation transmission scheme may be taken into consideration.

Distributed file system using torus network and method for operating the same

Disclosed herein are a method for automatically allocating IP addresses for a distributed storage system in a large-scale torus network and an apparatus for the method. The method for automatically allocating IP addresses includes acquiring neighboring-node information from multiple storage nodes that constitute the system; generating torus network topology for the multiple storage nodes by combining the neighboring-node information; generating IP address information through which a position of each of the multiple storage nodes in a structure corresponding to the torus network topology can be identified; and allocating IP addresses to the multiple storage nodes by delivering the IP address information to the multiple storage nodes.

Method for automatically allocating IP address for distributed storage system in large-scale torus network and apparatus using the same

Disclosed herein are a method and system for supporting user-level DMA I/O in a distributed file system environment. The system includes a DMA I/O library located in a user space and configured to process data-processing requests of an application using a control channel or a data channel, a distributed file system client process located in the user space and configured to process data while communicating with a remote distributed storage cluster, a VFS located in a kernel space, and a FUSE kernel module located in the kernel space, wherein the control channel is a path along which the DMA I/O library and the distributed file system client process are connected to each other through the VFS and the FUSE kernel module, and wherein the data channel is a path along which the DMA I/O library and the distributed file system client process are directly connected to each other.

System and method for supporting user-level direct memory access input/output in distributed file system environment

Disclosed herein is a distributed file system using a torus network. The distributed file system may include multiple servers. The multiple servers are connected with each other through an n-dimensional torus network, and each of the multiple servers may be arranged along n-dimensional axes. Among the servers in the distributed file system, a server group of an (n&#x2212;1)-dimensional torus network may be connected to a public network. Different loads of the distributed file system may be distributed based on the axes. Through the distribution, the processing performance of the distributed file system may be improved.

Distributed file system using torus network and method for configuring and operating distributed file system using torus network

Disclosed are a method and apparatus for reading data in a distributed file system in which a client and a server are separated. In the method and apparatus, a prefetching operation is performed to provide a continuous read function with high performance even in the distributed file system so that an optimum continuous read function of a local file system within the client may be effectively supported when an application program of the client requests continuous reading on a file (or chunk).

Method and apparatus for reading data in distributed file system

There are provided a system and method for providing a virtual desktop service using a cache server. A system for providing a virtual desktop service according to the invention includes a host server configured to provide a virtual desktop service to a client terminal using a virtual machine, a distributed file system configured to store data for the virtual machine, and a cache server that is provided for each host server group having at least one host server, and performs a read process or a write process of data using physically separate caches when the read process or write process of the data is requested from the virtual machine in the host server.

System and method for providing virtual desktop service using cache server

Provided are an apparatus and a method for acquiring a consistent result even if one client accesses any metadata server in a circumstance that the cluster configuring many metadata servers exist. The apparatus as mentioned above includes a deletion file list unit that stores information about a deleted metadata during a predetermined period; and a metadata server selector that selects a metadata server to receive a operation request about a metadata among a plurality of metadata servers based on information from the deletion file list unit.

Apparatus and method for accessing a metadata

Provided are a method and a system for managing a file metadata, which are independent of a address change of a data server and movements of a disk by using a location of disk where data exists actually as a location information of a file data. The method for managing the file metadata includes determining whether the request of the metadata is valid, verifying information of a disk storing a file data corresponding to the metadata and a data server address in which the file data exists, and transmitting the verified address of the data server to the client. According to the method and the system for managing the file metadata, data services can be continuously provided without modifications of a file metadata even if the data server address is changed.

Method and system for managing file metadata transparent about address changes of data servers and movements of their disks

A method for file deletion and recovery against system failures in a database management system comprising steps of deleting files listed in a pending action list during a transaction commit process, writing a non-atomic file deletion as an atomic operation into a log and recovering uncompleted file deletion during restart recovery by using the log is disclosed. When system failures occur during file deletion in a database management system, resources of which releasing is interrupted by failures are released perfectly through recovery step, so it is advantageous in that coherency of data is maintained and efficiency of storage device arises.

Growing community of inventors

Daejeon, South Korea

Hong-Yeon Kim