Electronics and Telecommunications Research Institute

Dong Jae Kang

Young Ho Kim

Chang Soo Kim

Sung In Jung

Bum Joo Shin

Eun Ji Lim

Yu Hyeon Bak

Ji Hyun Lee

Myung-Joon Kim

Myung Joon Kim

Hag Young Kim

Hyun Joo Bae

Chang-Soo Kim

Jin Mee Kim

Gyu Il Cha

Yuhyeon Bak

Gyu Ii Cha

Seok Ho Son

A cloud service broker apparatus and method thereof are provided. The cloud service broker apparatus includes a controller configured to provide a brokerage service between a plurality of cloud service providers and a cloud service user by dividing a cloud service requested by the cloud service user into a plurality of cloud service segments and distributing each of the cloud service segments to each of the clouds.

Cloud service broker apparatus and method thereof

Disclosed is a software architecture supporting a large-capacity collective memory layer in a multi-node system by using a remote direct memory access technique and a software virtualization technique and a computing system performing computing processing by using the architecture. In particular, provided is a software architecture including: a memory region managing module collectively managing a predetermined memory region of a node, a memory service providing module providing a large-capacity collective memory service to a virtual address space in a user process, and a memory sharing support module supporting sharing of the large-capacity collective memory of the multi-node system.

Software architecture for service of collective memory and method for providing service of collective memory using the same

Disclosed is an apparatus for processing a remote page fault included in an optional local node within a cluster system configuring a large integration memory (CVM) by integrating individual memories of a plurality of nodes. The apparatus includes a memory including a CVM-map, a node memory information table, a virtual memory area, and a CVM page table, and a main controller mapping the large integration memory to an address space of a process when a user process requests memory allocation.

Apparatus for processing remote page fault and method thereof

A file level striping method adds an option for indicating whether or not to support file level striping to a file creation interface in a file system, extends an inode structure to include a last disk ID field, initializes the last disk ID when the file is created in the file system, allocates a physical block based on the last disk ID when the physical block allocation is requested at the time of file I/O request in the file system, and modifies the last disk ID value to reflect the physical block allocation made by a volume manager. An apparatus using the file level striping method includes a number of disks for storing information actually, the volume manager for logically grouping a number of disks and a file system for creating files on said logical volume and performing I/O operations.

Apparatus and method for file level striping

An efficient snapshot technique based on a mapping for a large logical volume shared in multiple hosts. According to the present invention, problems of time delays in a conventional snapshot technique is solved by employing a FAB and an SSB, which are bits representing whether a COW operation is carried out to a mapping entry. In other words, the present invention solves the problems of delaying a write operation of corresponding volume, which is simultaneously executed when a snapshot is created, until the snapshot creation is completed.

System and method of an efficient snapshot for shared large storage

Disclosed is a coherence preservation method of duplicated data in RAID subsystem. The method comprises the steps of: if a read operation is requested by the RAID subsystem, selecting an arbitrary target disk among disks having duplicated data, and implementing the read operation on the selected disk; implementing a read error handling to determine whether an error occurs in the disks selected upon the read operation, and if the error occurs in the read operation of the selected target disk, repeating the read error handling until the read operation of the data succeeds by circulating the remaining metering-treated disks in turns; after the read error handling, if the read operation on the remaining disk in all succeeds, completing the read error handling, and if the read operation on the remaining disk in all fails, returning the error to the disk, and completing the read error handling; if a write operation is requested by the RAID subsystem, implementing the write operation on the disks having duplicated data; after implementing the write operation, if a temporary error occurs in the duplicated data, implementing a temporary error handling to maintain the data coherence in the disks having the duplicated data and to recover the temporary error; and after implementing the write operation, if a permanent error occurs in the duplicated data, implementing a permanent error handling to maintain the data coherence in the disks having the duplicated data and to recover the permanent error.

Coherence preservation method of duplicated data in RAID subsystem

Growing community of inventors

Daejeon, South Korea

Dong Jae Kang