-
公开(公告)号:KR1020170102772A
公开(公告)日:2017-09-12
申请号:KR1020160025336
申请日:2016-03-02
Applicant: 한국전자통신연구원
Inventor: 천한성
CPC classification number: G06F17/30082 , G06F3/0604 , G06F3/061 , G06F3/0631 , G06F3/064 , G06F3/0643 , G06F3/0659 , G06F3/0679 , G06F12/0246 , G06F17/30218 , G06F2212/1016 , G06F2212/214 , G06F2212/7202 , G06F2212/7205 , G06F2212/7207
Abstract: 본발명은로그구조파일시스템의메타데이터저장방법, 시스템및 컴퓨터판독가능한기록매체에관한것이다. 본발명에따른로그구조파일시스템의메타데이터를저장하는방법은, 블록번호와블록의할당요청인지해제요청인지여부를나타내는정보를포함하는블록관리요청신호를수신하는단계, 상기블록번호를참조로하여상기블록이속하는세그먼트번호를산출하는단계, 산출된세그먼트번호에대응하는메타데이터세그먼트사용정보(MSU) 항목-상기메타데이터세그먼트사용정보(MSU)는세그먼트번호와유효블록수에대한정보를포함함-을획득하는단계및 상기블록관리요청신호가할당요청에해당하는경우, 상기메타데이터세그먼트사용정보(MSU) 항목의유효블록수 값을하나증가하고, 상기블록관리요청신호가해제요청에해당하는경우, 상기메타데이터세그먼트사용정보(MSU) 항목의유효블록수 값을하나감소시키는단계를포함할수 있다.
Abstract translation: 元数据在日志结构文件系统中的存储方法,系统和计算机可读记录介质技术领域本发明涉及一种用于在日志结构文件系统中存储元数据的方法, 如何将日志结构文件系统的元数据存储在根据本发明,一种方法包括:接收包括指示信息的块管理请求信号是否关断是否一个块号和块请求的分配请求,参照块号 在步骤中,使用对应于所计算出的段数,用于计算属于该块的段数的信息(MSU)项的元数据段 - 使用的元数据段信息(MSU)包括在段号和信息的有效块的数目 下文中 - 为对相,并且当所述对应的分配请求块管理请求信号,所述元数据增加了使用信息(MSU)的项目的值的有效块的数目的一个段,并释放该块管理请求信号请求以获取 将元数据段使用信息(MSU)项目的有效块数量的值减1。
-
公开(公告)号:KR1020130087898A
公开(公告)日:2013-08-07
申请号:KR1020120009142
申请日:2012-01-30
Applicant: 한국전자통신연구원
IPC: G06F12/06
Abstract: PURPOSE: An apparatus and a method for allocation of memory block are provided to store only data on a read-only file in a block, of which the searched erasure number is greater, to prevent an additional writing operation even in the storage of a different new file or the operation of a garbage collector, thereby enhancing the overall performance of a flash memory. CONSTITUTION: A flash memory (200) includes a plurality of blocks. If the flash memory receives a request for the block allocation of a file, a memory controller (100) determines whether the file has a first attribute. If the file has the first attribute, the memory controller compares a size of the file with a size of each of the blocks. If the size of the file is larger than that of each of the blocks, the memory controller selects the first block. If data stored in the first block is not data having the first attribute, the memory controller moves the stored data to a second block, of which the erasure number is smallest. [Reference numerals] (100) Memory controller; (200) Flash memory
Abstract translation: 目的:提供一种用于分配存储器块的装置和方法,用于仅将数据存储在所搜索的擦除次数较多的块中的只读文件上,以防止即使在不同的存储器中存储附加的写入操作 新文件或垃圾收集器的操作,从而提高闪存的整体性能。 构成:闪存(200)包括多个块。 如果闪存接收到对文件的块分配的请求,则存储器控制器(100)确定文件是否具有第一属性。 如果文件具有第一个属性,则存储器控制器将文件的大小与每个块的大小进行比较。 如果文件的大小大于每个块的大小,则存储器控制器选择第一个块。 如果存储在第一块中的数据不是具有第一属性的数据,则存储器控制器将存储的数据移动到擦除次数最小的第二块。 (附图标记)(100)存储器控制器; (200)闪存
-
公开(公告)号:KR1020110070656A
公开(公告)日:2011-06-24
申请号:KR1020100018141
申请日:2010-02-26
Applicant: 한국전자통신연구원
Abstract: PURPOSE: Data processing method and device are provided to shorten mount time by reducing the occupancy of a main memory space. CONSTITUTION: A mapping table processor(10) generates a mapping table corresponding to a saving space of a flash memory. A write buffer(20) performs data write operation of the flash memory. If the data is recorded by a page unit, a block selector(30) selects an empty table by searching a page table from the mapping table. The write buffer records the data of the corresponding page.
Abstract translation: 目的:提供数据处理方法和设备,通过减少主存储空间的占用来缩短安装时间。 构成:映射表处理器(10)生成对应于闪速存储器的存储空间的映射表。 写入缓冲器(20)执行闪速存储器的数据写入操作。 如果数据由页面单元记录,则块选择器(30)通过从映射表搜索页表来选择一个空表。 写缓冲区记录相应页面的数据。
-
公开(公告)号:KR1020150104434A
公开(公告)日:2015-09-15
申请号:KR1020140026166
申请日:2014-03-05
Applicant: 한국전자통신연구원
Inventor: 천한성
IPC: G06F12/02
CPC classification number: G06F3/0619 , G06F3/061 , G06F3/0617 , G06F3/064 , G06F3/0679 , G06F17/30218
Abstract: 본 발명은 로그 구조 파일시스템(LFS; Log-structured File System)의 데이터 저장 방법에 관한 것으로, 세그먼트 요약 정보(SS)와 세그먼트 사용 정보(SU)를 별도로 저장하지 않고 체크포인트를 기록시 체크포인트 레코드에 포함시켜 기록함으로써 플래시 페이지에 기록해야 하는 메타데이터의 개수를 줄여 플래시 메모리에 대한 쓰기 성능을 높일 수 있는 방법에 관한 것이다.
Abstract translation: 本发明涉及用于存储日志结构文件系统(LFS)的数据的方法。 该方法不分别存储分段摘要(SS)信息和分段使用(SU)信息,并且在记录检查点时通过将检查点包括在检查点记录中来记录检查点,从而减少要记录在闪存中的元数据的数量 页面,并提高闪存的写入性能。
-
公开(公告)号:KR1020120072228A
公开(公告)日:2012-07-03
申请号:KR1020100134063
申请日:2010-12-23
Applicant: 한국전자통신연구원
Inventor: 천한성
CPC classification number: G06F12/0246 , G06F17/30218 , G06F2212/7205
Abstract: PURPOSE: A file system of a flash memory is provided to secure available main memory space and to increase booting time speed by reducing mount time for reading metadata. CONSTITUTION: A PEB(Physical Erase Block) layer(3) recognizes a PEB of a flash memory(4) as a PEB address unit. An LEB layer(2) supplies an LEB(logical erase block) address to the file system layer. The LEB layer performs wear-leveling and stores an erase counter in the PEB.
Abstract translation: 目的:提供闪存的文件系统来保护可用的主存储空间,并通过减少读取元数据的安装时间来增加引导时间速度。 构成:PEB(物理擦除块)层(3)将闪存(4)的PEB识别为PEB地址单元。 LEB层(2)向文件系统层提供LEB(逻辑擦除块)地址。 LEB层执行磨损均衡,并将擦除计数器存储在PEB中。
-
公开(公告)号:KR1020100062860A
公开(公告)日:2010-06-10
申请号:KR1020090032205
申请日:2009-04-14
Applicant: 한국전자통신연구원 , 이화여자대학교 산학협력단
IPC: G06T17/00
CPC classification number: G06T11/001 , G06K9/4661 , G06T13/80 , G06T15/06
Abstract: PURPOSE: A skin texture rendering method considering the observation direction and illumination and an apparatus thereof are provided, in which the outer cover and subcutaneous tissue of creature, and the external lighting and optical interaction are analyzed, and then the skin of creature is rendered according to the analyzed result. CONSTITUTION: An image acquisition unit obtains the image of the skin surface of creature(S301). A BRDF(Bidirectional Reflectance Distribution Function) estimation unit creates the BRDF image(S305) according to the location of the skin surface of creature. A spherical reflecting mirror measures the BRDF light source direction of the skin surface(S309). A white paper measures the BRDF light source intensity of skin surface(S313). An applying unit applies the image to the shader program(S317).
Abstract translation: 目的:提供考虑观察方向和照明的皮肤纹理渲染方法及其装置,其中分析生物的外盖和皮下组织,以及外部照明和光学相互作用,然后根据 分析结果。 构成:图像获取单元获得生物的皮肤表面的图像(S301)。 BRDF(双向反射分布函数)估计单元根据生物的皮肤表面的位置创建BRDF图像(S305)。 球面反射镜测量皮肤表面的BRDF光源方向(S309)。 白皮书测量皮肤表面的BRDF光源强度(S313)。 应用单元将图像应用于着色程序(S317)。
-
公开(公告)号:KR1020140038110A
公开(公告)日:2014-03-28
申请号:KR1020120104410
申请日:2012-09-20
Applicant: 한국전자통신연구원
Inventor: 천한성
CPC classification number: G06F12/0253 , G06F12/0246 , G06F17/30218
Abstract: A method for managing a file system and an apparatus using the same are disclosed. The file managing apparatus, according to one embodiment of the present invention, manages files using a logical erase block (LEB) which corresponds to a physical erase block (PEB), and comprises: a free LEB list which stores a free LEB capable of writing to all pages of the LEB; a dirty LEB list which stores a dirty LEB instead of the free LEB; and a worn-out area determination module which determines a worn-out area for at least one of the dirty LEB depending on whether a mapping of the LEB and a block table which displays the block usage for at least one block to the PEB is present or not. [Reference numerals] (2001) Dirty LEB list; (2002) Free LEB list; (2110) Write module; (2120) Block allocation module; (2130) Garbage collection module; (2140) Worn-out area determination module
Abstract translation: 公开了一种用于管理文件系统的方法和使用该文件系统的装置。 根据本发明的一个实施例的文件管理装置使用对应于物理擦除块(PEB)的逻辑擦除块(LEB)来管理文件,并且包括:一个免费的LEB列表,其存储能够写入的空闲LEB 到LEB的所有页面; 一个肮脏的LEB清单,存储一个脏的LEB而不是免费的LEB; 以及破坏区域确定模块,其根据是否存在向PEB显示至少一个块的块使用的LEB和块表的映射来确定用于至少一个脏LEB的磨损区域 或不。 [参考数字](2001)Dirty LEB list; (2002)免费LEB清单; (2110)写模块; (2120)块分配模块; (2130)垃圾收集模块; (2140)磨损区域确定模块
-
公开(公告)号:KR1020130068630A
公开(公告)日:2013-06-26
申请号:KR1020110135925
申请日:2011-12-15
Applicant: 한국전자통신연구원
CPC classification number: G06F9/4401 , G06F9/4411 , G06F9/24 , G06F9/4403 , G06F2211/1097
Abstract: PURPOSE: A method for Initializing an embedded device and a device thereof are provided to improve booting performance, to save memory spaces, and to resolve a duplication problem by composing an Initializing program and an Initializing script as one. CONSTITUTION: An initializing module(406) includes an execution module as an alternate function of an initializing script. A booting sequence control module(410) loads a booting sequence including an operation sequence of a boot process and the initializing module performs the alternate function based on the booting sequence. If a boot loader is operated and a kernel is loaded, an initializing program module(401) executes a function of the initializing module through the booting sequence control module and sets up an embedded system as an usable state. [Reference numerals] (401) Initializing program module; (402) Script replacement function module; (403) Process clean-up module; (404) State controller; (405) Service manager module; (406) Initializing module; (407) Kernel module initialization; (408) Application program initialization; (409) File system initialization; (410) Booting sequence control; (411) Network construction; (412) Environment variable initialization
Abstract translation: 目的:提供一种初始化嵌入式设备及其设备的方法,以提高启动性能,节省存储空间,并通过组合初始化程序和初始化脚本来解决复制问题。 构成:初始化模块(406)包括作为初始化脚本的备用功能的执行模块。 引导顺序控制模块(410)加载包括引导过程的操作序列的引导序列,并且初始化模块基于引导顺序执行备用功能。 如果操作引导加载程序并加载内核,则初始化程序模块(401)通过引导顺序控制模块执行初始化模块的功能,并将嵌入式系统设置为可用状态。 (附图标记)(401)初始化程序模块; (402)脚本替换功能模块; (403)过程清理模块; (404)国家控制人; (405)服务管理模块; (406)初始化模块; (407)内核模块初始化; (408)应用程序初始化; (409)文件系统的初始化; (410)启动顺序控制; (411)网络建设; (412)环境变量初始化
-
公开(公告)号:KR1020110067795A
公开(公告)日:2011-06-22
申请号:KR1020090124543
申请日:2009-12-15
Applicant: 한국전자통신연구원
Abstract: PURPOSE: A tightly-coupled memory management method is provided to improve the response of real-time processes by determining the page to be loaded on the TCM in consideration of a process priority or memory address accessed to TCM, access frequency and recent access time. CONSTITUTION: A process to be saved in a tightly-coupled memory (TCM) requests the access to TCM(210). The TCM transfers the process or the memory information to a TCM manager(220). The process information includes the priority information. The memory information includes the address of the accessed memory, access frequency and recent access time. The TCM manager determines a memory page to be loaded on TCM in consideration of the information on the process or the memory, and then executes the load(230).
Abstract translation: 目的:提供一种紧密耦合的存储器管理方法,以便考虑到访问TCM,访问频率和最近访问时间的进程优先级或存储器地址,确定要加载在TCM上的页面来改善实时进程的响应。 构成:要保存在紧耦合存储器(TCM)中的过程请求访问TCM(210)。 TCM将过程或存储器信息传送到TCM管理器(220)。 处理信息包括优先级信息。 存储器信息包括访问存储器的地址,访问频率和最近访问时间。 TCM管理器考虑到关于进程或存储器的信息来确定要在TCM上加载的存储器页面,然后执行负载(230)。
-
公开(公告)号:KR1020130075018A
公开(公告)日:2013-07-05
申请号:KR1020110143195
申请日:2011-12-27
Applicant: 한국전자통신연구원
Inventor: 천한성
IPC: G06F12/02
CPC classification number: G06F12/0253 , G06F12/0246 , G06F2212/7205
Abstract: PURPOSE: A data update apparatus applicable to a flash memory file system and a method thereof are provided to improve applicability of a disc file system, by reducing fast abrasion of a flash memory when the disc file system is applied in the flash memory. CONSTITUTION: When an input/output request signal is received, an update identification part (202) compares the input/output request signal with an update signal. A data storing part (205) stores mapping information about blocks belonging to a random file in an additional meta data region classified from a data region. A block allocation part (204) stores an address of an idle block among blocks. If the input/output request signal is the update signal, a data update part (203) acquires the address of the idle block to record an update file corresponding to the update signal through the block allocation part. [Reference numerals] (201) Input interface; (202) Update identification part; (203) Data update part; (204) Block allocation part; (205) Data load unit; (206) Data storing part
Abstract translation: 目的:提供一种适用于闪速存储器文件系统的数据更新装置及其方法,用于通过在将盘文件系统应用于闪速存储器时减少闪存的快速磨损来改善盘文件系统的适用性。 构成:当接收到输入/输出请求信号时,更新识别部分(202)将输入/输出请求信号与更新信号进行比较。 数据存储部(205)将属于随机文件的块的映射信息存储在从数据区域分类的附加元数据区域中。 块分配部(204)在块之间存储空闲块的地址。 如果输入/输出请求信号是更新信号,则数据更新部分(203)通过块分配部分获取空闲块的地址以记录与更新信号相对应的更新文件。 (附图标记)(201)输入接口; (202)更新识别部; (203)数据更新部分; (204)块分配部分; (205)数据加载单元; (206)数据存储部
-
-
-
-
-
-
-
-
-