CAJ | 학술논문

检查点算法作为一种有效的故障技术及容错手段，已广泛地运用在网格、分布式和云计算系统中。该文提出了一种非阻塞协调检查点算法，该算法增加了系统的可靠性，并允许检查点灵活设置，充分缩减了同步信息数量，加速了检查点形成时间。和典型的相关算法比较，该文提出的算法使用更少的同步控制消息，具有更低的费用，引入同步控制消息的时间复杂度由一般的O(n2)降到O(n)，且同步消息数仅仅为n-1。
검사점산법작위일충유효적고장기술급용착수단，이엄범지운용재망격、분포식화운계산계통중。해문제출료일충비조새협조검사점산법，해산법증가료계통적가고성，병윤허검사점령활설치，충분축감료동보신식수량，가속료검사점형성시간。화전형적상관산법비교，해문제출적산법사용경소적동보공제소식，구유경저적비용，인입동보공제소식적시간복잡도유일반적O(n2)강도O(n)，차동보소식수부부위n-1。
The technology of checkpoint as an effective method of fault tolerance has been widely used in grid ,distributed and cloud systems. In this paper, a non-blocking cooperative checkpoint algorithm, which increases the reliability of the system and set up checkpoints flexible. At the same time, it fully reduces the synchronization information quantity, speeds up the formation checkpoint time, fully reduced the amount of information synchronized, the checkpoint accelerated development time. When compared to noted recent algorithms, the proposed algorithm uses less synchronous control messages with lower overhead. While the time complexity of control message during synchronous phase is reduced from O(n2) to O(n), the algorithm’s controlling messages are reduced to n-1.