Á¤º¸°úÇÐȸ ³í¹®Áö D : µ¥ÀÌŸº£À̽º
ÇѱÛÁ¦¸ñ(Korean Title) |
°øÀ¯ µð½ºÅ© Ŭ·¯½ºÅÍ¿¡¼ ¹öÆÛ ±³Ã¼ ¾Ë°í¸®ÁòÀÇ ¼º´É Æò°¡ |
¿µ¹®Á¦¸ñ(English Title) |
Performance Evaluation of Disk Replacement Algorithms in a Shared Cluster |
ÀúÀÚ(Author) |
Á¶Çà·¡
Haengrae Cho
|
¿ø¹®¼ö·Ïó(Citation) |
VOL 35 NO. 06 PP. 0469 ~ 0480 (2008. 12) |
Çѱ۳»¿ë (Korean Abstract) |
°øÀ¯ µð½ºÅ©(Shared Disk: SD) Ŭ·¯½ºÅÍ´Â ¿Â¶óÀÎ Æ®·£Àè¼Ç 󸮸¦ À§ÇØ ´Ù¼ö °³ÀÇ Ã³¸® ³ëµåµéÀ» ¿¬µ¿ÇÏ´Â ¹æ½ÄÀ¸·Î, ¸ðµç ³ëµå´Â µð½ºÅ© °èÃþ¿¡¼ µ¥ÀÌŸº£À̽º¸¦ °øÀ¯ÇÑ´Ù. ºó¹øÇÑ µð½ºÅ© ¾×¼¼½º¸¦ ÇÇÇϱâ À§ÇÏ¿© °¢ ³ëµå´Â ÀÚ½ÅÀÇ ¸Þ¸ð¸® ¹öÆÛ¿¡ ÃÖ±Ù¿¡ ¾×¼¼½ºÇÑ ÆäÀÌÁöµéÀ» ij½ÌÇÑ´Ù. À̶§ µ¿ÀÏÇÑ ÆäÀÌÁö°¡ ¿©·¯ ³ëµåÀÇ ¸Þ¸ð¸® ¹öÆÛ¿¡ µ¿½Ã¿¡ ij½ÌµÉ ¼ö ÀÖÀ¸¹Ç·Î °¢ ³ëµå°¡ ÃÖ½ÅÀÇ ³»¿ëÀ» ¾×¼¼½ºÇϱâ À§Çؼ´Â ij½ÌµÈ ÆäÀÌÁöÀÇ ÀÏ°ü¼ºÀÌ À¯ÁöµÇ¾î¾ß ÇÑ´Ù. SD Ŭ·¯½ºÅÍ¿¡¼ ±âÁ¸¿¡ Á¦¾ÈµÈ ´ëºÎºÐÀÇ Ä³½¬ ÀÏ°ü¼º ±â¹ýµéÀº ¹öÆÛ ±³Ã¼ ¾Ë°í¸®ÁòÀ¸·Î LRU¸¦ °¡Á¤ÇÏ¿´´Ù. ÀÌ¿Í´Â ´Þ¸® º» ³í¹®¿¡¼´Â SD Ŭ·¯½ºÅÍÀÇ Æ¯Â¡À» °í·ÁÇÑ ³× °¡ÁöÀÇ ¹öÆÛ ±³Ã¼ ¾Ë°í¸®ÁòµéÀ» Á¦¾ÈÇÏ°í ¼º´ÉÀ» Æò°¡ÇÑ´Ù. Ŭ·¯½ºÅÍ ±¸¼º°ú µ¥ÀÌŸº£À̽º ºÎÇϸ¦ ´Ù¾çÇÏ°Ô º¯°æÇÏ¸é¼ ½ÇÇèÀ» ¼öÇàÇÏ¿´°í, Á¦¾ÈÇÑ ¾Ë°í¸®ÁòÀº LRU¿¡ ºñÇØ ÃÖ´ë 5¹è±îÁö ¼º´ÉÀÌ Çâ»óµÊÀ» È®ÀÎÇÒ ¼ö ÀÖ¾ú´Ù. |
¿µ¹®³»¿ë (English Abstract) |
A shared disk (SD) cluster couples multiple nodes for high performance transaction processing, and all the coupled nodes share a common database at the disk level. To reduce the number of disk accesses, each node caches database pages in its memory buffer. Since a particular page may be cached simultaneously in different nodes, cache consistency should be maintained to ensure that nodes can always access the most recent version of database pages. Most cache consistency schemes proposed in the SD cluster adopted LRU as a buffer replacement algorithm. In this paper, we first present four buffer replacement algorithms that consider the characteristics of the SD cluster. Then we compare the performance of the buffer replacement algorithms. We perform the experiments on a variety of cluster configurations and database workloads. The experiment results show that the proposed algorithms achieve performance improvement up to 5 times of LRU algorithm. |
Å°¿öµå(Keyword) |
Æ®·£Àè¼Ç ó¸®
Ŭ·¯½ºÅÍ
°øÀ¯ µð½ºÅ©
¹öÆÛ ±³Ã¼
ij½¬ ÀÏ°ü¼º
transaction processing
cluster
shared disks
buffer replacement
cache consistenc
|
ÆÄÀÏ÷ºÎ |
PDF ´Ù¿î·Îµå
|