• Àüü
  • ÀüÀÚ/Àü±â
  • Åë½Å
  • ÄÄÇ»ÅÍ
´Ý±â

»çÀÌÆ®¸Ê

Loading..

Please wait....

±¹³» ³í¹®Áö

Ȩ Ȩ > ¿¬±¸¹®Çå > ±¹³» ³í¹®Áö > Çѱ¹Á¤º¸Ã³¸®ÇÐȸ ³í¹®Áö > Á¤º¸Ã³¸®ÇÐȸ ³í¹®Áö A

Á¤º¸Ã³¸®ÇÐȸ ³í¹®Áö A

Current Result Document : 5 / 5 ÀÌÀü°Ç ÀÌÀü°Ç

ÇѱÛÁ¦¸ñ(Korean Title) ¸ÖƼÄÚ¾î ½Ã½ºÅÛ¿¡¼­ È帧 ¼öÁØ º´·Ä󸮿¡ ±â¹ÝÇÑ ¸®´ª½º TCP/IP ½ºÅÃÀÇ ¼º´É °³¼±
¿µ¹®Á¦¸ñ(English Title) A Performance Improvement of Linux TCP/IP Stack based on Flow-Level Parallelism in a Multi-Core System
ÀúÀÚ(Author) ±ÇÈñ¿õ   Á¤ÇüÁø   °ûÈı٠  ±è¿µÁ¾   Á¤±Ô½Ä   Huiung Kwon   Hyungjin Jung   Hukeun Kwak   Youngjong Kim   Kyusik Chung  
¿ø¹®¼ö·Ïó(Citation) VOL 16-A NO. 02 PP. 0113 ~ 0124 (2009. 04)
Çѱ۳»¿ë
(Korean Abstract)
ÃÖ±Ù ¸ÖƼÄھ ÀåÂøµÈ ½Ã½ºÅÛÀÌ Áõ°¡Çϸ鼭 À̸¦ ÅëÇÑ ¾ÖÇø®ÄÉÀÌ¼Ç ¼º´ÉÇâ»ó¿¡ ´ëÇÑ ³ë·ÂÀÌ °è¼Ó µÇ¾î¿Ô´Ù. ÇϳªÀÇ ½Ã½ºÅÛ¿¡ ´Ù¼öÀÇ Ã³¸®ÀåÄ¡°¡ Á¸ÀçÇÔÀ¸·Î ÀÎÇØ ÇÁ·Î¼¼½Ì ÆÄ¿ö´Â ±âÁ¸º¸´Ù Áõ°¡ÇßÁö¸¸ ±âÁ¸ÀÇ ¼ÒÇÁÆ®¿þ¾î³ª Çϵå¿þ¾îµéÀº ½Ì±ÛÄÚ¾î ½Ã½ºÅÛ¿¡ ÀûÇÕÇÏ°Ô ¼³°èµÈ °æ¿ì°¡ ¸¹¾Æ ¸ÖƼÄÚ¾îÀÇ ÀÌÁ¡À» ÃæºÐÈ÷ È°¿ëÇÏÁö ¸øÇÏ°í ÀÖ´Â °æ¿ì°¡ ¸¹´Ù. ±âÁ¸ÀÇ ¸¹Àº ¼ÒÇÁÆ®¿þ¾îµéÀº ¸ÖƼÄÚ¾î »ó¿¡¼­ °øÀ¯ ÀÚ¿ø¿¡ ´ëÇÑ º´¸ñÇö»ó°ú ºñÈ¿À²ÀûÀΠij½Ã ¸Þ¸ð¸® »ç¿ëÀ¸·Î ÀÎÇÏ¿© ÃæºÐÇÑ ¼º´ÉÇâ»óÀ» ±â´ëÇϱ⠾î·Á¿ì¸ç ÀÌ·¯ÇÑ ¹®Á¦Á¡µé·Î ÀÎÇÏ¿© ±âÁ¸ ¼ÒÇÁÆ®¿þ¾î´Â ÄÚ¾îÀÇ °³¼ö¿¡ ºñ·ÊÇÑ ¼º´ÉÀ» ¾òÁö ¸øÇϸç, ÃÖ¾ÇÀÇ °æ¿ì ¿ÀÈ÷·Á °¨¼ÒµÉ ¼ö ÀÖ´Ù.
º» ³í¹®¿¡¼­´Â TCP/IP¸¦ »ç¿ëÇÏ´Â ±âÁ¸ÀÇ ³×Æ®¿öÅ© ¾ÖÇø®ÄÉÀ̼ǰú ¿î¿µÃ¼Á¦¿¡ È帧 ¼öÁØ º´·Äó¸® ±â¹ýÀ» Àû¿ëÇÏ¿© ¼º´ÉÀ» Áõ°¡ ½Ãų ¼ö ÀÖ´Â ¹æ¹ýÀ» Á¦¾ÈÇÑ´Ù. Á¦¾ÈµÈ ¹æ½ÄÀº °³º° ÄÚ¾î´ÜÀ§·Î ³×Æ®¿öÅ© ¾ÖÇø®ÄÉÀ̼Ç, ¿î¿µÃ¼Á¦ÀÇ TCP/IP ½ºÅÃ, µð¹ÙÀ̽º µå¶óÀ̹ö, ³×Æ®¿öÅ© ÀÎÅÍÆäÀ̽º°¡ ¼­·Î °£¼· ¾øÀÌ ÀÛµ¿ÇÒ ¼ö Àִ ȯ°æÀ» ±¸¼ºÇϸç, L2 ½ºÀ§Ä¡¸¦ ÅëÇØ °¢ ÄÚ¾î ´ÜÀ§·Î Æ®·¡ÇÈÀ» ºÐ»êÇÏ´Â ¹æ¹ýÀ» Àû¿ëÇÏ¿´´Ù. À̸¦ ÅëÇØ °¢ ÄÚ¾î °£¿¡ ¾ÖÇø®ÄÉÀ̼ÇÀÇ µ¥ÀÌÅÍ ¹× ÀڷᱸÁ¶, ¼ÒÄÏ, µð¹ÙÀ̽º µå¶óÀ̹ö, ³×Æ®¿öÅ© ÀÎÅÍÆäÀ̽ºÀÇ °øÀ¯¸¦ ÃÖ¼ÒÈ­ÇÏ¿©, °¢ ÄھÀÇ ÀÚ¿øÀ» Â÷ÁöÇϱâ À§ÇÑ °æÀïÀ» ÃÖ¼ÒÈ­ÇÏ°í ij½Ã È÷Æ®À²À» Áõ°¡½ÃŲ´Ù. À̸¦ ÅëÇÏ¿© 8°³ÀÇ ¸ÖƼÄھ »ç¿ëÇÏ¿´À» °æ¿ì ³×Æ®¿öÅ© Á¢¼Ó¼Óµµ¿Í ´ë¿ªÆøÀÌ ÄÚ¾îÀÇ °³¼ö¿¡ µû¶ó ¼±ÇüÀûÀ¸·Î Áõ°¡ÇÔÀ» ½ÇÇèÀ» ÅëÇØ ÀÔÁõÇÏ¿´´Ù.
¿µ¹®³»¿ë
(English Abstract)
With increasing multicore system, much effort has been put on the performance improvement of its application. Because multicore system has multiple processing devices in one system, its processing power increases compared to the single core system. However in many cases the advantages of multicore can not be exploited fully because the existing software and hardware were designed to be suitable for single core. When the existing software runs on multicore, its performance improvement is limited by the bottleneck of sharing resources and the inefficient use of cache memory on multicore. Therefore, according as the number of core increases, it doesn¡¯t show performance improvement and shows performance drop in the worst case.

In this paper we propose a method of performance improvement of multicore system by applying Flow-Level Parallelism to the existing TCP/IP network application and operating system. The proposed method sets up the execution environment so that each core unit operates independently as much as possible in network application, TCP/IP stack on operating system, device driver, and network interface. Moreover it distributes network traffics to each core unit through L2 switch. The proposed method allows to minimize the sharing of application data, data structure, socket, device driver, and network interface between each core. Also it allows to minimize the competition among cores to take resources and increase the hit ratio of cache. We implemented the proposed methods with 8 core system and performed experiment. Experimental results show that network access speed and bandwidth increase linearly according to the number of core.
Å°¿öµå(Keyword) ¸ÖƼÄھ TCP/IP ½ºÅà  ij½Ã   À¥¼­¹ö   º»µù   È帧 ¼öÁØ º´·Ä󸮠  Multicore   TCP/IP Stack   Cache   Webserver   Bonding   Flow-Level Parallelism  
ÆÄÀÏ÷ºÎ PDF ´Ù¿î·Îµå