• 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¸°úÇÐȸ ³í¹®Áö > Á¤º¸°úÇÐȸ³í¹®Áö (Journal of KIISE)

Á¤º¸°úÇÐȸ³í¹®Áö (Journal of KIISE)

Current Result Document :

ÇѱÛÁ¦¸ñ(Korean Title) ÄÁÅ×ÀÌ³Ê È¯°æ¿¡¼­ÀÇ °úÇÐ ¿öÅ©Ç÷ο츦 À§ÇÑ µ¿Àû ¸Þ¸ð¸® ÇÒ´ç
¿µ¹®Á¦¸ñ(English Title) Dynamic Memory Allocation for Scientific Workflows in Containers
ÀúÀÚ(Author) ¾ÆµÎǪ Å׿Àµµ¶ó   ÃÖÁöÀº   ±èÀ±Èñ   Theodora Adufu   Jieun Choi   Yoonhee Kim  
¿ø¹®¼ö·Ïó(Citation) VOL 44 NO. 05 PP. 0439 ~ 0448 (2017. 05)
Çѱ۳»¿ë
(Korean Abstract)
´ë±Ô¸ð HPC °úÇÐ ÀÀ¿ëÀÇ ¿öÅ©·Îµå°¡ Àüü ½ÇÇà½Ã°£ µ¿¾È ´Ù¾çÇÏ°Ô º¯È­ÇÏ´Â ÀÚ¿ø ¿ä±¸»çÇ×À» °®°Ô µÇ¸é¼­ ƯÁ¤ ½ÃÁ¡¿¡ °©Àڱ⠿䱸»çÇ×ÀÌ Áõ°¡ÇÏ´Â(bursty) ÇüÅ°¡ µÇ°í ÀÖ´Ù. ±×·¯³ª ÀÌ·¯ÇÑ ÀÀ¿ë ¿öÅ©·Îµå¸¦ °í·ÁÇÏÁö ¾Ê°í, ÃÖ´ë ÀÚ¿ø ¿ä±¸»çÇ׸¸À» ¹Ý¿µÇÑ °¡»ó ÀÚ¿øÀÇ ¿À¹ö-ÇÁ·ÎºñÀú´×Àº °úÇÐ ÀÀ¿ëÀÇ ¼º´ÉÀ» º¸ÀåÇÏÁö¸¸ ´Ù¸¥ ÀÀ¿ëÀÌ »ç¿ëÇÒ ¼ö ¾ø´Â À¯ÈÞ ÀÚ¿øÀ» ´Ã¸®´Â ¹®Á¦·Î ³²¾ÆÀÖ´Ù. º» ³í¹®¿¡¼­´Â OS-level °¡»óÈ­ ȯ°æ¿¡¼­ ÀÀ¿ëÀÇ ÀÚ¿ø »ç¿ë ÆÐÅÏ¿¡ ´ëÇÑ ÇÁ·ÎÆÄÀϸµ µ¥ÀÌÅ͸¦ ±â¹ÝÀ¸·Î ¸Þ¸ð¸® ÀÚ¿ø À籸¼º ±â¹ýÀ» Á¦¾ÈÇÑ´Ù. ÀÌ´Â À¯ÈÞ »óÅÂÀÇ ¸Þ¸ð¸® ÀÚ¿øÀ» ½Å¼ÓÇÏ°Ô Ç®¾îÁÖ¾î »õ·Î¿î ÀÀ¿ëÀÌ ÀÚ¿øÀ» »ç¿ëÇÏ¿© ¼öÇàÇÒ ¼ö ÀÖµµ·Ï ÇÑ´Ù. º» ¿¬±¸¿¡¼­´Â °æ·®È­µÈ OS-level °¡»óÈ­ ½Ã½ºÅÛÀÇ ÇϳªÀÎ Docker¿¡¼­ °úÇÐ ¿öÅ©Ç÷οì ÀÀ¿ëÀ» ÀÌ¿ëÇÏ¿© Á¦¾ÈÇÏ´Â ¾Ë°í¸®ÁòÀ» °ËÁõÇÏ¿´´Ù. ½ÇÇèÀ» ÅëÇØ °úÇÐ ÀÀ¿ëÀ» ½ÇÇàÇÏ´Â µ¿¾È ÄÁÅ×À̳ʿ¡ ´ëÇÑ ¸Þ¸ð¸® ÇÒ´ç ¹Ì¼¼ Á¶Á¤ÀÌ Àü¹ÝÀûÀÎ ¸Þ¸ð¸® ÀÚ¿ø È°¿ëÀ» Çâ»ó½Ãų ¼ö ÀÖÀ½À» º¸¿´´Ù. ¶ÇÇÑ ÀÀ¿ëÀÇ ¸Þ¸ð¸® »ç¿ë ÇÁ·ÎÆÄÀÏ µ¥ÀÌÅ͸¦ ±â¹ÝÀ¸·Î ÇÏ´Â ½Ã¹Ä·¹ÀÌ¼Ç ½ÇÇèÀ» ÅëÇØ, Á¦¾ÈÇÏ´Â µ¿Àû ¸Þ¸ð¸® ÇÒ´ç ±â¹ýÀ» »ç¿ëÇÏ´Â °æ¿ì ´ë±â ÀÛ¾÷¿¡ À¯ÈÞ»óÅÂÀÇ ¸Þ¸ð¸®¸¦ ÇÒ´çÇÏ¿© Àüü ´ë±â ÀÛ¾÷ÀÇ ¼ö¸¦ ÁÙÀÌ°í ½Ã½ºÅÛ ÀÛ¾÷ ´ë±â ½Ã°£ÀÌ ÁÙ¾îµé¾úÀ½À» º¸¿´´Ù.
¿µ¹®³»¿ë
(English Abstract)
The workloads of large high-performance computing (HPC) scientific applications are steadily becoming ¡°bursty¡± due to variable resource demands throughout their execution life-cycles. However, the over-provisioning of virtual resources for optimal performance during execution remains a key challenge in the scheduling of scientific HPC applications. While over-provisioning of virtual resources guarantees peak performance of scientific application in virtualized environments, it results in increased amounts of idle resources that are unavailable for use by other applications. Herein, we proposed a memory resource reconfiguration approach that allows the quick release of idle memory resources for new applications in OS-level virtualized systems, based on the applications resource-usage pattern profile data. We deployed a scientific workflow application in Docker, a light-weight OS-level virtualized system. In the proposed approach, memory allocation is fine-tuned to containers at each stage of the workflows execution life-cycle. Thus, overall memory resource utilization is improved.
Å°¿öµå(Keyword) À籸¼º   ÄÁÅ×À̳ʠ  ÀÚ¿ø ÇÁ·ÎºñÀú´×   ÀÚ¿ø °ü¸®   °¡»óÈ­   reconfiguration   container   resource provisioning   resource management   virtualization  
ÆÄÀÏ÷ºÎ PDF ´Ù¿î·Îµå