• 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 : 21 / 41 ÀÌÀü°Ç ÀÌÀü°Ç   ´ÙÀ½°Ç ´ÙÀ½°Ç

ÇѱÛÁ¦¸ñ(Korean Title) Spark Streaming ±â¹Ý Ŭ¶ó¿ìµå ½Ã½ºÅÛ¿¡¼­ ½Ç½Ã°£ °íÀå º¹±¸¸¦ Áö¿øÇϱâ À§ÇÑ ±â¹ýµé
¿µ¹®Á¦¸ñ(English Title) Techniques to Guarantee Real-Time Fault Recovery in Spark Streaming Based Cloud System
ÀúÀÚ(Author) ±èÁ¤È£   ¹Ú´ëµ¿   ±è»ó¿í   ¹®¿ë½Ä   È«¼º¼ö   Jungho Kim   Daedong Park   Sangwook Kim   Yongshik Moon   Seongsoo Hong  
¿ø¹®¼ö·Ïó(Citation) VOL 44 NO. 05 PP. 0460 ~ 0468 (2017. 05)
Çѱ۳»¿ë
(Korean Abstract)
½Ç½Ã°£ Ŭ¶ó¿ìµåÀÇ ½ÇÇö¿¡ À־ µ¥ÀÌÅÍ ºÐ¼® ÇÁ·¹ÀÓ¿öÅ©´Â ÁßÃß ¿ªÇÒÀ» ¼öÇàÇÑ´Ù. ÇöÁ¸ÇÏ´Â ÇÁ·¹ÀÓ¿öÅ©µé Áß¿¡ °¡Àå ¸¹Àº ¿ä±¸»çÇ×µéÀ» ÃæÁ·ÇÏ´Â °ÍÀº Spark StreamingÀÌ´Ù. ÇÏÁö¸¸ ÀÌ ÇÁ·¹ÀÓ¿öÅ©´Â ÃÊ ´ÜÀ§ ½Ç½Ã°£ °íÀå º¹±¸¸¦ ÃæÁ·ÇÏÁö ¸øÇÏ°í ÀÖ´Ù. Spark StreamingÀÇ °íÀå º¹±¸ ±â¹ýÀº Á¤»ó µ¿ÀÛ ½Ã¿¡ ±â·ÏµÈ ´©Àû º¯Çü È÷½ºÅ丮¸¦ Åä´ë·Î °íÀå Á÷Àü ¸¶Áö¸· »óÅ µ¥ÀÌÅ͸¦ À翬»êÇÏ¿© º¹±¸Çϱ⠶§¹®¿¡ È÷½ºÅ丮ÀÇ ±æÀÌ¿¡ ºñ·ÊÇÏ¿© º¹±¸ ½Ã°£ÀÌ Áõ°¡µÈ´Ù. µû¶ó¼­ Á¦ÇÑµÈ ½Ã°£ À̳»¿¡ °íÀå º¹±¸°¡ ¿Ï·áµÊÀ» º¸ÀåµÇÁö ¾Ê´Â´Ù. ¶ÇÇÑ Ãʱ⠻óÅ µ¥ÀÌÅ͸¦ °íÀå °¨³» ½ºÅ丮Áö¿¡¼­ Àд ½Ã°£ÀÌ ¼ö½Ê ÃÊ¿¡ ´ÞÇÏ¿© ÃÊ ´ÜÀ§ °íÀå º¹±¸ ½Ã°£À» ´Þ¼ºÇÒ ¼ö ¾ø´Ù. º» ³í¹®¿¡¼­´Â ¾ð±ÞµÈ ¹®Á¦µéÀ» ÇØ°áÇϱâ À§ÇÑ µÎ °¡Áö ±â¹ýµéÀ» Á¦¾ÈÇÑ´Ù. À̸¦ Spark Streaming 1.6.2¿¡ Àû¿ëÇÏ°í, ½ÇÇèÀ» ÅëÇØ °íÀå º¹±¸ ½Ã°£ÀÌ Á¦ÇÑ ½Ã°£ À̳»¿¡ ¿Ï·áµÇ¸ç Æò±Õ ¾à 41.57% ´ÜÃàµÊÀ» È®ÀÎÇß´Ù.
¿µ¹®³»¿ë
(English Abstract)
In a real-time cloud environment, the data analysis framework plays a pivotal role. Spark Streaming meets most real-time requirements among existing frameworks. However, the framework does not meet the second scale real-time fault recovery requirement. Spark Streaming fault recovery time increases in proportion to the transformation history length called lineage. This is because it recovers the last state data based on the cumulative lineage recorded during normal operation. Therefore, fault recovery time is not bounded within a limited time. In addition, it is impossible to achieve a second-scale fault recovery time because it costs tens of seconds to read initial state data from fault-tolerant storage. In this paper, we propose two techniques to solve the problems mentioned above. We apply the proposed techniques to Spark Streaming 1.6.2. Experimental results show that the fault recovery time is bounded and the average fault recovery time is reduced by up to 41.57%.
Å°¿öµå(Keyword) ½ºÆÄÅ© ½ºÆ®¸®¹Ö   °íÀå º¹±¸   ½Ç½Ã°£   µ¥ÀÌÅÍ ºÐ¼® ÇÁ·¹ÀÓ¿öÅ©   Spark Streaming   fault recovery   real-time   data analytics framework  
ÆÄÀÏ÷ºÎ PDF ´Ù¿î·Îµå