• 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 ¼ÒÇÁÆ®¿þ¾î ¹× µ¥ÀÌÅÍ °øÇÐ

Á¤º¸Ã³¸®ÇÐȸ ³í¹®Áö ¼ÒÇÁÆ®¿þ¾î ¹× µ¥ÀÌÅÍ °øÇÐ

Current Result Document : 3 / 4 ÀÌÀü°Ç ÀÌÀü°Ç   ´ÙÀ½°Ç ´ÙÀ½°Ç

ÇѱÛÁ¦¸ñ(Korean Title) À¯Àüü ºÐ¼® ÆÄÀÌÇÁ¶óÀÎÀÇ I/O ¿öÅ©·Îµå ºÐ¼®
¿µ¹®Á¦¸ñ(English Title) Genome Analysis Pipeline I/O Workload Analysis
ÀúÀÚ(Author) ÀÓ°æ¿­   ±èµ¿¿À   ±èÈ«¿¬   ¹Ú±âÇÑ   Ãֹμ®   ¿øÀ¯Áý   Kyeongyeol Lim   Dongoh Kim   Hongyeon Kim   Geehan Park   Minseok Choi   Youjip Won  
¿ø¹®¼ö·Ïó(Citation) VOL 02 NO. 02 PP. 0123 ~ 0130 (2013. 02)
Çѱ۳»¿ë
(Korean Abstract)
ÃÖ±Ù À¯Àüü µ¥ÀÌÅÍÀÇ ±Þ°ÝÇÑ Áõ°¡·Î ÀÎÇØ À̸¦ ó¸®Çϱâ À§ÇÑ °í¼º´É ÄÄÇ»Æà ½Ã½ºÅÛÀÌ ÇÊ¿ä·Î ÇÏ°Ô µÇ¾úÀ¸¸ç ´ë·®ÀÇ À¯Àüü µ¥ÀÌÅ͸¦ ÀúÀå °ü¸®ÇÒ ¼ö ÀÖ´Â °í¼º´É ÀúÀå ½Ã½ºÅÛÀÌ ÇÊ¿äÇÏ°Ô µÇ¾ú´Ù. º» ³í¹®¿¡¼­´Â ´ë·« 5¾ï °³ Á¤µµÀÇ ½ÃÄý½º ¸®µå µ¥ÀÌÅ͸¦ ºÐ¼®ÇÏ´Â À¯Àüü ºÐ¼® ÆÄÀÌÇÁ¶óÀÎÀÇ I/O¿öÅ©·Îµå¸¦ ¼öÁý ¹× ºÐ¼®ÇÏ¿´´Ù. ½ÇÇèÀº 86½Ã°£ µ¿¾È ¼öÇàµÇ¾ú´Ù. 1031.7 GByte Å©±âÀÇ 630°³ ÆÄÀÏÀÌ »ý¼ºµÇ¾úÀ¸¸ç 91.4 GByte Å©±âÀÇ 535°³ÀÇ ÆÄÀÏÀÌ »èÁ¦µÇ¾ú´Ù. Àüü 654°³ÀÇ ÆÄÀÏ Áß 0.3%ÀÎ 2°³ÀÇ ÆÄÀÏÀÌ Àüü Á¢±Ù ºóµµÀÇ 80%¸¦ Â÷ÁöÇÏ¿© Àüü ÆÄÀÏ Áß ÀϺκÐÀÇ ÆÄÀÏÀÌ ´ëºÎºÐÀÇ I/O¸¦ ¹ß»ý½ÃŲ´Ù´Â °ÍÀ» ¾Ë ¼ö ÀÖ´Ù. ¿äû Å©±â ´ÜÀ§·Î´Â Àб⿡¼­ ÁÖ·Î 512 KByte Å©±â ÀÌ»óÀÇ ¿äûÀÌ ¹ß»ýÇß°í ¾²±â¿¡¼­ ÁÖ·Î 1 MByte Å©±â ÀÌ»óÀÇ ¿äûÀÌ ¹ß»ýÇß´Ù. ÆÄÀÏÀÌ ¿­·ÁÀÖ´Â µ¿¾ÈÀÇ Á¢±Ù ÆÐÅÏÀº Àбâ¿Í ¾²±â ¿¬»ê¿¡¼­ °¢°¢ ÀÓÀÇ¿Í ¼øÂ÷ÆÐÅÏÀ» º¸¿´´Ù. IOPS¿Í ´ë¿ªÆøÀº °¢ ´Ü°è¸¶´Ù °íÀ¯ÇÑ ÆÐÅÏÀ» º¸¿´´Ù.

¿µ¹®³»¿ë
(English Abstract)
As size of genomic data is increasing rapidly, the needs for high-performance computing system to process and store genomic data is also increasing. In this paper, we captured I/O trace of a system which analyzed 500 million sequence reads data in Genome analysis pipeline for 86 hours. The workload created 630 file with size of 1031.7 Gbyte and deleted 535 file with size of 91.4 GByte. What is interesting in this workload is that 80% of all accesses are from only two files among 654 files in the system. Size of read and write request in the workload was larger than 512 KByte and 1 Mbyte, respectively. Majority of read write operations show random and sequential patterns, respectively. Throughput and bandwidth observed in each processing phase was different from each other.
Å°¿öµå(Keyword) ¹ÙÀÌ¿ÀÀÎÆ÷¸Åƽ½º   ¿öÅ©·Îµå ºÐ¼®   SSD   Bioinformatics   Workload Analysis  
ÆÄÀÏ÷ºÎ PDF ´Ù¿î·Îµå