BEGIN:VCALENDAR
VERSION:2.0
PRODID:Linklings LLC
BEGIN:VTIMEZONE
TZID:America/Denver
X-LIC-LOCATION:America/Denver
BEGIN:DAYLIGHT
TZOFFSETFROM:-0700
TZOFFSETTO:-0600
TZNAME:MDT
DTSTART:19700308T020000
RRULE:FREQ=YEARLY;BYMONTH=3;BYDAY=2SU
END:DAYLIGHT
BEGIN:STANDARD
TZOFFSETFROM:-0600
TZOFFSETTO:-0700
TZNAME:MST
DTSTART:19701101T020000
RRULE:FREQ=YEARLY;BYMONTH=11;BYDAY=1SU
END:STANDARD
END:VTIMEZONE
BEGIN:VEVENT
DTSTAMP:20260422T000711Z
LOCATION:401-402
DTSTART;TZID=America/Denver:20231116T163000
DTEND;TZID=America/Denver:20231116T170000
UID:submissions.supercomputing.org_SC23_sess166_pap400@linklings.com
SUMMARY:Xfast: Extreme File Attribute Stat Acceleration for Lustre
DESCRIPTION:Yingjin Qian (DataDirect Networks (DDN)), Wen Cheng and Lingfa
 ng Zeng (Zhejiang Lab), Xi Li (DataDirect Networks (DDN)), Marc-André Vef 
 (Johannes Gutenberg University Mainz), Andreas Dilger and Siyao Lai (Whamc
 loud Inc), Shuichi Ihara (DataDirect Networks (DDN)), Yong Fan (Intel Corp
 oration), and André Brinkmann (Johannes Gutenberg University Mainz)\n\nDir
 ectory tree walks on parallel file systems are costly operations frequentl
 y required by many storage management tasks. Even listing the contents of 
 a single directory can take minutes to hours for huge directories, as the 
 tree walk performance of parallel file systems in Linux is severely thrott
 led by sequentially accessing distributed metadata for each file through t
 he syscall interface. \n\nWe present extreme file attribute stat (Xfast), 
 which scales the performance of directory tree walks by combining techniqu
 es that have been developed over a time frame of 10 years for the Lustre f
 ile system. Scalable statahead predicts file access patterns and prefetche
 s required attributes, while the Size on MDT (SOM) mechanism reduces the n
 umber of RPC calls to collect file attributes. Xfast improves the performa
 nce of common directory operations, e.g. reduces the time to list one mill
 ion files from 11 minutes to less than one minute for a single process.\n\
 nTag: Data Analysis, Visualization, and Storage, I/O and File Systems, Sta
 te of the Practice\n\nRegistration Category: Tech Program Reg Pass\n\nRepr
 oducibility Badges: Artifact Available, Artifact Functional, Results Repro
 duced\n\nSession Chair: Sarah Neuwirth (Johannes Gutenberg University Main
 z)\n\n
END:VEVENT
END:VCALENDAR