HI
Have you enable log aggregation..? 1. If log aggregation is enabled then you can get logs from hdfs below path. Both aggregated logs and profiler will be in same file. ${yarn.nodemanager.remote-app-log-dir}/${user}/logs/<app-id>/ If not enabled, then check inside ${yarn.nodemanager.log-dirs}/<app-id>/<container-id>/profile.out(default name) Thanks & Regards Rohith Sharma K S From: Jakub Stransky [mailto:stransky...@gmail.com] Sent: 23 September 2014 16:27 To: user@hadoop.apache.org Subject: Cannot fine profiling log file Hello experienced users, I did try to use profiling of tasks during mapreduce <property> <name>mapreduce.task.profile</name> <value>true</value> </property> <property> <name>mapreduce.task.profile.maps</name> <value>0-5</value> </property> <property> <name>mapreduce.task.profile.params</name> <value>-agentlib:hprof=cpu=samples,heap=sites,depth=6,force=n,thread=y,verbose=n,file=%s</value> </property> The file got generated I see that thrugh Resource Manager console but I can't find it from where to download. Where to find that file or how to download it? Thanks for any advices! Jakub