You are viewing a plain text version of this content. The canonical link for it is here.

Posted to hdfs-user@hadoop.apache.org by ch huang <ju...@gmail.com> on 2013/11/26 09:25:39 UTC

yarn active node health report problem

hi,maillist:

              i check the job status find  one of my disk which store
mapreduce local data  all the data miss ,why?
1/2 local-dirs turned bad: /data/7/mrlocal/yarn/local;1/2 log-dirs turned
bad: /data/7/mrlocal/yarn/logs


# df -h
Filesystem            Size  Used Avail Use% Mounted on
/dev/sda2              50G   17G   31G  36% /
tmpfs                 7.8G     0  7.8G   0% /dev/shm
/dev/sda1             388M   36M  332M  10% /boot
/dev/sda5              46G   18G   27G  40% /data/1
/dev/sda6              46G   44G   29M 100% /data/2
/dev/sda7             184G  153G   22G  88% /data/3
/dev/sda8             184G  152G   23G  88% /data/4
/dev/sda9             184G  154G   21G  89% /data/5
/dev/sda10             92G  389M   87G   1% /data/6
/dev/sda12             40G  182M   38G   1% /data/8
/dev/sda11             92G  188M   87G   1% /data/7
# ls /data/7
lost+found