Go through the jobtracker, find the relevant node that handled attempt_201012061426_0001_m_000292_0 and figure out
if there are FS or permssion problems. Raj ________________________________ From: Adarsh Sharma <adarsh.sha...@orkash.com> To: common-user@hadoop.apache.org Sent: Wed, December 8, 2010 7:48:47 PM Subject: Re: Reduce Error Ted Yu wrote: > Any chance mapred.local.dir is under /tmp and part of it got cleaned up ? > > On Wed, Dec 8, 2010 at 4:17 AM, Adarsh Sharma <adarsh.sha...@orkash.com>wrote: > > >> Dear all, >> >> Did anyone encounter the below error while running job in Hadoop. It occurs >> in the reduce phase of the job. >> >> attempt_201012061426_0001_m_000292_0: >> org.apache.hadoop.util.DiskChecker$DiskErrorException: Could not find any >> valid local directory for >>taskTracker/jobcache/job_201012061426_0001/attempt_201012061426_0001_m_000292_0/output/file.out >>t >> >> It states that it is not able to locate a file that is created in >> mapred.local.dir of Hadoop. >> >> Thanks in Advance for any sort of information regarding this. >> >> Best Regards >> >> Adarsh Sharma >> >> > > Hi Ted, My mapred.local.dir is in /home/hadoop directory. I also check it with in /hdd2-2 directory where we have lots of space. Would mapred.map.tasks affects. I checked with default and also with 80 maps and 16 reduces as I have 8 slaves. <property> <name>mapred.local.dir</name> <value>/home/hadoop/mapred/local</value> <description>The local directory where MapReduce stores intermediate data files. May be a comma-separated list of directories on different devices in order to spread disk i/o. Directories that do not exist are ignored. </description> </property> <property> <name>mapred.system.dir</name> <value>/home/hadoop/mapred/system</value> <description>The shared directory where MapReduce stores control files. </description> </property> Any further information u want. Thanks & Regards Adarsh Sharma