hadoop-common-user mailing list archives

Site index · List index
Message view « Date » · « Thread »
Top « Date » · « Thread »
From Sayali Kulkarni <sayali_s_kulka...@yahoo.co.in>
Subject Too many fetch failures AND Shuffle error
Date Thu, 19 Jun 2008 14:06:48 GMT
Hello,
I have been getting 
Too many fetch failures (in the map operation)
and 
shuffle error (in the reduce operation)

and am unable to complete any job on the cluster.

I have 5 slaves in the cluster. So I have the following values in the hadoop-site.xml file:
  <name>mapred.map.tasks</name>
  <value>53</value>
// 53 = nearest prime to 5*10

  <name>mapred.reduce.tasks</name>
  <value>7</value>
// 7 = nearest prime to 5

Please let me know what would be the suggest fix for this.

Hadoop version I am using is hadoop-0.16.3 and it is installed on  Ubuntu.

Thanks!
--Sayali


       
---------------------------------
Sent from Yahoo! Mail.
A Smarter Email.
Mime
  • Unnamed multipart/alternative (inline, 8-Bit, 0 bytes)
View raw message