hadoop-common-user mailing list archives

Site index · List index
Message view « Date » · « Thread »
Top « Date » · « Thread »
From Amar Kamat <ama...@yahoo-inc.com>
Subject Re: Too many fetch failures AND Shuffle error
Date Fri, 20 Jun 2008 04:56:40 GMT
Sayali Kulkarni wrote:
> Hello,
> I have been getting 
> Too many fetch failures (in the map operation)
> and 
> shuffle error (in the reduce operation)
>
>   
Can you post the reducer logs. How many nodes are there in the cluster? 
Are you seeing this for all the maps and reducers? Are the reducers 
progressing at all? Are all the maps that the reducer is failing from a 
remote machine? Are all the failed maps/reducers from the same machine? 
Can you provide some more details.
Amar
> 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
View raw message