hadoop-common-user mailing list archives

Site index · List index
Message view « Date » · « Thread »
Top « Date » · « Thread »
From Balanagireddy Mudiam <balanagiredd...@gmail.com>
Subject Reducing the retry connections from task tacker to job tracker
Date Wed, 12 May 2010 14:39:00 GMT

I am launching hadoop cluster on amazon ec2. For a period of 30-40
minutes, hdfs is in safemode and recovering the blocks. Till then job
tracker doesn't to accept connections from task tracker. I can see
from logs that task trackers are unsuccessfully trying to establish
connection with job tracker during this period. Is there a parameter
to reduce the number of retries a task tracker does per unit time?

Thank you.

Bala Mudiam

View raw message