You are right, in heartbeat response namenode sends commands to the
datanode. Commands sent this way include deletion of blocks, replication,
block recovery secret key updates etc. Increasing the heartbeat interval
results
in namenode not being able to quickly act on the events in the cluster and
My understanding is that the 10 minute timeout helps to avoid replication
storms, especially during startup.
You might be interested in HDFS-3703, which adds a stale state which
datanodes are placed into after 30 seconds of missing heartbeats. (This is
an optional feature controlled by
Thanks Colin and Suresh!
On Wed, Mar 13, 2013 at 3:08 PM, Colin McCabe cmcc...@alumni.cmu.eduwrote:
My understanding is that the 10 minute timeout helps to avoid replication
storms, especially during startup.
You might be interested in HDFS-3703, which adds a stale state which
datanodes are
No take on this one?
In Zookeeper the heartbeats happen on every third of the timeout. If I am
not mistaken, recomended timeout is more than 2 minutes to avoid false
positives.
But I still cannot see the relationship on HDFS between heartbeat interval
and timeout. Okay 10 minutes seems to be a
Hi,
Is there any particular reason why the default heartbeat interval is 3
seconds and the timeout is 10 minutes? Everywhere I looked (code, Google,
..) only mentions the values but no clue on why those values were chosen.
Thanks in advance,
André Oriani
