hadoop-common-user mailing list archives

Site index · List index
Message view « Date » · « Thread »
Top « Date » · « Thread »
From Zhenhua Guo <jen...@gmail.com>
Subject Question regarding block replication
Date Tue, 01 Mar 2011 18:08:44 GMT
I wonder how replication is handled in detail. I am reading the source
code. It seems class DataStreamer at client side is responsible for
setting up upload pipeline. From the perspective of client, the upload
call returns immediately after a packet is sent to the first data node
in the pipeline? or after the packet is replicated to all assigned
replication nodes? Which data node classes in the source code should I
read?

Thanks

Gerald

Mime
View raw message