That makes sense. Thanks A
On 8/7/07, Raghu Angadi <[EMAIL PROTECTED]> wrote: > > Phantom wrote: > > > Basically my question is whether the namenode > > is involved in every write request. > > No. > > Name node is contacted once for each "block". If your block size is 64MB > and you write 5GB file, namenode will be contacted once for each of the > 16 blocks and once for closing the file. > > Raghu. > > > Thanks > > A > > > > On 8/7/07, Raghu Angadi <[EMAIL PROTECTED]> wrote: > >> > >> To write data to HDFS, you should be able to connect to both Namenode > >> and to all of the datanodes. NameNode decides where to place the data > >> blocks and tells the client (you) to send the blocks to corresponding > >> datanodes. > >> > >> Raghu. > >> > >> Phantom wrote: > >>> Hi > >>> > >>> When I write data into HDFS do I always need to connect to the > datanode > >> to > >>> write the data ? Can I connect to any namenode to do so ? If so how > does > >> the > >>> datanode keep track of where the various chunks are going to be placed > ? > >> Any > >>> resource that I can look at or could someone explain this to me ? > >>> > >>> Thanks > >>> A > >>> > >> > > > >
