Your cluster has the following characteristics:
A rack aware topology is configured and on
Replication is set to 3
Cluster block size is set to 64MB
Which describes the file read process when a client application connects into the cluster and
requests a 50MB file?
A.
The client queries the NameNode for the locations of the block, and reads all three copies. The
first copy to complete transfer to the client is the one the client reads as part of hadoop’s
speculative execution framework.
B.
The client queries the NameNode for the locations of the block, and reads from the first location
in the list it receives.
C.
The client queries the NameNode for the locations of the block, and reads from a random
location in the list it receives to eliminate network I/O loads by balancing which nodes it retrieves
data from any given time.
D.
The client queries the NameNode which retrieves the block from the nearest DataNode to the
client then passes that block back to the client.
D is the correct answer.
Client gets location of nearest replica out of three from Namenode.
and then client start reading the data from it.
0
0
Why is D? I think B is correct answer,
When an application reads a file, the HDFS client first asks the NameNode for the list of DataNodes that host replicas of the blocks of the file. The list is sorted by the network topology distance from the client. The client contacts a DataNode directly and requests the transfer of the desired block.
http://www.aosabook.org/en/hdfs.html
0
0
B ist the correct answer. The NameNode gives a list of DataNodes to the client, which is already sorted according to the distance to the client. Therefore the first node in the list is the nearest to the client.
D ist wrong! The NameNode does not retrieve the block and pass it to the client.
0
0
Yes B
0
0
B is correct answer.
0
0
Yep B according to the definitive guide
0
0
B is the right answer
0
0
B
0
0