There are currently 3 racks, and there is a file that needs to be stored in 3 copies. Copy 1 and copy 2 are stored in the same rack as the client but on different servers. According to the HDFS copy…

Question

Options

• ATrue
• BFalse

• A
  27% (10)
• B
  73% (27)

Explanation

Option B (False) is correct because the HDFS default replica placement strategy does not place both Copy 1 and Copy 2 in the client's rack. The actual policy places Copy 1 on the client's local node, Copy 2 on a node in a different rack, and Copy 3 on a different node in the same rack as Copy 2 - meaning only one replica lives in the client's rack, not two. The scenario described in the question directly contradicts this, since storing Copy 1 and Copy 2 in the same rack would undermine fault tolerance (a single rack failure would eliminate two of the three copies). Option A is wrong because it accepts a premise that misrepresents how HDFS distributes replicas for resilience.

Memory tip: Remember the pattern as "1 local, 1 remote rack, 1 near-remote" - HDFS splits the first two replicas across racks, then keeps the third close to the second. If you see a claim that two replicas share the client's rack, flag it as false.

No community discussion yet for this question.