number of network switches is much larger than the three-tier DCN. The architecture is
composed of k pods, where each pod contains, (k/2)2 servers, k/2 access layer switches,
and k/2 aggregate layer switches in the topology. The core layers contain (k/2)2 core
switches where each of the core switches is connected to one aggregate layer switch in
each of the pods.
The fat tree architecture uses a customized addressing scheme and routing algorithm
Addressing:
All IP addresses in the network within the private 10.0.0.0/8 block.
The pod switches are given addresses of the form 10.pod.switch.1
Give core switches addresses of the form 10.k.j.i,
Routing paradigm:
Each entry in the main routing table will potentially have an additional pointer to
a small secondary table of (suffix, port) entries.
1.2 Dcell
1. What is the physical structure of DCell?
The DCell follows a recursively build hierarchy of cells. A cell
0
is the basic unit and building
block of DCell topology arranged in multiple levels, where a higher level cell contains multiple lower
layer cells. The cell
0
is building block of DCell topology, which contains n servers and one commodity
network switch. The network switch is only used to connect the server within a cell
0
. A
cell
1
contain k=n+1 cell
0
cells, and similarly a cell
2
contains k * n + 1 cell
1
.
2. DCell properties:
Scalability: The number of servers scales doubly exponentially
Fault-tolerance: The bisection width is larger than
3. How DCell route data flows? How to handle different types of failures?
Consider two nodes src and dst that are in the same DCell
k
but in two different
DCell
k-1
s. When computing the path from src to dst in a DCell
k
, we first calculate the
1)1(
2
1
)
2
1
(
1
22
������
�kk
nNn