Filter
Top Products
Power savings
Using the optimal number of virtual machines, which is 36, a
simple calculation of direct power costs was done comparing
the before (native) and after (virtualized).
Table 1 shows that with 36 virtual machines, with each virtual
machine having three game servers and each game server
supporting 12 players, we can see a consolidation ration of 18:1.
This means we can consolidate 18 of ESL’s existing Intel® Core™2
Duo processor-based native servers onto one Intel Xeon proces-
sor 7400 server by using virtualization in combination with VMDq
and NetQueue technologies without impacting the gaming
latency and gaming experience. This translates to direct power-
cost savings of $648,000 annually for every 1,000 Intel Core
2 Duo processor-based servers that will be converted. In these
calculations we are taking into consideration that these game
servers are running 24x7, 365 days per year, and we used the
actual power rate ESL is paying (0.16 euros/kWh).
Other savings
The above savings are only direct power savings. We did not
take into account other savings like cooling, datacenter
space, network hardware, and manageability.
Table 1. ESL standard native hardware deployment metrics (“Before”) vs. virtualized deployment Proof-of-Concept metrics
as described in this paper (“After”).
Before After
Server 1P Intel® Core™2 Duo processor 4P Intel® Xeon® processor 7400
Cores 2 24
Game server processes 3 per CPU core 3 per VM; 4.5 per CPU core
VMs per box N/A 36
Game server per box 6 108
Total users per box 72 1,296
CPU utilization 60-80% 75%
Power utilized per server 350 W 710 W
Consolidation ratio 18 1
Annual direct power cost $731,000 per 1,000 servers $83,000 per 56 servers
12
White Paper Consolidation of a Performance-Sensitive Application