This is how much FishOS can save you!
FishOS raises utilization to lower costs
By raising utilization, while meeting service level and ensuring service quality, FishOS helps you to mitigate servers over-provisioning, optimizing data center operations, lowering energy OpEx, servers CapEx, and facilities CapEx.
Server utilization in data centers has been found to be low, ranging from below 10% to approximately 35%, according to a New York Times article. For a virtualized data center, low utilization can be summarized to be due to these 2 problems:
1. Initial Placement Problem
This problem is due to the workload not being optimally placed. When starting VMs, they need to be optimally and rapidly placed within a large dynamically changing facility. But this is non-trivial computationally and the amount of data required is immense, further compounded with size in a large data center.
2. Rebalancing Problem
This problem is due to servers in the data center not being rebalanced despite workload variation. Along with changing VMs workload (and workload can change a lot!), the VMs need to be rebalanced across a large data center, while meeting workload requirements and right-sizing the number of servers to match workload requirements. Above all, this is also very difficult to accomplish computationally, involving large amounts of data, and made harder with an increase in data center size.
Solving two halves of the problem
The Initial Placement Problem and Rebalancing Problem are two halves of the core of the low utilization problem.
Firstly, by solving the Initial Placement Problem and the Rebalancing Problem, service level requirements can be met without having to over-provision servers and, service quality degradation can be avoided. Secondly, data center operations can also be optimized, lowering energy OpEx, servers CapEx, and facilities CapEx.
No wastage: optimized OpEx and CapEx
Cloud resources are usually managed based on reservation. This leads to wastage for cloud operators, with their server utilization typically in the lowly range of 10 – 15%.
With FishOS, cloud resources are optimally managed, leading to significant savings. For instance, by permitting FishOS to raise your server utilization from the meager 15% to say 45% (fully achievable, and by no means the limit), your energy OpEx would be reduced by 67%. Take a moment to consider how this would affect your bottom line. Then add the cost-saving effect of having to obtain and replace less equipment to handle your workloads (as the servers you do acquire would be optimally utilized).
Here’s what doubling your server utilization would mean in terms of energy OpEx:
Energy OpEx saving – Case 1
| Number of servers | 55,000 |
| Electricity cost (per kWh) | EUR 0.10 |
| Annual electricity bill | EUR 15M |
| OpEx saving achievable by raising utilization 2x | EUR 7.5M |
Energy OpEx saving – Case 2
| Number of servers | 120 |
| Electricity cost (per kWh) | EUR 0.10 |
| Annual electricity bill | EUR 140,000 |
| OpEx saving achievable by raising utilization 2x | EUR 70,000 |
Here’s what it’ll save you on hardware and infrastructure CapEx:
Hardware and infrastructure CapEx saving – Case 1 (existing facility)
| Number of servers | 55,000 |
| Workload growth | 16% |
| Hardware and infrastructure CapEx over 4 years | EUR 1B |
| CapEx saving achievable by raising utilization 2x | EUR 168M |
Hardware and infrastructure CapEx saving – Case 2 (new facility)
| Number of servers | 120 |
| Workload growth | 16% |
| Hardware and infrastructure CapEx over 4 years | EUR 4.6M |
| CapEx saving achievable by raising utilization 2x | EUR 2.3M |
Find out more about how we can lower your cloud costs.