Infrastructure Built for Performance

Cloud Environment Overview

Our Cloud has been meticulously architected to ensure performance and reliability. The hardware stack is built leveraging fully-redundant, KVM-based cloud server solutions powered by enterprise grade hardware from Hewlett Packard Enterprise. Our cloud servers are engineered from the ground up for reliability and are backed by our 5 9’s uptime availability guarantee.

  • HPE Hardware
    Our cloud environment leverages enterprise grade hardware from Hewlett Packard, and features modern Intel E5 series processors, redundant RAM, Disk, and Power supplies.
  • Cisco Networking
    Networking equipment from Cisco ensures consistent availability and throughput. We utilize Cisco Nexus platform switches, allowing us to provide both software AND chassis redundancy.
  • KVM Virtualization
    Our cloud environment is powered by open source virtualization technologies. KVM allows us to provision the widest variety of virtual guests in our cloud server offering without vendor lock-in.
  • Automation
    Our cloud server environment is fully automated, featuring fault-tolerance and failover without human intervention. Your cloud environment remains online even in the event of underlying hardware failure.
  • Self-Provisioning Tools
    Provision your own cloud environment directly from our customer portal. Bring additional services online, access support and monitor your cloud servers performance directly from a web interface.

Data Centers

The Cosmos Cloud utilizes several Data Centers to ensure stability, redundancy and reliability. 

Our data center facility in Chicago, Illinois is situated within a private, secured campus built and operated by Equinix. The facility is centrally managed and offers tenant space in the private data center suite. In addition to this, the facility offers private network operations and a staging environment. Furthermore, connectivity is available to multiple Tier-1 ISP’s, ensuring consistent availability for our cloud environment and the redundancy needed to provide an enterprise-class offering.


Security and physical access control is a priority. The data center employs 24/7 security monitoring, a thoroughly secured campus environment, stationary and roving officers, man-traps, anti-tailgating protocols, key card access, biometric access, PTZ, and stationary cameras.
Redundancy in key infrastructure is an important aspect of the Chicago facility. 2N+1 Utility power, 2N+1 UPS, Static Switch PDUs, N+2 CRAHs, N+1 central chilled water plant, diverse communication pathways, communication entrance vaults, and BMS monitoring and control. With the capacity to provide over 20 MW of critical IT power, this facility is built to scale, explaining why our Chicago data center has become a vital element of our Cloud.
We understand the value of compliance which is why we selected the Chicago Data Center, it is an SSAE 16 certified facility with Hyper-V and VMware-certified technicians and engineers available as needed.


Our data center facility in Atlanta, Georgia is well positioned to take advantage of the explosive growth in cloud computing and network connectivity in the region.  Adjacent to 56 Marietta Street, this facility features significant network and power capacity for future expansion.  In our private suite, operated and managed by Equinix, our cloud environment benefits from 4MW of power capacity, and upwards of 25,000 square feet of contiguous computing space. 

The Atlanta data center facility is collocated with several critical pieces of infrastructure, including primary offices for the City of Atlanta’s 911 dispatch center.  The nature of these activities ensures not only that the building is a priority for authorities in the event of a disaster, but that security and availability are at the top of the priority list.

Our Atlanta data center undergoes constant facility audits, and maintains ISO 27100, SOC-2 and SSAE-16 SOC1 Type II accreditations. The building itself has strict dual-zone access control and identity verification.  24x7x365 onsite security staff monitor access to the facility, and technical staff onsite work to maintain our cloud SLA’s related to systems availability. 

OS and Software Support

Supported Operating Systems:

  • CentOS (6.x, 7.x)
  • RHEL (6.x, 7.x)
  • Debian
  • FreeBSD (10.x, 11.x)
  • Ubuntu (14.04, 16.04, 18.04, LTS)
  • Cloud Linux
  • FreeNAS
  • PFSense
  • Windows Server 2008/R2 (Standard, Enterprise)
  • Windows Server 2012/R2  (Web, Standard, Enterprise, Datacenter)
  • Windows Server 2016 (Web, Standard, Enterprise, Datacenter)

Supported Applications:

  • cPanel/WHM
  • MySQL
  • PHP
  • Apache
  • Litespeed Web Server
  • Microsoft SQL
  • Microsoft Exchange
  • Microsoft Sharepoint
  • Oracle DB
  • PFsense/TNSR Routing Suite
  • Ceph
  • GlusterFS

Need a Quote?

Have a Question?

We maintain a vast knowledge base full with articles, guides, how-tos, instructions, and answers to our client’s most frequently asked questions. If you have a question, odds are the answer is here

Comprehensive Migration Services

Environmental Analysis

AMDS Cosmos Engineers perform an in-depth environmental analysis, including internal network scans, documentation, and systems mapping, as part of our comprehensive cloud migration service. The findings of this environmental analysis inform our design and build engineers of any pain points in the existing setup, such as latency or throughput, and guide us as we work to architect a solution for your specific application and business needs.


Once the Design and Build phase of the migration service is complete – Cosmos Engineers work to implement the approved design and build documentation. This includes working with the customer to obtain necessary connectivity, credentials, and application license keys needed to effectively build the solution. The solution is then provisioned using our cloud orchestration system, and applications are installed locally or by enlisting the help of third party vendors.

Design and Build

Following an extensive environmental analysis and thorough documentation of the existing environment, Cosmos engineers set out to translate the existing infrastructure into functional cloud workload requirements. All applications, microservices, features and functionality are converted into a cloud-based architecture for the purpose of developing a migration plan. This cooperative phase of migration heavily involves the customer’s design approval.

Ongoing Support

Ensuring that your solution continues to function optimally is a key part of the comprehensive migration service offered here at Cosmos. As part of the implementation phase, our engineers will work with you to determine appropriate application and service monitoring, and will build in procedures to ensure that both your organization and our engineers can remain involved in scaling your solution as necessary. This is effectively the solution completion phase.