4D Data Centre

FAQs

For someone who doesn’t work in IT, what is a ‘colocation data centre’?

‘Colocation’ is a fancy word we and other people in the IT industry use to describe putting Company A’s IT equipment into Company B’s building to look after. Company A still owns and manages all the equipment and can visit whenever they want, hence the name ‘co-locate’.

The reason they would want to ‘co-locate’ their IT equipment is because the new building has been designed specifically to look after computers and provide really fast connections to the internet.  In essence, their primary commodity is the housing and transfer of data, hence the term ‘data centres’.

Thanks to economies of scale, a colocation data centre is able to offer the following at a greatly reduced cost in comparison with businesses trying to achieve the same results in-house:

Check out our video explanation here.

How does 4D Data Centres charge for bandwidth?

We charge for bandwidth based on throughput (Mbps) with a committed data rate (CDR) rather than data transfer (GB per month). This allows us to offer burstable bandwidth to meet changing demands or peaks in user activity without any degradation in service or limitations on the amount of data you can transfer per month. All bandwidth is billed on the 95th percentile rule (see below for more details).

What is the 95th percentile rule?

Bandwidth usage is measured from the switches and recorded in a log file every five minutes. At the end of the month, the samples taken are sorted from highest to lowest by our billing system, and the top 5% of data (which equates to approximately 36 hours of a 30-day billing cycle) is thrown a way. This allows for short, unexpected bursts in traffic (for example, a new product launch or large data backup) that will not be charged for as “over-usage” bandwidth.

Based on this model, the top 36 hours (top 5% of 720 hours) of peak traffic is not taken into account when billed for an entire month. Bandwidth could be utilised at a higher rate for up to 72 min a day with no financial penalty.

What does 99.999% uptime actually mean?

Availability is usually expressed as a percentage of uptime in a given year.

The following table shows the downtime that will be allowed for a particular percentage of availability, presuming that the system is required to operate continuously.

Service level agreements often refer to monthly downtime or availability in order to calculate service credits to match monthly billing cycles.

The following table shows the translation from a given availability percentage to the corresponding amount of time a system would be unavailable per year, month, or week.

 

Availability %

Downtime per year

Downtime per month*

Downtime per week

90% ("one nine")

36.5 days

72 hours

16.8 hours

95%

18.25 days

36 hours

8.4 hours

99% ("two nines")

3.65 days

7.20 hours

1.68 hours

99.5%

1.83 days

3.60 hours

50.4 minutes

99.9% ("three nines")

8.76 hours

43.2 minutes

10.1 minutes

99.95%

4.38 hours

21.56 minutes

5.04 minutes

99.99% ("four nines")

52.56 minutes

4.32 minutes

1.01 minutes

99.999% ("five nines")

5.26 minutes

25.9 seconds

6.05 second

* For monthly calculations, a 30-day month is used.

How much power per rack can 4D Data Centres offer?

We offer the following power as standard in our racks

Using something called the ‘80% rule’ all our power is provisioned over correctly sized breakers and cables allowing you to consistently draw the full amount of power you pay for.

Some data centres offer 16Amps of power but in actual fact this is an absolute limit and if you go over it, you may end up tripping the breaker causing you to lose power to your whole rack.

What is a ‘U’ of space?

A rack unit or U is a unit of measure used to describe the height of equipment intended for mounting in a rack (which is measured in ‘U’ for height).

One rack unit (U) is 1.75 inches (44.45 mm) high.

I’ve got dual power feed servers, can you accommodate them?

In short, yes. Our standard options for power give you the choice of having single or dual feeds into the rack along with a couple of different ways of managing the resilience, depending on the type of equipment you are installing.

APC Power Bar Options:

Standard APC Power Bar

The standard APC power bar has 42 ports with reporting capabilities to view power draw in real time with historical data but no remote reboot functionality.

Intelligent APC Power Bar

The intelligent APC power bar has 42 ports with reporting capabilities to view power draw in real time with historical data but also has remote reboot functionality to allow for power cycling of devices connected to each outlet.

Single Feed Power (A-Only):

Single APC Power Bar

This gives a single route of power onto one APC power bar (PDU) in the rack.

Dual Feed Power (A+B):

Dual APC Power Bars

This gives two routes of power into the rack each of which is fed from a separate data floor distribution board over separate power paths from the building UPS.

This setup is ideal for clients who have high availability equipment with dual power supplies as it provides complete resilience over the failure of any one power delivery component.

Single APC Power Bar with Static Transfer Switch (STS)

This gives two routes of power into the rack which are terminated onto an STS with a single APC power bar in the rack. The STS provides the functionality to switch from the ‘A’ power feed to the ‘B’ power feed without loss of power delivery to the rack.

This setup is ideal for clients who have single power supply equipment but still require some level of resilience on power delivery.

What do you mean by 'resilient connectivity' to the racks?

Our standard setup for network delivery gives you two Cat5e connections to the 4D Data Centres core network with each cable going back to a separate switch. These are normally on 100Mbps switch ports but can be upgraded to 1Gbps or 10Gbps as well as replaced with Cat6, Cat6a or fibre if needed.

Routing is either provided over a static route where we will supply you with a gateway IP address to use and we handle all routing aspects of the connection, or if you wish to run your own routers we will supply the connection over a BGP peer giving you more flexibility on how your traffic is handled. With BGP peering we have pre-defined communities to allow you to influence how your traffic is handled across our network and upstream providers.

We also offer IPv4 and IPv6 address space to all clients. We have native IPv6 support with IPv6 enabled upstream carriers and peers.

The following options are available for configuring resilience: