How to choose a data center location for your server

The right location for a server is usually the one closest to most of your users, but distance is only part of the answer. This guide explains how latency works, how to measure it properly, and how data protection rules, CDNs and resilience fit into the decision. HyperDC servers run in 24 data center locations; the data centers page lists them with the services each one offers.

Before you start

• Know where your users are. Your analytics, store orders or game server logs show the countries and networks most of your traffic comes from.
• Know your workload. A website, a game server and a remote desktop have different limits for acceptable latency.
• Have a terminal ready to run ping and mtr (Linux and macOS) or pathping (Windows).

Why distance turns into latency

Light in optical fibre travels at about two thirds of its speed in a vacuum, roughly 200,000 kilometres per second. The ITU's planning figure for fibre is five microseconds per kilometre, so every 100 kilometres adds about one millisecond to a round trip. Real routes are longer than a straight line on a map, and measured round trips are often several times slower than that minimum.

Latency also multiplies. Opening a secure web page takes several round trips before the first byte arrives: the DNS lookup, the TCP connection, the TLS handshake and the request itself. A server 100 milliseconds away can therefore cost a first-time visitor several hundred milliseconds.

How much latency is too much?

Step 1: Measure from your users' side

A ping from your office says little about your visitors. Measure from the regions your users are in, ideally from several networks and at different times of day. Use the test IP or looking glass that a location card on our data centers page shows, where one is available, as the target. In the examples, replace 203.0.113.10 with that address.

ping -c 20 203.0.113.10

mtr -rwc 50 203.0.113.10

Test-Connection 203.0.113.10 -Count 20
pathping 203.0.113.10

Verify: compare the typical value (the average or median) and how much it varies, not the best single result. Loss at a hop in the middle that does not continue to the last hop is usually a router that de-prioritises replies to pings, not a real problem.

For a broader picture, a public measurement network such as RIPE Atlas tests from many networks at once.

Step 2: Use the order form's estimate

When you order a HyperDC server, the order form shows an estimate of the latency from your location to each data center. It is a quick way to compare candidates from where you sit; combine it with measurements from your users' regions.

Step 3: Check where your data may live

Where a server stands can matter legally as well as technically. Under the EU's GDPR, personal data may leave the European Economic Area only for countries with an adequacy decision or with safeguards such as standard contractual clauses. Some sectors and contracts also require data to stay in a particular country. Choosing a location inside the required region is the simplest way to meet such rules, but backups, monitoring and support access can involve transfers too. Check your obligations with a legal adviser.

Step 4: Weigh the other factors

• Connectivity: how a location connects to your users' internet providers matters as much as distance.
• Protection: check whether DDoS protection is included for the plan in that location; the plan card shows it.
• Hardware and plans: not every server model is offered in every location.
• Time zones: consider when maintenance and your own working hours fall for your users.
• Price: the same hardware can cost a different amount in different locations.

Step 5: Decide on a CDN or a second location

A content delivery network caches images, scripts and other static files close to your visitors, which helps a site with a worldwide audience. Dynamic requests, such as a checkout, a search or an API call, still go to your server, so the application and its database should sit close to most of your users and close to each other. See Cloudflare in front of your site.

A second location makes sense when downtime would be costly. Options range from backups you can restore in another region to a warm standby that can take over quickly. Each step up costs more and needs regular failover tests.

Troubleshooting

Latency is fine at night and high in the evening. Congestion on a route at peak hours. Measure at the hours your users are active and compare locations at those times.

The closest location is not the fastest. Traffic follows network connections rather than straight lines. A location a little farther away can be faster if it connects better to your users' providers.

Users in one country report slowness. Ask them for mtr or pathping output to your server, and open a ticket with it if the delay appears inside our network.

Next steps

• Compare server lines: VPS vs VDS vs dedicated server.
• Questions about our locations: data centers FAQ.
• Moving an existing site? Move a website without downtime.