Skip to main content
.com domains from $2.99 — free WHOIS privacy on every name

Diligence brief · Frankfurt

Frankfurt hosting, with the evidence attached

A counterparty has sent a fourteen-page questionnaire about your web infrastructure and your current host answers everything with the word robust.

The short answer

Answer a diligence questionnaire with figures, not adjectives: a 99.9% uptime target under continuous monitoring with a pro-rated credit when a month falls short through our fault, free SSL on every hostname renewed before expiry, daily backups with self-service restore, two-factor authentication on the account, and a UK-registered counterparty on English-law terms.

The performance section answers just as plainly. Our published Western European band is 10–35 ms round trip to the London origin, every plan from $2.42/mo runs NVMe storage behind a server-level LiteSpeed cache, and the cache header on any response tells the reviewer whether a page was served or rebuilt.

By the HostingFast team · Reviewed 12 August 2026

Free

Migration, engineer-run

24/7

Engineers on shift

Daily

Backups, restore yourself

$0

Setup, every tier

The European Central Bank, the exchange and the densest concentration of banking supervision on the continent sit here, with DE-CIX humming away in the same skyline. Vendor questionnaires are a normal part of the week, and a firm that cannot answer one loses the mandate rather than the argument.

So this page is written as evidence. What the commitments actually are, what the numbers actually say, which parts of a site the exchange next door cannot help with, and how a trade-fair week behaves.

The questions a reviewer actually asks

Availability: a 99.9% target, monitored continuously, with a pro-rated credit applied on request when a calendar month falls short through a fault on our side. Encryption: free SSL on every hostname, issued automatically and renewed before it can lapse. Recovery: daily backups on every plan, every 6 hours on Nitro, restored by you from the panel rather than by a ticket. Access: two-factor authentication on the account.

Contracting: a UK-registered company on English-law terms, which shortens the data-handling section of most conversations considerably. Send the questionnaire itself and we will complete the infrastructure part rather than leaving your compliance officer to translate marketing copy into answers.

The performance section, in figures

We publish 10–35 ms round trip for Western and Northern Europe to our London origin, described as indicative for a well-connected consumer network rather than as a guarantee, because that is what it is. Set against the 800 ms Google treats as a good time to first byte, the distance is spending a few per cent of the budget.

The rest of the answer is architectural: NVMe storage, a LiteSpeed cache built into the server and OPcache on current PHP 8.x, so a cached page is answered without booting the application and an uncached one is still cheap to build. A reviewer can verify the cache claim in one request by reading the response header.

What the exchange next door cannot fix

Frankfurt is one of the best-connected cities on earth and none of that helps the parts of a site that cannot be cached. A client login, a document portal, a database query behind a search box and any SSH or FTP session all speak to the origin on every request, and no amount of peering changes the fact that the work happens at one end of the link.

The honest response is architectural rather than geographic. Reduce the number of round trips per action, batch admin work, and where an application is uncacheable end to end, place it on a VPS with root access instead of pretending a cache applies. You will get that recommendation before the invoice, which is a shorter conversation than the alternative.

Messe week is a cache-ratio question

Trade-fair traffic is people skimming company profiles between halls, which is the most cacheable behaviour there is. Those pages serve pre-built and never touch the database, so the busiest week of your year should be the most boring week for the server. Bandwidth runs 500 GB a month on Sprint, 1 TB on Turbo and 2 TB on Nitro.

Check the ratio before the fair rather than during it. Request your top ten URLs twice each, record which return a cache hit on the second attempt, and fix whatever is blocking the rest — usually a session cookie set sitewide or a personalisation snippet in the header. Ten minutes of work, done in a quiet week.

An aisle of racks inside the London datacentre

What goes in the pack

The 99.9% availability target and its pro-rated credit, free SSL on every hostname, daily backups with self-service restore, two-factor authentication, and a UK-registered contracting party on English-law terms.

On the technical side: NVMe storage, server-level LiteSpeed caching, OPcache on current PHP 8.x, per-site PHP control and a published latency band you can quote.

  • 99.9% uptime target with a pro-rated credit
  • Daily backups, every 6 hours on Nitro
  • Free SSL on every hostname, renewed automatically
  • A published 10–35 ms European latency band

Why HostingFast

Standard on every plan

Commitments with numbers

A 99.9% uptime target and a pro-rated credit when a month misses it through our fault — a figure with a remedy, not an adjective.

Recovery you control

Daily backups on every plan and every 6 hours on Nitro, restored by you from the panel in minutes rather than by a ticket overnight.

Encryption without a diary entry

Free SSL on every hostname, issued as soon as the name resolves here and renewed automatically long before it can lapse.

A verifiable performance claim

Server-level LiteSpeed caching with a response header that reports hit or miss, so a reviewer can check the claim rather than take it.

A single contracting party

A UK-registered company on English-law terms, which keeps the legal section of a vendor questionnaire short and unambiguous.

Migration under your control

Engineers move the site free while it stays live, and delegation changes only on your sign-off — which suits a change-controlled environment.

Quick Start

From order to online

  1. 1

    Collect the figures first

    Uptime target and credit, backup cadence, SSL policy, authentication and contracting party. Those five answer most of a questionnaire on their own.

  2. 2

    Measure the site as it stands

    Three curl runs, the field LCP, and the cache result on the second request for your ten busiest URLs. That is your before, and it is evidence.

  3. 3

    Migrate on your change window

    One free migration request, verification on a temporary address, and delegation changed at a time you choose rather than one we impose.

Built In

Loaded onto every plan

  • 99.9% uptime as the target, monitored around the clock
  • Daily backups, with self-service restores you run from the panel
  • Free SSL on every plan, renewed automatically before it can expire
  • NVMe SSD storage on every tier, not just the expensive ones
  • LiteSpeed caching built into the server rather than patched in by plugin
  • Current PHP 8.x with OPcache enabled from the start
  • Staging environments for testing changes before they ship
  • Per-site PHP version switching from the control panel
  • WordPress and 400+ other applications installed in one click
  • Money-back cover: 30 days on hosting plans, 7 on reseller

Frequently Asked

What people ask us most often

What do we hand a reviewer asking about availability?

The 99.9% target, the fact that it is monitored continuously, and the pro-rated credit that applies on request when a calendar month falls short through a fault on our side. Alongside it: daily backups with self-service restore, free SSL on every hostname, two-factor authentication, and a UK-registered counterparty on English-law terms.

Can a reviewer verify the caching claim independently?

Yes, in one request. Fetch any public page twice and read the cache header on the second response — a served page reports a hit. That is a better answer than a paragraph about architecture, because it is reproducible from the reviewer's own machine without any access to ours.

Does DE-CIX proximity change what we should host where?

For cacheable pages, no — the band we publish is 10–35 ms and a cache hit is answered pre-built anyway. For an application that is logged in end to end, peering does not help either, because the work happens at the origin. That is a VPS conversation rather than a location one.

How is a change window handled during migration?

Engineers copy files, databases and mail to the new account while the existing site keeps serving. You verify on a temporary address, and delegation changes only when you say so — so the cutover lands inside your own change window rather than ours.

Keep reading

Changing hosts? Run through our checklist first.

A straightforward sequence for a switch your visitors never feel: which files move first, how to shift email across without losing a single message, the right moment to repoint DNS, and the two mistakes behind almost all the downtime we get asked to rescue.

You'll get the checklist email, then occasional pointers on keeping a site running fast. Unsubscribe the moment you want out — the privacy policy covers the rest.

Answer it with figures.

NVMe behind a server-level LiteSpeed cache from $2.42/mo, a 99.9% target with a credit, daily backups and free SSL on every hostname.

View Node.js Hosting plans