In progress - Scheduled maintenance is currently in progress. We will provide updates as necessary.
Mar 24, 2026 - 13:00 CET
Scheduled - In the next few days, we will continue the previously announced network upgrades to further improve the availability and resilience of our network. We do not anticipate any service interruptions.

What we are doing
We will:
- take a new dark fiber between maincubes FRA01 and our Equinix FR4 PoP into production
- add new DDoS filters to our scrubbing cluster
- migrate additional physical and logical interfaces in line with our modernized network design
- upgrade our connectivity with a new transit carrier (GTT) and several private peerings at our Equinix PoP (Zet.net, Rostelecom, Google, BiMajLink, Bytedance / TikTok)
- shift more load to our new Equinix PoP and its local carriers and peerings

If a connection must be taken out of service during the maintenance, traffic will be rerouted gracefully beforehand. Redundancy and available bandwidth will be reduced temporarily, but sufficient capacity will remain and all services are expected to stay online.

Expected impact
No service interruption is expected at any datacenter, but it cannot be ruled out entirely. Brief periods of slightly higher latency or minor packet loss may occur during some changes, but any impact is expected to be limited.

Routing from and to various locations will change as part of this maintenance. These routing changes are intended to improve the overall network quality. If you notice a persistent degradation in quality (e.g. packet loss or high latency), please reach out to our support.

Affected customers
This maintenance affects the network infrastructure behind all dataforest services and locations. No customer action is required.

Fallback plan
Should any action cause an unforeseen disruption or significant packet loss, we will roll back the relevant change. This should restore normal connectivity within 1-5 minutes, depending on the exact impact. We will also update this status post transparently. If an issue occurs, please allow us a few minutes to publish an update before contacting us.

Mar 24, 2026 13:00 - Apr 7, 2026 02:00 CEST
[dataforest Backbone] Interxion FRA8 Under Maintenance
90 days ago
100.0 % uptime
Today
Edge Network (affects all locations) Under Maintenance
90 days ago
100.0 % uptime
Today
DDoS Protection (affects all locations) Operational
90 days ago
100.0 % uptime
Today
Dedicated Servers (40G / 100G / 400G) Operational
90 days ago
100.0 % uptime
Today
Facilites Operational
90 days ago
100.0 % uptime
Today
[Datacenter] maincubes FRA01 Under Maintenance
90 days ago
99.99 % uptime
Today
Datacenter Routing and Switching Infrastructure Under Maintenance
90 days ago
100.0 % uptime
Today
Ceph Cluster Operational
90 days ago
100.0 % uptime
Today
Virtual Servers Operational
90 days ago
99.98 % uptime
Today
Managed Servers Operational
90 days ago
100.0 % uptime
Today
Dedicated Servers Operational
90 days ago
100.0 % uptime
Today
Plesk Web Hosting Operational
90 days ago
100.0 % uptime
Today
TeamSpeak3 Servers Operational
90 days ago
99.99 % uptime
Today
Network Storage Operational
90 days ago
100.0 % uptime
Today
Colocation Racks Operational
90 days ago
100.0 % uptime
Today
Facilites Operational
90 days ago
100.0 % uptime
Today
[Datacenter] firstcolo FRA4 Under Maintenance
90 days ago
99.99 % uptime
Today
Datacenter Routing and Switching Infrastructure Under Maintenance
90 days ago
99.99 % uptime
Today
Dedicated Servers Operational
90 days ago
100.0 % uptime
Today
Colocation Racks Operational
90 days ago
100.0 % uptime
Today
Facilites Operational
90 days ago
100.0 % uptime
Today
General Services Operational
90 days ago
100.0 % uptime
Today
Avoro CP & Support Operational
90 days ago
100.0 % uptime
Today
PHP-Friends CRM & Support Operational
90 days ago
100.0 % uptime
Today
Hotline Operational
90 days ago
100.0 % uptime
Today
Dedicated Control Panel Operational
90 days ago
100.0 % uptime
Today
IPMI VPN Operational
90 days ago
100.0 % uptime
Today
DDoS Manager Operational
90 days ago
100.0 % uptime
Today
Operational
Degraded Performance
Partial Outage
Major Outage
Maintenance
Major outage
Partial outage
No downtime recorded on this day.
No data exists for this day.
had a major outage.
had a partial outage.

Scheduled Maintenance

[Action Required] Disruptive power maintenance affecting selected racks at firstcolo FRA4 Apr 2, 2026 13:00-16:00 CEST

Deutsch / German
(English version below)

Zur Behebung eines Problems an einer USV-Anlage sind kurzfristige Wartungsarbeiten an der Strom-Unterverteilung "UV-P" am Standort firstcolo FRA4 erforderlich. Betroffen sind 17 von 48 dataforest-Racks an diesem Standort.

Im Rahmen der Arbeiten wird diese Unterverteilung kurzzeitig abgeschaltet und auf eine andere Niederspannungshauptverteilung migriert. Diese Maßnahme war im Zuge einer geplanten Modernisierung ohnehin vorgesehen, muss nun jedoch aufgrund eines akuten Problems vorgezogen werden.

Diese Ankündigung ist ausnahmsweise zweisprachig. Weitere Updates veröffentlichen wir auf Englisch.

Wer betroffen ist:
Betroffen sind manche Systeme am Standort "fc-fra4". Server an den Standorten "mc-fra01", "ix-fra8" und "eqx-fr4" sind nicht betroffen.

Bei Servern mit redundanter Stromversorgung (laut Vertrag / Produktbeschreibung) ist kein Ausfall zu erwarten, da unsere Racks aus unterschiedlichen Unterverteilungen gespeist werden. Während der Wartung fällt jedoch ein Stromfeed weg, sodass für etwa ein Drittel unserer Racks vorübergehend keine Stromredundanz besteht.

Server mit nur einem Netzteil, die an der betroffenen Unterverteilung "UV-P" angeschlossen sind, werden während der Wartung stromlos sein und müssen vorher sauber heruntergefahren werden, um Datenverlust und Dateisystemschäden zu vermeiden. Betroffene Managed Dedicated Server fahren wir herunter.

So prüfen Sie, ob Ihr Server betroffen ist:
Im Kundenbereich bzw. unter https://dedicated.dataforest.cloud sehen Sie den Namen Ihres Servers. In den letzten zwei Tagen haben wir Server in betroffenen Racks um ihre jeweilige Unterverteilung ergänzt. Wenn Ihr Server das Kürzel "-UV-P" trägt, zum Beispiel "root1234.fc-fra4-UV-P", ist er direkt betroffen. Bitte achten Sie darauf, nicht nur auf ein zusätzliches Kürzel zu prüfen, sondern ausdrücklich auf "-UV-P".

Ablauf der Wartung:
Das angegebene Wartungsfenster ist ein Richtwert, da die Arbeiten unter anderem von externen Elektrofachfirmen abhängen. Wir haben dieses bereits so exakt wie möglich eingegrenzt. Etwa 15-30 Minuten vor der tatsächlichen Abschaltung veröffentlichen wir in diesem Statuspost ein weiteres Update.

Falls Sie im Wartungsfenster nicht flexibel reagieren können, müssen Sie betroffene Server vor Beginn der Arbeiten selbst herunterfahren. Andernfalls würden diese durch die Stromabschaltung hart ausgeschaltet. Diese wird voraussichtlich 30-45 Minuten andauern.

In einigen betroffenen Racks nutzen wir die Abschaltung zusätzlich für den vorgezogenen Austausch von PDUs eines Modells, das in der Vergangenheit durch eine ungewöhnlich hohe Ausfallquote aufgefallen ist. Dadurch vermeiden wir für betroffene nicht redundante Server eine weitere kurzfristige Stromwartung. Diese zusätzlichen Arbeiten werden weitgehend parallel zur ohnehin notwendigen Abschaltung durchgeführt, sodass nur wenig zusätzliche Downtime entsteht. Je nach Rack rechnen wir insgesamt mit 45-90 Minuten.

Wir informieren während der Wartung hier über die Wiederherstellung der einzelnen Rack-Stromfeeds. Server starten mit unserer Standard-BIOS-Konfiguration nach Wiederherstellung der Stromversorgung automatisch. Server, die sich nicht automatisch einschalten, prüfen wir selbstständig. Bitte greifen Sie in diesen Prozess nicht manuell ein.

Welche Racks in welcher Form betroffen sind:

Racks mit redundanten Servern:
X03, X04, X06, X12
Diese Server verlieren einen Stromfeed, laufen aber weiter. Je nach CPU und Last ist ein geringerer Maximaltakt möglich. Es gibt drei Ausnahmen; die betroffenen Server wurden entsprechend mit UV-P gekennzeichnet.

Racks mit primär nicht redundanten Servern:
X13, Z07, Z08
Diese Racks sind während der Wartung der Unterverteilung auf einem Feed stromlos. Dedicated Server an UV-P sind entsprechend gekennzeichnet.

X07, X08, X10, X11
In diesen Racks wird zusätzlich eine PDU getauscht, daher sind unterschiedliche Ausfallzeiten zu erwarten. Dedicated Server an UV-P sind entsprechend gekennzeichnet.

Colocation-/Kundenracks ohne PDU-Austausch:
X14, X17

Colocation-/Kundenracks mit PDU-Austausch:
X15, X16, X18

Sie können das Rack Ihres Servers anhand der Switchport-Statistiken zuordnen. Bei Kundenracks haben wir keine Kenntnis über die Stromredundanz der angeschlossenen Server.

Zusätzlich wird im dataforest-Core-Rack X09 ebenfalls ein Stromfeed abgeschaltet und eine PDU getauscht, wodurch für die Dauer der Wartungsarbeiten keine Stromredundanz für Routing und Coreswitching besteht und insofern ein erhöhtes Risiko vorliegt.

Wie Sie sich vorbereiten sollten:
- Abonnieren Sie diese Statusseite, um Updates zu erhalten.
- Prüfen Sie, ob Ihr Server an "UV-P" hängt.
- Planen Sie bei Bedarf einen eigenen Shutdown und die Downtime ein.
- Informieren Sie Ihre Nutzer bzw. Kunden.
- Führen Sie möglichst vorab einen Test-Reboot durch und prüfen Sie, ob alle benötigten Dienste automatisch starten.
- Prüfen Sie per IPMI, ob im BIOS "Restore on AC Power Loss -> Power On" gesetzt ist. Diese Einstellung setzen wir standardmäßig, empfehlen aber eine zusätzliche Kontrolle. Auf Wunsch übernimmt unser Support diese Prüfung für Sie. Bitte melden Sie sich hierfür spätestens bis zum 01.04.2026.
- Prüfen Sie RAID und Backups und erstellen Sie unmittelbar vor der Wartung ein aktuelles vollständiges Backup.

Wenn Ihr Server nach der Wartung nicht erreichbar ist:
Prüfen Sie zunächst diesen Statuspost. Sobald die Wartung aus unserer Sicht erfolgreich abgeschlossen ist, kontrollieren Sie bitte per IPMI im Dedicated-Server-Controlpanel die Bildschirmausgabe Ihres Systems und beheben gegebenenfalls Softwareprobleme, die den Start verhindern. Wenn Sie einen Hardwaredefekt vermuten, kontaktieren Sie unseren Support per Ticketsystem.

Wie dataforest vorbereitet ist:
- Top-of-Rack-Switches sind redundant an Strom und Netzwerk angebunden. Das heißt: Auch wenn Sie nur einen Uplink gebucht haben, verfügt Ihr Switch über zwei Stromfeeds und zwei Coreswitch-Uplinks. dataforest implementiert grundsätzlich "doppelte Redundanz", wo immer dies sinnvoll möglich ist.
- Unser Ersatzteillager wird aufgestockt, um eventuelle Defekte schnell beheben zu können.
- dataforest-Mitarbeiter sind vor Ort und koordinieren die Arbeiten mit den Dienstleistern.
- Redundante Netzteile werden vorab überprüft.

Vielen Dank für Ihre Mithilfe.

English / Englisch

To resolve an issue affecting a UPS system, short-notice maintenance is required on the "UV-P" power subdistribution at our firstcolo FRA4 site. 17 out of 48 dataforest racks at this location are affected.

As part of this work, this subdistribution will be shut down briefly and migrated to a different low-voltage main distribution. This measure had already been planned as part of a broader modernization, but must now be brought forward due to an acute issue.

This announcement is exceptionally bilingual. Further updates will be published in English.

Who is affected:
Some systems at the "fc-fra4" site are affected. Servers at "mc-fra01", "ix-fra8", and "eqx-fr4" are not affected.

For servers with redundant power supply (according to contract / product description), no outage is expected, as our racks are fed from different power subdistributions. However, one power feed will be unavailable during the maintenance, which means that roughly one third of our racks will temporarily lose power redundancy.

Single-PSU servers connected to the affected "UV-P" subdistribution will lose power during the maintenance and must be shut down cleanly in advance to avoid data loss and filesystem corruption. We will shut down affected Managed Dedicated Servers ourselves.

How to check whether your server is affected:
In the customer area or at https://dedicated.dataforest.cloud, you can see your server name. During the last two days, we have added the corresponding power subdistribution to servers in affected racks. If your server name includes the suffix "-UV-P", for example "root1234.fc-fra4-UV-P", it is directly affected. Please do not only check whether an additional suffix is present, but specifically whether it is "-UV-P".

How the maintenance will proceed:
The announced maintenance window is an estimate, as the work depends in part on external electrical contractors. We have already narrowed it down as precisely as possible. Approximately 15-30 minutes before the actual shutdown begins, we will publish another update in this status post.

If you are unable to react flexibly during the maintenance window, you must shut down affected servers yourself before the work starts. Otherwise, they would be hard powered off by the maintenance. The shutdown itself is expected to last 30-45 minutes.

In some affected racks, we are also using this shutdown window to bring forward the replacement of PDUs of a model that has shown an unusually high failure rate in the past. This allows us to avoid another short-notice power maintenance event for affected non-redundant servers. These additional works will be carried out largely in parallel with the already required shutdown, resulting in little additional downtime. Depending on the rack, we expect a total duration of 45-90 minutes.

During the maintenance, we will use this status post to report the restoration of the individual rack power feeds. Servers will automatically power on once power has been restored, based on our standard BIOS configuration. Servers that do not power on automatically will be checked by us. Please do not interfere manually with this process.

Which racks are affected and in what way:

Racks with redundant servers:
X03, X04, X06, X12
These servers will lose one power feed but will remain online. Depending on CPU and load, a lower maximum clock speed may be possible. There are three exceptions; the affected servers have been marked accordingly with UV-P.

Racks with primarily non-redundant servers:
X13, Z07, Z08
These racks will lose one feed during the subdistribution maintenance. Dedicated Servers connected to UV-P are marked accordingly.

X07, X08, X10, X11
An additional PDU will be replaced in these racks, so different outage durations are to be expected. Dedicated Servers connected to UV-P are marked accordingly.

Colocation / customer racks without PDU replacement:
X14, X17

Colocation / customer racks with PDU replacement:
X15, X16, X18

You can identify your server's rack based on the switch port statistics. For customer racks, we do not have visibility into whether the connected servers are actually power-redundant.

In addition, one power feed in the dataforest core rack X09 will also be shut down and one PDU will be replaced. As a result, routing and core switching will operate without power redundancy for the duration of the maintenance, which increases risk during the work.

How to prepare:
- Subscribe to this status page to receive updates.
- Check whether your server is connected to "UV-P".
- If necessary, plan a manual shutdown and the resulting downtime.
- Inform your users or customers.
- Perform a test reboot beforehand if possible and verify that all required services start automatically.
- Check via IPMI whether your BIOS is configured to power on automatically after AC power is restored ("Restore on AC Power Loss -> Power On"). We set this by default, but strongly recommend verifying it. Our support team can perform this check for you on request. Please contact us no later than 2026-04-01.
- Check your RAID integrity and backup concept, and create a fresh full backup immediately before the maintenance.

If your server is not reachable after the maintenance:
Please check this status post first. Once the maintenance has been marked as successfully completed from our side, please verify your server's console output via IPMI in the Dedicated Server Control Panel and resolve any software-side issues that may prevent the system from booting. If you suspect a hardware fault, please contact our support team via ticket.

How dataforest is prepared:
- Top-of-rack switches are connected redundantly to both power and network. This means that even if you only ordered one uplink, your switch still has two power feeds and two core switch uplinks. dataforest generally implements "double redundancy" wherever this is reasonably possible.
- We are increasing our spare parts stock so that any potential defects can be resolved quickly.
- dataforest staff will be on site and coordinate the work with the involved service providers.
- Redundant power supplies will be checked in advance.

Thank you for your cooperation.

Posted on Mar 28, 2026 - 17:01 CET
Mar 28, 2026

No incidents reported today.

Mar 27, 2026

No incidents reported.

Mar 26, 2026

No incidents reported.

Mar 25, 2026

No incidents reported.

Mar 24, 2026

Unresolved incident: Network Maintenance Notification.

Mar 23, 2026

No incidents reported.

Mar 22, 2026

No incidents reported.

Mar 21, 2026

No incidents reported.

Mar 20, 2026

No incidents reported.

Mar 19, 2026

No incidents reported.

Mar 18, 2026

No incidents reported.

Mar 17, 2026

No incidents reported.

Mar 16, 2026
Completed - The scheduled maintenance has been completed.
Mar 16, 22:53 CET
In progress - Scheduled maintenance is currently in progress. We will provide updates as necessary.
Mar 16, 16:00 CET
Scheduled - We will carry out maintenance on our DDoS protection infrastructure.

What we are doing
We will deploy software updates to our redundant DDoS scrubbing cluster. Filter appliances will be taken out of production and updated one by one to ensure mitigation capacity is always sufficient. After each update, functionality will be verified before we move on to the next filter.

Expected impact
No customer impact is expected at any datacenter, but it cannot be ruled out entirely. Idle (inactive) connections and sessions may time out; active ones should not, as they are expected to remain synchronized during the startup of a new software release. If you notice anything unusual – such as timeouts of active sessions or the inability to connect to your server – please contact our support immediately. We will continue monitoring new tickets for a while after the maintenance.

Affected customers
All IP prefixes routed through our DDoS protection (which is the default) are affected by this maintenance. Only prefixes that have been explicitly configured to bypass our DDoS protection (which we do not recommend) are unaffected. In any case, no customer action is required.

Fallback plan
Should the update fail and cause issues, we will disconnect the filters within a few seconds and update this status post transparently. In that case, mitigation of attacks will not be possible for 30-60 minutes while we prepare a rollback.

Mar 15, 13:55 CET
Completed - The scheduled maintenance has been completed.
Mar 16, 00:00 CET
In progress - Scheduled maintenance is currently in progress. We will provide updates as necessary.
Mar 15, 23:00 CET
Scheduled - We will carry out emergency maintenance on our DDoS protection infrastructure due to various issues affecting voice services with a specific type of traffic.

What we are doing
We will deploy software updates to our redundant DDoS scrubbing cluster. Filter appliances will be taken out of production and updated one by one to ensure mitigation capacity is always sufficient. After each update, functionality will be verified before we move on to the next filter.

Expected impact
No customer impact is expected at any datacenter, but it cannot be ruled out entirely. Idle (inactive) connections and sessions may time out; active ones should not, as they are expected to remain synchronized during the startup of a new software release. If you notice anything unusual – such as timeouts of active sessions or the inability to connect to your server – please contact our support immediately. We will continue monitoring new tickets for a while after the maintenance.

Affected customers
All IP prefixes routed through our DDoS protection (which is the default) are affected by this maintenance. Only prefixes that have been explicitly configured to bypass our DDoS protection (which we do not recommend) are unaffected. In any case, no customer action is required.

Fallback plan
Should the update fail and cause issues, we will disconnect the filters within a few seconds and update this status post transparently. In that case, mitigation of attacks will not be possible for 30-60 minutes while we prepare a rollback.

Mar 15, 22:48 CET
Mar 15, 2026
Mar 14, 2026

No incidents reported.