Duration: 2 days, 4 hours and 10 minutes

Affected Components: Nueva York, Dallas

Jul 16, 05:40:01 GMT+0
Investigando - We are investigating reports of players being unable to join servers and experiencing timeouts while fetching resources. The issue originates with our upstream provider, CosmicGuard. We are awaiting a fix from their team and will provide updates as they become available..

Jul 18, 09:50:09 GMT+0
Resuelto - We have worked closely with CosmicGuard to identify and resolve the underlying issue, and all related problems should now be resolved. This incident primarily affected servers created during a specific timeframe and did not impact all services. If you are still experiencing any issues, please contact our support team. We appreciate your patience and cooperation while we worked toward a resolution..

Duration: 6 hours and 59 minutes

Affected Components: Miami, Singapore, Nueva York, Ciudad del lago salado, Australia, VPS Panel, París, Dallas

Jul 8, 17:12:48 GMT+0
Identificado - A critical security vulnerability (CVE-2026-53359) has been discovered in KVM, the virtualization technology we use for all virtual private servers, and for parts of our infrastructure. While there are no public working exploits at this time, we believe the situation will change in the near future. To ensure security and stability, we must intervene as soon as possible. Starting 12AM EST on 9 July, 2026, we will being applying the security patch to all host hypervisors, which also requires a reboot of all virtual private servers. We expect a brief downtime of around 15 to 30 minutes per virtual machine. if your server is unreachable for a longer duration, and you don't see any further updates in our status page, please reach out to our support team. Please also ensure that your server is configured to gracefully handle reboots, and restart any necessary services. Affected Services: \- All virtual private servers \- All bot hosting services \- All database hosts We will also be sending emails separate for every affected service. We will also share any necessary updates on our status page at <https://status.sparkedhost.com/>.

Jul 9, 04:00:01 GMT+0
Identificado - El mantenimiento está ahora en progreso.

Jul 9, 10:58:51 GMT+0
Completado - Maintenance has completed successfully..

Duration: 5 minutes

Affected Components: Nueva York, Dallas

Jul 5, 20:47:34 GMT+0
Identificado - Our upstream, CosmicGuard, identified a mitigation rule desync issue within their systems. This means that depending on which location of theirs you pass through to get to our Ashburn and Dallas locations, you may see connections being blocked. We are working with them to get this issue resolved as soon as possible. .

Jul 5, 20:52:18 GMT+0
Resuelto - Our upstream has confirmed that they aren't seeing any desync'd rules at this time. If you continue to experience issues connecting to services, please let us know. .

Duration: 1 hour and 54 minutes

Affected Components: Miami

Jun 23, 22:25:52 GMT+0
Investigando - We are aware of a network outage affecting Miami. We have isolated the cause to our upstream (DataPacket/CDN77). We have already reached out to them and they're working on a fix. We apologize for the inconvenience..

Jun 24, 00:19:37 GMT+0
Resuelto - Connectivity was restored, and this incident is resolved as of 18:04 EST. There was a power outage in the facility, affecting both A+B feeds of a specific floor. While our floor (and our services) were not directly impacted, our network upstream provider's equipment was in the affected floor and there was a network outage as a result. We already started the process of adding an additional carrier to this location a few weeks back, and we expect it to be completed shortly, which should improve redundancy..

Duration: 23 hours and 56 minutes

Affected Components: Dallas

Jun 2, 19:03:44 GMT+0
Identificado - We are aware that Dallas has had sporadic outages over the past few hours. Here is the update we got from CosmicGuard: We are currently investigating two separate issues in the Dallas region. We have an open ticket with one upstream regarding potential congestion we are seeing on their end. Separately, we have identified a faulty optic in a separate transit partner, and we have dispatched someone to replace the faulty optic. <https://status.as30456.net/cmpx01z2z016tp5aw1qo3tyb2>.

Jun 2, 20:45:22 GMT+0
Identificado - We have received a new update from them: The GTT instability is still being investigated with them. We have since disabled Telia routing in Dallas until the optics are replaced, and everything has been stable since for over an hour..

Jun 3, 15:10:49 GMT+0
Supervisando - Update from CosmicGuard: **Telia Link** \- The Telia link was restored last night at approximately 7:00 PM CST and has remained stable since. While we observed normal light levels and no errors on the port on our end, we proactively replaced the optic, which appears to have resolved the issue. **GTT Link** \- The GTT port showed similar symptoms—normal light levels with no errors. We replaced that optic yesterday as well, but the link continued to experience problems. GTT was scheduled to perform maintenance on their end at 1:00 AM CST but missed that window. We've temporarily removed this link from service and are awaiting their maintenance, which we've asked them to complete as soon as possible..

Jun 3, 19:00:00 GMT+0
Resuelto - This incident has been resolved..

Duration: 1 day and 6 hours

Affected Components: Apollo

Jun 1, 06:00:00 GMT+0
Identificado - We will be performing an update to the Apollo Panel on Monday, June 1st, 2026, from 2:00 AM to 2:30 AM EST. The panel will be placed in maintenance mode, which means you will not be able to access your panel during the 30-minute window. Game servers will remain online. This is in preparation to move to a new deployment/firewall system, which will improve our ability to apply DDoS filters from our providers..

Jun 1, 06:00:01 GMT+0
Identificado - El mantenimiento está ahora en progreso.

Jun 1, 06:30:00 GMT+0
Completado - Maintenance has completed successfully..

Duration: 25 days

Affected Components: París

May 28, 18:00:00 GMT+0
Identificado - On Thursday, May 28th, at 8 PM CEST, we will perform maintenance at our Paris location. All servers will be inaccessible for roughly 4-5 hours as we reorganize our racks and upgrade our network equipment to support 10G/40G. All services will be safely powered off and automatically powered back on once the maintenance is completed..

May 28, 18:00:01 GMT+0
Identificado - El mantenimiento está ahora en progreso.

May 29, 04:00:00 GMT+0
Completado - Maintenance has completed successfully..

Duration: 4 hours and 42 minutes

Apr 28, 22:02:01 GMT+0
Supervisando - Our vendor, cPanel, has pushed out an update and we applied it a few minutes ago. If you have any trouble logging in, please let us know..

Apr 28, 23:36:01 GMT+0
Resuelto - This incident has been resolved..

Apr 28, 18:54:26 GMT+0
Identificado - Due to a critical vulnerability reported by cPanel, we have chosen to proactively block access to the cPanel and WHM login portals for our shared web hosting services. Websites will continue functioning as normal, this only affects cPanel access. More information can be found here: <https://support.cpanel.net/hc/en-us/articles/40073787579671-Critical-Vulnerability-with-cPanel-WHM-Login-Authentication>.

Duration: 15 minutes

Affected Components: Apollo

Apr 9, 07:00:00 GMT+0
Identificado - We will be performing an update to the Apollo Panel on Thursday, April 9, 2026, from 3:00 AM to 3:15 AM EST. The panel will be placed in maintenance mode, which means you will not be able to access your panel during the 15-minute window. Game servers will remain online. This is in preparation to move to a new backup/database system to make things easier for our clients..

Apr 9, 07:00:01 GMT+0
Identificado - El mantenimiento está ahora en progreso.

Apr 9, 07:15:00 GMT+0
Completado - El mantenimiento se ha completado con éxito.

Duration: 15 minutes

Affected Components: Miami

Mar 2, 01:02:18 GMT+0
Identificado - We are aware of an outage affecting Miami at the moment, this is unrelated to the previous maintenance. Our upstream's technicians are looking into this..

Mar 2, 01:17:18 GMT+0
Resuelto - This incident has been resolved..

Duration: 5 days

Affected Components: Miami

Feb 26, 19:00:01 GMT+0
Identificado - El mantenimiento está ahora en progreso.

Feb 26, 19:05:39 GMT+0
Identificado - Our team is preparing to start the maintenance window. Servers will not go offline until announced. .

Feb 26, 19:00:00 GMT+0
Identificado - El mantenimiento está ahora en progreso.

Feb 25, 22:11:57 GMT+0
Identificado - The team has arrived in Miami. There is a good chance we will need to delay our maintenance windows to Friday-Monday. We are working with the facility to get our new space settled so that we can start as intended, we will keep you all updated. .

Feb 26, 19:00:00 GMT+0
Identificado - We will be performing major maintenance in Miami, with the following windows: Wednesday, Feb 25th, Thursday, Feb 26th, and Friday, Feb 27th. The maintenance will take place during the general workday. This maintenance is due to relocating our current cabs to a different floor within the facility. This will deliver a better cabinet layout, increased power, more network options, and additional space. On Wednesday, the 25th, we plan to cut over our network to the new racks. We plan to have minimal downtime, if any. The newly planned network will also include redundant routers to minimize future downtime. On Thursday, the 26th, starting around 10 AM EST, we will transfer half of our Miami servers to the new racks, resulting in 3-6 hours of downtime. Specifics on which racks are affected will be announced accordingly. On Friday the 27th, we will again begin transferring the other half of our Miami servers around 10 AM EST. The downtime should be around 3-6 hours as well. We may need to perform additional maintenance on Saturday, Sunday, and Monday, pending any issues that arise. Ensure you monitor the updates channel and your client email. Notifications will be sent via Apollo Panel and the Sparked Host Discord approximately 30 minutes before maintenance. All affected clients will be emailed to confirm their maintenance date. If you would like to place a dedicated server order, this would be the perfect time! We are on-site and ready to deploy. Just make a sales ticket! Current dedicated server owners, if you desire any upgrades or changes to your current server. This is the perfect time for you as well! For any questions or concerns regarding maintenance, Paul will be on site overseeing all operations. Please feel free to reach out via email at [paul.t@sparkedhost.com](mailto:paul.t@sparkedhost.com).

Feb 28, 11:20:44 GMT+0
Identificado - Unfortunately, due to issues with networking / cross connects, we were not able to start transfers today. Transfers will start around 11 AM EST on the 28 February, and 1 March, and run through 8 PM EST. We only expect a couple hours of downtime per server. If you have any questions don't hesitate to contact us via a ticket..

Mar 3, 19:00:00 GMT+0
Completado - El mantenimiento se ha completado con éxito.

Duration: 2 hours

Affected Components: París

Feb 19, 23:00:00 GMT+0
Identificado - DataPacket will be performing planned network maintenance in the Paris region during the window listed above. This maintenance involves upgrades to switch hardware and software to improve overall reliability and performance. During the maintenance window, services in the Paris region will experience a service interruption. Total expected downtime is up to 1 hour and 15 minutes, and disruptions may occur intermittently within the scheduled window. We will work to minimize impact and complete the maintenance as quickly as possible. Additional updates will be posted to this page if the schedule or impact changes..

Feb 19, 23:00:01 GMT+0
Identificado - El mantenimiento está ahora en progreso.

Feb 20, 01:00:00 GMT+0
Completado - El mantenimiento se ha completado con éxito.

Duration: 30 minutes

Affected Components: Ciudad del lago salado

Feb 3, 07:00:00 GMT+0
Identificado - **Summary:** Our upstream provider will be performing scheduled maintenance on Salt Lake City core routing infrastructure to support increased capacity and long term network reliability. **Impact:** During the maintenance window, traffic traversing the region may experience brief interruptions, packet loss, or routing reconvergence. Impact is expected to be minimal and limited to the maintenance window. **Action Required:** No customer action is required. Our network team will be actively monitoring the maintenance and will restore full service immediately upon completion..

Feb 3, 07:00:01 GMT+0
Identificado - El mantenimiento está ahora en progreso.

Feb 3, 07:30:00 GMT+0
Completado - El mantenimiento se ha completado con éxito.

Duration: 33 minutes

Affected Components: Miami

Jan 15, 19:00:00 GMT+0
Identificado - We will be onboarding Cloudflare Magic Transit for 163.227.179.0/24 in Miami at 2 PM EST today (1/15/26).

Jan 15, 19:33:18 GMT+0
Completado - Maintenance has completed successfully..

Duration: 2 hours

Affected Components: Nueva York

Jan 9, 19:30:00 GMT+0
Identificado - We will be upgrading our upstream network capacity in Ashburn. The actual impact should be around 15 minutes in the maintenance window..

Jan 9, 19:30:01 GMT+0
Identificado - El mantenimiento está ahora en progreso.

Jan 9, 21:30:00 GMT+0
Completado - El mantenimiento se ha completado con éxito.

Duration: 30 minutes

Affected Components: Nueva York

Dec 4, 04:45:00 GMT+0
Identificado - We will be performing firmware upgrades on our edge routers in Ashburn during the upcoming maintenance window. Our network is fully redundant, so no service disruption is expected. As each redundant router is rebooted, you may see a brief moment of packet loss, but traffic will continue to flow normally across alternate paths. We appreciate your understanding. If you have any questions, please contact our support team..

Dec 4, 04:45:01 GMT+0
Identificado - El mantenimiento está ahora en progreso.

Dec 4, 05:15:00 GMT+0
Completado - El mantenimiento se ha completado con éxito.

Duration: 5 minutes

Affected Components: Dallas

Sep 6, 03:00:00 GMT+0
Identificado - El mantenimiento está ahora en progreso.

Sep 6, 03:05:14 GMT+0
Completado - Maintenance has completed successfully..

Sep 6, 03:00:00 GMT+0
Identificado - **Impact**: Brief network interruption in Dallas **Maintenance Description**: We are conducting a scheduled maintenance event to test our network redundancy protocols at our Dallas facility. This test involves a controlled reboot of one of our core spine switches to validate our failover mechanisms. While our network is designed with redundancy between our spine and access switches, a brief, minor interruption may occur as traffic reroutes during the failover. We expect any impact to be minimal and short-lived. This proactive testing is essential to ensure the continued stability and resilience of our network infrastructure. Thank you for your understanding. **Technical Background**: Our network infrastructure in Dallas uses a spine-and-leaf topology, which is a highly scalable and resilient data center network architecture. This design consists of spine switches (the backbone) and leaf switches (access points for servers). To ensure high availability and prevent a single point of failure at the core of our network, we've configured our two core spine switches using Multi-Chassis Link Aggregation (MLAG). MLAG is a proprietary protocol that allows two or more switches to act as a single logical switch. It works by bundling multiple physical links from different switches into a single logical channel, providing both link and device-level redundancy. Our access switches are connected to both spine switches with redundant links. This setup allows them to continue functioning even if one of the spine switches becomes unavailable. During this maintenance window, we'll be deliberately rebooting one of the MLAG-configured spine switches to simulate a failure. This test will verify that our network traffic seamlessly fails over to the remaining spine switch without any prolonged interruption. The access switches will automatically redistribute traffic across the active links to the functioning spine switch. This is a critical step in ensuring our network can withstand unexpected failures and maintain consistent performance..

Duration: 4 hours

Affected Components: Miami

Aug 29, 15:00:00 GMT+0
Identificado - NeoProtect will be performing maintenance on Friday, August 29th, from 11:00 AM EST to 3:00 PM EST. This maintenance will add more capacity to help prevent the ongoing issues we’ve seen over the past few weeks. We don’t expect significant downtime since we have a redundant setup. However, you may notice a brief 1-minute blips as traffic falls back to other tunnels we have in place..

Aug 29, 19:00:00 GMT+0
Completado - El mantenimiento se ha completado con éxito.

Aug 29, 15:00:01 GMT+0
Identificado - El mantenimiento está ahora en progreso.

Duration: 1 hour and 6 minutes

Affected Components: Ciudad del lago salado

Aug 13, 21:45:01 GMT+0
Identificado - El mantenimiento está ahora en progreso.

Aug 13, 21:45:00 GMT+0
Identificado - Our team identified a system in one of our racks in Salt Lake City that is malfunctioning and needs to be immediately shut down to repair a part of the hardware. The outage will start in the next five minutes of you receiving this email. For customers who are on our budget, extreme, or enterprise/premium hosting plans, your ability to access your database will be impacted. For customers on bot nodes, your service will be offline during the hardware repair. This will cause an immediate outage to: \- Database nodes (db-slc) \- Bot nodes (v-slc) \- Dedicated Server management \- Webhosting (web-slc-01 and 02).

Aug 13, 22:50:57 GMT+0
Completado - Services are being started again. We appreciate your patience through this. .

Aug 13, 22:49:38 GMT+0
Identificado - This is continuing to be worked on. We don't have an ETA for restoration yet. .

Duration: 1 hour and 45 minutes

Affected Components: Ciudad del lago salado, Dedicated Server Panel, Apollo

Aug 12, 20:45:00 GMT+0
Identificado - We will be onsite starting at 2 PM MST to upgrade IPMI switches and install breakout cables for backup systems. This will not impact regular network or internet services. Any downtime will be limited to IPMI access for dedicated clients and is expected to last no longer than 1 hour and 45 minutes..

Aug 12, 20:45:01 GMT+0
Identificado - El mantenimiento está ahora en progreso.

Aug 12, 22:30:00 GMT+0
Completado - El mantenimiento se ha completado con éxito.

Duration: 7 hours and 34 minutes

Affected Components: Ciudad del lago salado

Aug 5, 07:55:04 GMT+0
Completado - All services are online, upgrades and cabling complete! Thank you all for your patience!.

Aug 4, 23:00:00 GMT+0
Identificado - We will be performing scheduled maintenance at our Salt Lake City location on **August 4th, 2025**. This maintenance will involve the installation of a new router and access switches, which will result in a **temporary, full network outage** during the work period. Additionally, **some customers may be required to power down their servers** as we proceed with the replacement of power distribution units (PDUs). A detailed maintenance window, including specific timing, will be communicated in the coming days. We appreciate your understanding and cooperation as we work to improve infrastructure reliability and performance..

Aug 5, 00:21:29 GMT+0
Identificado - Maintenance is now in progress. All customer services are now offline. .

Aug 5, 06:32:45 GMT+0
Identificado - The following services are being brought online now: * Bot Hosting (All v-slc nodes) * Web Hosting (web-slc-01 and web-slc-02) * All database servers.

Aug 5, 06:31:32 GMT+0
Identificado - Good news! We completed the cleanup of our racks and did a few upgrades. * Our team is checking all services to make sure they are back online. * Network equipment has been upgraded to 10G Switches.