New on LowEndTalk? Please Register and read our Community Rules.
All new Registrations are manually reviewed and approved, so a short delay after registration may occur before your account becomes active.
All new Registrations are manually reviewed and approved, so a short delay after registration may occur before your account becomes active.
Dartnode down
ifiwereaman
Member
in Outages
Both dartnode.com and hosts appear to be down for at least Jan 29 at 4pm EST. Anyone have any news?
Comments
Citing https://status.dartnode.com,
There is some problems on HOU-1 vps, is that ur node?
In fact, their services began to be affected from 9am on January 29th. on that time, I was unable to refresh virtual machines status on their control panel.
I had a feeling that the consequences were serious and something fatal was going to happen, so I switched to another provider (I had a backup server set up on their network for my personal services).
I can see last up time end to Jan 29 3:50 PM and 7:46 PM from my monitor server.
Thanks for the status page - the website wasn't working before to even get there, I guess my nodes must be on the cluster with the issue.
They have problems, very often
mine goes down and come back up.... not a stable provider from my experience, I wont renew my service....
@DartNode
@keoir
DartNode.com cannot be accessed.
My vps is down as well.
Good morning---greetings from New Jersey, USA.
Bad news is DartNode still down.
Ouch.
Only... If only... You have checked other threads as well.
Oh, even services are restored, but disk speed.... emmm... only 4MB/s.
I am curious about what happens.
My server has never gone down, but I think they should hire more staff because support is really slow
I wouldn't bother about downtime if no one mentioned SLA, but they do, and a whopping 100% uptime guarantee. I will ask for SLA credits even for 15 minutes because it's just ridiculous.
They took their name too seriously.
No needed, here it's automatically applied.
That's cool, so you would have unlimited funds to renew your server going forward if they keep having downtimes -- $0/yr vps
/s
Thank you for proactively crediting account with SLA credit, without needing ticket.
status page shows all systems up. but my vps is still down.
I'm in the same situation as you
Weird, mine came up right away when they fixed the issue. What does your dashboard say? Curious if you might have to start it up or reboot it from there.
My dashboard displays normally, I can still see the CPU beating, the machine cannot connect, and the network is blocked.
I also tried restarting, shutting down, turning on, etc., but they all failed.
At this rate your service with SLA credit should be free for next 2 years. Congrats.
Congrats on upcoming Credits.
Darn. I ordered a vps before seeing this thread. 6 hours and the vm provisionong is still pending and still no replies from the support. Let's hope for the best.
Howdy all. With a heavy heart and tired team, we come with some updates and a general timeline of events relating to the partial outages over the past few days.
What Happened:
As the weather has started to warm up here in Texas, we started to notice our total environment running warmer. We noticed a few small faults start to pop up, however temps were still on the higher end of acceptable/normal. We reported this to our partner datacenter and were told provisions were being made to handle the issue.
Late last week we started to encounter sync errors in our environment which caused the first SLA event when the environment stopped responding, and struggled to come back online. The control panel saw the greatest impact, and dedicated customers were not impacted by this.
On Saturday night our overnight NOC shift noticed temp alarms and a abnormally high inlet temperature on our equipment. Our overall cage environment was high and it continued to rise quickly. Our on site technician raised alarm with the rest of the team, and the datacenter staff. We took emergency measures, in tandem with our partner datacenter to cool off the equipment as rapidly as possible. We also put limits in place on the equipment during the event to try to reduce cooling load. The datacenter lowered the setpoints, and did their best to respond to the situation by addressing pinpointed inefficiencies in their setup of our environment.
The Aftermath
Most VM customers are online, however N-3 and N-5 did sustain, what currently looks like multiple drive failures. Logs show they reached temps of 149F before failure. Our switches were reporting 130F even in safe mode. Recovery operations have been running but are not looking good on Node-3. Node-5 is looking questionable but we are still working on operations. We did have a dedicated customer drive fail due to temps as well, but it appears most dedicated customers were unaffected in terms of hardware and downtime. Latency was high during the period due to high temps on the switches.
We are working with the datacenter to see what happened on their end, and are providing our data to them. We've heard a few theories ranging from human error to equipment failure, but are waiting for an official cause to address how to move forward with them.
Our Response
We take every effort to protect our environment. Unfortunately this situation has had some factors outside of our control that left us feeling a little helpless. We are investing in more sensitive temp monitoring equipment so we can verify adequate cooling prior to it evolving into another disaster event.
We are very sorry for the impact this may have caused. Anyone with dataloss on N-3 or N-5 will be getting their due date extended by 12 months, and will be restored from a backup, if available. If anyone has any questions, or wants more information as we get it going forward - please reach out via ticket or DM. We understand data loss goes way beyond a typical SLA, and we're absolutely gutted and reeling from this.
So, case closed? OK