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.
cociu - hostsolutions.ro - NETSILVANIA | Move your services!
This discussion has been closed.
Comments
By the way, do we know this for sure?
Before his Message my heart ran on Raid0, just as a single device. xD
Was it too much though to just add a single sentence such as "we're facing an issue with one of our storage arrays and we're trying to resolve the issue as soon as we can" without keeping your customers waiting for a week?
Mhnn... Not very satisfying. What about the bankruptcy? I'm not returning, too much hassle, rather stay at new host (though more expensive).
Of course its a joke.. Nobody would be that stupid to ran RAID0 with such amount of drives.. Right?
@cociu wish you all the best! Take the day off regarding and try getting rid of that depression
I always learn new vocabulary when Cociu posts something. Not bad, I guess
I wasn't sure whether I had missed something and that everyone else knew for sure that he ran RAID 0!
It's the past tense of involucrate, which means "a collection or rosette of bracts subtending a flower cluster, umbel, or the like".
So I guess it was some kind of attack by the flower kingdom. They're probably mad that so many of their kind have been victims of Marius' perfume empire.
When using a RAID0 now all data would be lost.
I dont think all the 400 drives are in the same machine.
Poor @cociu , it's really not an opportune time to need to acquire disks at normal prices
True, and @cociu says that they were able to recover around 50 disks so far ... so I guess that we can conclude that he doesn't use RAID 0 after all ...
3 of 3 VM are gone for me. So I've exhausted all my misfortune for 2021, yet, I guess!?
I don't really care for any data loss on those machines. - Good luck in getting everything up and running again!
Powered by only a dual e5-2450L, no wonder why VM is slow.
Not sure from that if the expectation is to recover customer data from the old array(s).
I'm sure many like me only use their instance as a 'long stop' backup or transit area, and would be more than happy to forego their old data if that helps the recovery plan. Just a suggestion...
@cociu
Thanks for personally updating everyone on the current situation.
That's good to know and I'm sure lots of people here wants you to be around providing services to them. There's always room for improvements.
Take it step by step and don't rush into things.
If you need any sort of advice, don't hesitate or feel ashamed to reach out to other providers, or even community members. Listen to everyone and learn from everyone. Nobody knows everything but everyone knows something.
One thing's for sure, you definitely need to appoint a rep in places you advertise and sell your products and services.
Imagine what slack all the higher end providers would get for an answer like that.
Just cause you're paying less shouldn't mean you can be treated like shit but oh well. Each to their own.
involucrated !
But since he is back, I will buy his new offers..
Just wondering how one can get 400 drives corrupted at same time ..
Loose power.
As per the update only storage VPS were affected but few people had posted about SSD and NVMe nodes also being offline
Was that just for more drama or actually were offline ?
Asking as mine NVMe wasnt offline during this outage
A whole rack I suppose, not just a node.
😂
zxhost anyone?
I'll probably never understand why some providers act like this. why would a provider in that situation not reach out to the affected clients first , tell that shit hit the fan and a lot is broken.
be upfront, declare how highly (un)likely it is to recover the data and ask if people rather want to have their service redeployed empty elsewhere or if they want to wait for recovery attempts which may take xy days or weeks or if they want a refund.
that way you can split the tasks and handle easy cases first, esp. redeploying (assuming you have some room spare for that) and also eventually need less temp space for recovery and all that. essentially you want to get rid of as many customers breathing down your neck as possible - especially for those low priced stuff.
most likely even cheaper to lose half of them instead of trying to get your hands on new disks right now...
it's good to recover/move out the data instead of having the raid rebuild, though. raid50/60 with these large disks are prone to fail because of UREs, this has been discussed quite some times before.
best of luck!
Totally this^^! While I suspect that @cociu will miss it. - And yes, Ashley!
So...
Was it a UPS issue, or not?
Edit:
Or is it an Oops! issue ?
You will never know the truth. It is very unlikely that multiple servers malfunction from standard power outage, even if there multiple shortages. PSU of modern server has fail safe. Massive, multi server damage may happen from flooding, fire or fuck*n emp.
The UPS may have been interrupted.
Just wipe the drives and start over. I doubt anyone here would mind, drive prices being what they are because of china miners etc
A UPS failure can cause data corruption sure, but how would that even destroy the drives?
Like one power outage and half the drives are gone?
That is some grade A bs.