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.
Comments
Not really sure exactly what you are asking but Tailscale has been great for me. Way easier than trying to setup wireguard vpn yourself.
BudgetKVMSGDC1-2 from GreenCloud's Flash Sale.
prem
## ## ## ## ## ## ## ## ## ## ## ## ## ## ## ## ##
Yet-Another-Bench-Script
v2025-01-01
https://github.com/masonr/yet-another-bench-script
## ## ## ## ## ## ## ## ## ## ## ## ## ## ## ## ##
Wed Jan 22 14:00:02 CET 2025
ARM compatibility is considered experimental
Basic System Information:
Uptime : 0 days, 0 hours, 36 minutes
Processor : Neoverse-N1
BIOS virt-6.2 CPU @ 2.0GHz
CPU cores : 6 @ ??? MHz
AES-NI : ✔ Enabled
VM-x/AMD-V : ❌ Disabled
RAM : 7.8 GiB
Swap : 0.0 KiB
Disk : 251.9 GiB
Distro : Debian GNU/Linux 12 (bookworm)
Kernel : 6.1.0-30-arm64
VM Type : KVM
IPv4/IPv6 : ✔ Online / ✔ Online
IPv6 Network Information:
ISP : netcup GmbH
ASN : AS197540 netcup GmbH
Host : De Netcup KVM VIE
Location : Vienna, Vienna (9)
Country : Austria
fio Disk Speed Tests (Mixed R/W 50/50) (Partition /dev/vda4):
iperf3 Network Speed Tests (IPv4):
iperf3 Network Speed Tests (IPv6):
Geekbench 6 Benchmark Test:
Test | Value
|
Single Core | 1049
Multi Core | 4787
Full Test | https://browser.geekbench.com/v6/cpu/10058564
YABS completed in 13 min 20 sec
I just give up with all the dramas made
specially with all the Powerful Ryzen sh1t$ with low performance of network.
It just made headache. while its far from the truth.
## ## ## ## ## ## ## ## ## ## ## ## ## ## ## ## ##
Yet-Another-Bench-Script
v2025-01-01
https://github.com/masonr/yet-another-bench-script
## ## ## ## ## ## ## ## ## ## ## ## ## ## ## ## ##
Wed Jan 22 14:00:02 CET 2025
ARM compatibility is considered experimental
Basic System Information:
Uptime : 0 days, 0 hours, 36 minutes
Processor : Neoverse-N1
BIOS virt-6.2 CPU @ 2.0GHz
CPU cores : 6 @ ??? MHz
AES-NI : ✔ Enabled
VM-x/AMD-V : ❌ Disabled
RAM : 7.8 GiB
Swap : 0.0 KiB
Disk : 251.9 GiB
Distro : Debian GNU/Linux 12 (bookworm)
Kernel : 6.1.0-30-arm64
VM Type : KVM
IPv4/IPv6 : ✔ Online / ✔ Online
IPv6 Network Information:
ISP : netcup GmbH
ASN : AS197540 netcup GmbH
Host : De Netcup KVM VIE
Location : Vienna, Vienna (9)
Country : Austria
fio Disk Speed Tests (Mixed R/W 50/50) (Partition /dev/vda4):
iperf3 Network Speed Tests (IPv4):
iperf3 Network Speed Tests (IPv6):
Geekbench 6 Benchmark Test:
Test | Value
|
Single Core | 1049
Multi Core | 4787
Full Test | https://browser.geekbench.com/v6/cpu/10058564
YABS completed in 13 min 20 sec
They mentioned 2.5Gbps
Tested to not just 1 region, 1 host or 1 destination, 2gbps average
I believed many users did not understand Networks in details
)
While my experience 10years++ is in network
watching those AS Numbers and BGP Filters with blurry eyes
Guess you will understand, what kind of user I am
Should I put my BERO Benchmark ini here ?
Why not?
And they seem to deliver even a bit more, for example in the YABS to Amsterdam.
I've honestly no idea what point you're trying to make, but thanks for sharing YABS. Nice to see ARM making an appearance with a decent score.
Looks like you got a nice VPS, glad your luck with Netcup seems to have improved.
GreenCloudVPS BudgetKVMSingapuraDC1-2 🇸🇬
Enzonix 6GB | NYC
How can the Geekbench 6 Multi Core Score halve in 2 weeks? xD
One would bmgwt provisioned on a practically empty node. As time goes by, more neighbors are added. Many start actually utilizing the resources... AFAIK these are shared servers, so it is bound to happen.
Keeping numbers aside for a moment, what change has this score brought to your usecase in real world? Have you checked if there is any high Steal?
If it is impacting, you probably need to start looking for dedicated resources or find a provider that will guarantee 💯 the GB score. (It's practically impossible to find one)
If you are just looking at the number and feeling something is not correct, then that needs to be changed. You need to understand that these numbers represent "at the moment" status of the server. If there are many users having something run at that very moment, it will definitely show a degraded score. But maybe in some time it would bump back.
For the most part, from what I have seen, people just freak out over the loss of the numbers without it having any tangible effect on their applications.
Good luck!
such an unbeatable deal that I missed
Thank you very much for your detailed answered! I am totally aware of the points you mentioned and my use cases are not affected by the degradation at the moment. But it would be good to know how much reserves I have for future use cases.
I just wanted to compare if other people experienced similar behaviour. And yes, also complain a bit about the situation that some provider oversell more than they maybe should, also when they say they don't.
At the end I think at this price point it's still a good result. But it is not as honest as I wish it would be.
Would love to go dedicated one day but this is coming for sure for a lot higher price (not only the hardware but also the maintenance).
Generally speaking if you reach out to the provider, they may be be able to move you on a less crowded node when you actually start to see the performance degrading.
I am not sure why you feel they are not honest? Have you seen any provider that has promised xxxx gb6 score?
I would still ask that you check cpu steal and see how the numbers look.
Thanks again and sorry, if I took the wrong words. It seems that this is business-as-usual. I always asked myself how VPS providers can make profit because according to my calculations I would make a loss if I would divide my 128 core CPU by 32 customers to offer them some 4 core VPS.
I monitored the
stoftopcommand while running GB6 and it stays at0.0.So to stay at the topic of this thread:
I also benchmarked another VPS of the same provider with same specs again:
On this server I monitored over the last 30 days this steal times:
So yeah, you are right. It depends on the neighbors. It is just a bit weird that if one of my website visitors will complain about random slow loading times, then I will have to answer: Sorry, it depends on my VPS neighbors
It is like having a 400 horse power car. You barely need it, but it is good to know that you could if you would.
It's always the neighbors fault 😅
This is really good service it seems.
RoyaleHosting
NL VPS
Insanely cheap, had to get one for myself, lol.
50 Mbit/s
😁
59 rubles/month (~ $0.59 USD) and u get 1000 Mbit/s 2GB RAM and 20 GB NVMe
Insanely cheap 2
I have this 59rub plan for a couple of weeks now, very stable. Works well with bolvan's zapret to unblock YouTube. They're affiliated in some way with HostVDS btw.
On DDoS, they null route your IP after a bit of time, but after a ticket, fix it without issues.
Unlike vdc.ru that suspended my service without refund and told me that they wouldn't want me as a customer because for 125rub/month they can't afford to have no guarantee if other attack will come or not.
The CEO is the same person and most likely support agents are shared between platforms, but that's it. They just wanted to separate their Russian assets to a Russian-based company.
skyhost.ru is also owned by the same guy.
GreenCloud Budget KVM-2 Frankfurt
GreenCloudVPS BudgetKVMJPVF-2
It feels like this one is of higher quality.
GreenCloudVPS BudgetKVMJP-2 (Softbank)
Mine is 7B12, you're 7C13. Not much diffirent i guess.
But i don't know what is the diffirence between SoftBank and Non-SoftBank one
since my vm is still in SoftBank network.
They said my vm will be move to IIJ line in Feb, I hope this mean better network
I don't know who is IIJ anyways