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.
Can we update the Rules to require minimum Geekbench scores to sell it as VPS
Otherwise just sell it as door stopper or so.
77 Geekbench is the worst I have ever seen so far.
# ## ## ## ## ## ## ## ## ## ## ## ## ## ## ## ## ## #
# Yet-Another-Bench-Script #
# v2024-01-01 #
# https://github.com/masonr/yet-another-bench-script #
# ## ## ## ## ## ## ## ## ## ## ## ## ## ## ## ## ## #
Wed Feb 21 09:36:33 PM MSK 2024
Basic System Information:
---------------------------------
Uptime : 0 days, 0 hours, 37 minutes
Processor : Intel(R) Xeon(R) CPU E5-2697 v4 @ 2.30GHz
CPU cores : 1 @ 2299.998 MHz
AES-NI : ✔ Enabled
VM-x/AMD-V : ✔ Enabled
RAM : 457.5 MiB
Swap : 1024.0 MiB
Disk : 5.8 GiB
Distro : Debian GNU/Linux 12 (bookworm)
Kernel : 6.1.0-18-amd64
VM Type : KVM
IPv4/IPv6 : ✔ Online / ✔ Online
IPv4 Network Information:
---------------------------------
ISP : BFB ONE FZ-LLC
ASN : AS59878 BFB ONE FZ-LLC
Host : BFB ONE FZ-LLC
Location : Dubai, Dubai (DU)
Country : United Arab Emirates
fio Disk Speed Tests (Mixed R/W 50/50) (Partition /dev/vda1):
---------------------------------
Block Size | 4k (IOPS) | 64k (IOPS)
------ | --- ---- | ---- ----
Read | 8.50 MB/s (2.1k) | 9.79 MB/s (153)
Write | 8.54 MB/s (2.1k) | 10.26 MB/s (160)
Total | 17.04 MB/s (4.2k) | 20.06 MB/s (313)
| |
Block Size | 512k (IOPS) | 1m (IOPS)
------ | --- ---- | ---- ----
Read | 9.23 MB/s (18) | 9.08 MB/s (8)
Write | 10.21 MB/s (19) | 10.23 MB/s (9)
Total | 19.44 MB/s (37) | 19.32 MB/s (17)
iperf3 Network Speed Tests (IPv4):
---------------------------------
Provider | Location (Link) | Send Speed | Recv Speed | Ping
----- | ----- | ---- | ---- | ----
Clouvider | London, UK (10G) | 10.4 Mbits/sec | 7.17 Mbits/sec | 114 ms
Scaleway | Paris, FR (10G) | busy | 9.75 Mbits/sec | 128 ms
NovoServe | North Holland, NL (40G) | 10.9 Mbits/sec | 9.65 Mbits/sec | 117 ms
Uztelecom | Tashkent, UZ (10G) | 10.7 Mbits/sec | 6.64 Mbits/sec | 215 ms
Clouvider | NYC, NY, US (10G) | 10.5 Mbits/sec | 7.66 Mbits/sec | 192 ms
Clouvider | Dallas, TX, US (10G) | 10.4 Mbits/sec | 7.68 Mbits/sec | 217 ms
Clouvider | Los Angeles, CA, US (10G) | 10.3 Mbits/sec | 7.79 Mbits/sec | 246 ms
iperf3 Network Speed Tests (IPv6):
---------------------------------
Provider | Location (Link) | Send Speed | Recv Speed | Ping
----- | ----- | ---- | ---- | ----
Clouvider | London, UK (10G) | 10.7 Mbits/sec | 7.01 Mbits/sec | 114 ms
Scaleway | Paris, FR (10G) | busy | 9.65 Mbits/sec | 119 ms
NovoServe | North Holland, NL (40G) | 10.1 Mbits/sec | 9.54 Mbits/sec | 117 ms
Uztelecom | Tashkent, UZ (10G) | 10.7 Mbits/sec | 7.29 Mbits/sec | 215 ms
Clouvider | NYC, NY, US (10G) | 10.5 Mbits/sec | 7.54 Mbits/sec | 192 ms
Clouvider | Dallas, TX, US (10G) | 8.51 Mbits/sec | 7.57 Mbits/sec | 217 ms
Clouvider | Los Angeles, CA, US (10G) | 8.23 Mbits/sec | busy | 250 ms
Geekbench 5 Benchmark Test:
---------------------------------
Test | Value
|
Single Core | 77
Multi Core | 74
Full Test | https://browser.geekbench.com/v5/cpu/22244876
YABS completed in 36 min 18 sec
Comments
Scummy providers will just fake it, or use the one saved from first run on an empty node.
Users report the Provider, if said Provider has x reports, he can't sell anymore on LET.
My lord. I don't know what is worse, if they are throttling so bad or if the systems are being abused so bad?
Both its capped and Oversold.
only problem I see with this is when they first do an offer CPU usage is likely to hit max since everyone installing/benchmarking their new VPS causing artificially low scores for the first little bit.
Which provider is this? Layer?
We need a place here on LET where we can upload all our yabs results. Everyone can then check yabs results from each provider, for each package, if they oversell or limit cpu usage hard.
With diagrams and statistics where we can see max/average/min performance of each offered VPS.
I believe many of us run „quite a few“ yabs runs on our VPS hehe
Premium JustHost
https://yabsdb.com/
If you searched a but you would have discovered this gem....
You mean like yabsdb?
It's called LET YABS Thread, started by @Astro , member of Team push-ups.
https://lowendtalk.com/discussion/176305/let-yabs-thread
GB6 is still running.... holy fucking shit
Requiring a minimum GB score sounds ridiculous to me. I've been personally using just.hosting with their PROMO plan and true, it's slow and whatever, but it serves my purpose, and works just fine for me. It's also the most reliable from all my providers, so why I voted them as most reliable.
Most importantly, it costs 70RUB (or $1.16 USD/month) for highly premium locations (UAE, Latvia, HK, Singapore, ...)
Considering I even reinstalled it, almost 11 months of uptime seems amazing to me.
Forgot about this thread. My bad. But with diagrams you we could check deviations and fluctuations of all the VPS being offered here
I knew about this site and the vpsbenchmarks site. However one does not list the provider (only raw stats), the other only has data of old, out of date VPS…
Forced me to buy VPS from multiple vendors so I could „yabs“ them all to make my own chart for comparison haha.
Are they hosting on a calculator or something? That score is horrible.
It is not an excuse but based on the location, what network speeds were you promised?
Can we also add voting system? If X LET users doesn't like a given host then host will be banned?
Back to '90
no
Its 10Mbit, the Network speed is fine.
Yes, its a unique offer true however the usability is questionable.
I even tried to run a wireguard tunnel, It had easily 40-80ms jitter due to the bad cpu performance.
mtr didn't show any jitter, so at least the network seems to be better.
Perhaps not mandating a minimum benchmark result, but rather requiring sellers to disclose the benchmark results of their products at the point of sale.
Insane speeds tho
I thought LET was about the race to the bottom?
What's up wi' dat?
Honestly, while this would cut drama (bad), I wonder why it isn't the case already. Seriously, not having 200$ and not having to tell they are "finalizing the rule" seems like better for the whole let community. But well.
mzungu my beloved
I'm using it as my proxy and works just fine, although it barely relies on CPU, such as how a VPN would do.
I use it for streaming purposes, so network seems fine, but most likely if you stress that poor CPU it will become an issue.
Can you check your CPU values on Proxmox? I think it was limited to 30% (cpulimit=0.3) or something like that.
Some YABS scores have providers on them - Linode, RamNode, OVH, Hetzner - but they seem to be the minority.
Guys come on. It's a buyers choice to buy or not. Imposing such limits doesn't make sense. There are many small, tiny but decent providers offering VPS that aren't exactly high-end but one must to start someone. Not everyone has access to a credit line. Let's be reasonable.
bad idea, it'll reduce the amount of lowend drama