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
KS-2 16TB
VULTR Dallas, The Lone Star State
Texas
## ## ## ## ## ## ## ## ## ## ## ## ## ## ## ## ##
Yet-Another-Bench-Script
v2024-06-09
https://github.com/masonr/yet-another-bench-script
## ## ## ## ## ## ## ## ## ## ## ## ## ## ## ## ##
Mon Nov 11 08:46:04 PM UTC 2024
Basic System Information:
Uptime : 0 days, 0 hours, 34 minutes
Processor : AMD EPYC 9654 96-Core Processor
CPU cores : 2 @ 2399.998 MHz
AES-NI : ✔ Enabled
VM-x/AMD-V : ✔ Enabled
RAM : 3.8 GiB
Swap : 0.0 KiB
Disk : 58.0 GiB
Distro : Ubuntu 24.10
Kernel : 6.11.0-9-generic
VM Type : KVM
IPv4/IPv6 : ✔ Online / ✔ Online
IPv6 Network Information:
ISP : Advin Services LLC
ASN : AS206216 Advin Services LLC
Host : Advin Services LLC
Location : Wilmington, Delaware (DE)
Country : United States
fio Disk Speed Tests (Mixed R/W 50/50) (Partition /dev/sda2):
iperf3 Network Speed Tests (IPv4):
iperf3 Network Speed Tests (IPv6):
Geekbench 6 Benchmark Test:
Test | Value
|
Single Core | 1829
Multi Core | 3257
Full Test | https://browser.geekbench.com/v6/cpu/8785657
@labze HostBrr
Mon Nov 11 09:50:20 PM CET 2024 Basic System Information: --------------------------------- Uptime : 0 days, 0 hours, 16 minutes Processor : AMD EPYC 9534 64-Core Processor CPU cores : 1 @ 2446.326 MHz AES-NI : ✔ Enabled VM-x/AMD-V : ✔ Enabled RAM : 924.2 MiB Swap : 924.0 MiB Disk : 14.9 GiB Distro : Debian GNU/Linux 12 (bookworm) Kernel : 6.1.0-9-amd64 VM Type : KVM IPv4/IPv6 : ❌ Offline / ✔ Online IPv6 Network Information: --------------------------------- ISP : dataforest GmbH ASN : AS58212 dataforest GmbH Location : Frankfurt am Main, Hesse (HE) Country : Germany fio Disk Speed Tests (Mixed R/W 50/50) (Partition /dev/vda3): --------------------------------- Block Size | 4k (IOPS) | 64k (IOPS) ------ | --- ---- | ---- ---- Read | 175.99 MB/s (43.9k) | 1.02 GB/s (15.9k) Write | 176.46 MB/s (44.1k) | 1.02 GB/s (16.0k) Total | 352.46 MB/s (88.1k) | 2.05 GB/s (32.0k) | | Block Size | 512k (IOPS) | 1m (IOPS) ------ | --- ---- | ---- ---- Read | 674.21 MB/s (1.3k) | 2.20 GB/s (2.1k) Write | 710.04 MB/s (1.3k) | 2.35 GB/s (2.2k) Total | 1.38 GB/s (2.7k) | 4.55 GB/s (4.4k) iperf3 Network Speed Tests (IPv6): --------------------------------- Provider | Location (Link) | Send Speed | Recv Speed | Ping ----- | ----- | ---- | ---- | ---- Clouvider | London, UK (10G) | 6.79 Gbits/sec | 6.07 Gbits/sec | 14.6 ms Eranium | Amsterdam, NL (100G) | 6.42 Gbits/sec | 6.49 Gbits/sec | 10.8 ms Uztelecom | Tashkent, UZ (10G) | 1.53 Gbits/sec | 1.61 Gbits/sec | 97.2 ms Leaseweb | Singapore, SG (10G) | 903 Mbits/sec | 1.15 Gbits/sec | -- Clouvider | Los Angeles, CA, US (10G) | 1.19 Gbits/sec | 1.19 Gbits/sec | 147 ms Leaseweb | NYC, NY, US (10G) | 1.94 Gbits/sec | 1.39 Gbits/sec | 83.5 ms Edgoo | Sao Paulo, BR (1G) | 771 Mbits/sec | 907 Mbits/sec | 191 ms Geekbench 6 Benchmark Test: --------------------------------- Test | Value | Single Core | 1163 Multi Core | 738 Full Test | https://browser.geekbench.com/v6/cpu/8785787 YABS completed in 18 min 32 secThis is DigitalOcean "Regular" droplet (i.e. not Premium Intel or Premium AMD) in the SFO3 availability zone.
The fio results are truly impressive. Network is okay. I did not include Geekbench 6 because it would take so long to complete. Here is a Geekbench 5 result from the same machine: https://browser.geekbench.com/v5/cpu/23043676 -- 517 SC, 1359 MC -- a true bottleneck compared with other parts of the system.
1 day 38 hours 0 min uptime
For 1 gb VPS, the multi core GB6 score is not accurate due to low memory and swap space. In any case, for 1 vCore. VPS the multi-core score would be same as single core
Both are not accurate, single core GB6 also does not fit into 1GB.
Should be 1 day 0 hours 38 min
I should open a pull request on this for yabs.sh...
From @lakira GB6
1 vCore AMD EPYC 9534 / 1GB
2 vCore AMD EPYC 9534 / 10GB
The Single Core GB6 score is in the same range for 1GB and 10GB VPS
Jeruk VPS aka @orangevps
Picking a losing fight again eh? "Same score" again eh?
Thanks for correcting me. Learning is always a two way street.
It seems that GB6 needs 4GB memory for efficiently running. So basically any test done in under 4GB VPS may not accurately reflect the benchmark scores.
Depends on number of cores, for 1 core 2GB ram should be fine.
Is that ChatGPT
@dev_vps
Sigh, one would assume person with "dev" in nickname understands 'AI' is just a statistical model that actually just 'tells' one what they want to hear based on their request:
And in reality there's this.
So far, it's one way.
Thanks for correcting me. again. I have no shame in admitting my mistakes.
I was about to post the same link, as I realized 4GB is minimum for MacOS and Windows OS, but not for Linux based OS
web link -- https://www.geekbench.com/download/
Well, hopefully it will change sooner than expected.
Thanks, again.
PS - I will never tag you in my post .
@Chunkserve
4 vCore E5-2690v4 / 8 GB / 90 GB SSD
Custom Plan
price? orderlink?
It's from their birdthday deal, it's over. 15.6eur/mo.
Now they have about the same one with more ram and storage for ±20eur
@hyperblast
My vps plan with BeroHost
https://lowendtalk.com/discussion/comment/4031997/#Comment_4031997
This one is also one of the current berohost offers
@hostdare $9.10/Year Custom LET 11.11 Deal
More berohost
FameSystems
GB6 performance profile over the last month:
Quite a drop since the sale, but slowly improving since start of Nov, which aligns with provider's promise to get rid of some miners. Overall performance i'd say is mid for 12 cores but adequate for 9754 vps, uptime is 100%, cpu steal is 0% and provider is very friendly overall.
+1 for @FameSystems
I have a custom vps plan
one can always wonder if it is free or paid .... I won't tell you
Nice graph @egoror!
And thanks for YABS of that specific configuration, which can now be compared to also FameSystems 12-core EPYC VPS, but older generation. The results are unbelievably close, which supports my recent theory that EPYC Genoa/Bergamo when loaded is usually not all that better than say lightly loaded Milan. Something like that... I mean as soon as CPU gets hot, the performance drop is even more visible on the newer generations, because apparently they boost higher when unloaded. I'll try to prove this theory once I have a bit of free time (read: after BF).
Hope you’re as excited as we are! Black Friday is just around the corner, and here at FameSystems, we’re in full prep mode – building, tweaking, and fine-tuning to bring you the best deals!
Stay tuned.
https://techreviewteam.com/hardware/does-cpu-temperature-affect-performance-fact-checked/