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
Unfortunately the Biznet location was the only public iperf3 server in that region. Couldn't find a single other one throughout all of APAC. If you find another location out that way or a provider willing to sponsor one, please let me know!
Quite the beefy machine you've got there, @eKo!
@eKo trying to show off :-) er... inspire others to aim big
Hi, thats a Hetzner EX62-NVMe
Quite Impressed by It, but I would prefer to switch to Ryzen. (soon a benchmark of it).
Which Ryzen? 3950X?
Selectel's CL05. Surprisingly, the actual CPU is i5 4670 instead of the listed i5 3550. I didn't like the disks but it's alright for its price
Thanks for the wonderful script!
> gazmull said: Disk Speed Tests:
Write | 31.60 MB/s | 34.90 MB/s | 37.60 MB/s | 34.70 MB/s
Read | 7.72 MB/s | 8.41 MB/s | 11.48 MB/s | 9.20 MB/s
The disk seems slow?
Thank you so much ❤️
Network speed test for east coast, us?
Velocity Online, Tallahassee, FL, US (1G). 8th under IPv4.
Thanks.
Thats a RAID-0 NMVe setup, Centos 7.
Enjoy. Im staying with the EX62 (also raid-0 NMVe). Cheers.
Indeed but that was on RAID-1. Tested it right now without RAID-1:
Just pushed an update to the repo - https://github.com/masonr/yet-another-bench-script.
Notable changes:
Here's the updated sample output:
Please continue to let me know if you have any issues or suggestions for YABS!
Why read is slow than write?
will the script also work on android smartphone?
dd sequence on php-friends vps does not work:
(how can i put the resualty in a yellow box?)
## ## ## ## ## ## ## ## ## ## ## ## ## ## ## ## ##
Yet-Another-Bench-Script
v2020-01-08
https://github.com/masonr/yet-another-bench-script
## ## ## ## ## ## ## ## ## ## ## ## ## ## ## ## ##
Fr 10. Jan 00:00:00 CET 2020
Basic System Information:
Processor : Intel(R) Xeon(R) CPU E5-2630 v4 @ 2.20GHz
CPU cores : 2 @ 2199.998 MHz
AES-NI : ✔ Enabled
VM-x/AMD-V : ✔ Enabled
RAM : 5,8G
Swap :
Disk : 64G
dd Sequential Disk Speed Tests:
Write | | | | 0,00 MB/s
Read | | | | 0,00 MB/s
iperf3 Network Speed Tests (IPv4):
Provider | Location (Link) | Send Speed | Recv Speed
| | |
Bouygues Telecom | Paris, FR (10G) | 932 Mbits/sec | 878 Mbits/sec
Online.net | Paris, FR (10G) | 507 Mbits/sec | 876 Mbits/sec
Severius | The Netherlands (10G) | 530 Mbits/sec | 482 Mbits/sec
Worldstream | The Netherlands (10G) | 520 Mbits/sec | 837 Mbits/sec
wilhelm.tel | Hamburg, DE (10G) | 930 Mbits/sec | 863 Mbits/sec
Biznet | Bogor, Indonesia (1G) | 438 Mbits/sec | 254 Mbits/sec
Hostkey | Moscow, RU (1G) | 688 Mbits/sec | 826 Mbits/sec
Vultr | Piscataway, NJ, US (1G) | 564 Mbits/sec | 773 Mbits/sec
Velocity Online | Tallahassee, FL, US (10G) | 468 Mbits/sec | 567 Mbits/sec
Airstream Communications | Eau Claire, WI, US (10G) | 521 Mbits/sec | 569 Mbits/sec
Hurricane Electric | Fremont, CA, US (10G) | 421 Mbits/sec | 393 Mbits/sec
iperf3 Network Speed Tests (IPv6):
Provider | Location (Link) | Send Speed | Recv Speed
| | |
Bouygues Telecom | Paris, FR (10G) | 532 Mbits/sec | 808 Mbits/sec
Online.net | Paris, FR (10G) | 759 Mbits/sec | 788 Mbits/sec
Severius | The Netherlands (10G) | 733 Mbits/sec | 692 Mbits/sec
Worldstream | The Netherlands (10G) | 524 Mbits/sec | 868 Mbits/sec
wilhelm.tel | Hamburg, DE (10G) | 600 Mbits/sec | 861 Mbits/sec
Vultr | Piscataway, NJ, US (1G) | 580 Mbits/sec | 781 Mbits/sec
Airstream Communications | Eau Claire, WI, US (10G) | 534 Mbits/sec | 433 Mbits/sec
Hurricane Electric | Fremont, CA, US (10G) | 339 Mbits/sec | 384 Mbits/sec
Geekbench 4 Benchmark Test:
Test | Value
|
Single Core | 2731
Multi Core | 4750
Full Test | https://
v2019-10-08
Not sure, I'll look into it and see if there's anything to fix.
Probably not would be my guess.
What's the output of
dd --version
?To put stuff in the yellow box put the text inside of
<pre>
...</pre>
tags.Looks normal. Let's take this to PM to debug further.
I have the same problem as hyperblast.
Yeah, we've narrowed down the issue. It seems to be the locale that's throwing it off. I'll have to do some further testing and edit the script to handle differ locales.
Many updates have been pushed to the repo, including replacing dd sequential speed tests with fio, making the script both IPv6-only and 32-bit compatible, and other updates to make it able to handle error cases and bad results.
Please let me know if you run into any errors with the script! Here's what the current' output looks like:
@MasonR
800MHz CPU? That sounds fishy. Not from the script, but your provider. Overheating, maybe?
speed step... it's been idle before grepping that info and running the bench, simple as that. the geekbench obivously speaks another language ;-)
other than that @MasonR you could think of heating up the cpu a bit before reading the cpuinfo LOL
PS: thanks a ton for maintaining, improving and releasing it.
PPS: and on another note, I really like the geekbench4 numbers, because I am used to it and can compare them at the first glance. however long term you probably should switch to gb5 rather sooner than later.
maybe while doing this it could be interesting to create a yabs account with geekbench and have the script claim all benchmarks and maybe even interactively ask the people running the bench for some data about the provider. could eventually build some proper library with that ;-)
Hetzner Cloud with the updated YABS.
Amazing script. However, it doesn't work that well on my server.
I'm running Ubuntu 18.04.4 LTS x86_64 in a KVM.
ExtraVM Dallas, Debian 10
Could you explain what diff block sizes represent in real world?