lol @ their cert being invalid for 4 days already.
Can't see a order button either, what do you pay for a location that exotic?
I got quoted the following (basically what I've asked) for 36$/month:
1 vCPU
1GB of RAM
20 GB of Storage
10Mbit/s port. 1TB of monthly bandwidth
1 IPv4.
Did the YABS on a trial VM, but after seeing they would charge $500/month for an extra 1TB of bandwidth, slow staff responses, "cloud vps" which they don't even allow you to install your own O.S (they reinstall manually for what it seems), I guess I'm going to skip it.
Who do GB multi core scores don't multiply wrt cores. For example, if single core score of an 8 core VPS is 1000, then why the multi core score is around 4000 most of the time, and not 8000. It's usually around single core score x around half of total cores of that plan.
I see this happening more in plans with more than 6 cores. It multiples correctly as long as it's a 2 core plan, but then the ratio starts going down from one towards half with higher core plans.
Is it just throttling by host, CPU generation/quality, or something else?
Any ideas, @Mason, @cybertech, @all?
MS said:
Who do GB multi core scores don't multiply wrt cores. For example, if single core score of an 8 core VPS is 1000, then why the multi core score is around 4000 most of the time, and not 8000. It's usually around single core score x around half of total cores of that plan.
I see this happening more in plans with more than 6 cores. It multiples correctly as long as it's a 2 core plan, but then the ratio starts going down from one towards half with higher core plans.
Is it just throttling by host, CPU generation/quality, or something else?
Any ideas, @Mason, @cybertech, @all?
I bet my ass, they are throttled or you see 6 cores but you can only use 4, so they limit you to 400%.
Lemme run another geekbench with 4.
MS said:
Who do GB multi core scores don't multiply wrt cores. For example, if single core score of an 8 core VPS is 1000, then why the multi core score is around 4000 most of the time, and not 8000. It's usually around single core score x around half of total cores of that plan.
I see this happening more in plans with more than 6 cores. It multiples correctly as long as it's a 2 core plan, but then the ratio starts going down from one towards half with higher core plans.
Is it just throttling by host, CPU generation/quality, or something else?
Any ideas, @Mason, @cybertech, @all?
I bet my ass, they are throttled or you see 6 cores but you can only use 4, so they limit you to 400%.
Lemme run another geekbench with 4.
I see this with all kinds of hosts, with their newer and not so new nodes. And, all kinds of CPUs.
A 12 core E5 v4 plan with 700 for SC and around 4400 for MC.
A 6 core Ryzen 7XXX with 1800 for SC and around 5900 for MC.
single core is always higher than all cores benched together.
also for example, if you are sharing 4 cores with one other user who is using 2 cores workload, then your single will look good while 4 obviously looks less. the more users sharing the lower it likely will be.
finally there is always the possibility provider caps the max cpu, but that would likely mean the scores are usually consistent(ly low). perfect example would be c1vhosting.
Comments
Kamatera Cloud - $4 VPS
1 CPU / 1GB
Cheeky self plug review: https://cyberhost.uk/a-proper-review-of-kamatera-cloud-4-vps/
https://cyberhost.uk
SecureHost Cloud VPS (Bahamas)
Speedypage Singapore
Speedypage Singapore @lu5ck how much $/month
Here we go with our new Sweden Location for VPS!
Alexhost, Sweden Location
lol @ their cert being invalid for 4 days already.
Can't see a order button either, what do you pay for a location that exotic?
Their price is on their site.
8GB €10/yr NVME KVM - C1V HOSTING
2 vCore CPU, 8GB DDR4 ECC RAM, 70GB SSD NVMe PCIe, 25TB @ 1Gbps monthly traffic usage, 1 IPv4 address, 1 IPv6 address
welcome to the 80.0ST club
I bench YABS 24/7/365 unless it's a leap year.
$5.5/m from Layer.ae
based on this offer? - https://lowendspirit.com/discussion/7264/layer-les-exclusive-amd-ryzen-7950x-4x-4-5ghz-4gb-ddr5-ram-50gb-nvme-10tb-10gbit - how did you double the nvme?
i asked politely, usually it just works
edit: i mean on OGF
HostCram Ryzen 9 7900 @ 5.40 GHz
HostCram LLC - Web Hosting Built For Speed, Reliability, Security & Uptime! [We operate AS39618]
Virmach @ Ashburn
I got quoted the following (basically what I've asked) for 36$/month:
Did the YABS on a trial VM, but after seeing they would charge $500/month for an extra 1TB of bandwidth, slow staff responses, "cloud vps" which they don't even allow you to install your own O.S (they reinstall manually for what it seems), I guess I'm going to skip it.
microLXC Pakistan
Free NAT KVM | Free NAT LXC
JustVM,
8,31€ (as I don't pay for the VAT) - RS 1000 G9.5 SE WD24 Vienna
https://www.netcup-sonderangebote.de/vserver/rs-1000-g9-5-se-wd24/
Mi 31. Jan 16:49:26 CET 2024 Basic System Information: --------------------------------- Uptime : 0 days, 2 hours, 16 minutes Processor : AMD EPYC 7702P 64-Core Processor CPU cores : 4 @ 1996.249 MHz AES-NI : ✔ Enabled VM-x/AMD-V : ❌ Disabled RAM : 7.8 GiB Swap : 0.0 KiB Disk : 314.8 GiB Distro : Debian GNU/Linux 12 (bookworm) Kernel : 6.1.0-17-amd64 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/vda3): --------------------------------- Block Size | 4k (IOPS) | 64k (IOPS) ------ | --- ---- | ---- ---- Read | 114.27 MB/s (28.5k) | 640.43 MB/s (10.0k) Write | 114.57 MB/s (28.6k) | 643.80 MB/s (10.0k) Total | 228.84 MB/s (57.2k) | 1.28 GB/s (20.0k) | | Block Size | 512k (IOPS) | 1m (IOPS) ------ | --- ---- | ---- ---- Read | 2.56 GB/s (5.0k) | 2.92 GB/s (2.8k) Write | 2.70 GB/s (5.2k) | 3.11 GB/s (3.0k) Total | 5.27 GB/s (10.3k) | 6.04 GB/s (5.9k) iperf3 Network Speed Tests (IPv4): --------------------------------- Provider | Location (Link) | Send Speed | Recv Speed | Ping ----- | ----- | ---- | ---- | ---- Clouvider | London, UK (10G) | 2.68 Gbits/sec | 2.22 Gbits/sec | 26.8 ms Scaleway | Paris, FR (10G) | 2.63 Gbits/sec | 1.80 Gbits/sec | 27.7 ms NovoServe | North Holland, NL (40G) | 2.71 Gbits/sec | 2.23 Gbits/sec | 18.0 ms Uztelecom | Tashkent, UZ (10G) | 341 Mbits/sec | 1.77 Gbits/sec | 106 ms Clouvider | NYC, NY, US (10G) | 1.67 Gbits/sec | 1.18 Gbits/sec | 99.2 ms Clouvider | Dallas, TX, US (10G) | 952 Mbits/sec | 264 Mbits/sec | 132 ms Clouvider | Los Angeles, CA, US (10G) | 932 Mbits/sec | 667 Mbits/sec | 159 ms iperf3 Network Speed Tests (IPv6): --------------------------------- Provider | Location (Link) | Send Speed | Recv Speed | Ping ----- | ----- | ---- | ---- | ---- Clouvider | London, UK (10G) | 2.60 Gbits/sec | 2.17 Gbits/sec | 26.8 ms Scaleway | Paris, FR (10G) | 2.53 Gbits/sec | 2.19 Gbits/sec | 40.5 ms NovoServe | North Holland, NL (40G) | 2.68 Gbits/sec | 2.21 Gbits/sec | 18.0 ms Uztelecom | Tashkent, UZ (10G) | 258 Mbits/sec | 1.17 Gbits/sec | 102 ms Clouvider | NYC, NY, US (10G) | 1.46 Gbits/sec | 1.25 Gbits/sec | 99.1 ms Clouvider | Dallas, TX, US (10G) | 935 Mbits/sec | 354 Mbits/sec | 131 ms Clouvider | Los Angeles, CA, US (10G) | 764 Mbits/sec | 824 Mbits/sec | 159 ms Geekbench 6 Benchmark Test: --------------------------------- Test | Value | Single Core | 996 Multi Core | 3138 Full Test | https://browser.geekbench.com/v6/cpu/4687203Amadex • Hosting Forums • Webshop • Virtmach • Wie ist meine IP-Adresse?
Aeza - Sweden - €1.09/month.
https://browser.geekbench.com/v6/cpu/4796376
Got for a pretty good price.
PrepaidHost after they upgraded the CEPH cluuster
Free NAT KVM | Free NAT LXC
Who do GB multi core scores don't multiply wrt cores. For example, if single core score of an 8 core VPS is 1000, then why the multi core score is around 4000 most of the time, and not 8000. It's usually around single core score x around half of total cores of that plan.
I see this happening more in plans with more than 6 cores. It multiples correctly as long as it's a 2 core plan, but then the ratio starts going down from one towards half with higher core plans.
Is it just throttling by host, CPU generation/quality, or something else?
Any ideas, @Mason, @cybertech, @all?
I bet my ass, they are throttled or you see 6 cores but you can only use 4, so they limit you to 400%.
Lemme run another geekbench with 4.
Free NAT KVM | Free NAT LXC
I see this with all kinds of hosts, with their newer and not so new nodes. And, all kinds of CPUs.
A 12 core E5 v4 plan with 700 for SC and around 4400 for MC.
A 6 core Ryzen 7XXX with 1800 for SC and around 5900 for MC.
its the CPU itself.
single core is always higher than all cores benched together.
also for example, if you are sharing 4 cores with one other user who is using 2 cores workload, then your single will look good while 4 obviously looks less. the more users sharing the lower it likely will be.
finally there is always the possibility provider caps the max cpu, but that would likely mean the scores are usually consistent(ly low). perfect example would be c1vhosting.
I bench YABS 24/7/365 unless it's a leap year.
Looks like a fixed cap.
Free NAT KVM | Free NAT LXC
looks to me CPU design with neighbors.
I bench YABS 24/7/365 unless it's a leap year.
I/O does fluctuate quite a bit, because its under load.
I barely see any CPU steal plus the cpu benchmarks are too consistent.
Its always 4x and a bit, never 5x or 6x.
Free NAT KVM | Free NAT LXC