@Not_Oles said: That's a 17% difference in favor of LXC over bare metal on this test!
Please correct me if I'm wrong, but doesn't the above indicate that the 17% CPU utilization difference is in favor of bare metal over LXC (the lower the CPU utilization, the better)? Basically the task uses 71.77% of the CPU on bare metal, but the same task uses 88.93% of the CPU when run in a container -- meaning the 17% difference is the CPU working harder (and having more overhead) within the container. At least that's how I'm interpreting the results.
@Not_Oles said: That's a 17% difference in favor of LXC over bare metal on this test!
Please correct me if I'm wrong, but doesn't the above indicate that the 17% CPU utilization difference is in favor of bare metal over LXC (the lower the CPU utilization, the better)? Basically the task uses 71.77% of the CPU on bare metal, but the same task uses 88.93% of the CPU when run in a container -- meaning the 17% difference is the CPU working harder (and having more overhead) within the container. At least that's how I'm interpreting the results.
Thank you! I was imagining it meant that LXC got more work done because it utilized the CPU for a longer time, i.e., higher CPU utilization and lower the idle time, the better.
@Abdullah said: @Not_Oles looks excellent already! can try set disk cache to writeback too.
Bad idea, unless your cache device is redundant and hopefully backed by some kind of battery sir.
yes...so do we should set it to writethrough ?
In proxmox, there is a 'writeback' & a 'writeback (unsafe)' option. I wonder if they are different, you have any idea @Not_Oles ?
I also read at another place virtualizor uses writeback in default cache option, with some 'optimizations'...not sure if they have a way to safely use writeback.
@Abdullah said: @Not_Oles looks excellent already! can try set disk cache to writeback too.
Bad idea, unless your cache device is redundant and hopefully backed by some kind of battery sir.
yes...so do we should set it to writethrough ?
In proxmox, there is a 'writeback' & a 'writeback (unsafe)' option. I wonder if they are different, you have any idea @Not_Oles ?
I also read at another place virtualizor uses writeback in default cache option, with some 'optimizations'...not sure if they have a way to safely use writeback.
sorry to OP for being offtopic here, do you use virtualizor? can it work with kernel 5.11 in production?
@Abdullah said: @Not_Oles looks excellent already! can try set disk cache to writeback too.
Bad idea, unless your cache device is redundant and hopefully backed by some kind of battery sir.
yes...so do we should set it to writethrough ?
In proxmox, there is a 'writeback' & a 'writeback (unsafe)' option. I wonder if they are different, you have any idea @Not_Oles ?
I also read at another place virtualizor uses writeback in default cache option, with some 'optimizations'...not sure if they have a way to safely use writeback.
sorry to OP for being offtopic here, do you use virtualizor? can it work with kernel 5.11 in production?
hostvds
$1.59 per mth
don't be fooled by "data centers", only Russia available
performance wise, really crap bad throttled CPU (imagine virmach being virmached)
the score is GB4 not GB5!!!!!!
take hours to install simple webserver panel complete
Yabs inside a Proxmox KVM. Bare metal is running 5.4.98-1-pve. The kernel in the KVM was updated to the latest Proxmox-edge-kernel, 5.11.2-1-pve.
With 5.11.2-1-pve the KVM single core GB score was 1736.
Previously, on the bare metal, the GB single core score was 1719. That 1719 was with whatever kernel preceded the current stable Proxmox kernel, 5.4.98-1-pve.
It seems that the performance of the 5.11 kernel might be improved compared to 5.4. Unless I'm confused, which happens often. Luckily I have you guys to catch my mistakes!
Rerunning yabs. Same setup as above, kernel 5.11.2 from fabianishere running on Hetzner AX101 bare metal. GB5 single core slightly up: 1673, 1719, now 1725.
Nope, the same Samsung SAS SSDs in RAID 10 as with the other nodes. But, given the low density of these new nodes, more I/O throughput will be left per VM.
Alwyzon - Virtual Servers in Austria starting at 4,49 €/month (excl. VAT)
Nope, the same Samsung SAS SSDs in RAID 10 as with the other nodes. But, given the low density of these new nodes, more I/O throughput will be left per VM.
Wiredblade
$5/mth with 50% discount (UP $10)
2 X vCPU
4GB Ram
40GB NVMe
2TB transfer
10gbps
Phoenix AZ
ISPmanager control panel
their 10gbps connection looks pretty nice. see bonus bench.sh. Let me know what else you wanna test on network.
ISPmanager is lovely. all IP and VNC info is shown clearly, custom ISO mount is supported and easy to use. prefer this over virtualizor, and maybe solusvm.
support is helpful to enable CPU passthrough. timely even on weekend.
Comments
Please correct me if I'm wrong, but doesn't the above indicate that the 17% CPU utilization difference is in favor of bare metal over LXC (the lower the CPU utilization, the better)? Basically the task uses 71.77% of the CPU on bare metal, but the same task uses 88.93% of the CPU when run in a container -- meaning the 17% difference is the CPU working harder (and having more overhead) within the container. At least that's how I'm interpreting the results.
yabs daddy
Thank you! I was imagining it meant that LXC got more work done because it utilized the CPU for a longer time, i.e., higher CPU utilization and lower the idle time, the better.
@Not_Oles looks excellent already! can try set disk cache to writeback too.
https://webhorizon.net
Bad idea, unless your cache device is redundant and hopefully backed by some kind of battery sir.
Nexus Bytes Ryzen Powered NVMe VPS | NYC|Miami|LA|London|Netherlands| Singapore|Tokyo
Storage VPS | LiteSpeed Powered Web Hosting + SSH access | Switcher Special |
$7 256MB 5GB NAT Singapore
@mikho
$7 512MB 7GB NAT Singapore
@Abdullah
yes...so do we should set it to writethrough ?
In proxmox, there is a 'writeback' & a 'writeback (unsafe)' option. I wonder if they are different, you have any idea @Not_Oles ?
I also read at another place virtualizor uses writeback in default cache option, with some 'optimizations'...not sure if they have a way to safely use writeback.
https://webhorizon.net
sorry to OP for being offtopic here, do you use virtualizor? can it work with kernel 5.11 in production?
I bench YABS 24/7/365 unless it's a leap year.
I use proxmox+virtualizor & kernel is 5.4
https://webhorizon.net
hostvds
$1.59 per mth
don't be fooled by "data centers", only Russia available
performance wise, really crap bad throttled CPU (imagine virmach being virmached)
the score is GB4 not GB5!!!!!!
take hours to install simple webserver panel complete
I bench YABS 24/7/365 unless it's a leap year.
Cape Town ZappieHost
Free NAT KVM | Free NAT LXC
Auckland ZappieHost
Free NAT KVM | Free NAT LXC
Nice CPU and network, but SAS is very low
... Netcup RS 2000 G8 SAS
fio Disk Speed Tests 64k (IOPS) has doubled
Netcup RS1000G9
Nexusbytes from new NL location.
It's too premium to keep for idling.
ApeWeb VM2
Nexus Bytes Ryzen Powered NVMe VPS | NYC|Miami|LA|London|Netherlands| Singapore|Tokyo
Storage VPS | LiteSpeed Powered Web Hosting + SSH access | Switcher Special |
What else can I do as first command on my new VM? Oh yes, we will run a YABS of course! (It's also the last command it will run on that install!)
naranja.tech KVM-NVME-16GB - NEW YEAR OFFER
Yabs inside a Proxmox KVM. Bare metal is running 5.4.98-1-pve. The kernel in the KVM was updated to the latest Proxmox-edge-kernel, 5.11.2-1-pve.
With 5.11.2-1-pve the KVM single core GB score was 1736.
Previously, on the bare metal, the GB single core score was 1719. That 1719 was with whatever kernel preceded the current stable Proxmox kernel, 5.4.98-1-pve.
It seems that the performance of the 5.11 kernel might be improved compared to 5.4. Unless I'm confused, which happens often. Luckily I have you guys to catch my mistakes!
Maybe I am gonna try 5.11 on the bare metal node.
another one from hostvds.
they using openstack it seems
I bench YABS 24/7/365 unless it's a leap year.
Naranjatech 2G
Jasa Setup VPS
amazing
Kernel 5.11.2 from fabianishere running on Hetzner AX101 bare metal. Single core GB5 at 1673 down slightly from 1719.
Rerunning yabs. Same setup as above, kernel 5.11.2 from fabianishere running on Hetzner AX101 bare metal. GB5 single core slightly up: 1673, 1719, now 1725.
Inside KVM also running 5.11. GB5 single core score is 1454.
Oopsie! Hall of shame time! Apparently I didn't give this one an IPv6 address. I will fix that.
Umm. GB5 bare metal score 1725 - 1454 = 271 GB5 points penalty for running inside KVM-qemu? Might a shell account be faster for some tasks?
Yabs inside an LXC container on a Hetzner AX101 Proxmox node running fabianishere Linux kernel 5.11.2
Geekbench 5 scores
(AX101 Ryzen 9 5950X, Linux kernel 5.11.2)
@Not_Oles enough ... relax , time to do something else
... have fun
<spoiler>
</spoiler>
Alwyzon - Virtual Servers in Austria starting at 4,49 €/month (excl. VAT)
@alwyzon nice. RAID1 NVMe?
I bench YABS 24/7/365 unless it's a leap year.
Nope, the same Samsung SAS SSDs in RAID 10 as with the other nodes. But, given the low density of these new nodes, more I/O throughput will be left per VM.
Alwyzon - Virtual Servers in Austria starting at 4,49 €/month (excl. VAT)
raid10 is always lovely.
I bench YABS 24/7/365 unless it's a leap year.
Avoro 2019 winter promo revisited
seems like the powers returning on the CPU
10gbps
I bench YABS 24/7/365 unless it's a leap year.
Where are the iperf3 tests dear sir?
I'll try. iperf test trips the DDOS protection. it does around 7gbps
I bench YABS 24/7/365 unless it's a leap year.
@dosai
iperf3 Network Speed Tests (IPv4): --------------------------------- Provider | Location (Link) | Send Speed | Recv Speed | | | Clouvider | London, UK (10G) | 3.58 Gbits/sec | 7.26 Gbits/sec Online.net | Paris, FR (10G) | 7.35 Gbits/sec | 6.21 Gbits/sec WorldStream | The Netherlands (10G) | 7.52 Gbits/sec | 2.02 Gbits/sec Biznet | Jakarta, Indonesia (1G) | 879 Mbits/sec | 765 Kbits/sec Clouvider | NYC, NY, US (10G) | 2.11 Gbits/sec | 274 Mbits/sec Velocity Online | Tallahassee, FL, US (10G) | 1.65 Gbits/sec | 303 Mbits/sec Clouvider | Los Angeles, CA, US (10G) | 1.12 Gbits/sec | 195 Mbits/sec Iveloz Telecom | Sao Paulo, BR (2G) | busy | busyI bench YABS 24/7/365 unless it's a leap year.
MicroLXC Tiny
Sultan Muda - Amazon Store
Wiredblade
$5/mth with 50% discount (UP $10)
2 X vCPU
4GB Ram
40GB NVMe
2TB transfer
10gbps
Phoenix AZ
ISPmanager control panel
their 10gbps connection looks pretty nice. see bonus bench.sh. Let me know what else you wanna test on network.
ISPmanager is lovely. all IP and VNC info is shown clearly, custom ISO mount is supported and easy to use. prefer this over virtualizor, and maybe solusvm.
support is helpful to enable CPU passthrough. timely even on weekend.
sadly did not land on their AMD EPYC node.
their VPS FAQ page elaborates on all above.
I bench YABS 24/7/365 unless it's a leap year.
naranjatech
KVM-NVME-2GB
2 GB RAM
1 CPU Core
30 GB NVMe
5 TB Traffic
1 Gbps port speed
1 IPv4
/64 IPv6
mindblown
I bench YABS 24/7/365 unless it's a leap year.
<< too fast gif >>
IH 1GB KVM Netherlands
https://webhorizon.net
hostsolutions with telia
I bench YABS 24/7/365 unless it's a leap year.
Nexril 1GB Dallas "24 push-ups special"
We accept Karma donations for the last flan. 🍮 affbrr
any more provider giving pushup specials? was hoping to get my ass off the couch and this could be a good motivation
I bench YABS 24/7/365 unless it's a leap year.
anynode new year special revisited
noticed that it was powered down. start again and found 0 steal, worth a look.
I bench YABS 24/7/365 unless it's a leap year.
Our 5950x 4gb ram vps in New York Thing is a beast
`Basic System Information:
Processor : AMD Ryzen 9 5950X 16-Core Processor
CPU cores : 4 @ 3400.000 MHz
AES-NI : ✔ Enabled
VM-x/AMD-V : ✔ Enabled
RAM : 3.6 GiB
Swap : 1023.0 MiB
Disk : 38.3 GiB
fio Disk Speed Tests (Mixed R/W 50/50):
`
are you ever bringing back NL?
@hotlineservers how about
curl -sL yabs.sh | bash -s -- -9I bench YABS 24/7/365 unless it's a leap year.
`[root@test ~]# curl -sL yabs.sh | bash -s -- -9
## ## ## ## ## ## ## ## ## ## ## ## ## ## ## ## ##
Yet-Another-Bench-Script
v2020-12-29
https://github.com/masonr/yet-another-bench-script
## ## ## ## ## ## ## ## ## ## ## ## ## ## ## ## ##
Mon Mar 15 22:48:32 IST 2021
Basic System Information:
Processor : AMD Ryzen 9 5950X 16-Core Processor
CPU cores : 4 @ 3399.998 MHz
AES-NI : ✔ Enabled
VM-x/AMD-V : ✔ Enabled
RAM : 3.6 GiB
Swap : 1023.0 MiB
Disk : 38.3 GiB
fio Disk Speed Tests (Mixed R/W 50/50):
`
To get nice bench/code paste:
Triple backtick, newline
paste code
Triple backtick