Benchmarking Ubuntu's Low-Latency Kernel & Liquorix Post-Meltdown

[RelaxTrolls]

Here's how one can achieve real smoothness:

- Use openSUSE Tumbleweed, since it contains the best Linux Kernel config by default. (250Hz tick timer, PREEMPT enabled)

- Use the deadline İO scheduler.

- Use the 'performance' governor.

- Additionally, if stuck on İntel, make sure to set the 'performance-bias' to '0'!

Now enjoy your silky-smooth Linux experience!

using the performance governor is handy for some use cases, mainly since you'll avoid CPU scaling... but using it all the time seems like bad advice... especially on any device where you care about power-saving or temperatures ....

and FYI, any desktop or mobile linux kernel is mostly going to be preempt. pretty standard stuff.

[boxie]

The 'perf' test results vary by about three tenths of a millisecond over these kernels.
I don't think that test says anything meaningful and it should be discarded as 'win' or a 'loss'.
Time accounting precision in these kernels might vary by that amount (?) - anyone care to enlighten me on that thought.
In a practical sense, 3 tenths of a ms wont keep us awake at night.
$time ls /usr/bin varies by more. Does the test really do anything but return?

the Wins and Losses is a start, but as any statistic - it's a lie!
I would like to see a programatic way to see if something won or loss by "an inch or a mile"

[LuukD]

The 'perf' test results vary by about three tenths of a millisecond over these kernels.
I don't think that test says anything meaningful and it should be discarded as 'win' or a 'loss'.
Time accounting precision in these kernels might vary by that amount (?) - anyone care to enlighten me on that thought.
In a practical sense, 3 tenths of a ms wont keep us awake at night.
$time ls /usr/bin varies by more. Does the test really do anything but return?

[Licaon]

Sure would be interesting if somebody could measure actual input latency in say CS:GO with a variety of hardware and software.

Spectre/Meltdown appear to (mostly) not affect games.

Or were you talking about Liquorix and kernel latency in general?

[arjan_intel]

How exactly do you do the above?

see the x86_energy_perf_policy binary
(shipped often in kernel-tools or similarly named packages)

[Spooktra]

- Use the deadline İO scheduler.

- Use the 'performance' governor.

- Additionally, if stuck on İntel, make sure to set the 'performance-bias' to '0'!

How exactly do you do the above?

[eva2000]

wow thanks Michael

Liqourix was looking promising as I started reading until it came to nginx/apache and redis performance (my focus)

[starshipeleven]

Here's how one can achieve real smoothness:

- Use openSUSE Tumbleweed, since it contains the best Linux Kernel config by default. (250Hz tick timer, PREEMPT enabled)

- Use the deadline İO scheduler.

- Use the 'performance' governor.

- Additionally, if stuck on İntel, make sure to set the 'performance-bias' to '0'!

Now enjoy your silky-smooth Linux experience!

Damn son, what is this, XDA?

I'll just say BFQ beats Deadline by a long shot when under moderate/heavy I/O, and it's only going to get better.

[HenryM]

I'm surprised Liquorix topped any tests, as I'm pretty sure it is tuned for UX and low latency rather than throughput (which is why I use it).

Sure would be interesting if somebody could measure actual input latency in say CS:GO with a variety of hardware and software. I can't find anything like that online, other than someone testing the Dolphin emu on windows.

[Michael]

As a new premium member ;-) ... Thank you very much Michael!

Thanks and cheers.