AlmaLinux 9, openSUSE Leap 15.4, Ubuntu 22.04, Debian 11.3 & Clear Linux Benchmarks

[phoronix]

Phoronix: AlmaLinux 9, openSUSE Leap 15.4, Ubuntu 22.04, Debian 11.3 & Clear Linux Benchmarks

Given the recent releases of openSUSE Leap 15.4 and AlmaLinux 9.0, here are some fresh Linux server/workstation-oriented benchmarks on a dual Intel Xeon Platinum 8380 "Ice Lake" platform and running the fresh releases of various enterprise Linux choices.

https://www.phoronix.com/vr.php?view=31269

[Setif]

I think the high performance of Alma Linux is highly due to its defaulting to `x86_64-v2`.

[skeevy420]

I think the high performance of Alma Linux is highly due to its defaulting to `x86_64-v2`.

I completely forgot about RHEL9 moving to v2. Hmm. But that's related to what I was wondering: With how fast Alma and Rocky appeared it really surprises me that no one has made a v3 RHEL. I wonder if it is really as simple as changing a 2 to a 3 in the build flags and rebuilding it.

[andyprough]

Debian beats its child Ubuntu again. In the first place finishes category it was a resounding defeat. You should always include Debian in these multi-distro tests, although I would imagine you might get some nasty emails from Canonical over them.

[dekernel]

openSUSE might be the slowest in the group, but I will take it every day of the week. The reliability of it has been fantastic for me, but the ease of configuration with yast is a winner as well.

[archkde]

openSUSE might be the slowest in the group, but I will take it every day of the week. The reliability of it has been fantastic for me, but the ease of configuration with yast is a winner as well.

Just use Tumbleweed, which isn't using ancient software (including compiler), so it should be faster, and it has YaST as well.

[hax0r]

I think the high performance of Alma Linux is highly due to its defaulting to `x86_64-v2`.

I'm 99% sure its due to the CPU scaling governor being set to "performance" on Alma.

The benchmarks overall are unfair, all distros should have been set their cpu freq scaling governors to "performance".
Linux is still awful in 2022 in many aspects such as page trashing in near OOM conditions or cpu scheduler latency for decent desktop experience, and subpar cpu freq scaling governors are being one of them.

[skeevy420]

I'm 99% sure its due to the CPU scaling governor being set to "performance" on Alma.

The benchmarks overall are unfair, all distros should have been set their cpu freq scaling governors to "performance".
Linux is still awful in 2022 in many aspects such as page trashing in near OOM conditions or cpu scheduler latency for decent desktop experience, and subpar cpu freq scaling governors are being one of them.

Michael tests what they ship. Raise your complains with the distribution, not the tester.

AKA

Don't kill the messenger.

[rossocrama]

no wireguard test? i don't find it in the complete benchmark either (and it gave interesting results in the past distro comparison)

[Michael]

no wireguard test? i don't find it in the complete benchmark either (and it gave interesting results in the past distro comparison)

Forgot to toss it in the run queue.