The Power Efficiency Between Ubuntu 19.04, Clear Linux & openSUSE Tumbleweed With CompuLab's Airtop 3

[tildearrow]

On a desktop on first boot/the first day or two? Maybe. balooctl isn't known for being light on resources.

Oh never mind... I always disable Baloo on every KDE installation I do.

[andyprough]

When comparing a range of distributions on a fixed piece of hardware to see the power differences based on what the those distributions provide by default, the Joe Dumbass experience is exactly what needs to be tested because that's what regular users, not advanced users like ourselves, will use if they're actually capable of flashing a USB stick and installing Linux.

You've certainly quoted Ubuntu's philosophy perfectly. It's not one that I agree with.

[andyprough]

Why? Defaults are defaults.

Because, as has been pointed out numerous times on these pages, anyone looking for performance with Tumbleweed does not use the defaults. So benchmarking with the Tumbleweed defaults to see which distro is "faster" is pointless.

[skeevy420]

You've certainly quoted Ubuntu's philosophy perfectly. It's not one that I agree with.

Me neither, but we all started somewhere and, for a lot of us, that probably involved some ncurses or GUI installer and just going with it until we were knowledgeable enough know what the stuff under the advanced tabs did and why we might want to use them.

17 some odd years later...I wish I was a new user again so I could just go with it and enjoy it

[Linuxxx]

Me neither, but we all started somewhere and, for a lot of us, that probably involved some ncurses or GUI installer and just going with it until we were knowledgeable enough know what the stuff under the advanced tabs did and why we might want to use them.

17 some odd years later...I wish I was a new user again so I could just go with it and enjoy it

So true!

And that's why on a new install I just went with Ubuntu LTS instead of Arch/Manjaro!
Did my usual tweaks (performance governor with perf-bias set to 0, kyber IO-scheduler, vm.swappiness=1, booting kernel with nmi_watchdog=0, enabling triple-buffering for NVIDIA) and just went with Ubuntu's "lowlatency" kernel instead of compiling my own.

And You know what?

The system still feels incredibly smooth!

No more having to worry; just enjoying my Linux!

[starshipeleven]

I bet Clear would beat Ubuntu by a small margin, and SuSE would lose by a large margin.

Neither of the tests show anything remotely resembling "large margins"

[starshipeleven]

openSUSE defaults are questionable anyway. They are too busy fixing that. Gotta vote on yet another name change ..

You should try to troll harder, the lack of effort is apparent.

[starshipeleven]

Is OpenSUSE really that power-hungry...? I was thinking of upgrading my server to it...

No it isn't. It may not be as optimal as other distros on specific workloads with default configuration, but I've lost count Ubuntu or Debian ship completely worthless default configs for server applications anyway, so whatever, it's a coin toss.

Only one we know will be better is Clear Linux, because they do push on performance as hard as possible.

Btw, he is saying that Tumbleweed is so slow to process stuff that the hardware remains in high-power states longer and therefore the server uses more power over time.

[utrrrongeeb]

The total kWh consumed to complete the entire test suite, at the wall outlet, would be a much better indicator of overall platform efficiency with the installed software. I bet Clear would beat Ubuntu by a small margin, and SuSE would lose by a large margin.

Assuming the Watts Up measurements and PTS processing are valid, test run-time (s) multiplied by average power consumption (W) gives energy used for the test (J). Using the Blender graphs (which have many power samples over a relatively long time — the other tests are too short to use with much confidence), the results for Tumbleweed, Ubuntu, and Clear are respectively 91950.64, 86507.72, and 83275.52 joules. (Intermediate values - three significant digits would be generous. Also note that for differing run-counts N, those must be corrected for since the power graph is concatenated while the results are averaged.) In this one test, Tumbleweed uses 10.4% more energy than Clear.

Michael are the openbenchmarking.org links in the lower-left corner of the graphs supposed to go to /prospect/… paths, which are redirected to / index, instead of /result/…? Also, the intra-page graphs are at anchor …/#r-$UUID, instead of at path …/$UUID.

[linuxgeex]

Assuming the Watts Up measurements and PTS processing are valid, test run-time (s) multiplied by average power consumption (W) gives energy used for the test (J). Using the Blender graphs (which have many power samples over a relatively long time — the other tests are too short to use with much confidence), the results for Tumbleweed, Ubuntu, and Clear are respectively 91950.64, 86507.72, and 83275.52 joules. (Intermediate values - three significant digits would be generous. Also note that for differing run-counts N, those must be corrected for since the power graph is concatenated while the results are averaged.) In this one test, Tumbleweed uses 10.4% more energy than Clear.

Michael are the openbenchmarking.org links in the lower-left corner of the graphs supposed to go to /prospect/… paths, which are redirected to / index, instead of /result/…? Also, the intra-page graphs are at anchor …/#r-$UUID, instead of at path …/$UUID.

The reason I want the total power at the wall for the duration of the suite is because it would provide a total for all the runs, which is a good indication of power usage on an average server running mixed loads. In my experience, SuSE's power management is poorer. More power usage = lower thermal headroom = more throttling = lower performance.

Michael concluded that Clear outperformed Ubuntu while using only a little more power, but he kinda missed just how badly SuSE under-performed vs Ubuntu given it's much higher thermal/power results. This chart shows SuSE's median temp at what looks like 82C vs Ubuntu at 64C. Assuming 22C ambient, same suite duration, and same fan speed, that would indicate 104% higher core power consumption by the SuSE system. Obviously the fan speeds were significantly lower for Ubuntu, lol.

The Power Efficiency Between Ubuntu 19.04, Clear Linux & openSUSE Tumbleweed