Other Linux Distributions Begin Analyzing Clear Linux's Performance Optimizations

[phoronix]

Phoronix: Other Linux Distributions Begin Analyzing Clear Linux's Performance Optimizations

Fedora developers appear to be among those analyzing Intel's Clear Linux distribution for the performance optimizations made...

http://www.phoronix.com/scan.php?page=news_item&px=Fedora-Looks-At-Clear

[johnc]

I sort of thought this was the kind of thing that Valve would be doing with SteamOS. Well, until I realized they were completely phoning it in.

[arjan_intel]

Interesting and slightly misinformed... I wish they'd talk to the Clear Linux team directly...

So the Intel team (Clear Linux team and our adjacent teams) is working hard to make QEMU faster and have gotten very good results (patches in progress towards upstream)... good to see that Red Hat is now also interested.

On the kernel, we're not using LTO; I don't know where that idea comes from. We're certainly investigating it, since it's a cool feature, but haven't made the full switch yet.

Claiming that the clear containers kernel is extremely heavily patches is .. slightly dishonest. there's 24 patches (including security), most are very minor (both in size and in boot-time impact). The Fedora 24 kernel (snapshot) has 67 patches in it!! Distros patch kernels, usually in minor ways... calling out another distro for heavy patching when your own distro kernel has 2.5x the number of patches... shrug.

As to the preference for having one binary vs two binaries; for a long time RH/Fedora shipped multiple binaries (I know, I used to be their distro kernel maintainer). It's certainly not ideal, and I would agree with a preference of having fewer binaries, but I also have a preference for more secure containers...

[arjan_intel]

BTW to take away another misconception in the article; while Clear Linux sets a bar for minimum CPU (each distro does by definition, different distros set different bars), the bar set by Clear Linux is set at the "westmere" generation CPUs which were launched in 2010. .. calling that "only about the best and newest Intel CPUs"... really?

[Michael]

BTW to take away another misconception in the article; while Clear Linux sets a bar for minimum CPU (each distro does by definition, different distros set different bars), the bar set by Clear Linux is set at the "westmere" generation CPUs which were launched in 2010. .. calling that "only about the best and newest Intel CPUs"... really?

Looks like https://clearlinux.org/documentation..._hardware.html needs to be updated or better clarified, but I've updated my article to clarify.

[peppercats]

BTW to take away another misconception in the article; while Clear Linux sets a bar for minimum CPU (each distro does by definition, different distros set different bars), the bar set by Clear Linux is set at the "westmere" generation CPUs which were launched in 2010. .. calling that "only about the best and newest Intel CPUs"... really?

I assume that Clear Linux can't be ran on AMD CPUs then?
Is everything you guys do detailed on the clearlinux site?
Have you considered evaluating the CPU scheduler BFS(Brain Fuck Scheduler)? It seems to perform quite favorably in non-NUMA scenarios compared to CFQ.

[darkbasic]

Interesting and slightly misinformed... I wish they'd talk to the Clear Linux team directly...

So the Intel team (Clear Linux team and our adjacent teams) is working hard to make QEMU faster and have gotten very good results (patches in progress towards upstream)... good to see that Red Hat is now also interested.

On the kernel, we're not using LTO; I don't know where that idea comes from. We're certainly investigating it, since it's a cool feature, but haven't made the full switch yet.

Claiming that the clear containers kernel is extremely heavily patches is .. slightly dishonest. there's 24 patches (including security), most are very minor (both in size and in boot-time impact). The Fedora 24 kernel (snapshot) has 67 patches in it!! Distros patch kernels, usually in minor ways... calling out another distro for heavy patching when your own distro kernel has 2.5x the number of patches... shrug.

As to the preference for having one binary vs two binaries; for a long time RH/Fedora shipped multiple binaries (I know, I used to be their distro kernel maintainer). It's certainly not ideal, and I would agree with a preference of having fewer binaries, but I also have a preference for more secure containers...

OMG are you kidding? We're open source, there are far better options to find out what's happening than reverse engineering someone else's code, maybe just... asking?

[eydee]

Considering that Clear is not a general use OS, some of the optimizations coming to those would be welcome. An average desktop computer user will not use Clear, it doesn't even have a UI.

[GreatEmerald]

Hm, so that's nothing that would make it faster than Gentoo. Makes sense.

[rabcor]

intel has long history of cheating benchmarks

How so? I mean I know intel are idiots in various ways (I mean did they really give money to the feminist frequency? One of the most toxic things in the history of the internet...?), but how do they cheat benches? I know there are many unfair benchmarking softwares out there more tailored to one vendors products than anothers, is that what you mean? That's not exactly cheating.