Linux 5.0 Kernel Performance Is Sliding In The Wrong Direction

[Shevchen]

Seriously? We're going to argue that saying you can't mistreat other people or use slurs leads to poor code? This is why Linux users are portrayed as Neanderthals with beards in the popular media; we're not doing anything to dispel the image.

Strawman. If SJWs can't take any kind of critique and blame it on "mansplaining", even constructive and valid critique posted in a proper manner will come under the train.

Wojcian posted a benchmark showing it's a Ubuntu issue rather than a kernel issue, everyone ignores it and starts going on about the evils of being asked not to sexually harass women? Sheesh.

False dichotomy. This has nothing to do with sexually harassing people, its about analyzing the regression.

[Cybmax]

To be fair I'll also test 4.18 kernel with my custom config to see how it performs against 5.0. What I don't like Ubuntu has debugging enabled even for final releases. I'm not sure how it is in other distributions. FreeBSD has this disabled (and this is good!) as far as I remember. Probably the same in Windows, OS X, so it puts Ubuntu and maybe few other distributions in disadvantage for no reason.

I am very interested in the result, and possibly any custom config to compare to ubuntu default.

[linuxgeex]

I haven't looked at the kernel commit log, but given the announcement about SMAP I wouldn't be surprised if this regression is a result of adopting SMAP protection in some of the kernel subsystems.

I hope that SMAP ends up being something that can be toggled at boot time so that it can be used during kernel development to test for bad design, and used for security-hardened servers and devices, but I wouldn't want SMAP enabled on my desktop or media player.

[Wojcian]

I am very interested in the result, and possibly any custom config to compare to ubuntu default.

Here you go:

https://openbenchmarking.org/result/...KH-TEST1982530

I'm glad, because it seems Linux 5.0 kernel performance is sliding in the right direction which can't be said about Ubuntu kernels.

4.18-custom: http://s000.tinyupload.com/index.php...80013360624564

5.0-rc7-custom: http://s000.tinyupload.com/index.php...85656455218916

[tildearrow]

Seriously? We're going to argue that saying you can't mistreat other people or use slurs leads to poor code? This is why Linux users are portrayed as Neanderthals with beards in the popular media; we're not doing anything to dispel the image.

Have you even read the full "Code of Conduct" document in depth? The "Code of Conduct" (specifically the Contributor Covenant) may sound like a set of typical "be nice" rules, but it actually is a document on having to accept anyone's code, in the name of "diversity", regardless of quality/bugs.

[r08z]

Here you go:

https://openbenchmarking.org/result/...KH-TEST1982530

I'm glad, because it seems Linux 5.0 kernel performance is sliding in the right direction which can't be said about Ubuntu kernels.

4.18-custom: http://s000.tinyupload.com/index.php...80013360624564

5.0-rc7-custom: http://s000.tinyupload.com/index.php...85656455218916

Good job. Glad to see proof that custom kernels with crap disabled will always run the fastest.

[Cybmax]

I'm glad, because it seems Linux 5.0 kernel performance is sliding in the right direction which can't be said about Ubuntu kernels.

4.18-custom: http://s000.tinyupload.com/index.php...80013360624564

5.0-rc7-custom: http://s000.tinyupload.com/index.php...85656455218916

Thx. Not that different from my own custom hacks, save for some driver stuff

Could be that the Ubuntu-ppa for the "rc" kernel is not 100% final, but nice to see something can be gained from the 4.18 kernel too. I would possibly assume Ubuntu default kernel has a wee bit too much debugging and unneeded stuff enabled "just to be safe" in case you try to install Ubuntu on some 1992 model crap-o-matic piece of hardware?