Linux Networking Performance To Improve Thanks To Retpoline Overhead Reduction

[phoronix]

Phoronix: Linux Networking Performance To Improve Thanks To Retpoline Overhead Reduction

One of the areas where Linux performance has been lower this year since Spectre came to light has been for networking performance, but with the upcoming Linux 4.21 cycle that will be partially addressed...

http://www.phoronix.com/scan.php?page=news_item&px=Linux-Better-Retpoline-Net

[boxie]

Of all the spectre testing, I don't remember seeing the performance impact on network throughput in your tests Michael - Once this lands are you able to give us a quick round of tests demonstrating the perf impact ? (I am sure you are already planning it, but if you needed an excuse to do it then count this as a request for it!)

[enihcam]

If it is to fix an existing regression, it should be backported to current and long-term releases.

[hax0r]

Good way to fix Linux network performance is to use FreeBSD.

[Hi-Angel]

This may lead to some uglification around the indirect calls...

This is because C doesn't have proper macros support. Neither does C++. It makes me wonder, that in the course of improving language standards nobody figured to improve that.

[starshipeleven]

Good way to fix Linux network performance is to use FreeBSD.

FYI: Last tests we saw FreeBSd wasn't better.

[AsuMagic]

This is because C doesn't have proper macros support. Neither does C++. It makes me wonder, that in the course of improving language standards nobody figured to improve that.

Macros should die. C++ is moving away from them in a nicer and nicer way every new standard.

[Hi-Angel]

Macros should die. C++ is moving away from them in a nicer and nicer way every new standard.

I don't understand peoples, who hate C++ macros. I mean, of course you'd have to use templates whenever that possible. But if you remove macros, you'd be left with usecases which aren't covered by anything at all.

[michaelb1]

Intel fanboys should've paid for their "sins" but thanks to Intel corporate pressure some vuln migitations have been cancelled. Well, then enjoy your botched security :P

[AsuMagic]

I don't understand peoples, who hate C++ macros. I mean, of course you'd have to use templates whenever that possible. But if you remove macros, you'd be left with usecases which aren't covered by anything at all.

They should die because they come with a lot of problems but aren't dead because of their remaining usecases indeed. That was my point