Close to 40 comments and 90% of them are off-topic... That's really sad.
Announcement
Collapse
No announcement yet.
OpenSUSE's Spectre Mitigation Approach Is One Of The Reasons For Its Slower Performance
Collapse
X
-
Yeah, back on topic. Enough of generalizing distros.
1. Are there any real world example of Skylake+ machines getting attacked with retpoline when IBRS would have saved them?
2. Why default to IBRS on all machines?
3. Should Michael force retpoline to be used when benchmarking opensuse?
Originally posted by bobbie424242 View PostClose to 40 comments and 90% of them are off-topic... That's really sad.
- Likes 2
Comment
-
Originally posted by oooverclocker View PostI don't like how performance driven some people think and how also tests on Phoronix are tending a lot toward only performance.
Who cares about performance, teh pseudo security is what matters, aye? Don't be a hypocrite now.
- Likes 1
Comment
-
Originally posted by DanL View PostYeah, back on topic. Enough of generalizing distros.
1. Are there any real world example of Skylake+ machines getting attacked with retpoline when IBRS would have saved them?
2. Why default to IBRS on all machines?
3. Should Michael force retpoline to be used when benchmarking opensuse?
Comment
-
Originally posted by andyprough View Postshould not benchmark openSUSE
Originally posted by andyprough View Postused to run mainframes among other complex tasks
- Likes 2
Comment
-
Originally posted by andyprough View Post
Michael should not benchmark openSUSE. It is not built for gaming speed and multimedia like Ubuntu, or built to win benchmark contests like Intel has done with Clear. It is the testing ground for SLES, which is used to run mainframes among other complex tasks. Anyone using openSUSE for performance will be making significant changes from the default settings to eek out performance gains.
- Likes 2
Comment
-
Originally posted by xorbe View PostI simply don't understand this mentality. "We know it won't win so don't show it in a bad light, corporate customers may see these benchmarks" is my assumption here.
It's too bad other distros can't handle complex tasks or run on mainframes ...
Comment
-
Originally posted by andyprough View PostMichael should not benchmark openSUSE. It is not built for gaming speed and multimedia like Ubuntu, or built to win benchmark contests like Intel has done with Clear. It is the testing ground for SLES, which is used to run mainframes among other complex tasks. Anyone using openSUSE for performance will be making significant changes from the default settings to eek out performance gains.
Comment
-
I would argue that even if the OpenSuSE benchmarks are made on the "safe (but slow)" defaults, they do represent the out-of-box experience.
If anything, this implies that OpenSuSE is simply not targeted at the desktop per se.
Obviously, that does not mean that it can't be made to run decently as a desktop, but it seems to require skills that are normally reserved for the people who tinker with source-based distributions such as Gentoo and Exherbo (and Arch to some extent).
That said, one has to wonder why a (semi-)official desktop-kernel + assorted config tweaks isn't provided as per post #4? It seems a bit odd to me that people haven't pooled their resources in a common effort to address this particular need?Last edited by ermo; 16 April 2019, 01:30 PM.
- Likes 1
Comment
Comment