Is Fedora 15 Faster Than Ubuntu 11.04?

[eduperez]

Michael,

Is PTS still self compiling the tested software?
If so, have you considered adding, whenever possible the built in version to the mix?

- Gilboa

I guess that the vast majority of users are NOT going to compile their own software, but use the binaries provided within the distribution. Thus it makes much more sense to benchmarks those binaries, not your own compilations. Otherwise, these tests show the performance of the supplied kernel + glibc + gcc, not the full system.

[gilboa]

I guess that the vast majority of users are NOT going to compile their own software, but use the binaries provided within the distribution. Thus it makes much more sense to benchmarks those binaries, not your own compilations. Otherwise, these tests show the performance of the supplied kernel + glibc + gcc, not the full system.

I fully agree.
Hence the reason for my question

[Tgui]

Right, but blame AMD for not sending out CPUs to Phoronix...

Why not use some of the billions in ad revenue you make from this website to purchase a few AMD processors?



I keed.

[Obscene_CNN]

I guess that the vast majority of users are NOT going to compile their own software, but use the binaries provided within the distribution.

Gentoo users will.

[Prescience500]

I wonder if Fedora 15 (KDE) will still be faster than Kubuntu 11.04?

[Ard Righ]

Default LVM partitions

One of the annoyances of Fedora, is the LVM-by-default install pattern that is used, which is great for desktops, and possibly basic servers, but generally sucks arse for laptops.

And LVM will always kill performance.

I am fairly sure removing LVM would even the disk performance numbers up to minimal differences.

[baryluk]

Hmm. LVM vs non-LVM, as well encyprtion vs non-encryption would be really interesting benchmark. (remember to use some hardware with harware support for AES, like some newer core2 cpus).