Is Fedora 15 Faster Than Ubuntu 11.04?

[Michael]

Michael,

One severe short coming of this test is that it used only CPUs from intel. There are architectural differences between intel and AMD cpus that could effect performance and power consumption differently.

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

[Obscene_CNN]

Michael,

One severe short coming of this test is that it used only CPUs from intel. There are architectural differences between intel and AMD cpus that could effect performance and power consumption differently.

[devius]

Yes, defaults. Can do some SELinux benchmarks separately if there's interest.

That would be nice. Maybe include AppArmor in those tests as well, although that doesn't use special filesystem labels, but it should decrease application performance as well.

[damg]

As far as the disk performance discrepancy goes - did you test with SELinux enabled or disabled, on Fedora?

edit: you say 'out of the box', so I assume 'enabled'; it might be interesting to try with it disabled. Also it'd be interesting to know if you kept the OS default partitioning scheme (in which case the Fedora install would likely have an LVM layer the Ubuntu one would not.)

Good points. It would be interesting to see how much SELinux and LVM affect performance.

[Nobu]

The conclusion is [REDACTED]. (just kidding)

If you read carefully, the conclusion is on the last page...at the very top, even.

[kraftman]

Yes, defaults. Can do some SELinux benchmarks separately if there's interest.

It will be great.

[jcgeny]

fedora 15 & 14 with a hvr2200 can display two windows of tv hd with vlc
ubuntu 11 did one tv and was not able to open a second . after that first time vlc was not able to display even 1 tv .
from the original install of both os , i copied the file NXP7164-2010-03-10.1.fw in the lib folder and created an options file in the etc/modprobe.d folder with options saa7164 card=4 in it .
long ago , ubuntu 9 was perfect with an hvr1100 out of the box with tvtime

[FireBurn]

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'd be interested in seeing this too

Comparing local version, compiled with local gcc and compiled with phoronix gcc too

That would be very interesting

[Michael]

Where's the conclusion? I didn't really want to read through 6 pages..

Then that detracts from ad views otherwise...

[Michael]

As far as the disk performance discrepancy goes - did you test with SELinux enabled or disabled, on Fedora?

edit: you say 'out of the box', so I assume 'enabled'; it might be interesting to try with it disabled. Also it'd be interesting to know if you kept the OS default partitioning scheme (in which case the Fedora install would likely have an LVM layer the Ubuntu one would not.)

Yes, defaults. Can do some SELinux benchmarks separately if there's interest.