On Fri, 2009-06-12 at 21:49 -0700, Adam Williamson wrote:
On Sat, 2009-06-13 at 05:43 +0200, Kevin Kofler wrote:
and no, glxgears is not a benchmark!
Indeed, glxgears really sucks as as a benchmark, Phoronix's benchmark suite
(as imperfect as it is) is definitely more useful.
I
On Sat, 2009-06-13 at 21:05 +0200, Kevin Kofler wrote:
Too bad their hardware benchmarks do not match the development news, and too
bad they also feel it necessary to continuously warn about alleged
unsuitability of the Free drivers for production use (when in reality they
just work as long as
On Fri, 2009-06-12 at 21:49 -0700, Adam Williamson wrote:
On Sat, 2009-06-13 at 05:43 +0200, Kevin Kofler wrote:
and no, glxgears is not a benchmark!
Indeed, glxgears really sucks as as a benchmark, Phoronix's benchmark suite
(as imperfect as it is) is definitely more useful.
I
On Sat, Jun 13, 2009 at 11:02 AM, Gilboa Davaragilb...@gmail.com wrote:
On Fri, 2009-06-12 at 21:49 -0700, Adam Williamson wrote:
On Sat, 2009-06-13 at 05:43 +0200, Kevin Kofler wrote:
and no, glxgears is not a benchmark!
Indeed, glxgears really sucks as as a benchmark, Phoronix's
On Sat, Jun 13, 2009 at 06:05:52AM +0300, Gilboa Davara wrote:
Up until 30 minutes ago, I was unaware of the fact that they use
test-suite compiled binaries.
Though I'd imagine that in Phoronix' view, having (far) different
compile options in the distribution supplied binaries might generate
On Sat, 2009-06-13 at 12:20 +0200, drago01 wrote:
On Sat, Jun 13, 2009 at 11:02 AM, Gilboa Davaragilb...@gmail.com wrote:
On Fri, 2009-06-12 at 21:49 -0700, Adam Williamson wrote:
On Sat, 2009-06-13 at 05:43 +0200, Kevin Kofler wrote:
and no, glxgears is not a benchmark!
Indeed,
drago01 wrote:
There are alot of open source games[1} that are useable to for
benchmarking. glxgears is NOT a benchmark. If you don't have anything but
glxgears than you have NO benchmark.
+1
[1]: openarena, nexuiz, ...
Also etracer, torcs etc. Basically everything 3D with an FPS display
Gilboa Davara wrote:
I subscribed to Phoronix' RSS feed and at least 1/3-1/2 of their news
stories are on OSS driver (mostly Intel and ATI) driver development -
far more than any other OSS new site. [1]
Too bad their hardware benchmarks do not match the development news, and too
bad they also
On Fri, Jun 12, 2009 at 9:51 PM, Gilboa Davaragilb...@gmail.com wrote:
I apologize in advance, for the overly harsh language. (Not specifically
directed at you, Kevin).
I don't believe that you're being overly harsh. I've been surprised
in general in the amount of whining that I've been
I have read a lot of people voice their opinion on what they think to be a
flaw in the benchmark. How about we as a group put together a documented
benchmark process along with justification as to why those methods were
chosen to reflect real world scenarios and from there send it to reviewers
Am Freitag, den 12.06.2009, 19:55 +1000 schrieb Eric Springer:
2009/6/12 Christoph Höger choe...@cs.tu-berlin.de:
Could you explain why mp3 (or ogg) encoding is not a real world
benchmark? I do this quite often.
Because they are comparing file system on what is a CPU bound test. Notice
On 12.06.2009 13:33, Christoph Höger wrote:
Am Freitag, den 12.06.2009, 19:55 +1000 schrieb Eric Springer:
2009/6/12 Christoph Höger choe...@cs.tu-berlin.de:
Could you explain why mp3 (or ogg) encoding is not a real world
benchmark? I do this quite often.
Because they are comparing file
On 06/11/2009 10:41 PM, Xose Vazquez Perez wrote:
Eric Sandeen wrote:
I don't know much about apache but I bet a default ./configure winds up
with different builds depending on the build environment, which in this
case is probably dictated by whatever the default generic OS intall
contains.
On Fri, Jun 12, 2009 at 03:03:58PM +0200, Harald Hoyer wrote:
Nice find!
Maybe we can run the real world test suite (benchmark) before the
next release and try to straighten out such odds.
Most of the benchmark results they post are not showing scientific
results, only when something is
On Fri, Jun 12, 2009 at 8:11 AM, Thorsten Leemhuisfed...@leemhuis.info wrote:
IOW: a lot of those phoronix articles that contain benchmarks could be
half as long or even shorter if you rip out the results that are of no
value and replace them by No unexpected side effects could be found
when
Eric Springer wrote:
Especially considering how many people will use these benchmarks to make
conclusions about Fedora, we should make sure it presents as best as it
can.
I think we should rather do an informative press campaign on the lines
of Why Phoronix benchmarks are utter bullsh*t.
On 06/12/2009 09:24 AM, Kevin Kofler wrote:
Eric Springer wrote:
Especially considering how many people will use these benchmarks to make
conclusions about Fedora, we should make sure it presents as best as it
can.
I think we should rather do an informative press campaign on the lines
of
On 06/12/2009 06:42 PM, Kyle McMartin wrote:
It's almost certainly attributable to the default install using audit.
Roland and various others have done a lot of work improving things, but
there is always going to be a per-syscall overhead to this kind of
thing. A few extra usec a syscall adds
Casey Dahlin wrote:
Because they gave us a bad grade and now we're butthurt and we're taking
our ball and going home so there? Because that's what everyone's going to
hear, even if its not what we say.
If they love hearing bullsh*t, they should just go use a distro for bullsh*t
lovers, like
On Fri, 2009-06-12 at 19:01 +0530, Rahul Sundaram wrote:
On 06/12/2009 06:42 PM, Kyle McMartin wrote:
It's almost certainly attributable to the default install using audit.
Roland and various others have done a lot of work improving things, but
there is always going to be a per-syscall
On 06/12/2009 09:14 PM, Adam Williamson wrote:
On Fri, 2009-06-12 at 19:01 +0530, Rahul Sundaram wrote:
On 06/12/2009 06:42 PM, Kyle McMartin wrote:
It's almost certainly attributable to the default install using audit.
Roland and various others have done a lot of work improving things, but
Once upon a time, Adam Williamson awill...@redhat.com said:
On Fri, 2009-06-12 at 19:01 +0530, Rahul Sundaram wrote:
Is there a benefit to running audit by default? Is it worth the cost?
...and how does one disable it, so the people doing the benchmarks can
confirm that's the cause?
At the
Adam Williamson wrote:
On Fri, 2009-06-12 at 19:01 +0530, Rahul Sundaram wrote:
Is there a benefit to running audit by default? Is it worth the cost?
...and how does one disable it, so the people doing the benchmarks can
confirm that's the cause?
put selinux=0 audit=0 in kernel line at
On 06/12/2009 09:35 PM, Xose Vazquez Perez wrote:
put selinux=0 audit=0 in kernel line at /boot/grub/grub.conf
then reboot
$ dmesg | egrep -i audit|selinux
Kernel command line: ro root=UUID=c99c0f86-6ebc-4e0f-91ee-4a6ae7ae6aa9
vga=791 selinux=0 audit=0
audit: disabled (until reboot)
On Jun 12, 2009, at 11:11 AM, Rahul Sundaram wrote:
On 06/12/2009 09:35 PM, Xose Vazquez Perez wrote:
put selinux=0 audit=0 in kernel line at /boot/grub/grub.conf
then reboot
$ dmesg | egrep -i audit|selinux
Kernel command line: ro
root=UUID=c99c0f86-6ebc-4e0f-91ee-4a6ae7ae6aa9 vga=791
On Fri, Jun 12, 2009 at 5:28 AM, Casey Dahlincdah...@redhat.com wrote:
Because they gave us a bad grade and now we're butthurt and we're taking our
ball and going home so there? Because that's what everyone's going to hear,
even if its not what we say.
What I have a problem with is the lack
On 06/12/2009 12:44 PM, Jeff Spaleta wrote:
I don't have a problem getting a bad grade. I do have a general
problem with people who publish unexpected behavior regressions but
don't actually use the open development process to drive feedback
directly to developers. If we deserve a black eye
On Fri, Jun 12, 2009 at 07:55:56PM +1000, Eric Springer wrote:
I agree with the sentiment that phoronix reviews are lazy, poor, etc
-- but that doesn't mean nothing is revealed by them. Especially
considering how many people will use these benchmarks to make
conclusions about Fedora, we should
Hi,
Our Apache results on the Phoronix tests, AIUI, are from an
Apache they compiled, which is not what most people are going to
use.
Do similar results occur when you compare the installed Apaches instead,
or does the discrepancy go away?
There's also no mention of whether they
On Fri, 2009-06-12 at 15:24 +0200, Kevin Kofler wrote:
Eric Springer wrote:
Especially considering how many people will use these benchmarks to make
conclusions about Fedora, we should make sure it presents as best as it
can.
I think we should rather do an informative press campaign on
On Sat, 2009-06-13 at 04:33 +0300, Gilboa Davara wrote:
On Fri, 2009-06-12 at 15:24 +0200, Kevin Kofler wrote:
Eric Springer wrote:
Especially considering how many people will use these benchmarks to make
conclusions about Fedora, we should make sure it presents as best as it
can.
On Sat, 2009-06-13 at 00:47 +0200, Kevin Kofler wrote:
I know its a pipe dream...the laypress taking a proactive interest in
seeing problems resolved instead of just talking about them.
I don't think it's ever going to happen. The laypress should just die,
people need to go directly to
On Sat, 2009-06-13 at 04:33 +0300, Gilboa Davara wrote:
You don't like Phoronix' benchmark? Why? What should they have done
differently? Have you ever contacted Phoronix (E.g. Using their forums)
and tried to resolve these issues? Did they refuse?
They should use distribution-compiled
On Fri, 2009-06-12 at 17:25 -0400, Paul W. Frields wrote:
On Fri, Jun 12, 2009 at 07:55:56PM +1000, Eric Springer wrote:
I agree with the sentiment that phoronix reviews are lazy, poor, etc
-- but that doesn't mean nothing is revealed by them. Especially
considering how many people will use
On Sat, 2009-06-13 at 04:33 +0300, Gilboa Davara wrote:
Kevin,
I must admit that I didn't expect such childish reaction from someone
like you.
BTW, I suspect that Kevin's position has a lot to do with the response
KDE 4 got in the press...which is understandable.
--
Adam Williamson
Fedora
On Fri, Jun 12, 2009 at 9:31 AM, Rahul
Sundaramsunda...@fedoraproject.org wrote:
On 06/12/2009 06:42 PM, Kyle McMartin wrote:
It's almost certainly attributable to the default install using audit.
Roland and various others have done a lot of work improving things, but
there is always going to
On Fri, 2009-06-12 at 19:08 -0700, Adam Williamson wrote:
On Sat, 2009-06-13 at 04:33 +0300, Gilboa Davara wrote:
Kevin,
I must admit that I didn't expect such childish reaction from someone
like you.
BTW, I suspect that Kevin's position has a lot to do with the response
KDE 4 got
On Fri, 2009-06-12 at 19:05 -0700, Adam Williamson wrote:
On Sat, 2009-06-13 at 04:33 +0300, Gilboa Davara wrote:
You don't like Phoronix' benchmark? Why? What should they have done
differently? Have you ever contacted Phoronix (E.g. Using their forums)
and tried to resolve these issues?
Gilboa Davara wrote:
Might I remind everyone here that Phoronix was the first to offer a
comprehensive benchmark suite to the OSS world.
On the other hand, they actively hurt Free Software by continuously
providing free advertising for the latest and greatest graphics hardware
with only
On Sat, 2009-06-13 at 05:43 +0200, Kevin Kofler wrote:
and no, glxgears is not a benchmark!
Indeed, glxgears really sucks as as a benchmark, Phoronix's benchmark suite
(as imperfect as it is) is definitely more useful.
I keep meaning to file a feature request for glxgears - remove the FPS
hi,
In Apache Benchmark:
Ubuntu was able to sustain more than 58% more requests per second than Fedora
11
http://www.phoronix.com/scan.php?page=articleitem=fedora11_ubuntu904_perfnum=2
-thanks-
regards,
--
Polycommander, Erkowit, Urquiola, Andros Patria, Cason, Aegean Sea, Prestige,
...
--
On Fri, Jun 12, 2009 at 3:43 AM, Jeff Spaletajspal...@gmail.com wrote:
Why did you cherry pick the bad news instead of the summary?
Likely for the same reasons we have a bug tracker instead of a 'what
works list'. But I agree, Fedora performed quite favourably especially
taking into
The question becomes what is significantly different in the Apache
test? Is the Apache test essentially a network i/o test? What is
significantly different here that would not end up being tracked to an
upstream kernel networking stack regression? Is the apache performance
collatoral damage
2009/6/12 Christoph Höger choe...@cs.tu-berlin.de:
Without knowing how exactly the benchmark works I
would guess that most of those apache requests are
kernel calls so SELinux _might_ make a huge difference
here.
Shouldn't be overly hard to test as phoronix-test-suite is available
in Fedora's
Eric Springer wrote:
2009/6/12 Christoph Höger choe...@cs.tu-berlin.de:
Without knowing how exactly the benchmark works I
would guess that most of those apache requests are
kernel calls so SELinux _might_ make a huge difference
here.
Shouldn't be overly hard to test as phoronix-test-suite
On Thu, Jun 11, 2009 at 9:51 AM, Eric Springererik...@gmail.com wrote:
Likely for the same reasons we have a bug tracker instead of a 'what
works list'. But I agree, Fedora performed quite favourably especially
taking into consideration the database benchmarks.
The problem with knowing that
Xose Vazquez Perez wrote:
All Phoronix Test Suite[1] tests run in *local* host. NO net.
Basically the apache test do:
download http://archive.apache.org/dist/httpd/httpd-2.2.11.tar.gz
and
http://www.phoronix-test-suite.com/benchmark-files/apache-ab-test-files-1.tar.gz
then compile
On 06/11/2009 02:17 PM, Eric Sandeen wrote:
True, though over and over again I see things where I wish they'd at
least dig into the discrepancies they find, rather than just reporting
numbers.
Seconded, I mean, wtf is this?
with the test profiles that stress the system disk, Fedora 11
James M. Leddy wrote:
On 06/11/2009 02:17 PM, Eric Sandeen wrote:
True, though over and over again I see things where I wish they'd at
least dig into the discrepancies they find, rather than just reporting
numbers.
Seconded, I mean, wtf is this?
with the test profiles that stress the
On Thu, Jun 11, 2009 at 10:44 AM, Xose Vazquez
Perezxose.vazq...@gmail.com wrote:
then compile apache ; exec it and run ab:
$ ab -n 50 -c 100 http://localhost:8088/test.html
So did they use the phoronix-test-suite that is packaged as part of
fedora and used fedora packaged apache binaries?
Jeff Spaleta wrote:
On Thu, Jun 11, 2009 at 10:44 AM, Xose Vazquez
Perezxose.vazq...@gmail.com wrote:
then compile apache ; exec it and run ab:
$ ab -n 50 -c 100 http://localhost:8088/test.html
So did they use the phoronix-test-suite that is packaged as part of
fedora and used fedora
Eric Sandeen wrote:
I don't know much about apache but I bet a default ./configure winds up
with different builds depending on the build environment, which in this
case is probably dictated by whatever the default generic OS intall
contains.
And this is useful how? Geez.
Me, I'd rather
52 matches
Mail list logo