Jeff Spaleta wrote:
On Thu, Jun 11, 2009 at 9:26 AM, Xose Vazquez
Perez<xose.vazquez(a)gmail.com> wrote:
> 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=article&item=fedora11_ubuntu904...
Why did you cherry pick the bad news instead of the summary?
I am not interested when Fedora is doing right.
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 from selinux related latency? Something else in
userspace slowing Apache down. I've no idea. I can't imagine its
compiler related options on the Apache binaries.
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...
then compile apache ; exec it and run ab:
$ ab -n 500000 -c 100
http://localhost:8088/test.html
get more info doing "find . | grep apache" inside phoronix-test-suite dir
To clone Phoronix apache test:
$ wget
http://www.phoronix.net/downloads/phoronix-test-suite/releases/developmen...
$ tar xvf phoronix-test-suite-2.0.0a3.tar.gz
$ cd phoronix-test-suite
$ ./phoronix-test-suite install apache
$ ./phoronix-test-suite run apache
wait...
[1]
http://www.phoronix-test-suite.com/
--
Polycommander, Erkowit, Urquiola, Andros Patria, Cason, Aegean Sea, Prestige, ...