P
Pablo S
Hi there Perl folks, I am comparing performance on a new server
platform I am demoing and wanted to share this weird thing:
It started out when I noticed some expensive local db calls on my
mod_perl box were taking a while on the new, slightly beefier system.
They are the same accept for:
OLD system:
(a celeron 1.8 w/ 512SDRAM linux 2.4 running perl 5.6.1,
postgresql-7.2.1-5 with a perl web db on Apache/1.3.23 mod_perl 1.26
and dbi 1.37 with peristent db connections via apache:dbi. ) this
thing runs awesome, as in, it is FAST, for what it does.
NEW system:
(a p4 2.6 w/ 512DDR266 running the same web app via perl 5.8.3 on
fedora core 2 linux 2.6 postgresql-7.4.2-1 w/ Apache/2.0.49 &
mod_perl/1.99_12 & apache:dbi.) it, at this point, sucks and is
noticably slower to load pages, pull from DBI, and even do simple
loops.
Httpd.conf on apache2.0
Alias /cgi-bin /var/www/cgi-bin
<Directory /var/www/cgi-bin>
SetHandler perl-script
PerlResponseHandler ModPerl::Registry
PerlOptions +ParseHeaders
Options +ExecCGI
</Directory>
and on 1.3
Alias /cgi-bin/ "/home/httpd/cgi-bin/"
<Location /cgi-bin>
SetHandler perl-script
PerlHandler Apache::Registry
Options ExecCGI
allow from all
PerlSendHeader On
</Location>
I have one page where I run many queries. On the old server, it loads
in 1.5 seconds. On the new server, with the same data, it takes 6. I
am trying to find out why. After going nuts all over Pg, apache:dbi,
and all orders of other stuff I had both servers run your basic
my $i=10000000;
while ($i) {
$i--;
}
print "done!";
thing. The 1.8 is done in 2 seconds, the 2.4 takes almost 8.
Is apache the culprit? I was running all over looking at the database
I was talking to, etc etc, but heres a simple loop taking about 3x as
long.
Thank you for your interest!! Any comments welcome.
platform I am demoing and wanted to share this weird thing:
It started out when I noticed some expensive local db calls on my
mod_perl box were taking a while on the new, slightly beefier system.
They are the same accept for:
OLD system:
(a celeron 1.8 w/ 512SDRAM linux 2.4 running perl 5.6.1,
postgresql-7.2.1-5 with a perl web db on Apache/1.3.23 mod_perl 1.26
and dbi 1.37 with peristent db connections via apache:dbi. ) this
thing runs awesome, as in, it is FAST, for what it does.
NEW system:
(a p4 2.6 w/ 512DDR266 running the same web app via perl 5.8.3 on
fedora core 2 linux 2.6 postgresql-7.4.2-1 w/ Apache/2.0.49 &
mod_perl/1.99_12 & apache:dbi.) it, at this point, sucks and is
noticably slower to load pages, pull from DBI, and even do simple
loops.
Httpd.conf on apache2.0
Alias /cgi-bin /var/www/cgi-bin
<Directory /var/www/cgi-bin>
SetHandler perl-script
PerlResponseHandler ModPerl::Registry
PerlOptions +ParseHeaders
Options +ExecCGI
</Directory>
and on 1.3
Alias /cgi-bin/ "/home/httpd/cgi-bin/"
<Location /cgi-bin>
SetHandler perl-script
PerlHandler Apache::Registry
Options ExecCGI
allow from all
PerlSendHeader On
</Location>
I have one page where I run many queries. On the old server, it loads
in 1.5 seconds. On the new server, with the same data, it takes 6. I
am trying to find out why. After going nuts all over Pg, apache:dbi,
and all orders of other stuff I had both servers run your basic
my $i=10000000;
while ($i) {
$i--;
}
print "done!";
thing. The 1.8 is done in 2 seconds, the 2.4 takes almost 8.
Is apache the culprit? I was running all over looking at the database
I was talking to, etc etc, but heres a simple loop taking about 3x as
long.
Thank you for your interest!! Any comments welcome.