Re: Speed v Version

2011-06-07 Thread Matt Sergeant
Dave Hodgkinson wrote: My BBC sandbox is sane at least: $ uname -p x86_64 Shouldn't a BBC report 6502? ;-) __ This email has been scanned by the MessageLabs Email Security System. For more information please visit

Re: Speed v Version

2011-06-03 Thread Toby Wintermute
On 1 June 2011 18:46, Dirk Koopman d...@tobit.co.uk wrote: I contemplating providing encouragement to a customer to upgrade from 5.8.7 to something more modern. One of the overriding issues is speed. The customer is fixated with speed. Unfortunately one of the major things the customer's

Re: Speed v Version

2011-06-03 Thread Nigel Metheringham
On 3 Jun 2011, at 08:28, Toby Wintermute wrote: 1) Are they running old Red Hat or CentOS versions? I ask because the Perl shipped on those was, for quite a long time, very, very broken due to a vendor patch that made bless() take 1000x longer than it should. In that case, just using a

Re: Speed v Version

2011-06-03 Thread Dirk Koopman
On 03/06/11 09:28, Nigel Metheringham wrote: On 3 Jun 2011, at 08:28, Toby Wintermute wrote: 1) Are they running old Red Hat or CentOS versions? I ask because the Perl shipped on those was, for quite a long time, very, very broken due to a vendor patch that made bless() take 1000x longer than

Re: Speed v Version

2011-06-03 Thread Dave Hodgkinson
On 3 Jun 2011, at 10:21, Dirk Koopman wrote: Thank you all for your suggestions. I will see whether I can persuade them to upgrade. Which is almost certainly Not The Problem.

Re: Speed v Version

2011-06-03 Thread Dirk Koopman
On 03/06/11 10:56, Dave Hodgkinson wrote: On 3 Jun 2011, at 10:21, Dirk Koopman wrote: Thank you all for your suggestions. I will see whether I can persuade them to upgrade. Which is almost certainly Not The Problem. I agree it is Not The Problem. But increased speed is a killer hook

Re: Speed v Version

2011-06-02 Thread Andrew Beattie
On 01/06/2011 23:10, Dave Hodgkinson wrote: With added greengrocer's! FTFY. Andrew

Speed v Version

2011-06-01 Thread Dirk Koopman
I contemplating providing encouragement to a customer to upgrade from 5.8.7 to something more modern. One of the overriding issues is speed. The customer is fixated with speed. Unfortunately one of the major things the customer's clients do is replicate their ISAM data into databases, usually

Re: Speed v Version

2011-06-01 Thread Dave Hodgkinson
On 1 Jun 2011, at 09:46, Dirk Koopman wrote: I contemplating providing encouragement to a customer to upgrade from 5.8.7 to something more modern. One of the overriding issues is speed. The customer is fixated with speed. Unfortunately one of the major things the customer's clients do is

Re: Speed v Version

2011-06-01 Thread Nicholas Clark
On Wed, Jun 01, 2011 at 11:12:48AM +0100, Dave Hodgkinson wrote: On 1 Jun 2011, at 09:46, Dirk Koopman wrote: I contemplating providing encouragement to a customer to upgrade from 5.8.7 to something more modern. One of the overriding issues is speed. The customer is fixated with

Re: Speed v Version

2011-06-01 Thread Nicholas Clark
On Wed, Jun 01, 2011 at 02:00:14PM +0100, Dave Hodgkinson wrote: On 1 Jun 2011, at 11:57, Dave Lambley wrote: My former employer did some benchmarking of different versions of Perl, used inside mod_perl. Perl 5.10.x proved faster than 5.8.x, and 64 bit was faster than 32. This was

Re: Speed v Version

2011-06-01 Thread Dave Hodgkinson
On 1 Jun 2011, at 14:13, Nicholas Clark wrote: On Wed, Jun 01, 2011 at 02:00:14PM +0100, Dave Hodgkinson wrote: On 1 Jun 2011, at 11:57, Dave Lambley wrote: My former employer did some benchmarking of different versions of Perl, used inside mod_perl. Perl 5.10.x proved faster than

Re: Speed v Version

2011-06-01 Thread Dominic Thoreau
On 1 June 2011 17:12, Dave Hodgkinson daveh...@gmail.com wrote: On 1 Jun 2011, at 14:13, Nicholas Clark wrote: On Wed, Jun 01, 2011 at 02:00:14PM +0100, Dave Hodgkinson wrote: On 1 Jun 2011, at 11:57, Dave Lambley wrote: My former employer did some benchmarking of different versions of

Re: Speed v Version

2011-06-01 Thread Dave Hodgkinson
On 1 Jun 2011, at 17:26, Dominic Thoreau wrote: On 1 June 2011 17:12, Dave Hodgkinson daveh...@gmail.com wrote: On 1 Jun 2011, at 14:13, Nicholas Clark wrote: On Wed, Jun 01, 2011 at 02:00:14PM +0100, Dave Hodgkinson wrote: On 1 Jun 2011, at 11:57, Dave Lambley wrote: My former

Re: Speed v Version

2011-06-01 Thread Dave Hodgkinson
On 1 Jun 2011, at 14:13, Nicholas Clark wrote: but then as Dave says, changing from x86 to x86_64 halves the amount of (non-character, non floating point) stuff you can get in the same CPU's caches, and in the same machine's RAM. This kinda blew $client out of the water who have leaky code

Re: Speed v Version

2011-06-01 Thread Chris Devers
On Wed, Jun 1, 2011 at 12:12 PM, Dave Hodgkinson daveh...@gmail.com wrote: Also note on my perfectly 64 bit macbook pro: $ uname -p i386 On Mac OS X 10.6, the system boots to the 32-bit kernel by default. http://support.apple.com/kb/HT4287 http://support.apple.com/kb/HT3773 You may get a

Re: Speed v Version

2011-06-01 Thread Dave Hodgkinson
On 1 Jun 2011, at 17:46, Chris Devers wrote: On Wed, Jun 1, 2011 at 12:12 PM, Dave Hodgkinson daveh...@gmail.com wrote: Also note on my perfectly 64 bit macbook pro: $ uname -p i386 On Mac OS X 10.6, the system boots to the 32-bit kernel by default.

Re: Speed v Version

2011-06-01 Thread Alexander Clouter
Dominic Thoreau domi...@thoreau-online.net wrote: My former employer did some benchmarking of different versions of Perl, used inside mod_perl.  Perl 5.10.x proved faster than 5.8.x, and 64 bit was faster than 32.  This was for a CPU bound application though, which it sounds like your's is

Re: Speed v Version

2011-06-01 Thread Dave Hodgkinson
On 1 Jun 2011, at 21:29, Alexander Clouter wrote: Run's Perl just fine that box[1]... With added greengrocers!