Re: mem_node memory usage in 2.x

From: Guido Serassio <guido.serassio@dont-contact.us>
Date: Tue, 22 Apr 2008 21:58:34 +0200

Hi Adrian,

At 18:58 22/04/2008, Adrian Chadd wrote:

>In any case, Guido's response of "its the number of pages!" explained the
>base discrepancy. The unfortunate issue here is that "pagesize" can
>be variable
>and one would need to find the system/process' pagesize (and hope
>its constant!)
>to multiply that number by to get an accurate result.
>

As I know, the pagesize is usually related to the processor architecture.
On Windows is always 4096 bytes on x86 processor while on old Alpha
processor was 8192 bytes. I don't know what is the value for 64 bit
application running on x64 or Itanium Windows.

On Sparc Solaris it seems that a variable size at process level is
supported: http://blogs.sun.com/d/entry/using_large_dtlb_page_sizes

So, it's correct to expect different and sometimes unexpected values
from rusage().

Regards

Guido

-
========================================================
Guido Serassio
Acme Consulting S.r.l. - Microsoft Certified Partner
Via Lucia Savarino, 1 10098 - Rivoli (TO) - ITALY
Tel. : +39.011.9530135 Fax. : +39.011.9781115
Email: guido.serassio@acmeconsulting.it
WWW: http://www.acmeconsulting.it/
Received on Tue Apr 22 2008 - 19:59:24 MDT

This archive was generated by hypermail 2.2.0 : Wed Apr 30 2008 - 12:00:07 MDT