[nsp] Too much memory fragmentation on a GSR with 12.0(21)S5

[Gert Doering]

Hi,

On Thu, Mar 27, 2003 at 06:14:09PM +0800, Peter NOBLE wrote:
> 1. Does anyone of you guys see such an issue from 18S to 21S? ( Cisco was 
> claiming the new algorithm came in in 18S or something. )

This is a 7200 with 12.0(21)S6 and 160 Mbyte:

Cisco-M-XII uptime is 4 weeks, 1 day, 12 hours, 53 minutes
cisco 7206VXR (NPE300) processor with 155648K/40960K bytes of memory.
...
               Head   Total(b)    Used(b)    Free(b)  Lowest(b) Largest(b)
Processor  613D70E0   138579744   117482100   21097644   17839952 13347988

and this is one with (21)S5 and 256 Mbyte:

Cisco-M uptime is 4 weeks, 13 hours, 59 minutes
cisco 7206VXR (NPE400) processor with 245760K/16384K bytes of memory.
...
               Head   Total(b)    Used(b)    Free(b)  Lowest(b) Largest(b)
Processor  613D3040   230870976   123977480   106893496   83315004 78939492

so it's definitely not as bad as for your GSR.

[..]
> 4. The TAC said the memory will not be an issue in our case. Why do they 
> need to enhance the memory allocation arrangement if there is no problem at 
> all?

Don't ask these questions.... <:-o

gert
-- 
USENET is *not* the non-clickable part of WWW!
                                                           //www.muc.de/~gert/
Gert Doering - Munich, Germany                             gert at greenie.muc.de
fax: +49-89-35655025                        gert.doering at physik.tu-muenchen.de