Re: [ECOS] TCP/IP stack performance

[Jürgen Lambrecht <J dot Lambrecht at televic dot com>]

The TCP/IP stack uses threads with the priorities listed below. Maybe 
you use the same priorities in your application?


     1.12 ecos default priorities

Priorities go from 0 to 31

*priority name* 	*default* 	*own* 	*stack name* 	*default* 	*own*
CYGSEM_KERNEL_SYNCH_MUTEX_PRIORITY_INVERSION_PROTOCOL_DEFAULT_PRIORITY 	0 
	  	  	  	 
 	  	  	  	  	 
CYGPKG_NET_FAST_THREAD_PRIORITY 	6 	~ 	  	  	 
CYGPKG_NET_THREAD_PRIORITY 	7 	~ 	  	  	 
CYGPKG_NET_DHCP_THREAD_PRIORITY 	8 	  	  	  	 
CYGINT_NET_IPV6_ROUTING_THREAD_PRIORITY 	8 	  	  	  	 
CYGNUM_LIBC_MAIN_THREAD_PRIORITY  	10  	8 
CYGNUM_LIBC_MAIN_DEFAULT_STACK_SIZE 	8192 	~
CYGPKG_NET_TFTPD_THREAD_PRIORITY 	10 	9 
CYGPKG_NET_TFTPD_THREAD_STACK_SIZE 	3948 	4096
 	  	  	CYGNUM_HAL_COMMON_INTERRUPTS_STACK_SIZE 	4096 	~
 	  	  	  	  	 
 	  	  	  	  	 
CYGNUM_JFFS2_GC_THREAD_PRIORITY 	30 	  	  	  	 
idle thread 	31 	  	  	  	 



Neeraja wrote:

> Hi,
>       I am working on AT91RM9200 board.  The TCP/IP stack is working
> perfectly fine with this board.
>      But the problem is that at times the ping reply is taking very
> long(some 3 to 4 seconds) which usually will be only 2 or 3ms and is also
> timing out in between when it is taking long time to reply back. But the
> good thing is that
> the TCP/IP stack is not dying completely and is slowly resuming back to
> normal after some time( that is it is getting the ping reply within 2 
t0 3
> ms).
>       Why is this happening and is there any way that the performance 
can be
> improved?
>      Anyone suggestions regrading this could be of great help.
>
> Thanks & Regards,
> Neeraja.

--
Jürgen Lambrecht
R&D Engineer
Televic Transport Systems
http://www.televic.com
Televic NV / SA (main office)     
Leo Bekaertlaan 1
B-8870 Izegem
Tel: +32 (0)51 303045
Fax: +32 (0)51 310670


--
Before posting, please read the FAQ: http://ecos.sourceware.org/fom/ecos
and search the list archive: http://ecos.sourceware.org/ml/ecos-discuss