A lot of packets lost by ping

classic Classic list List threaded Threaded
3 messages Options
Reply | Threaded
Open this post in threaded view
|

A lot of packets lost by ping

Amir Bukhari-2
I have got lwip to work with uCOS-II/MPC5200 (using Bestcomm DMA), but I
have some performance issue.

When I ping my uC from a another computer I got response but slowly here is
some of this output

################
bukhari@data /tftpboot> ping seska
PING seska (141.21.7.245) 56(84) bytes of data.
64 bytes from seska (141.21.7.245): icmp_seq=3 ttl=64 time=0.234 ms
64 bytes from seska (141.21.7.245): icmp_seq=7 ttl=64 time=0.230 ms
64 bytes from seska (141.21.7.245): icmp_seq=9 ttl=64 time=0.232 ms
64 bytes from seska (141.21.7.245): icmp_seq=13 ttl=64 time=0.232 ms
64 bytes from seska (141.21.7.245): icmp_seq=14 ttl=64 time=0.234 ms
64 bytes from seska (141.21.7.245): icmp_seq=15 ttl=64 time=0.232 ms
64 bytes from seska (141.21.7.245): icmp_seq=16 ttl=64 time=0.234 ms
64 bytes from seska (141.21.7.245): icmp_seq=18 ttl=64 time=0.228 ms
64 bytes from seska (141.21.7.245): icmp_seq=19 ttl=64 time=0.233 ms
64 bytes from seska (141.21.7.245): icmp_seq=20 ttl=64 time=0.246 ms
64 bytes from seska (141.21.7.245): icmp_seq=29 ttl=64 time=0.230 ms
64 bytes from seska (141.21.7.245): icmp_seq=33 ttl=64 time=0.228 ms
64 bytes from seska (141.21.7.245): icmp_seq=34 ttl=64 time=0.232 ms
64 bytes from seska (141.21.7.245): icmp_seq=37 ttl=64 time=0.230 ms
64 bytes from seska (141.21.7.245): icmp_seq=39 ttl=64 time=0.233 ms
64 bytes from seska (141.21.7.245): icmp_seq=40 ttl=64 time=0.232 ms
64 bytes from seska (141.21.7.245): icmp_seq=45 ttl=64 time=0.246 ms
64 bytes from seska (141.21.7.245): icmp_seq=47 ttl=64 time=0.230 ms
64 bytes from seska (141.21.7.245): icmp_seq=48 ttl=64 time=0.232 ms

--- seska ping statistics ---
48 packets transmitted, 19 received, 60% packet loss, time 47057ms
################

I have only two process, one is dummy and the second is the receive task,
which get activated when a packet received by the interrupt handler. I have
no any lwip TCP connection active. Just I activated my network.

As you have more experience with LWIP, you could point for experience about
increasing performance!

-Amir


_______________________________________________
lwip-users mailing list
[hidden email]
http://lists.nongnu.org/mailman/listinfo/lwip-users
Reply | Threaded
Open this post in threaded view
|

RE: A lot of packets lost by ping

ming-2
Hi,

Have you tried to connect it to you computer directly with a cross-over
cable ?

It's necessary to make sure that the trouble's on the MPC board, I
think.

--
************************************************************************
********
Zeng, Ming
NIKHEF,  Kruislaan 409
1098 SJ Amsterdam - The Netherlands
email: [hidden email]
Tel.   31 (0)20 592 2147
Mobile 31 (0)6 4351 5283
************************************************************************
********



-----Original Message-----
From: lwip-users-bounces+ming=[hidden email]
[mailto:lwip-users-bounces+ming=[hidden email]] On Behalf Of Amir
Bukhari
Sent: Friday, November 04, 2005 11:45 AM
To: [hidden email]
Subject: [lwip-users] A lot of packets lost by ping


I have got lwip to work with uCOS-II/MPC5200 (using Bestcomm DMA), but I
have some performance issue.

When I ping my uC from a another computer I got response but slowly here
is some of this output

################
bukhari@data /tftpboot> ping seska
PING seska (141.21.7.245) 56(84) bytes of data.
64 bytes from seska (141.21.7.245): icmp_seq=3 ttl=64 time=0.234 ms 64
bytes from seska (141.21.7.245): icmp_seq=7 ttl=64 time=0.230 ms 64
bytes from seska (141.21.7.245): icmp_seq=9 ttl=64 time=0.232 ms 64
bytes from seska (141.21.7.245): icmp_seq=13 ttl=64 time=0.232 ms 64
bytes from seska (141.21.7.245): icmp_seq=14 ttl=64 time=0.234 ms 64
bytes from seska (141.21.7.245): icmp_seq=15 ttl=64 time=0.232 ms 64
bytes from seska (141.21.7.245): icmp_seq=16 ttl=64 time=0.234 ms 64
bytes from seska (141.21.7.245): icmp_seq=18 ttl=64 time=0.228 ms 64
bytes from seska (141.21.7.245): icmp_seq=19 ttl=64 time=0.233 ms 64
bytes from seska (141.21.7.245): icmp_seq=20 ttl=64 time=0.246 ms 64
bytes from seska (141.21.7.245): icmp_seq=29 ttl=64 time=0.230 ms 64
bytes from seska (141.21.7.245): icmp_seq=33 ttl=64 time=0.228 ms 64
bytes from seska (141.21.7.245): icmp_seq=34 ttl=64 time=0.232 ms 64
bytes from seska (141.21.7.245): icmp_seq=37 ttl=64 time=0.230 ms 64
bytes from seska (141.21.7.245): icmp_seq=39 ttl=64 time=0.233 ms 64
bytes from seska (141.21.7.245): icmp_seq=40 ttl=64 time=0.232 ms 64
bytes from seska (141.21.7.245): icmp_seq=45 ttl=64 time=0.246 ms 64
bytes from seska (141.21.7.245): icmp_seq=47 ttl=64 time=0.230 ms 64
bytes from seska (141.21.7.245): icmp_seq=48 ttl=64 time=0.232 ms

--- seska ping statistics ---
48 packets transmitted, 19 received, 60% packet loss, time 47057ms
################

I have only two process, one is dummy and the second is the receive
task, which get activated when a packet received by the interrupt
handler. I have no any lwip TCP connection active. Just I activated my
network.

As you have more experience with LWIP, you could point for experience
about increasing performance!

-Amir


_______________________________________________
lwip-users mailing list
[hidden email]
http://lists.nongnu.org/mailman/listinfo/lwip-users



_______________________________________________
lwip-users mailing list
[hidden email]
http://lists.nongnu.org/mailman/listinfo/lwip-users
Reply | Threaded
Open this post in threaded view
|

AW: A lot of packets lost by ping

Amir Bukhari-2

I have found that my Bestcomm image doesn't work correctly, I receive bad
currupted data, although the DMA doesn't give me any errors. I solved this
after I use the Bestcomm image from linuxppc (from www.denx.de) and now I
have no packets lost, I receive all correctly.

I have another question.
When I send a ping like following (linux):
Ping seska -s 2000

Windows and linux PC echo this request but lwip doesn't do that. My FEC fire
an error indicating sending a packet more than 1538. it seem that lwip
doesn't support this. Is that correct?

-Amir


-----Urspr√ľngliche Nachricht-----
Von: lwip-users-bounces+bukhari=[hidden email] im Auftrag von
[hidden email]
Gesendet: Fr 11/4/2005 1:05
An: 'Mailing list for lwIP users'
Betreff: RE: [lwip-users] A lot of packets lost by ping
 
Hi,

Have you tried to connect it to you computer directly with a cross-over
cable ?

It's necessary to make sure that the trouble's on the MPC board, I
think.

--
************************************************************************
********
Zeng, Ming
NIKHEF,  Kruislaan 409
1098 SJ Amsterdam - The Netherlands
email: [hidden email]
Tel.   31 (0)20 592 2147
Mobile 31 (0)6 4351 5283
************************************************************************
********



-----Original Message-----
From: lwip-users-bounces+ming=[hidden email]
[mailto:lwip-users-bounces+ming=[hidden email]] On Behalf Of Amir
Bukhari
Sent: Friday, November 04, 2005 11:45 AM
To: [hidden email]
Subject: [lwip-users] A lot of packets lost by ping


I have got lwip to work with uCOS-II/MPC5200 (using Bestcomm DMA), but I
have some performance issue.

When I ping my uC from a another computer I got response but slowly here
is some of this output

################
bukhari@data /tftpboot> ping seska
PING seska (141.21.7.245) 56(84) bytes of data.
64 bytes from seska (141.21.7.245): icmp_seq=3 ttl=64 time=0.234 ms 64
bytes from seska (141.21.7.245): icmp_seq=7 ttl=64 time=0.230 ms 64
bytes from seska (141.21.7.245): icmp_seq=9 ttl=64 time=0.232 ms 64
bytes from seska (141.21.7.245): icmp_seq=13 ttl=64 time=0.232 ms 64
bytes from seska (141.21.7.245): icmp_seq=14 ttl=64 time=0.234 ms 64
bytes from seska (141.21.7.245): icmp_seq=15 ttl=64 time=0.232 ms 64
bytes from seska (141.21.7.245): icmp_seq=16 ttl=64 time=0.234 ms 64
bytes from seska (141.21.7.245): icmp_seq=18 ttl=64 time=0.228 ms 64
bytes from seska (141.21.7.245): icmp_seq=19 ttl=64 time=0.233 ms 64
bytes from seska (141.21.7.245): icmp_seq=20 ttl=64 time=0.246 ms 64
bytes from seska (141.21.7.245): icmp_seq=29 ttl=64 time=0.230 ms 64
bytes from seska (141.21.7.245): icmp_seq=33 ttl=64 time=0.228 ms 64
bytes from seska (141.21.7.245): icmp_seq=34 ttl=64 time=0.232 ms 64
bytes from seska (141.21.7.245): icmp_seq=37 ttl=64 time=0.230 ms 64
bytes from seska (141.21.7.245): icmp_seq=39 ttl=64 time=0.233 ms 64
bytes from seska (141.21.7.245): icmp_seq=40 ttl=64 time=0.232 ms 64
bytes from seska (141.21.7.245): icmp_seq=45 ttl=64 time=0.246 ms 64
bytes from seska (141.21.7.245): icmp_seq=47 ttl=64 time=0.230 ms 64
bytes from seska (141.21.7.245): icmp_seq=48 ttl=64 time=0.232 ms

--- seska ping statistics ---
48 packets transmitted, 19 received, 60% packet loss, time 47057ms
################

I have only two process, one is dummy and the second is the receive
task, which get activated when a packet received by the interrupt
handler. I have no any lwip TCP connection active. Just I activated my
network.

As you have more experience with LWIP, you could point for experience
about increasing performance!

-Amir


_______________________________________________
lwip-users mailing list
[hidden email]
http://lists.nongnu.org/mailman/listinfo/lwip-users



_______________________________________________
lwip-users mailing list
[hidden email]
http://lists.nongnu.org/mailman/listinfo/lwip-users


_______________________________________________
lwip-users mailing list
[hidden email]
http://lists.nongnu.org/mailman/listinfo/lwip-users

winmail.dat (5K) Download Attachment