[j-nsp] strange packet loss without impact

[Matthias Brumm]

Hello!

show pfe statistics traffic is the first command, showing some errors:

Packet Forwarding Engine hardware discard statistics:
    Timeout                    :                    0
    Truncated key              :                    0
    Bits to test               :                    0
    Data error                 :                    0
    Stack underflow            :                    0
    Stack overflow             :                    0
    Normal discard             :            557491798
    Extended discard           :                    0
    Invalid interface          :                    0
    Info cell drops            :                    0
    Fabric drops               :                    0

Is "Normal discard" an error or something "Normal", as the name would say.

Matthias

2011/7/4 Christian <cdebalorre at neotelecoms.com>

> **
>
> If in doubt run show system processes summary to check for busy process
> during your peak time.
> Also you can have some interesting stats with a show pfe statistics traffic
>
> Christian
>
>
> Le 04/07/2011 15:33, Matthias Brumm a écrit :
>
> Hello!
>
> At the moment I am monitoring it with top on UNIX shell, do you have
> another suggestion? In top this process is idleing.
>
> Regards,
>
> Matthias
>
> 2011/7/4 Christian <cdebalorre at neotelecoms.com>
>
> Hi,
> Try to monitor the fwdd process - when running high it causes packet to
> drop on these pc's.
>
> Christian
>
>
> Le 04/07/2011 13:11, Adam Leff a écrit :
>
>  I realize this will sound silly, but have you checked for half-duplex
> on your interfaces?
>
> Those onboard J6350 interfaces are actually 10/100/1000, so if you
> don't have the speed and link-mode hardcoded,  do a show interfaces
> extensive ge-0/0/# and check the link partner section to ensure you're
> running full-duplex.
>
> Adam
>
> On Jul 4, 2011, at 7:01, Matthias Brumm<matthias at brumm.net>  wrote:
>
>  Hello!
>
> Since some weeks now, we have a strange packet loss on one of our edge
> locations.
>
> A few days ago an IX informed us about packet loss on our router. The
> router
> in place is a J6350. We have a 1 Gig line to us and two 1 Gig lines to some
> uplinks. Every communication goes through a 1 Gig copper link to a ProCurve
> 2810-24G. So the external links are connected to the switch and the switch
> via one cable with the router.
>
> The packet loss is strange, because:
>
> 1. In smokeping during the busy hours of the day, there are losses of about
> 5%
> 2. From my workstation I get packet loss of about 10 up to 50%
> 3. There are no errors on the switch or router interface (except i.e. VLAN
> errors)
> 4. no customers have reported any problems. But there are many customers
> relying on real time communication (VoIP/RDP)
> 5. The switch port with the router is showing maximum 200 Mbit
> 6. The router is showing 20% real-time threads
>
> According to the datasheet the J-Series should be able to deliver this
> performance easily. Or are the onboard Gig-Interfaces the problem? Of
> course
> I know, that this physical configuration is a bad idea, and I will change
> is
> very soon to ease the load on this particular port.
>
> Any other ideas?
>
> Regards,
>
> Matthias
> ______________________________ _________________
> juniper-nsp mailing list juniper-nsp at puck.nether.net
> https://puck.nether.net/ mailman/listinfo/juniper-nsp<https://puck.nether.net/mailman/listinfo/juniper-nsp>
>
> ______________________________ _________________
> juniper-nsp mailing list juniper-nsp at puck.nether.net
> https://puck.nether.net/ mailman/listinfo/juniper-nsp<https://puck.nether.net/mailman/listinfo/juniper-nsp>
>
> ______________________________ _________________
> juniper-nsp mailing list juniper-nsp at puck.nether.net
> https://puck.nether.net/ mailman/listinfo/juniper-nsp<https://puck.nether.net/mailman/listinfo/juniper-nsp>
>
>
>