[j-nsp] packet checksum error in input fab_stream

[Saku Ytti]

Hey,

Over fabric you have 1 stream per NPU_ingress to NPU_egress per QoS.
Usually just 2 QoS classes, I think maybe in ICHIP just 1 class. At
any rate as the stream numbers are so small, these are low priority
streams even in Trio.
It is telling you that traffic coming to egress ICHIPs in those FPCs,
are seeing mangled data coming from fabric, from specific ingress NPU.

So likely either your fabric has broken memory, or more probably your
ingress NPU is has bad memory, If this issue persists, I'd swap the
egress FPC, if it still persists, fabric. Or you could first ensure
that each FPC is getting sufficient cooling, ensure intake isn't
blocked, filters are clean, pop isn't sauna.

It definitely has effect, you just dropped some packets. Drop rate
maybe very very small, so unless you have good instrumentations or
customers have, it might be something with 0 business impact, but
might become more pathological over tie.


On 1 August 2017 at 05:22, Joerg Staedele <js at tnib.de> wrote:
> Hi Guys,
>
> i get several messages like:
>
> Aug  1 03:34:13 xxx fpc0 ICHIP(3)_REG_ERR:packet checksum error in input fab_stream 4 pfe_id 128
> Aug  1 03:34:19 xxx fpc2 ICHIP(0)_REG_ERR:packet checksum error in input fab_stream 7 pfe_id 128
> Aug  1 03:36:24 xxx fpc7 ICHIP(3)_REG_ERR:packet checksum error in input fab_stream 6 pfe_id 128
> Aug  1 03:36:24 xxx fpc7 ICHIP(3)_REG_ERR:packet checksum error in input fab_stream 17 pfe_id 128
>
> JunOS 14.1R8 on MX960 (with dual RE-2000)
>
> It does not seem to have any effect.
>
> Anyone knows what exactly it means?
>
> Kind regards
>  Joerg
> _______________________________________________
> juniper-nsp mailing list juniper-nsp at puck.nether.net
> https://puck.nether.net/mailman/listinfo/juniper-nsp



-- 
  ++ytti