Re: [j-nsp] Slow RE path 20 x faster then PFE path
--- Begin Message --- Hello, Well, my first advice - don't use interface-style service-sets until You 100% understand what You are actually doing. Just don't. Second - don't try to mimic SRX' NAPT-to-interface-address translation feature on MX with inline NAT, it is not supported, albeit technically possible and very complex. Just don't. Third - don't tinker with static routes to next-table and similar stuff in conjunction with inline services. Fourth - use nexthop-style service-sets with both ends of SI- IFL pair in different routing-instances. It is the most straightforward inline NAT config possible. Hopefully that's enough to get You started , and without Your config I have no other ideas to share, perhaps others can chime in. Thanks Alex -- Original Message -- From: "Robert Raszuk" To: "Alexander Arseniev" Cc: "Juniper List" Sent: 24/03/2020 08:24:36 Subject: Re: Re[2]: [j-nsp] Slow RE path 20 x faster then PFE path Yes NAT is configured there as I indicated via presence of si- phantom load ... Having NAT there is not my idea though :). But sorry can not share the config. If you could shed some more light on your comment how to properly configure it and what to avoid I think it may be very useful for many folks on this list. Many thx, R. On Tue, Mar 24, 2020 at 5:00 AM Alexander Arseniev wrote: Hello, Another interesting observation is that show command indicated services inline input traffic over 33 Mpps zero output while total coming to the box was at that time 1 Mpps Do You have inline NAT configured on this box? Is it possible to share the config please? It is quite easy to loop traffic with NAT (inline or not) and while looped inside same box, TTL does not get decremented so You end up with eternal PFE saturation. Thanks Alex--- End Message --- ___ juniper-nsp mailing list juniper-nsp@puck.nether.net https://puck.nether.net/mailman/listinfo/juniper-nsp
Re: [j-nsp] Slow RE path 20 x faster then PFE path
You can confirm PPE load by: RMPC0(r24.labxtx01.us.bb-re0 vty)# show xl-asic 0 npu_stats NPU Stats Dump for FPC0:NPU0 Global NPU Utilization: 0. (xl or lu, depending on platform) Also piping output to file and aggregating: 'show xl-asic 0 ppe cntx' can be very useful to see what the PPEs are doing, particularly when you have datapoint from working and non-working box, aggregation how many PPEs contexts are in which Ucode address will be a dead give-away. I was recently troubleshooting issue where on some reboots PPS performance is good, some reboots less good, and looking at the PPE contexts was illuminating for that. I suspect if this is PPE spending time on NAT thing, then on bad box global NPU load should be high as well as context uCode address distribution to be widly different (good box mosty sleeping). On Tue, 24 Mar 2020 at 10:31, Robert Raszuk wrote: > > Yes NAT is configured there as I indicated via presence of si- phantom load > ... Having NAT there is not my idea though :). But sorry can not share the > config. > > If you could shed some more light on your comment how to properly configure > it and what to avoid I think it may be very useful for many folks on this > list. > > Many thx, > R. > > > > On Tue, Mar 24, 2020 at 5:00 AM Alexander Arseniev > wrote: > > > Hello, > > > > > > > > Another interesting observation is that show command indicated services > > inline input traffic over 33 Mpps zero output while total coming to the box > > was at that time 1 Mpps > > > > > > Do You have inline NAT configured on this box? Is it possible to share the > > config please? > > It is quite easy to loop traffic with NAT (inline or not) and while looped > > inside same box, > > TTL does not get decremented so You end up with eternal PFE saturation. > > > > Thanks > > Alex > > > ___ > juniper-nsp mailing list juniper-nsp@puck.nether.net > https://puck.nether.net/mailman/listinfo/juniper-nsp -- ++ytti ___ juniper-nsp mailing list juniper-nsp@puck.nether.net https://puck.nether.net/mailman/listinfo/juniper-nsp
Re: [j-nsp] Slow RE path 20 x faster then PFE path
Yes NAT is configured there as I indicated via presence of si- phantom load ... Having NAT there is not my idea though :). But sorry can not share the config. If you could shed some more light on your comment how to properly configure it and what to avoid I think it may be very useful for many folks on this list. Many thx, R. On Tue, Mar 24, 2020 at 5:00 AM Alexander Arseniev wrote: > Hello, > > > > Another interesting observation is that show command indicated services > inline input traffic over 33 Mpps zero output while total coming to the box > was at that time 1 Mpps > > > Do You have inline NAT configured on this box? Is it possible to share the > config please? > It is quite easy to loop traffic with NAT (inline or not) and while looped > inside same box, > TTL does not get decremented so You end up with eternal PFE saturation. > > Thanks > Alex > ___ juniper-nsp mailing list juniper-nsp@puck.nether.net https://puck.nether.net/mailman/listinfo/juniper-nsp