Description

Customer uses MX-SPC3 to provide CGNAT for DHCP end clients. Those DHCP end clients having their corresponding static gateway interfaces configured on the MX.

 

They faced an issue with the SPC3 card where its stopped being able to do translations and is dropping traffic after migrating more than 60000 end clients.

 

From syslog, below can be seen:

 

Jul 18 21:20:14.449 re0 (FPC Slot 2, PIC Slot 0) usp_ipc_client_open: failed to create client socket: Resource temporarily unavailable (11)

Jul 18 21:20:16.282 re0 (FPC Slot 2, PIC Slot 0) usp_ipc_client_open: failed to create client socket: Resource temporarily unavailable (11)

Jul 18 21:23:16.785 re0 (FPC Slot 2, PIC Slot 0) usp_ipc_client_open: failed to create client socket: Connection refused (111)

Jul 18 21:23:16.785 re0 (FPC Slot 2, PIC Slot 0) usp_ipc_client_open: failed to create client socket: Operation now in progress (115)

 

Symptoms

MX-SPC3 PICs failed to carry traffic and syslog like "(FPC Slot 8, PIC Slot 1) usp_ipc_client_open: failed to create client socket: Resource temporarily unavailable (11)" can be seen

Solution

Customer has static interfaces configured to provide the gateway for the end DHCP clients. Example of interface configure as this:

  ae10 {

    unit 10000 {

      description STAG3206CTAG1;

      vlan-tags outer 3206 inner 1;

      family inet {

        mtu 1600;

        address 10.187.160.1/30;

      }

    }

     

  set interfaces ge-0/0/0 gigether-options 802.3ad ae10

   

So, for each subinerface, there will have 2 ifls being installed in the PFE ukernel, ie, ae10.10000 and ge-0/0/0.10000.

 

When in problem state, either PIC0 or PIC1 will not be accessible, and the kernel memory is nearly 100%.

 

{master}

labroot@re0> start shell

% vty fpc2.pic0

<<<<<<<<<<<<<<<<<< pic0 no response now

 

% vty fpc2.pic1

 

 

TOR platform (2299 Mhz Intel(R) Xeon(R) processor, 0MB memory, 16384KB flash)

 

FLOWD_SPC3-2.1(vty)# show heap

ID    Base    Total(b)    Free(b)    Used(b)   %  Name

-- ----------  -----------  -----------  ----------- ---  -----------

0 7f63c0000000  1073741824   10343552  1063398272   99 Kernel

           ^^^^^^^^ Only 1G MB was assiged, which is too less

1 7f6a06620000  28883943424  7163653056  21720290368  75 User

 

FLOWD_SPC3-2.1(vty)# show ifl sum

IFL subsystem information

ifl count    = 64344

ifl up count  = 64278

 

Here is the same show output from MPC7E in the same box:

SMPC10(re0 vty)# show ifl summary   

IFL subsystem information

ifl count    = 64358

ifl up count  = 64292

 

SMPC10(re0 vty)# show heap

ID    Base   Total(b)    Free(b)    Used(b)  %  Name

-- ----------  -----------  -----------  ----------- ---  -----------

0  31338000  3321884648  2617089960   704794688  21 Kernel

          <<<<<<<<<<<< 3.3GB, and 21% load only

1  1c000000   234881024   183254640   51626384  21 DMA

2  18dfffe0   52428784   52428784       0  0 Blob

3  1d3e1000   21221376   21219880     1496  0 Turbotx

 

 

This is a day-1 design issue, Juniper engineering team is working on the solution.

As a wokaround, customer can either reduce the static routing interface scale, or change to follow the Junos Subscriber-Management way to use dynamic interfaces for those end clients.

 

Modification History

2024-09-19 : Article Created