Switching

Expand all | Collapse all

High Latency ping times

  • 1.  High Latency ping times

    Posted 09-11-2012 12:13

    Everyone,

     

    Hi, I have an EX8208 and experiencing slow ping times when pinging the default gateway.  Ping times greater than 9ms is typical. 

     

    What makes it weirder is when I do a ping or tracert to one of the servers, it consistently gives me <1ms which is what it should be.  How can I improve the default gateway ping response?  Any help is greatly appreciate.

     

    Thanks.



  • 2.  RE: High Latency ping times

    Posted 09-11-2012 12:59
    Hi,

    It seems the serves are in a different L2 domain and the default-gateway has to do routing in hardware (depending on model/vendor) towards the servers.
    If both ping to the gateway AND first step in traceroute towards the server show high latency, then checking the CPU usage on the gateway might help.

    If that's not the case, please provide a simplified topology which mentions the 8208, the gateway and the server; and the output of traceroute to the server (please mark the corresponding hops on the diagram).

    Thanks,
    ankit


  • 3.  RE: High Latency ping times

    Posted 10-31-2012 10:51

    running version 12.2R1.8

     

    This is from a client to the gateway.  This is actually better than it was before but should be consistently <1ms.

     

    Pinging 192.168.1.1 with 32 bytes of data:

    Reply from 192.168.1.1: bytes=32 time=8ms TTL=64
    Reply from 192.168.1.1: bytes=32 time=2ms TTL=64
    Reply from 192.168.1.1: bytes=32 time=1ms TTL=64
    Reply from 192.168.1.1: bytes=32 time=2ms TTL=64

     

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

     

    This is from a client to one of the servers.  Consistently showing <1ms (except for the first try).

     

    Pinging 192.168.1.10 with 32 bytes of data:

    Reply from 192.168.1.10: bytes=32 time=6ms TTL=128
    Reply from 192.168.1.10: bytes=32 time<1ms TTL=128
    Reply from 192.168.1.10: bytes=32 time<1ms TTL=128
    Reply from 192.168.1.10: bytes=32 time<1ms TTL=128

     

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

     

    Here's the CPU state.  Not much load.

     

    admin@TA-Core-Switch-1> show chassis routing-engine
    Routing Engine status:
      Slot 0:
        Current state                  Master
        Election priority              Master (default)
        Temperature                 23 degrees C / 73 degrees F
        DRAM                      2048 MB
        Memory utilization          28 percent
        CPU utilization:
          User                       3 percent
          Background                 0 percent
          Kernel                     8 percent
          Interrupt                  1 percent
          Idle                      89 percent
        Model                          RE-EX8208
        Start time                    
        Uptime                         44 days, 21 hours, 57 minutes, 30 seconds
        Last reboot reason             Router rebooted after a normal shutdown.
        Load averages:                 1 minute   5 minute  15 minute
                                           0.16       0.08       0.03

     

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

     

    So this is just normal behavior?

     



  • 4.  RE: High Latency ping times

    Posted 10-31-2012 10:53

    Yes this is normal.  You will see this across the Junos family of products.



  • 5.  RE: High Latency ping times

    Posted 04-16-2017 00:28

    Hi can anyone halp me, How to reduce latency in Ex3300it running in JUNOS 15.1R5. its newly implemented device the latency is 2ms but i need to achive this as <1ms



  • 6.  RE: High Latency ping times

    Posted 04-16-2017 00:28

    Hi can anyone help me, How to reduce latency in Ex3300it running in JUNOS 15.1R5. its newly implemented device the latency is 2ms but i need to achive this as <1ms



  • 7.  RE: High Latency ping times

    Posted 04-17-2017 01:13

    Seems like the answer is no. I would suggest opening a ticket with Juniper, but it seems like they already addressed it. A quick Google search shows similar answers. This is a result of the design of Juniper platforms. 

    https://kb.juniper.net/InfoCenter/index?page=content&id=KB28157

     

    [Junos OS] ICMP Ping Showing Latency for Host Inbound and Outbound traffic

     


    SUMMARY:

    This article discusses latency in ICMP pings when a Junos OS platform is responsible for ICMP echo reply.

    SYMPTOMS:

    An ICMP ping shows intermittent latency on a directly connected link with the default Junos Class of Service (CoS) configuration.

    CAUSE:
     
    SOLUTION:

    Topology

    SRX1 (192.168.1.1)---------------------------(192.168.1.2) SRX2

    Procedure

    From SRX1, ping the directly connected interface IP 192.168.1.2:

    SRX1> ping 192.168.1.2

    64 bytes from 192.168.1.2: icmp_seq=28 ttl=64 time=0.524 ms
    64 bytes from 192.168.1.2: icmp_seq=29 ttl=64 time=0.503 ms
    64 bytes from 192.168.1.2: icmp_seq=30 ttl=64 time=16.205 ms
    64 bytes from 192.168.1.2: icmp_seq=31 ttl=64 time=0.543 ms
    64 bytes from 192.168.1.2: icmp_seq=32 ttl=64 time=32.299 ms

    Note that the time is nearly 0.5 ms for most of the ping requests, but in some instances we see a value which is much larger.

    Although ICMP is a great way to check for link availability, it is not a good way to test latency or delay on a Juniper Networks platform. One of the best and most accurate ways to test for latency is to simulate data plane traffic using a traffic generator for the transit traffic.

    Juniper Networks platform architecture separates the control plane from the data plane. There are various rate-limiting and prioritization functions within the packet forwarding engine (PFE) and the routing engine. When a ping is sent from the routing platform to the end device, it is using the control plane on the local router in order to generate the ICMP request packet. The control plane is used again when the ICMP reply packet is received from the end device.

    ICMP messages are considered low priority within Junos OS, so the routing platform will respond to and process other higher priority messages, such as routing updates, before processing the ICMP messages. The microkernel may introduce tens of milliseconds of processing delay to ICMP message handling. The delay is not uniform, meaning that some ICMP messages might be delayed while others may not be delayed. This matches the behavior observed here with the testing.

    ICMP ping latency in traffic generated for the device itself is not a recommended way of testing the bandwidth or integrity of the link.



  • 8.  RE: High Latency ping times

    Posted 09-18-2012 11:35

    Hi,

     

     

    What junos that u running? is it suddenly happen or new installation. I have face similar case previously. JTAC advise to upgrade the Junos.



  • 9.  RE: High Latency ping times

    Posted 09-24-2012 07:51

    I was told in the past that this is normal behavior.  It has to do with how Junos processes pings to the router itself.  The short of it is that the Transit traffic latency is what is important here and that is always very low on the EX series.  

     

    High latency pings TO the EX switch is not a sign of poor performance but a result of the design.  It wont affect traffic.