Latency/Interrupt issues



  • Hello everyone,

    First post here and new to pfSense.

    We just installed a pair of pfSense in HA(2.4.4-RELEASE-p3). They both are running in VMWare 6.5.

    PfSense are configured with 4 vCpu and 8 GB of RAM.

    I use vmxnet3 with Open-VM-Tools installed.

    We have 3 interfaces :
    vmx2 : HA Sync
    vmx1 : Trunk with about 30 VLAN's
    vmx0 : It's the WAN but it is disable right now.

    When running "top -SH", it's showing me about 20% interrupts.

    *last pid: 20695; load averages: 1.06, 0.89, 0.92 up 10+09:31:04 00:23:54
    214 processes: 6 running, 155 sleeping, 53 waiting
    CPU: 0.0% user, 0.0% nice, 0.0% system, 18.7% interrupt, 81.3% idle
    Mem: 78M Active, 140M Inact, 240M Wired, 76M Buf, 7457M Free
    Swap: 2560M Total, 2560M Free

    PID USERNAME PRI NICE SIZE RES STATE C TIME WCPU COMMAND
    11 root 155 ki31 0K 64K RUN 1 244.5H 98.44% idle{idle: cpu1}
    11 root 155 ki31 0K 64K CPU2 2 241.6H 97.95% idle{idle: cpu2}
    11 root 155 ki31 0K 64K CPU3 3 241.7H 94.91% idle{idle: cpu3}
    12 root -92 - 0K 864K CPU0 0 74.4H 65.70% intr{irq266: vmx1}
    11 root 155 ki31 0K 64K RUN 0 174.6H 34.87% idle{idle: cpu0}
    12 root -72 - 0K 864K WAIT 2 215:25 3.65% intr{swi1: pfsync}
    12 root -92 - 0K 864K WAIT 1 51:21 0.88% intr{irq275: vmx2}
    25421 root 20 0 6604K 2868K bpf 0 14:25 0.15% filterlog
    66294 root 20 0 7816K 4340K CPU1 1 0:02 0.11% top
    20 root -16 - 0K 16K - 1 7:56 0.09% rand_harvestq
    ]*

    I also checked my interfaces and most of them have in/out errors.

    Under System-Advanced-Networking, all offloading stuff are disabled.

    Is someone else also having this type of issue ?

    Thank you


Log in to reply