[CentOS] Loss of network connectivity | kernel: irq 68: nobody cared (try booting with the "irqpoll" option)

[James A. Peltier]

----- Original Message -----
| Greetings all,
| 
| Running CentOS 6.5 x86_64 2.6.32-431.5.1.el6.x86_64.
| (already booting with the irqpoll option in grub)
| 
| Every few months I lose network connectivity and have to restart the
| server:
| 
| in /var/log/messages:
| 
| "
| Mar  7 18:54:21 backup03 kernel: irq 68: nobody cared (try booting
| with the
| "irqpoll" option)
| Mar  7 18:54:21 backup03 kernel: Pid: 0, comm: swapper Not tainted
| 2.6.32-431.1.2.0.1.el6.x86_64 #1
| Mar  7 18:54:21 backup03 kernel: Call Trace:
| Mar  7 18:54:21 backup03 kernel: <IRQ>  [<ffffffff810e8ffb>] ?
| __report_bad_irq+0x2b/0xa0
| Mar  7 18:54:21 backup03 kernel: [<ffffffff810e91fc>] ?
| note_interrupt+0x18c/0x1d0
| Mar  7 18:54:21 backup03 kernel: [<ffffffff810e9845>] ?
| handle_edge_irq+0xf5/0x180
| Mar  7 18:54:21 backup03 kernel: [<ffffffff8100faf9>] ?
| handle_irq+0x49/0xa0
| Mar  7 18:54:21 backup03 kernel: [<ffffffff81530fec>] ?
| do_IRQ+0x6c/0xf0
| Mar  7 18:54:21 backup03 kernel: [<ffffffff8100b9d3>] ?
| ret_from_intr+0x0/0x11
| Mar  7 18:54:21 backup03 kernel: [<ffffffff8107a893>] ?
| __do_softirq+0x73/0x1e0
| Mar  7 18:54:21 backup03 kernel: [<ffffffff810ac9da>] ?
| tick_program_event+0x2a/0x30
| Mar  7 18:54:21 backup03 kernel: [<ffffffff8100c30c>] ?
| call_softirq+0x1c/0x30
| Mar  7 18:54:21 backup03 kernel: [<ffffffff8100fa75>] ?
| do_softirq+0x65/0xa0
| Mar  7 18:54:21 backup03 kernel: [<ffffffff8107a795>] ?
| irq_exit+0x85/0x90
| Mar  7 18:54:21 backup03 kernel: [<ffffffff815310ba>] ?
| smp_apic_timer_interrupt+0x4a/0x60
| Mar  7 18:54:21 backup03 kernel: [<ffffffff8100bb93>] ?
| apic_timer_interrupt+0x13/0x20
| Mar  7 18:54:21 backup03 kernel: <EOI>  [<ffffffff812e09ce>] ?
| intel_idle+0xde/0x170
| Mar  7 18:54:21 backup03 kernel: [<ffffffff812e09b1>] ?
| intel_idle+0xc1/0x170
| Mar  7 18:54:21 backup03 kernel: [<ffffffff81426707>] ?
| cpuidle_idle_call+0xa7/0x140
| Mar  7 18:54:21 backup03 kernel: [<ffffffff81009fc6>] ?
| cpu_idle+0xb6/0x110
| Mar  7 18:54:21 backup03 kernel: [<ffffffff81520e2c>] ?
| start_secondary+0x2ac/0x2ef
| Mar  7 18:54:21 backup03 kernel: handlers:
| Mar  7 18:54:21 backup03 kernel: [<ffffffffa015f260>]
| (e1000_msix_other+0x0/0x1f0 [e1000e])
| Mar  7 18:54:21 backup03 kernel: Disabling IRQ #68
| "
| 
| cat /proc/interrupts | grep 68
|   68:          2          0          0          0  IR-PCI-MSI-edge
|        eth0
| 
| I'm already booting with irqpoll set in grub:
| 
| kernel /vmlinuz-2.6.32-431.5.1.el6.x86_64 ro
| root=UUID=b535f362-3152-4cc1-a9f2-b86f44331510 nomodeset rd_NO_LUKS
|  KEYBOARDTYPE=pc KEYTABLE=us LANG=en_US.UTF-8 rd_NO_MD quiet
| SYSFONT=latarcyrheb-sun16 rhgb crashkernel=auto rd_NO_LVM rd_NO_DM
| irqpoll
| 
| Anyone have any ideas or suggestions? Not sure what else I can do
| here.
| 
| Thanks in advance!
| 
| -PJF

What kind of machine are you running this on?  If you have a BIOS check to see if there is an update available for it.  Assuming that you have the latest BIOS on the machine try booting with MSI-X disabled and see if it becomes more stable.

James A. Peltier
Manager, IT Services - Research Computing Group
Simon Fraser University - Burnaby Campus
Phone   : 778-782-6573
Fax     : 778-782-3045
E-Mail  : jpeltier at sfu.ca
Website : http://www.sfu.ca/itservices

"Around here, however, we don’t look backwards for very long.  We KEEP MOVING FORWARD, opening up new doors and doing things because we’re curious and curiosity keeps leading us down new paths." - Walt Disney