lkml.org 
[lkml]   [2008]   [Jun]   [26]   [last100]   RSS Feed
Views: [wrap][no wrap]   [headers]  [forward] 
 
Messages in this thread
    /
    Date
    From
    SubjectRe: Strange problem with e1000 driver - ping packet loss
    On Wed, Jun 25, 2008 at 03:04:59PM -0400, Len Brown wrote:
    > On Wed, 25 Jun 2008, Len Brown wrote:
    >
    > > > Linux version 2.6.18-53.el5
    >
    > can you find out if the latest upstream kernel still has this problem?

    Len,
    We'd tried 2.6.25 and found it doesnt help.

    > > > ACPI: PCI Interrupt 0000:00:1d.1[B] -> GSI 19 (level, low) -> IRQ 177
    > > > PCI: Setting latency timer of device 0000:00:1d.1 to 64
    > > > uhci_hcd 0000:00:1d.1: UHCI Host Controller
    > > > uhci_hcd 0000:00:1d.1: new USB bus registered, assigned bus number 2
    > > > uhci_hcd 0000:00:1d.1: irq 177, io base 0x0000e880
    > >
    > > > SELinux: initialized (dev sysfs, type sysfs), uses genfs_contexts
    > > > audit(1213972202.305:3): policy loaded auid=4294967295
    > > > Intel(R) PRO/1000 Network Driver - version 7.3.20-k2-NAPI
    > > > Copyright (c) 1999-2006 Intel Corporation.
    > > > ACPI: PCI Interrupt 0000:02:02.0[B] -> GSI 18 (level, low) -> IRQ 193
    > > > e1000: 0000:02:02.0: e1000_probe: (PCI-X:66MHz:64-bit) 00:04:23:00:90:ab
    > > > e1000: eth0: e1000_probe: Intel(R) PRO/1000 Network Connection
    > > > ACPI: PCI Interrupt 0000:02:02.1[B] -> GSI 18 (level, low) -> IRQ 193
    > > > e1000: 0000:02:02.1: e1000_probe: (PCI-X:66MHz:64-bit) 00:04:23:00:90:aa
    > > > e1000: eth1: e1000_probe: Intel(R) PRO/1000 Network Connection
    >
    > your /proc/interrutps showed just eth1, and it was on IRQ 177 --
    > was that from a different boot than this dmesg?

    Yes the dmesg and /proc/interrupts output I'd sent was from different
    boot instances.

    > in any case, when you boot these on a new kernel
    > they should both show up on IRQ 18 (because they're on GSI 18).

    hmm ok. we can verify.

    > Also, these IOAPIC interrupts are not programmable -- they
    > are hard-coded, so the issue is not in the ACPI PCI interrupt
    > link programming code.

    So is the issue likely with the e1000 device itself then? I have sent
    ethregs output to Jesse ...hopefully that will give us some clues.

    --
    Regards,
    vatsa


    \
     
     \ /
      Last update: 2008-06-26 15:37    [W:0.055 / U:1.560 seconds]
    ©2003-2016 Jasper Spaans. hosted at Digital OceanAdvertise on this site