Messages in this thread |  | | Date | Fri, 13 Oct 2000 01:33:36 +1100 | From | Andrew Morton <> | Subject | Re: 2.2.14 SMP 3com905: transmit timed out: Odd lost irq and ip-stack lockup |
| |
"Dr. Michael Weller" wrote: > > Dear list, > > I run a Compaq Proliant 1500 (dual Pentium 75.200) with hardware raid > (Smart2) with two ethernet cards 3com905 (b or c, I can't tell you right > now) as a firewall and web/mail virus scanner which (needless to say) > needs to be up 7d/24h. > > Recently, during a pretty fast download the machine (ethernet technically, > you could login on the console, even ping the ethernet ip address) locked > up with the following error log: > > Oct 9 17:29:02 fwintern kernel: eth0: transmit timed out, tx_status > 00 status e681.
Here is your problem:
> Oct 9 17:29:02 fwintern kernel: eth0: Interrupt posted but not > delivered -- IRQ blocked by another device?
This is the infamous APIC bug. I have about ten reports of this over a four-month period. Mark Hemment mentioned it just yesterday.
This is not a 3c59x problem. It is due to the APIC forgetting how to generate interrupts for a particular IRQ. It happens mostly for NICs because they generate a lot of interrupts. I've had it happen just once. In that case, _nothing_ would make the interrupt come back (including a driver unload/reload).
This gets reported a lot by 3c59x users because this driver specifically detects and reports on the problem.
Donald Becker says that this is a software bug (I don't know why he thinks this). He says that he _always_ boots linux with the `noapic' option to prevent it happening.
> The problem was reproducible (several times) with the same download (a > 300MB file) after a reboot.
Interesting. So you had a stable 2.2.14 machine which suddenly started repeatedly exhibiting this problem? Is it still reproducible? - To unsubscribe from this list: send the line "unsubscribe linux-kernel" in the body of a message to majordomo@vger.kernel.org Please read the FAQ at http://www.tux.org/lkml/
|  |