Messages in this thread | | | Date | Sat, 19 Jan 2002 12:14:19 -0500 | From | Mike Phillips <> | Subject | Re: [PATCH] IBM Lanstreamer bugfixes |
| |
On Fri, Jan 18, 2002 at 05:02:57PM -0600 or sometime in the same epoch, Kent E Yoder scribbled: > Ok, I thought of one thing that might make things clearer here: when I > say "the write failed", I mean that we saw the write go out on the PCI bus > and then the box locked up. We were looking at it on a PCI bus analyzer. > That, and it wasn't just this write, or just writes in general, it really > seemed random. >
Kent,
We had this on olympic for certain high end IBM boxen. Spent forever trying to trap it as I couldn't emulate the behaviour on my test boxes. We weren't getting correct values from pci reads/write and we were running out of buffers as they weren't getting flushed. The machine wouldn't lock but the adapter would stop tx/rx.
Turned out the pci bridge on the machine itself was causing the problems. Tweaking the pci bus fixed the problem.
-- Mike Phillips Linux Token Ring Project http://www.linuxtr.net mailto: mikep@linuxtr.net
- To unsubscribe from this list: send the line "unsubscribe linux-kernel" in the body of a message to majordomo@vger.kernel.org More majordomo info at http://vger.kernel.org/majordomo-info.html Please read the FAQ at http://www.tux.org/lkml/
| |