>
>
<snip>
>
> I'd like to (again) point out that this is nothing new. This has _always_
> been true, because this is how the interrupts under Linux have worked
> since Day 1. It may be that on your particular machine, using the IO-APIC
> shows up some timing issue that you hadn't seen before, but that
> timing-issue has existed before, and your machine just didn't happen to
> see it. I bet other machines have seen it.
>
> Linus
>
I tend to agree. From experience over the past month running 2.1
kernels on a 4 processor machine, we are seeing *lots* of problems that
are obviously timing based. IE one person with a 2 processor machine
reports that ethernet traffic works fine. I run my 4 processor machine
and discover that it will barely work at all under any kind of traffic
load, and in working thru the code with debug stuff added, I find that
someone is confused about what happened... Either someone "misses" a
count, or someone "overuses" a counter... with bad results.
I'd bet we find more problems if we had machines handy with 8 and 16
heads....
I like the "KISS" principle here, less code is better code, if the
less code works. :)
-
To unsubscribe from this list: send the line "unsubscribe linux-kernel" in
the body of a message to majordomo@vger.rutgers.edu