Re: possible spinlock optimizations

Manfred (manfreds@colorfullife.com)
Tue, 28 Sep 1999 20:16:57 +0200


From: David S. Miller <davem@redhat.com>
> I don't think you can assume that NT has a contention problem.
> Ok, but then...
> I bet the contention of WinNT4 is lower than the contention of
> 2.3.18.
> by the same argument you cannot make this assumption either.
> With that in mind, can you state anything factual about this matter?

No.
I wanted to say:
1) if Microsoft optimized their contention behaviour, this does not mean
that they have a contention problem. They just have many developers, and
they want to do something.
If they add it into W2K, it must help. We should check if we could use it.

2) I _guess_ that
- NT has a lower contention than 2.3.18.
- for most operation, the difference won't be huge.
- the filesystem (create, delete, remove) of WinNT is better.

> But hear me right, we know where we still have some problems, but Rome
> was not built in a day ya know.
And the architects copied many ideas from greece.

--
    Manfred

- To unsubscribe from this list: send the line "unsubscribe linux-kernel" in the body of a message to majordomo@vger.rutgers.edu Please read the FAQ at http://www.tux.org/lkml/