>On Mon, 13 Sep 1999, Daniel J Blueman wrote:
>
>>Having looked at the source for kflushd, I did a complete re-write offering
>>significantly less overhead. I am preparing a patch against 2.3.18.
>
>IMHO in 2.3.18* the buffer flushing code is bad. IMHO there's no way to
>take it as it is for 2.4.x if we want decent cache performances (with
>decent I mean at least as 2.2.x). I am rewriting the algorithms from
>scratch as I just have invented my own heuristic and so now I really want
>to implement them as I want my system running as I want for me. So expect
>a re-write also from me.
I think my email wasn't complete and you risk to take me wrong. I don't
want to suggest you to stop your work. Instead I suggest you to post your
patch.
Actually I seen no patch from you yet, and unfortunately I read your
announce really too late so at this point I think I'll complete my work
unless your patch _completly_ obsoletes my current stuff.
But this in turn simply means that once finished we'll merge the good
stuff from both the two patches to generate a still better patch, so
I can't see any real issue (no panic yet ;).
Apologies if I am not been not clear. Also thanks to who pointed out to me
privately that I am been not clear.
Andrea
-
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/