>
> I continue to wonder why
> it is that on my computer
> Win4Lin performs so much better
> in the context of Linux 2.2.16-22
> than it does in the context of Linux 2.4.2-2
>
It turns out that the way win4lin hooks into the virtual memory
system for 2.4 had some undesirable side effects that were not
initially visible. This may be because things changed from 2.4.1
(on which we based the first port) or because the problem just doesn't
always show up. The bottom line is that in some circumstances the OS ends
up doing a whole heck of a lot of extra (unnecessary) disk writes in the
name of trying to keep available (stealable) pages available. Don't
get me wrong: this was OUR bug and not a bug in 2.4.X. We have a
fix for this which we were able to put into the win4lin RPM itself
(as opposed to the kernel) and with the fix, performance is pretty much
back to what it was with 2.2 kernels.
The fix is in QA. It will be win4lin 3.0.5 (rpm Win4Lin-5.2.5?). I am not
sure how long it will take for it to get through the QA cycle, but the good
news is that there is light at the end of the tunnel! There will be a message
posted to this mailing list as soon as the fix is made available.
Thanks for everyone's patience.
Richard <rwb>
--
Richard W. Bass
Systems Software Architect
NeTraverse, Inc.
mailto: [EMAIL PROTECTED]
_______________________________________________
Win4Lin-users mailing list
[EMAIL PROTECTED]
https://lists.netraverse.com/mailman/listinfo/win4lin-users
