Hello Ingo,
running I3 on top of 2.4.18-pre3-I3-VM-22-preempt-lock ;-)
This combination rouks!
But my reported "smooth" KDE-2.2.2 artsd Ogg-Vorbis/MP3 playback is hurt with
I3 (both artsd processes reniced to -16/19). H7 worked OK.
-Dieter
--
Dieter N?tzel
Graduate Student, Computer Science
University of Hamburg
Department of Computer Science
@home: [email protected]
On Thursday, 17. January 2002 00:09, you wrote:
> On Wed, 16 Jan 2002, Dieter [iso-8859-15] N?tzel wrote:
> > running I3 on top of 2.4.18-pre3-I3-VM-22-preempt-lock ;-) This
> > combination rouks!
>
> could you try the -J0 patch i've just uploaded? It has a number of fixes
> and improvements.
Somewhat better but a reniced artsd (-16 or -19) stutters a little during
dbench 32. Maybe there is one show stopper slipped into preempt or lock-break
during my 10_vm-22 merge. Few stalls during heavy IO. But I have the buffer.c
fix applied.
2.4.18-pre4-J0-VM-22-preempt-lock
32 clients started
................................................................................................................................................................................................................................................................................................................................................................................................................................................................................................................................................................................................................................................................................................................................................................................................................................................................................................................................................................................................................................................................................................+..+...................................................................+..+.+.+.++++.++.+...........++...........++...+.+++.+++.........+...+.++.....+...++....+********************************
Throughput 51.711 MB/sec (NB=64.6388 MB/sec 517.11 MBit/sec)
14.260u 49.860s 1:22.71 77.5% 0+0k 0+0io 939pf+0w
More to come after some sleep...
-Dieter
BTW I'll prepare a unified patch for wider testing if anybody want.