Messages in this thread | | | Date | Thu, 3 Jul 1997 13:25:10 +0200 | From | "Dr. Werner Fink" <> | Subject | Re: Time for a pre-patch-2.0.31-3? |
| |
> > And with your latest patch with pre-patch 2.0.31-2 > > > > -------Sequential Output-------- ---Sequential Input-- --Random-- > > -Per Char- --Block--- -Rewrite-- -Per Char- --Block--- --Seeks--- > > Machine MB K/sec %CPU K/sec %CPU K/sec %CPU K/sec %CPU K/sec %CPU /sec %CPU > > 100 2262 76.8 4841 30.6 1362 15.5 1445 52.7 1568 7.6 120.1 5.3 > > > > Note the drastic fall in read performance. :( These results are consistent. > > I rememember the original port of the 2.1 buffer.c into 2.0.30 was inspired > by this read performance problem. Leonard Zubkoff presented a patch for it > at this time. Maybe he knows how to fix it. It *should* be fixed for 2.0.31. > > -Andi
I found only a answer on mail of Leonard Zubkoff in http://www.linuxhq.com/patch/20-p0408.html ... smething similar is included. Leonards fix on the old buffer code of 2.0.29 is useless in my changes because there is no such code anymore :-)
The Linux 2.0 SMP Lockup (deadlock) patch of Leonard is a really interesting one for smp users and it is NOT included in my changes.
Werner
| |