Viestissä Lauantai 18. Tammikuuta 2003 16:51, Thomas Backlund kirjoitti: > since the nforce2 ide wont work with latest cooker kernel: > > kernel-2.4.21.0.pre3.1mdk-1-1mdk > > I took Alan Cox ac4 patch and removed all but nforce2 > patch and applied it to latest MDK kernel (above)... > (renamed it to: kernel-2.4.21.0.pre3.1TmB-1-1mdk) > > It works great: > here is the hd speed with the MDK 9.0 kernel (on full Cooker): > /dev/hda: > Timing buffer-cache reads: 128 MB in 0.33 seconds =387.88 MB/sec > Timing buffered disk reads: 64 MB in 19.11 seconds = 3.35 MB/sec > > and here is the speed with my patched kernel (on full Cooker): > /dev/hda: > Timing buffer-cache reads: 128 MB in 0.32 seconds =400.00 MB/sec > Timing buffered disk reads: 64 MB in 2.11 seconds = 30.33 MB/sec > > So the patch is included with this mail. > > And if you dont want to apply the patch yourself, go to: > http://www.iki.fi/~tmb/Cooker/
There is some "features" missing in this patch that I haven't fixed yet... It does not recognize the chipsets (or is it the cable?) support for UDMA/133, so it will default to UDMA/33 wich means it's limiting the system performance... Booting with "ide0=udma66" switches the support to UDMA/100 !! so you get some more speed out of it: /dev/hda: Timing buffer-cache reads: 128 MB in 0.32 seconds =412.91 MB/sec Timing buffered disk reads: 64 MB in 1.34 seconds = 47.76 MB/sec Another limit of this patch is the fact that it uses nforce1 support as base, wich means AFAIK it wont go over UDMA/100... I can issue the command 'hdparm -X70 /dev/hda' to tell it to go to UDMA/133, and hdparm reports OK but the system stays at UDMA/100. I'll try to fix theese, and make a better patch, if no-one beats me to it... --- Thomas ****** [EMAIL PROTECTED] www.iki.fi/~tmb/ ****** * Theory is when you now everything, but nothing works... * Reality is when everything works, but nobody nows why... * Here Theory and Reality is combined... * Nothing works, and Nobody nows why ... *