SCSI kontra EIDE

[Jan Kasprzak]

Ales Pour pise:
: 
: No ja ziju s presvedcenim, ze scsi se projevi kdyz se systemu
: nalozi trochu vic na zada... Drive, kdyz (e)ide radice
: nedelaly busmastering, tak to vsechno odnes procesor.
: Nevim jak dobry sou ty novejsi...

	Presne tak. Tagged queuing(sp?) je mocna vec. U PIIX
je sice DMA, ale je myslim mozny v jednom okamziku pouze jeden
bezici pozadavek a myslim ze tohle i v pripade, ze jsou dva disky
na ruznych kanalech PIIX (moderni SCSI disky prevezmou vic pozadavku
a mohou si je preskladat). Z linux/drivers/block/triton.c:

 * Up to four drives may be enabled for DMA, and the Triton chipset will
 * (hopefully) arbitrate the PCI bus among them.  Note that the i82371 chip
 * provides a single "line buffer" for the BM IDE function, so performance of
 * multiple (two) drives doing DMA simultaneously will suffer somewhat,
 * as they contest for that resource bottleneck.  This is handled transparently
 * inside the i82371 chip.

	To, ze i na jednouzivatelskem stroji casto vyvstane potreba
nekolika paralelne bezicich diskovych operaci, asi nemusim pripominat.

-Yenya

--
\ Jan "Yenya" Kasprzak <kas at fi.muni.cz>       http://www.fi.muni.cz/~kas/
\\ PGP: finger kas at aisa.fi.muni.cz   0D99A7FB206605D7 8B35FCDE05B18A5E //
\\\      Czech Linux Homepage:  http://www.fi.muni.cz/~kas/linux/        ///
///      MS is a lot better at making money  than it is at making        \\\
//       good operating systems.                 --Linus Torvalds         \\