Was Collecting SBUs now, Fast compile engines
d95-bli.no at spam.nada.kth.se
Sat Jun 8 00:54:36 PDT 2002
Ian Molton wrote:
> On Fri, 07 Jun 2002 23:53:50 +0200
> Björn Lindberg <d95-bli.no at spam.nada.kth.se> wrote:
> > > 1/2 the CPU speed - BIG effect on compiling
> > > run the HDD at PIO4 instead of UDMA100 - BIG effect on compiling
> > > use PC133 instead of DDR - tiny effect on compiling.
> > I agree with the first and third one. I don't think HDD performance
> > would have that big an impact, but of course I could be wrong.
> try it for yourself...
> use hdparm to turn off UDMA and use PIO 4.
Oh, I see now. But that is not the result of lower HDD speed per se, but
rather that the processor has to spend time doing HDD reads when not
using DMA (Direct Memory Access), whereas with DMA all processor time
can be spent on the actual compiling.
When I was talking about HDD speed, I meant SCSI vs IDE, or 7200rpm vs
5400rpm, etc. Ie the way HDD speed affects compile times /directly/.
Unsubscribe: send email to listar at linuxfromscratch.org
and put 'unsubscribe lfs-chat' in the subject header of the message
More information about the lfs-chat