Seth Kurtzberg <[EMAIL PROTECTED]> wrote:
> Joerg Schilling wrote:
>
> >Hugo van der Merwe <[EMAIL PROTECTED]> wrote:
> >
> >
> >
> >>growisofs does not provide much info regarding buffer/fifo fill % like
> >>cdrecord does. Cdrecord has no problems keeping the buffer above 95%
> >>full, so the system does not have some fundamental flaw... I do wish
> >>growisofs could provide more info.
> >>
> >>
> >
> >If you are talking about the drive buffer fill ratio, then your conclusions
> >are
> >correct.
> >
> >A full FIFO does not mean that there are no problems as the kernel could
> >just reject to send data to the drive.
> >
> >
> I was thinking more of an empty FIFO. Isn't that a good indication that
> data was not available when needed for a write?
If the FIFO empties, then the filesystem read performance is not sufficient.
If the drive buffer empties, then the I/O performance to the drive is not
sufficient.
J�rg
--
EMail:[EMAIL PROTECTED] (home) J�rg Schilling D-13353 Berlin
[EMAIL PROTECTED] (uni)
[EMAIL PROTECTED] (work) Blog: http://schily.blogspot.com/
URL: http://cdrecord.berlios.de/old/private/ ftp://ftp.berlios.de/pub/schily
--
To UNSUBSCRIBE, email to [EMAIL PROTECTED]
with a subject of "unsubscribe". Trouble? Contact [EMAIL PROTECTED]
