On Mon, Jul 11, 2005 at 01:46:35AM +0300, martin f krafft wrote:
> also sprach Nathan Scott <nathans@xxxxxxx> [2005.07.11.0116 +0300]:
> > > Grub menu file is changed
> > > kernel freezer is activated
> > > filesystems are left untouched
> > > system is shut down
> >
> > There's no xfs_freeze(8) in that test case...? I'm confused.
> >
> > > grub starts and /boot has not been flushed.
> >
> > Hmm, AFAICT you didn't really freeze the filesystem. The software
> > suspend "freezer" is putting the system into a state such that it
> > stops writing, such that kernel daemons go to "sleep" (and don't
> > wakeup on their usual timer-driven way), etc. The assumption
> > there is the system will be woken up from this state at some point
> > not switched off and cold booted.
>
> Sorry for leaving out this vital info, I freeze (and unfreeze) right
> after changing the grub menu file.
Ah, OK thats more interesting then - can you describe the way
in which the Grub menu file is changed? e.g. ... is a new
inode created or is an existing one overwritten? is it written
via write(2) or mmap? Is it using buffered or direct IO? etc.
thanks.
--
Nathan
|