Re: Linux 2.4.10-pre11

Alexander Viro (viro@math.psu.edu)
Wed, 19 Sep 2001 19:30:55 -0400 (EDT)


On Thu, 20 Sep 2001, Andrea Arcangeli wrote:

> On Wed, Sep 19, 2001 at 05:17:23PM -0400, Alexander Viro wrote:
> > fsync_dev() is not needed for raw devices or swap. It _is_ needed for
> > file access.
>
> then what's the difference between raw devices and swap.

Keep in mind that at some point we may want to add exclusions - e.g.
"swapon() messing with block_size when accidentially called for mounted
fs" problem can be easily solved that way - that's probably the
simplest way to deal with it. Ditto for RAID vs. filesystem - current
code for that is ugly and not too reliable.

> And there's reason we should we avoid the fsync_dev with the raw devices
> and swap.

Umm... Not doing unnecessary work? Semantics of releasing a block device
depends on the kind of use. BTW, I'm less than sure that fsync_dev() is
the right thing for file access now that you've got that in pagecache -
__block_fsync() seems to be more correct thing to do.

> I just found it an useless complication.

<shrug> in the eye of beholder...

/me goes to get some sleep.

-
To unsubscribe from this list: send the line "unsubscribe linux-kernel" in
the body of a message to majordomo@vger.kernel.org
More majordomo info at http://vger.kernel.org/majordomo-info.html
Please read the FAQ at http://www.tux.org/lkml/