Direct IO and Page cache

[gmate.amit@gmail.com (Kumar amit mehta)]

On Fri, Jul 26, 2013 at 10:59:25AM -0400, Valdis.Kletnieks at vt.edu wrote:
> On Fri, 26 Jul 2013 00:02:31 -0400, Kumar amit mehta said:
> 
> > So leaving the hardware at the mercy of the application doesn't sound
> > like a good practice. This __may__ compromise kernel stability too. Also
> > think of this:
> 
> In what possible way does it compromise kernel stability?

Sorry for forgetting that we are talking about userspace programs.
Recently I came across an old HBA driver, which for some reason failed
to properly intialize the firmware(maybe someone didn't properly copied
the firmware in the /lib/firmware directory, i don't know) and because
of that the firmware initialization code tried the same thing for a
couple of iteration, failiing which it tried to reset the board, but
somewhere during this recovery process started disabling the interrupt
on the CPU. Later, watchdog timer kicked in, considering this as hard
lock up and issued a system reset.

When I first saw the firmware initialization error, I thought what harm
this could bring to my overall system other than the particular HBA
turning into an unusable one, but It turned out to be much more disruptive.
When I said "This __may__ compromise kernel stability too", I was
thinking, something on those lines and completely forgot that we are
currently in uspace.

!!amit