On Mon, Sep 03, 2012 at 10:49:27AM +1000, Dave Chinner wrote:

Given that we are working around stack depth issues in the
filesystems already in several places, and now it seems like there's
a reason to work around it in the block layers as well, shouldn't we
simply increase the default stack size rather than introduce
complexity and performance regressions to try and work around not
having enough stack?

I mean, we can deal with it like the ia32 4k stack issue was dealt
with (i.e. ignore those stupid XFS people, that's an XFS bug), or
we can face the reality that storage stacks have become so complex
that 8k is no longer a big enough stack for a modern system....

I'm not arguing against increasing the default stack size (I really
don't have an opinion there) - but it's not a solution for the block
layer, as stacking block devices can require an unbounded amount of
stack without the generic_make_request() convert recursion-to-iteration
thing.