Hello, Dave.

On Wed, Sep 05, 2012 at 01:57:59PM +1000, Dave Chinner wrote:

quoted

But, yeah, this can't be solved by enlarging the stack size.  The
upper limit is unbound.

Sure, but recursion issue is isolated to the block layer.

If we can still submit IO directly through the block layer without
pushing it off to a work queue, then the overall stack usage problem
still exists. But if the block layer always pushes the IO off into
another workqueue to avoid stack overflows, then the context
switches are going to cause significant performance regressions for
high IOPS workloads.  I don't really like either situation.

Kent's proposed solution doesn't do that.  The rescuer work item is
used iff mempool allocation fails w/o GFP_WAIT.  IOW, we're already
under severe memory pressure and stalls are expected all around the
kernel (somehow this sounds festive...)  It doesn't alter the
breadth-first walk of bio decomposition and shouldn't degrade
performance in any noticeable way.

So while you are discussing stack issues, think a little about the
bigger picture outside of the immediate issue at hand - a better
solution for everyone might pop up....

It's probably because I haven't been bitten much from stack overflow
but I'd like to keep thinking that stack overflows are extremely
unusual and the ones causing them are the bad ones.  Thank you very
much. :p

-- 
tejun