On Wed, Jul 01, 2020 at 06:57:47PM +0100, Matthew Wilcox wrote:

On Wed, Jul 01, 2020 at 12:41:03PM -0400, Mike Snitzer wrote:

quoted

On Wed, Jul 01 2020 at  5:06am -0400,
Christoph Hellwig [off-list ref] wrote:

quoted

Hi Jens,

we have a lot of bdi congestion related code that is left around without
any use.  This series removes it in preparation of sorting out the bdi
lifetime rules properly.

I could do some git archeology to see what the fs, mm and block core
changes were to stop using bdi congested but a pointer to associated
changes (or quick recap) would save me some time.

Also, curious to know how back-pressure should be felt back up the IO
stack now? (apologies if these are well worn topics, I haven't been
tracking this area of development).

It isn't.  Jens declared the implementation was broken, and broke it
more.  So we're just living with stupid broken timeouts.

Here's a thread about it.  This would have been a discussion topic at
LSFMM2020, but COVID.

https://lore.kernel.org/linux-mm/20190917115824.16990-1-linf@wangsu.com/T/#u (local)