Re: per-cpu blk_plug_list

[Andrew Morton <akpm@osdl.org>]

Miquel van Smoorenburg <miquels@cistron.nl> wrote:
>
> According to Andrew Morton:
>  >  And also having looked at Miquel's (currently slightly defective)
>  >  implementation of the any_congested() API for devicemapper:
>  > 
>  >  ftp://ftp.kernel.org/pub/linux/kernel/people/akpm/patches/2.6/2.6.4-rc1/2.6.4-rc1-mm1/broken-out/queue-congestion-dm-implementation.patch
>  > 
>  >  I am thinking that an appropriate way of solving the blk_run_queues() lock
>  >  contention problem is to nuke the global plug list altogther and make the
>  >  unplug function a method in struct backing_device_info.
>  > 
>  >  This is conceptually the appropriate place to put it - it is almost always
>  >  the case that when we run blk_run_queues() it is on behalf of an
>  >  address_space, and the few remaining case can be simply deleted -
>  >  mm/mempool.c is the last one I think.
>  > 
>  >  The implementation of backing_dev_info.unplug() would have to run the
>  >  unplug_fn of every queue which contributes to the top-level queue (the
>  >  thing which the address_space is sitting on top of).
> 
>  But then you need a pointer to the queue. In that case,
>  you might as well put the congested_fn pointer in the request_queue
>  too.

It already is.  backing_dev_info is a member of struct request_queue.

> Then you get something like
>  https://www.redhat.com/archives/linux-lvm/2004-February/msg00203.html
>  (though I'd replace "rw" with "bdi_bits" like in the current patch).

Sure.  This is all nice and simple stuff, except for the locking, which
needs serious work.