[dm-devel] [RFC PATCH 0/4] dm mpath: vastly improve blk-mq IO performance

[Mike Snitzer]

On Thu, Apr 07 2016 at 10:58am -0400,
Hannes Reinecke <hare at suse.de> wrote:

> On 03/31/2016 10:04 PM, Mike Snitzer wrote:
> > I developed these changes some weeks ago but have since focused on
> > regression and performance testing on larger NUMA systems.
> > 
> > For regression testing I've been using mptest:
> > https://github.com/snitm/mptest
> > 
> > For performance testing I've been using a null_blk device (with
> > various configuration permutations, e.g. pinning memory to a
> > particular NUMA node, and varied number of submit_queues).
> > 
> > By eliminating multipath's heavy use of the m->lock spinlock in the
> > fast IO paths serious performance improvements are realized.
> > 
> [ .. ]
> > Jeff Moyer has been helping review these changes (and has graciously
> > labored over _really_ understanding all the concurrency at play in DM
> > mpath) -- his review isn't yet complete but I wanted to get this
> > patchset out now to raise awareness about how I think DM multipath
> > will be changing (for inclussion during the Linux 4.7 merge window).
> > 
> > Mike Snitzer (4):
> >   dm mpath: switch to using bitops for state flags
> >   dm mpath: use atomic_t for counting members of 'struct multipath'
> >   dm mpath: move trigger_event member to the end of 'struct multipath'
> >   dm mpath: eliminate use of spinlock in IO fast-paths
> > 
> >  drivers/md/dm-mpath.c | 351 ++++++++++++++++++++++++++++----------------------
> >  1 file changed, 195 insertions(+), 156 deletions(-)
> > 
> Finally got around to test this.
> The performance is comparable to the previous (RCU-ified) patchset,
> however, this one is the far superious approach.
> In fact, the first two are pretty much identical to what I've
> already had, but I've shirked at modifying the path selectors.
> So well done here.

Awesome, thanks for reviewing and testing, very much appreciated.

I'll get this set staged in linux-next for 4.7 shortly.