Re: [PATCH] rwsem: add rwsem_is_contended

[Josef Bacik <jbacik@fusionio.com>]

On Sun, Sep 01, 2013 at 01:32:36AM -0700, Michel Lespinasse wrote:
> Hi Josef,
> 
> On Fri, Aug 30, 2013 at 7:14 AM, Josef Bacik <jbacik@fusionio.com> wrote:
> > Btrfs uses an rwsem to control access to its extent tree.  Threads will hold a
> > read lock on this rwsem while they scan the extent tree, and if need_resched()
> > they will drop the lock and schedule.  The transaction commit needs to take a
> > write lock for this rwsem for a very short period to switch out the commit
> > roots.  If there are a lot of threads doing this caching operation we can starve
> > out the committers which slows everybody out.  To address this we want to add
> > this functionality to see if our rwsem has anybody waiting to take a write lock
> > so we can drop it and schedule for a bit to allow the commit to continue.
> > Thanks,
> >
> > Signed-off-by: Josef Bacik <jbacik@fusionio.com>
> 
> FYI, I once tried to introduce something like this before, but my use
> case was pretty weak so it was not accepted at the time. I don't think
> there were any objections to the API itself though, and I think it's
> potentially a good idea if you use case justifies it.
> 
> Two comments:
> 
> - Note that there are two rwsem implementations - if you are going to
> add functionality to rwsem.h you want to add the same functionality in
> rwsem-spinlock.h as well.
> 

Sure thing.

> - I would prefer if you could avoid taking the wait_lock in your
> rwsem.h implementation. In your use case (read lock is known to be
> held), checking for sem->count < 0 would be sufficient to indicate a
> writer is queued (or getting onto the queue). In the general case,
> some architectures have the various values set up so that
> RWSEM_WAITING_BIAS != RWSEM_ACTIVE_WRITE_BIAS - for these
> architectures at least, you can check for waiters by looking if the
> lowest bit of RWSEM_WAITING_BIAS is set in sem->count.

Question about this one, I can't just do

if (sem->count < 0)

since each arch has their own atomic way of looking at count, so I'd have to add
something to do just a normal read of count for each arch and call that wouldn't
I?  If that's what you want me to do then I'm fine with that (though I'll need a
really thorough review), just want to double check before I make a bunch of
extra work for myself.  Thanks,

Josef