Re: [Qemu-devel] [RFC] dataplane: IOThreads and writing dataplane-capable code

[Dr. David Alan Gilbert]

* Stefan Hajnoczi (address@hidden) wrote:
> On Thu, May 8, 2014 at 3:44 PM, Dr. David Alan Gilbert
> <address@hidden> wrote:
> > * Stefan Hajnoczi (address@hidden) wrote:
> >
> > <snip>
> >
> >> How to synchronize with an IOThread
> >> -----------------------------------
> >> AioContext is not thread-safe so some rules must be followed when using 
> >> file
> >> descriptors, event notifiers, timers, or BHs across threads:
> >>
> >> 1. AioContext functions can be called safely from file descriptor, event
> >> notifier, timer, or BH callbacks invoked by the AioContext.  No locking is
> >> necessary.
> >>
> >> 2. Other threads wishing to access the AioContext must use
> >> aio_context_acquire()/aio_context_release() for mutual exclusion.  Once the
> >> context is acquired no other thread can access it or run event loop 
> >> iterations
> >> in this AioContext.
> >>
> >> aio_context_acquire()/aio_context_release() calls may be nested.  This
> >> means you can call them if you're not sure whether #1 applies.
> >>
> >> Side note: the best way to schedule a function call across threads is to 
> >> create
> >> a BH in the target AioContext beforehand and then call qemu_bh_schedule(). 
> >>  No
> >> acquire/release or locking is needed for the qemu_bh_schedule() call.  But 
> >> be
> >> sure to acquire the AioContext for aio_bh_new() if necessary.
> >
> > How do these IOThreads pause during migration?
> > Are they paused by the 'qemu_mutex_lock_iothread' that the migration thread 
> > calls?
> 
> Currently the only IOThread user is virtio-blk data-plane.  It has a
> VM state change listener registered that will stop using the IOThread
> during migration.
> 
> In the future we'll have to do more than that:
> It is possible to suspend all IOThreads simply by looping over
> IOThread objects and calling aio_context_acquire() on their
> AioContext.  You can release the AioContexts when you are done.  This
> would be suitable for a "stop the world" operation for migration
> hand-over.

That worries me for two reasons:
   1) I'm assuming there is some subtlety so that it doesn't deadlock when
     another thread is trying to get a couple of contexts.
   2) The migration code that has to pause everything is reasonably time
      critical (OK not super critical - but it worries if it gains more than a 
few
      ms).   Doing something to each thread in series where that thread might
      have to finish up a transaction sounds like it could add together to be 
quite
      large.

> For smaller one-off operations like block-migration.c it may also make
> sense to acquire/release the AioContext.  But that's not necessary
> today since dataplane is disabled during migration.

I guess it's probably right to hide this behind some interface on the Aio stuff
that migration can call and it can worry about speed, and locking order etc.

I also would we end up wanting some IOThreads to continue - e.g. could we be 
using
them for transport of the migration stream or are they strictly for the guests
use?

Dave
--
Dr. David Alan Gilbert / address@hidden / Manchester, UK