Re: [PATCH v1 3/3] migration: multifd: Enable zerocopy

["Daniel P. Berrangé" <berrange@redhat.com>]

On Tue, Sep 07, 2021 at 12:13:28PM +0100, Dr. David Alan Gilbert wrote:
> * Daniel P. Berrangé (berrange@redhat.com) wrote:
> > On Wed, Sep 01, 2021 at 11:35:33AM -0400, Peter Xu wrote:
> > > On Wed, Sep 01, 2021 at 09:53:07AM +0100, Daniel P. Berrangé wrote:
> > > > On Tue, Aug 31, 2021 at 04:29:09PM -0400, Peter Xu wrote:
> > > > > On Tue, Aug 31, 2021 at 02:16:42PM +0100, Daniel P. Berrangé wrote:
> > > > > > On Tue, Aug 31, 2021 at 08:02:39AM -0300, Leonardo Bras wrote:
> > > > > > > Call qio_channel_set_zerocopy(true) in the start of every multifd thread.
> > > > > > > 
> > > > > > > Change the send_write() interface of multifd, allowing it to pass down
> > > > > > > flags for qio_channel_write*().
> > > > > > > 
> > > > > > > Pass down MSG_ZEROCOPY flag for sending memory pages, while keeping the
> > > > > > > other data being sent at the default copying approach.
> > > > > > > 
> > > > > > > Signed-off-by: Leonardo Bras <leobras@redhat.com>
> > > > > > > ---
> > > > > > >  migration/multifd-zlib.c | 7 ++++---
> > > > > > >  migration/multifd-zstd.c | 7 ++++---
> > > > > > >  migration/multifd.c      | 9 ++++++---
> > > > > > >  migration/multifd.h      | 3 ++-
> > > > > > >  4 files changed, 16 insertions(+), 10 deletions(-)
> > > > > > 
> > > > > > > @@ -675,7 +676,8 @@ static void *multifd_send_thread(void *opaque)
> > > > > > >              }
> > > > > > >  
> > > > > > >              if (used) {
> > > > > > > -                ret = multifd_send_state->ops->send_write(p, used, &local_err);
> > > > > > > +                ret = multifd_send_state->ops->send_write(p, used, MSG_ZEROCOPY,
> > > > > > > +                                                          &local_err);
> > > > > > 
> > > > > > I don't think it is valid to unconditionally enable this feature due to the
> > > > > > resource usage implications
> > > > > > 
> > > > > > https://www.kernel.org/doc/html/v5.4/networking/msg_zerocopy.html
> > > > > > 
> > > > > >   "A zerocopy failure will return -1 with errno ENOBUFS. This happens 
> > > > > >    if the socket option was not set, the socket exceeds its optmem 
> > > > > >    limit or the user exceeds its ulimit on locked pages."
> > > > > > 
> > > > > > The limit on locked pages is something that looks very likely to be
> > > > > > exceeded unless you happen to be running a QEMU config that already
> > > > > > implies locked memory (eg PCI assignment)
> > > > > 
> > > > > Yes it would be great to be a migration capability in parallel to multifd. At
> > > > > initial phase if it's easy to be implemented on multi-fd only, we can add a
> > > > > dependency between the caps.  In the future we can remove that dependency when
> > > > > the code is ready to go without multifd.  Thanks,
> > > > 
> > > > Also, I'm wondering how zerocopy support interacts with kernel support
> > > > for kTLS and multipath-TCP, both of which we want to be able to use
> > > > with migration.
> > > 
> > > Copying Jason Wang for net implications between these features on kernel side
> > > and whether they can be enabled together (MSG_ZEROCOPY, mptcp, kTLS).
> > > 
> > > From the safe side we may want to only enable one of them until we prove
> > > they'll work together I guess..
> > 
> > MPTCP is good when we're network limited for migration
> > 
> > KTLS will be good when we're CPU limited on AES for migration,
> > which is essentially always when TLS is used.
> > 
> > ZEROCOPY will be good when we're CPU limited for data copy
> > on migration, or to reduce the impact on other concurrent
> > VMs on the same CPUs.
> > 
> > Ultimately we woudld benefit from all of them at the same
> > time, if it were technically possible todo.
> 
> I think last time I spoke to Paolo Abeni there were some interactions
> between them; I can't remember what though (I think mptcp and ktls
> didn't play at the time).

MPTCP and KTLS use the same kernel hook in the network layer and
only 1 hook is permitted at a time, making them mutually exclusive
for now. In theory this can be fixed but no one is actively working
on it yet.


Regards,
Daniel
-- 
|: https://berrange.com      -o-    https://www.flickr.com/photos/dberrange :|
|: https://libvirt.org         -o-            https://fstop138.berrange.com :|
|: https://entangle-photo.org    -o-    https://www.instagram.com/dberrange :|