Volker Lendecke Volker.Lendecke at SerNet.DE
Wed Feb 15 05:49:03 MST 2012

On Wed, Feb 15, 2012 at 02:39:42PM +0100, David Disseldorp wrote:
> > Can we get a _send and _recv pair of those into the VFS, for
> > obvious reasons?
> Should copy_chunk asynchronicity be handled at a higher layer, or is it
> the intention that VFS presents send/receive pairs for all operations
> that are potentially IO intensive?

Not sure. Handling it at a higher layer means we have to
make the VFS thread-safe, so that we can handle VFS calls in
a helper thread. This is surely doable, but I would expect
it to be a major undertaking and a really high burden on all
vfs module implementers.

On a second thought: Why do we need copychunk in the VFS at
all? We have pread and pwrite in both sync and async
flavor. We could handle the copychunk stuff in the core smbd
building upon those. Or are there native file systems that
do copychunk? If so, I would still vote for _send and _recv,
to enable a pthreadpool implementation.

With best regards,

Volker Lendecke

SerNet GmbH, Bahnhofsallee 1b, 37081 Göttingen
phone: +49-551-370000-0, fax: +49-551-370000-9
AG Göttingen, HRB 2816, GF: Dr. Johannes Loxen
http://www.sernet.de, mailto:kontakt at sernet.de

More information about the samba-technical mailing list