threads and VMS [Re: dce/rpc "client" api]

[Luke Kenneth Casson Leighton]

On Wed, 23 Aug 2000, Jeremy Allison wrote:

> Bob Mastors wrote:
> > 
> > A single NT client running netbench will have multiple outstanding
> > CIFS commands to a server at many points in time. In other words
> > the NT client will not always wait for a CIFS command to complete
> > before issuing another one.
> 
> That's fine - such things get queued in the TCP layer
> in the current smbd design.

the point is that if you can take them out of the TCP queue and initiate
them, where potentially the max_mux negotiation says that there could be
up to *50* CIFS commands coming at you over the same SMB connection, only
dealing with one at a time seems to say "bottleneck" if the server-end is
a single-process, to me.
 
> > To take advantage of this you could keep the samba model of one
> > smbd per connection but redesign smbd to use posix threads.
> > This won't make the security context issues any different than
> > in the current smbd design.
> 
> True - but it does complicate the smbd architecture considerably.
> All smbd code would need to be fixed to be thread safe. This is
> not a trivial change.

there is an alternative, and it may hit with a small performance penalty,
i described it in other messages.