Re: [PATCH v2 7/7] 9pfs: reduce latency of Twalk

[Greg Kurz]

On Fri, 02 Jul 2021 17:05:32 +0200
Christian Schoenebeck <qemu_oss@crudebyte.com> wrote:

> On Freitag, 2. Juli 2021 16:36:56 CEST Greg Kurz wrote:
> > On Fri, 4 Jun 2021 17:38:31 +0200
> > 
> > Christian Schoenebeck <qemu_oss@crudebyte.com> wrote:
> > > As with previous performance optimization on Treaddir handling;
> > > reduce the overall latency, i.e. overall time spent on processing
> > > a Twalk request by reducing the amount of thread hops between the
> > > 9p server's main thread and fs worker thread(s).
> > > 
> > > In fact this patch even reduces the thread hops for Twalk handling
> > > to its theoritical minimum of exactly 2 thread hops:
> > > 
> > > main thread -> fs worker thread -> main thread
> > > 
> > > This is achieved by doing all the required fs driver tasks altogether
> > > in a single v9fs_co_run_in_worker({ ... }); code block.
> > > 
> > > Signed-off-by: Christian Schoenebeck <qemu_oss@crudebyte.com>
> > > ---
> > > 
> > >  hw/9pfs/9p.c | 89 +++++++++++++++++++++++++++++++++++++++++-----------
> > >  1 file changed, 70 insertions(+), 19 deletions(-)
> > > 

[...]

> 
> Yeah, there is a lot more to do on v9fs_walk(), both cleanup, as well as the 
> previously (couple weeks ago) mentioned protocol fix (i.e. Twalk should only 
> reply Rerror if there is an error on the very first path element).
> 

Ah yes... I had forgotten about this one. One more argument for a thorough
rewrite of this function.

> If you don't mind, I queue this patch as is for now and prepare a PR for the 
> current 9p patches in my queue in order to bring them into the soft freeze 
> deadline.
> 

Sure, please do.

> Thanks for looking at this Greg, I appreciate it!
> 

Upcoming soft freeze provided the extra motivation to finish the review :-)

> Best regards,
> Christian Schoenebeck
> 
> 

Cheers,

--
Greg