messenger changes

messenger changes

[Sage Weil]

Hey Matt,

Can you join us for the core standup tomorrow, or shortly after, to sycn 
up on the messenger changes needed for xio?

I've taken most of the generic messenger refactoring and changes that I 
see that aren't yet xio-specific and pulled them into wip-msgr:

	https://github.com/ceph/ceph/pull/1883

The main things I see now that are blocking the rest of the xio stuff:

 - xio specific code in the buffer class

 - the Message completion hook and other stuff needs to be separated out 
into a separate patch that goes ahead of the other pieces

 - I don't think creating multiple Messenger instances for all of the OSD, 
mon, etc is going to work well.  We need to figure out a generic way to 
instantiate them without adding support that is specific to every 
subsystem/client/daemon/whatever.  Probably this means passing an address 
type to the Messenger::create() method, or something similar. For now, I 
think we can focus on a single transport for each part of the system 
(e.g., osd<->osd) and not worry about multiprotocol support.  That will 
get us to something usable much sooner.

sage

Re: messenger changes

[Matt W. Benjamin]

Hi Sage,

Sure, I'll join the core standup.  I think you have the right ideas, I'll give
it some more thought as well, before tomorrow's meeting.

Thanks,

Matt

----- "Sage Weil" <sage@inktank.com> wrote:

> Hey Matt,
> 
> Can you join us for the core standup tomorrow, or shortly after, to
> sycn 
> up on the messenger changes needed for xio?
> 
> I've taken most of the generic messenger refactoring and changes that
> I 
> see that aren't yet xio-specific and pulled them into wip-msgr:
> 
> 	https://github.com/ceph/ceph/pull/1883
> 
> The main things I see now that are blocking the rest of the xio
> stuff:
> 
>  - xio specific code in the buffer class
> 
>  - the Message completion hook and other stuff needs to be separated
> out 
> into a separate patch that goes ahead of the other pieces
> 
>  - I don't think creating multiple Messenger instances for all of the
> OSD, 
> mon, etc is going to work well.  We need to figure out a generic way
> to 
> instantiate them without adding support that is specific to every 
> subsystem/client/daemon/whatever.  Probably this means passing an
> address 
> type to the Messenger::create() method, or something similar. For now,
> I 
> think we can focus on a single transport for each part of the system 
> (e.g., osd<->osd) and not worry about multiprotocol support.  That
> will 
> get us to something usable much sooner.
> 
> sage
> 
> --
> To unsubscribe from this list: send the line "unsubscribe ceph-devel"
> in
> the body of a message to majordomo@vger.kernel.org
> More majordomo info at  http://vger.kernel.org/majordomo-info.html

-- 
Matt Benjamin
The Linux Box
206 South Fifth Ave. Suite 150
Ann Arbor, MI  48104

http://linuxbox.com

tel.  734-761-4689 
fax.  734-769-8938 
cel.  734-216-5309