On Thu, Jul 08, 2010 at 11:54:18AM -0400, sfaibish wrote:
> Do you have an agenda? I want to include the details of the October
> BAT and a
> short discussion. I have a sketch of a webpage that I would like to
> post on CITI
> site today after the call. It is still WiP as I build it by myself
> until I can
> get our marketting to help. This is what I want to discuss assuming
> there is a call.
OK; how about the following.--b.
1. upstream status/merge plans (trond, bfields)
2. State of pNFS tree (bhalevy)
3. Client
3.1. Client pNFS status
3.2. Client state management design documentation (trond)
4. Server
4.1. Todo's for minimal 4.1 server (bfields)
4.2. pnfs
pnfs/gfs2
exofs
5. boston bakeathon
6. new business
7. next meeting
--b.
I posted a preliminary web page announcement for the Fall Bake-a-Thon in
Boston
on CITI website:
http://www.citi.umich.edu/projects/nfsv4/citi_bakeathon/15th_nfsv4_bakeathon.html
On Thu, 08 Jul 2010 13:45:58 -0400, J. Bruce Fields <[email protected]>
wrote:
> Also I'd like to hand off running and taking notes on this meeting to
> someone else for a while. (Benny, maybe?) Or we can go back to making
> the meeting more informal if that's preferred.
>
> --b.
>
> 1. upstream status/merge plans (trond, bfields)
> - upstream at 2.6.35-rc4.
> - server side: some bugfixes merged to callback code; allocation
> failures changed to return DELAY.
> - discussion of error return on client callback-parsing error.
> - trond: everything from before bakeathon is in nfs-2.6.36
> branch or upstream. Also some file locking bugfixes
> (bugzilla.kernel.org #14501). Also sending release_lockowner
> more often to keep server resources down.
>
> 2. State of pNFS tree (bhalevy)
> - working on patches from boaz and andy for release branch.
> Anyone else have big pending patchsets?
> - Jim is getting complex-volume block patches tested,
> will send them out soon.
> - Fred has some pending stuff ("minor cleanup")
> - next week would like to start cleaning up and squashing
> together patches. Also will truncate some of the history.
>
> 3. Client
> 3.1. Client pNFS status
> - Andy needs to look at state reclaim stuff?
> - Andy still wondering what to do with the nfs inode
> layout pointer. What's the lifetime of the thing that
> points to?
> 3.2. Client state management design documentation (trond)
> - Also, on docs: Andy will check that wiki docs are
> uptodate. And will do some more documentation of
> refcnts, as will Fred.
>
> 4. Server
> 4.1. Todo's for minimal 4.1 server (bfields)
> - still working on callback changes. Trond notes
> ongoing rpc code improvements may allow us to do much
> of this by keeping a single client and modifying its
> transports, in which case I may be able to replace my
> callbacks with single rpc tasks.
> - also fixing 4.0/4.1 bug that prevents exclusive locks
> on upgraded open.
> 4.2. pnfs
> - pnfs/gfs2
> - I'll ask Eric for a report on gfs2 bakeathon
> testing.
> - exofs
> - I'll ask Brian about citi exofs setup status.
>
> 5. boston bakeathon
> - October 4-8.
> - Details are finalized, to be posted soon.
> - If your company will be bringing large equipment, let Sorin
> know.
> - If anyone would be interested in sponsoring a reception or
> other addition to the bakeathon, contact Sorin. (Or if you
> know who at your company would handle such a thing, let Sorin
> know.)
>
> 6. new business
> - Sorin asked Trond for summary of layout-commit discussion.
> Discussion ensued.
>
> 7. next meeting
> - next week as usual.
> --
> To unsubscribe from this list: send the line "unsubscribe linux-nfs" in
> the body of a message to [email protected]
> More majordomo info at http://vger.kernel.org/majordomo-info.html
>
>
--
Best Regards
Sorin Faibish
Corporate Distinguished Engineer
Network Storage Group
EMC?
where information lives
Phone: 508-435-1000 x 48545
Cellphone: 617-510-0422
Email : [email protected]
Also I'd like to hand off running and taking notes on this meeting to
someone else for a while. (Benny, maybe?) Or we can go back to making
the meeting more informal if that's preferred.
--b.
1. upstream status/merge plans (trond, bfields)
- upstream at 2.6.35-rc4.
- server side: some bugfixes merged to callback code; allocation
failures changed to return DELAY.
- discussion of error return on client callback-parsing error.
- trond: everything from before bakeathon is in nfs-2.6.36
branch or upstream. Also some file locking bugfixes
(bugzilla.kernel.org #14501). Also sending release_lockowner
more often to keep server resources down.
2. State of pNFS tree (bhalevy)
- working on patches from boaz and andy for release branch.
Anyone else have big pending patchsets?
- Jim is getting complex-volume block patches tested,
will send them out soon.
- Fred has some pending stuff ("minor cleanup")
- next week would like to start cleaning up and squashing
together patches. Also will truncate some of the history.
3. Client
3.1. Client pNFS status
- Andy needs to look at state reclaim stuff?
- Andy still wondering what to do with the nfs inode
layout pointer. What's the lifetime of the thing that
points to?
3.2. Client state management design documentation (trond)
- Also, on docs: Andy will check that wiki docs are
uptodate. And will do some more documentation of
refcnts, as will Fred.
4. Server
4.1. Todo's for minimal 4.1 server (bfields)
- still working on callback changes. Trond notes
ongoing rpc code improvements may allow us to do much
of this by keeping a single client and modifying its
transports, in which case I may be able to replace my
callbacks with single rpc tasks.
- also fixing 4.0/4.1 bug that prevents exclusive locks
on upgraded open.
4.2. pnfs
- pnfs/gfs2
- I'll ask Eric for a report on gfs2 bakeathon
testing.
- exofs
- I'll ask Brian about citi exofs setup status.
5. boston bakeathon
- October 4-8.
- Details are finalized, to be posted soon.
- If your company will be bringing large equipment, let Sorin
know.
- If anyone would be interested in sponsoring a reception or
other addition to the bakeathon, contact Sorin. (Or if you
know who at your company would handle such a thing, let Sorin
know.)
6. new business
- Sorin asked Trond for summary of layout-commit discussion.
Discussion ensued.
7. next meeting
- next week as usual.