Re: [Gluster-devel] GlusterFS 4.0 plan

[Amar Tumballi]

On Thu, Dec 12, 2013 at 9:02 PM, Jeffrey Darcy <address@hidden> wrote:

> Here is a working draft of the plan for 4.0. It has pretty significant
> changes from the current model. Sending it out for early review/feedback.
> Further revisions will follow over time.

> https://gist.github.com/avati/af04f1030dcf52e16535#file-plan-md

Because I like inline comments for document collaboration and neither gist
nor etherpad have the right kind of support, I've created a Google Docs
version here.

    http://goo.gl/qLw3Vz

That's the public edit link; at this point others should be able to
*comment* but not edit the existing text.  Avati/Vijay, I'll gladly add
you as editors if you have Google accounts (or of course you're free to
make a copy).  I've added a bunch of my own comments already to get
discussions started.  >;-}

The topics mentioned are really nice to have for 4.0, but would be great to define what is our target, fixed time or fixed features.

At the moment, i see categories in there:

-> Filesystem related

  o Thinnified client (ie, implement a multipath xlator)

  o Sharding xlator

-> Mgmt related:

  o Everything glusterd

-> Some overlaps:

  o EHT: If glusterd is scalable to 10k nodes, then EHT becomes important (so in terms of time, this should come along with glusterd changes).

As Jeff says, Thinnified client should be our absolute goal for 4.0, and everything else as a EXPERIMENTAL (considering the sheer amount of work going to be involved in there). With this, i would like to propose a time bound approach (say late July 2014 (7 more months)) for branching 4.0, and another 2 more months for stress testing it and stabilizing.

Let me know thoughts.

-Amar

 

_______________________________________________
Gluster-devel mailing list
address@hidden
https://lists.nongnu.org/mailman/listinfo/gluster-devel