[Gluster-users] gluster 3.2.0 - totally broken?

[Whit Blauvelt]

On Wed, May 18, 2011 at 10:34:43AM -0700, Anand Avati wrote:
>      3.1.4 - gained a few bugs
> 
>    Can someone throw more light on this? We do not have any open bugs in
>    bugzilla marked against 3.1.4 - which means either
>    a) They were reported and fixed, but we haven't made a release yet
>    b) We have not been fixing it because we have not yet heard about it!
>    Avati

I was summarizing statements on this list recently, to the effect that 3.1.4
was less dependable in production than 3.1.3. That can be true, and still be
consistent with those bugs having been reported and fixed, but you "haven't
made a release yet." From the point of view of a systems administrator, bug
fixes which haven't been released are of no use. The only question for a
sysadmin in a corporate context is what software, in what version can be run
dependably today. So it may be that 3.1.4 _as it was released_ has more bugs
than 3.1.3 as it was released. If those have been closed since, that's all
to the good, but only truly useful in the real world if a 3.1.5 version is
released that contains only bug fixes to the 3.1.x series, and no new
features. New features can introduce new bugs and regressions. From a number
of reports here, it looks like that's what happened with 3.2.0.

A 3.1.x release with 100% implementation of Posix group file permissions,
for instance, would be a very good thing, and be a solid foundation on which
to build your reputation. If you already have the Posix group permissions
bug fixed, just rolling that into 3.1.x and releasing that as 3.1.5 should
do you well. Once 3.1.x simply does all its advertised features well, that
in itself will be a compelling argument for installation and use. Once you
have a large installed user base, your market for support contracts will
expand greatly, in turn allowing you to hire more staff for quality control
as you add more features to the core product.

Best,
Whit