[Gluster-Maintainers] [Gluster-devel] Changing Submit Type on review.gluster.org

Niels de Vos ndevos at redhat.com
Thu Sep 7 10:49:39 UTC 2017


On Thu, Sep 07, 2017 at 12:06:19PM +0530, Amar Tumballi wrote:
> On Thu, Sep 7, 2017 at 11:50 AM, Nigel Babu <nigelb at redhat.com> wrote:
> 
> > Hello folks,
> >
> > A few times, we've merged dependent patches out of order because the Submit
> > type[1] did not block us from doing so. The last few times we've talked
> > about
> > this, we didn't actually take a strong decision either way. In yesterday's
> > maintainers meeting, we agreed to change the Submit type to
> > Rebase-If-Necessary. This change will happen on 18th September 2017.
> >
> > What this means:
> > * No more metadata flags added by Gerrit. There will only be a Change-Id,
> >   Signed-off-by, and BUG (if you've added it). Gerrit itself will not add
> > any
> >   metadata.
> > * If you push a patch on top of another patch, the Submit button will
> > either be
> >   grayed out because the dependent patches cannot be merged or they will be
> >   submited in the correct order in one go.
> >
> > Some of the concerns that have been raised:
> > Q: With the Reviewed-on flag gone, how do we keep track of changesets
> >    (especially backports)?
> > A: The Change-Id will get you all the data directly on Gerrit. As long you
> >    retain the Change-Id, Gerrit will get you the matching changesets.
> >
> > Q: Will who-wrote-what continue to work?
> > A: As far as I can see, it continues to work. I ran the script against
> >    build-jobs repo and it works correctly. Additionally, we'll be setting
> > up an
> >    instance of Gerrit Stats[2] to provide more detailed stats.
> >
> > Q: Can we have some of the metadata if not all?
> > Q: Why can't we have the metadata if we change the submit type?
> > A: There's no good answer to this other than, this is how Gerrit works and
> >    I can neither change it nor control it.
> >
> >
> One of the major other concerns, which is valid is, stats on 'Reviewed-By'.
> Ie, people who actually reviewed the code. This metrics is equally
> important as 'who-wrote-the-patch', again, getting an infra like [2] below
> will solve it.

The <glusterfs>/extras/who-wrote-glusterfs/who-wrote-glusterfs.sh script
will continue to work, but some of the statistics will not be available.
It is nice to have a Reviewed-by tag in the git commit message, but the
one that Gerrit adds is not complete in any case. Reviewers that did not
review the last version of the patch before it got merged do not get
added in the Gerrit-automated-commit-message-ammending. The statistics
of the who-wrote-glusterfs.sh script are cool, and people appreciate
their names in the git logs, but the script should not be used for
serious statistic gathering.

The gerritstats webapp seems much more appropriate for this.

Cheers,
Niels


> 
> Regards,
> Amar
> 
> 
> > [1]: https://review.gluster.org/Documentation/intro-project-
> > owner.html#submit-type
> > [2]: http://gerritstats-demo.firebaseapp.com/
> >
> > --
> > nigelb
> > _______________________________________________
> > maintainers mailing list
> > maintainers at gluster.org
> > http://lists.gluster.org/mailman/listinfo/maintainers
> >
> 
> 
> 
> -- 
> Amar Tumballi (amarts)

> _______________________________________________
> Gluster-devel mailing list
> Gluster-devel at gluster.org
> http://lists.gluster.org/mailman/listinfo/gluster-devel



More information about the maintainers mailing list