Date: Fri, 29 Oct 2010 09:17:04 -0700 From: Jeremy Chadwick <freebsd@jdc.parodius.com> To: freebsd-fs@FreeBSD.ORG, rainer@ultra-secure.de Subject: Re: 8.1-RELEASE and cddl-sources from STABLE Message-ID: <20101029161704.GA81450@icarus.home.lan> In-Reply-To: <201010291556.o9TFuo15069942@lurza.secnetix.de> References: <ab57553ca5f4ad33ab091924d72be95b.squirrel@webmail.ultra-secure.de> <201010291556.o9TFuo15069942@lurza.secnetix.de>
next in thread | previous in thread | raw e-mail | index | archive | help
On Fri, Oct 29, 2010 at 05:56:50PM +0200, Oliver Fromme wrote:
> rainer@ultra-secure.de wrote:
> > is it possible to somehow get all the MFCs for ZFS-stuff that went into
> > STABLE to compile in RELENG_8_1?
> > I tried (as suggested by someone) to just copy over the cddl-src-tree, but
> > that did not work:
> >
> > [142 lines of error messages]
>
> RELENG_8 (a.k.a. 8/stable) will most certainly be more stable
> than trying to cross-breed major parts of the source tree from
> different branches.
>
> Best regards
> Oliver
> (who never used a "-RELEASE" in ~ 15 years of FreeBSD, except
> for testing purposes or for inital installs from CD/DVD which
> where then updated to -stable promptly.)
It might not be worth much, but my opinions follow that of Oliver and
Andriy. We haven't run -RELEASE branches on any of our production
servers since the early 4.x days, nor have I run such at home. I do the
exact same thing as Oliver.
I recently described the reasoning to someone on a forum who asked for
my advice as to whether or not he should follow/use RELENG_8, in
anticipation of RELENG_8_2 (8.2-RELEASE), with his main focus being ZFS.
I always assume users want overall stability/reliability *in addition*
to support for bugs they encounter -- and you will encounter them.
Here's a snippet of what I wrote:
= The most common response on freebsd-stable to someone running -RELEASE
= is "can you please try RELENG_8 instead?" The RELENG_x_y branches I've
= never followed because the instant you encounter a bug you have to wait
= until the next -RELEASE to experience the fix; the only things
= backported are major (as in widespread) kernel panics or security
= issues. Years of experience has shown me that 90% of the time a "bug"
= is going to be something less severe than those two, but still severe
= enough to cause major anxiety ("How the heck am I going to fix this?
= Can I work around it? Oh god, rolling back to 7.x?!") and make you
= wonder what you're going to do about it (feeling of helplessness,
= etc.). Just follow the -STABLE branch and watch commits and/or
= follow the mailing lists.
The last half of the above should (hopefully) hit home.
You should run whatever branch (or OS for that matter!) works best for
you and your situation, but I get better overall support (both from
developers and the community) running RELENG_x and not -RELEASE.
"But isn't -STABLE 'riskier' than -RELEASE?" Yes. But nothing forces
you to update your src tree. If you do csup one day, rebuild
world/kernel, and find you're encountering a problem, it's painless to
roll back to a previous date with csup: look at the "date=" option which
you can use in your supfiles. I've had to use this quite a few times
over the years.
Of course, I csup once a day, sometimes more than that. I also follow
commits as best as I can. I'm a bit more OCD than your average system
administrator -- but that comes from past experiences where being lax
and expecting a server to "manage itself" (turn it on, don't touch it
for 7 million days, e.g. negligence) resulted in Bad Things(tm).
--
| Jeremy Chadwick jdc@parodius.com |
| Parodius Networking http://www.parodius.com/ |
| UNIX Systems Administrator Mountain View, CA, USA |
| Making life hard for others since 1977. PGP: 4BD6C0CB |
Want to link to this message? Use this URL: <https://mail-archive.FreeBSD.org/cgi/mid.cgi?20101029161704.GA81450>