Re: lockf in installworld -- not a good idea

From: Ruslan Ermilov <ru_at_freebsd.org>
Date: Fri, 29 Sep 2006 18:24:05 +0400
On Fri, Sep 29, 2006 at 09:07:19AM -0500, Astrodog wrote:
> Personally, I find it much, much more important to be able to do an
> installworld from a "real" single user mode via NFS, than it is to support
> -j. I don't think I've ever had a circumstance where I really needed make
> installworld to finish quickly.
> 
This doesn't mean it's unused.  For example, our release engineers
build releases on fast SMP machines, and "make release" can complete
faster with -j on real SMP hardware.  This is btw how this bug was
found in the first place.

> Besides, if there's significant use of
> locks in installworld, -j doesn't get a whole lot of performance gain
> anyway.
> 
No, it's insignificant.

> Another thought here, is that in my experience, installworld is disk, or
> network I/O bound, not CPU... Under those circumstances, we may find that
> there's reduced performance with -j anyway, in which case there's no
> reason to support it that I can see.
> 
Do you have numbers on real SMP hardware to share?


Cheers,
-- 
Ruslan Ermilov
ru_at_FreeBSD.org
FreeBSD committer

Received on Fri Sep 29 2006 - 12:24:11 UTC

This archive was generated by hypermail 2.4.0 : Wed May 19 2021 - 11:39:00 UTC