Skip site navigation (1)Skip section navigation (2)
Date:      Wed, 18 Jan 2006 11:11:09 -0500 (EST)
From:      Daniel Eischen <deischen@freebsd.org>
To:        rookie@gufi.org
Cc:        freebsd-hackers@freebsd.org
Subject:   Re: How priority propagation works on read/write lock?
Message-ID:  <Pine.GSO.4.43.0601181100511.18649-100000@sea.ntplx.net>
In-Reply-To: <3bbf2fe10601180715k25297666y@mail.gmail.com>

next in thread | previous in thread | raw e-mail | index | archive | help
On Wed, 18 Jan 2006, rookie wrote:

> 2006/1/18, Daniel Eischen <deischen@freebsd.org>:
> >You will eventually do priority propagation for all of them
> > (A, B, and C) until G's priority is <= the priority of RW1.
> > It doesn't matter if you do one at a time or all of them
> > at once.  They all (A, B, C) have to release RW1 before
> > G can run
>
> You don't point out the problem.
> Here the problem is propagating priority to D, {E1, E2, E3} and F. If it
> doesn't happen the whole system will starve.

I assume we already know how to propagate priority for mutexes, so
once you know how to propagate for RWlocks, it all just works.
Yes, once you choose a thread to propagate, you have to keep
propagating through whatever it is blocked on or until you
reach a point where the propagated priority is <= the priority
of the next thread in the heirarchy.  I never questioned that
part of it, just the need to do it for all threads owning the
RW lock at the same time.

-- 
DE




Want to link to this message? Use this URL: <https://mail-archive.FreeBSD.org/cgi/mid.cgi?Pine.GSO.4.43.0601181100511.18649-100000>