Re: Kernel deadlock using nbd over acenic driver.

From: "Peter T. Breuer" <ptb@it.uc3m.es>
To: Oliver Xymoron <oxymoron@waste.org>
Cc: "Peter T. Breuer" <ptb@it.uc3m.es>,
	"chen, xiangping" <chen_xiangping@emc.com>,
	"'Jes Sorensen'" <jes@wildopensource.com>,
	"'Steve Whitehouse'" <Steve@ChyGwyn.com>,
	linux-kernel@vger.kernel.org
Subject: Re: Kernel deadlock using nbd over acenic driver.
Date: Thu, 16 May 2002 18:45:29 +0200 (MET DST)	[thread overview]
Message-ID: <200205161645.g4GGjTu29201@oboe.it.uc3m.es> (raw)
In-Reply-To: <Pine.LNX.4.44.0205161042330.14957-100000@waste.org> from Oliver Xymoron at "May 16, 2002 11:22:13 am"

"Oliver Xymoron wrote:"
> On Thu, 16 May 2002, Peter T. Breuer wrote:
> > Any way of making sure that send_msg on the socket can always get the
> > (known a priori) buffers it needs?
> 
> Not at present. Note that we also need reservations on the receive side
> for ACK handling which is "interesting".

One thing at a time.  What if there is a zone "ceiling" that we keep
lowered exactly until it is time for the process that does the send_msg
to run, when we raise the ceiling.  (I don't know how this VM stuff
works in detail inside - this is an invitation to list the objections).
The scheduler could presumably be trained to muck with the ceilings
according to flags on the process (task?) structs.

Peter