From mboxrd@z Thu Jan  1 00:00:00 1970
MIME-Version: 1.0
In-Reply-To: <8958c1578747eede379d83afdf918114@ladd.quanstro.net>
References: <20100206161207.GA31545@centaur.acm.jhu.edu>
	<8958c1578747eede379d83afdf918114@ladd.quanstro.net>
From: Venkatesh Srinivas <me@acm.jhu.edu>
Date: Thu, 11 Feb 2010 08:31:14 -0500
Message-ID: <f75780241002110531l34204808icbabc8430737bcfd@mail.gmail.com>
To: Fans of the OS Plan 9 from Bell Labs <9fans@9fans.net>
Content-Type: text/plain; charset=UTF-8
Content-Transfer-Encoding: quoted-printable
Subject: Re: [9fans] kenfs question?
Topicbox-Message-UUID: d2891a60-ead5-11e9-9d60-3106f5b1d025

On Sat, Feb 6, 2010 at 11:16 AM, erik quanstrom <quanstro@quanstro.net> wro=
te:
>> ilock() (pc/lock.c) calls splhi() and then calls lock(). If that lock we=
re contended,
>> how would the system not stop? And on a UP system, if you're inside an s=
plhi() block,
>> why would you need to take an uncontended lock?
>
> good question. =C2=A0on a up system, splhi() is sufficient. =C2=A0on a mp
> system, the losing process will spin until the winning process
> is finished.
>
> ken fs does need to return to its mp roots.
>

Did kenfs ever run on MP systems and use >1 CPU?

-- vs