From mboxrd@z Thu Jan  1 00:00:00 1970
X-Spam-Checker-Version: SpamAssassin 3.4.4 (2020-01-24) on inbox.vuxu.org
X-Spam-Level: *
X-Spam-Status: No, score=1.1 required=5.0 tests=DATE_IN_PAST_03_06
	autolearn=no autolearn_force=no version=3.4.4
Received: (qmail 3641 invoked from network); 2 Apr 2021 19:32:54 -0000
Received: from 1ess.inri.net (216.126.196.35)
  by inbox.vuxu.org with ESMTPUTF8; 2 Apr 2021 19:32:54 -0000
Received: from duke.felloff.net ([216.126.196.34]) by 1ess; Fri Apr  2 10:31:35 -0400 2021
Message-ID: <BD0954193FCDD8EA226429D4A9EF81E1@felloff.net>
Date: Fri, 02 Apr 2021 16:31:24 +0200
From: cinap_lenrek@felloff.net
To: 9front@9front.org
In-Reply-To: <4716E825-EBBF-46DD-8BC9-5F836C9E294E@cpan.org>
MIME-Version: 1.0
Content-Type: text/plain; charset="US-ASCII"
Content-Transfer-Encoding: 7bit
List-ID: <9front.9front.org>
List-Help: <http://lists.9front.org>
X-Glyph: ➈
X-Bullshit: general-purpose framework event-based frontend 
Subject: Re: [9front]
Reply-To: 9front@9front.org
Precedence: bulk

This is why we'r loosing amlsost 2GB of user memory because
of the high fragmentation of the memory map.

The xinit errors are due to us running out of pallocmem slots.

change the Palloc struct in /sys/src/9/port/portdat.h:

-	Pallocmem	mem[16];	/* physical user page banks */
+	Pallocmem	mem[32];	/* physical user page banks */

We could also try to minimize the memory loss by sorting the
Conf.mem[] array by region size.

For the machine check, do you confirm that it is related to
the bcm ethernet driver? And when you removed the driver
that it went away?

--
cinap