Date: Mon, 07 Nov 2005 18:30:35 +0100 From: Attila Nagy <bra@fsn.hu> To: Scott Long <scottl@samsco.org> Cc: freebsd-amd64@FreeBSD.ORG, SXren Schmidt <sos@FreeBSD.ORG> Subject: Re: busdma dflt_lock on amd64 > 4 GB Message-ID: <436F8F3B.6050306@fsn.hu> In-Reply-To: <4360DE3C.6010209@samsco.org> References: <6.2.3.4.0.20051025171333.03a15490@pop.interactivemediafactory.net> <6.2.3.4.0.20051026131012.03a80a20@pop.interactivemediafactory.net> <435F8E06.9060507@samsco.org> <08A81034-AB5D-4BFC-8F53-21501073D674@FreeBSD.ORG> <435FA542.3030209@samsco.org> <6.2.3.4.0.20051026180325.03ad7558@wheresmymailserver.com> <42A1B51D-5A5E-4849-96D0-BC5C2DD1AE97@FreeBSD.ORG> <6.2.3.4.0.20051027121824.03d34dd8@wheresmymailserver.com> <4360DE3C.6010209@samsco.org>
next in thread | previous in thread | raw e-mail | index | archive | help
Scott Long wrote: >> I also wonder if allocating bounce pages on <=4G configurations is >> really needed/useful? There are probably situations where this is >> needed, but I'm not sure I understand why. > It sounds like the only real bug in busdma is that it gets confused by > ALLOCNOW and doesn't allow enough pages to be allocated when > bus_dmamap_create() is called. I'll look into this. It seems that this is the last post in this topic. I have an HP DL145G2 with 4 GB RAM (dual AMD64) and with two SATA disks, on which I created a mirror (gmirror). It dies with this in the moment I issue gmirror insert ad6 on a degraded mirror. Setting hw.physmem below 4G solves the issue. The interesting stuff is that the machine worked with 4G with earlier kernels (6.0-BETA5 I think). What has changed? Thanks, -- Attila Nagy e-mail: Attila.Nagy@fsn.hu Free Software Network (FSN.HU) phone: +3630 306 6758 ISOs: http://www.fsn.hu/?f=download
Want to link to this message? Use this URL: <https://mail-archive.FreeBSD.org/cgi/mid.cgi?436F8F3B.6050306>