Date: Tue, 15 Apr 2008 14:42:22 +0200 From: "Niclas Zeising" <niclas.zeising@gmail.com> To: "=?ISO-8859-1?Q?S=F8ren_Schmidt?=" <sos@freebsd.org> Cc: cvs-src@freebsd.org, src-committers@freebsd.org, cvs-all@freebsd.org Subject: Re: cvs commit: src/sys/dev/ata ata-all.h ata-chipset.c ata-dma.c ata-lowlevel.c Message-ID: <bc292860804150542w524995b2p6255da691d20f5cd@mail.gmail.com> In-Reply-To: <1DFDA463-5E5E-4EE5-BF2D-E738D10E57F7@FreeBSD.org> References: <200804141834.m3EIYOXP044870@repoman.freebsd.org> <4803D34C.4030706@gmail.com> <1DFDA463-5E5E-4EE5-BF2D-E738D10E57F7@FreeBSD.org>
next in thread | previous in thread | raw e-mail | index | archive | help
On Tue, Apr 15, 2008 at 2:28 PM, S=F8ren Schmidt <sos@freebsd.org> wrote: > Hi > > Thats actually a separate problem. I've put in stops to check that the P= RD > table size doesn't get out of hand. Until now that wasn't a problem but n= ow > that we move to having more than on request flying pr channel it needs to= be > within bounds. > The check correctly panic's as we outgrow the table, however thats not v= ery > usefull :) Not really, no ;) Just a (perhaps silly) question, is my hardware wierd as no-one else has reported this problem (as I've seen anyway). I'm just curious. > > Fix coming up with the next round of updates, I also need to go back to = the > old way of preallocing the SG tables etc, busdma is simply too cycle gree= dy > to be called for each request, as performance has been shown to decrease > quite a bit. Okay. I'll sit tight and wait for the fix. If you need some testing just drop me a note. Thanks for the quick reply! > > -S=F8ren > > [SNIP old messages] Regards! Niclas
Want to link to this message? Use this URL: <https://mail-archive.FreeBSD.org/cgi/mid.cgi?bc292860804150542w524995b2p6255da691d20f5cd>