[3348] in linux-scsi channel archive
Re: Warning low DMA Buffers
daemon@ATHENA.MIT.EDU (flavio santos)
Mon Feb 16 14:39:38 1998
Date: Mon, 16 Feb 1998 17:29:42 -0300
From: flavio santos <flavio@dtpdf.gov.br>
Reply-To: flavio@dtpdf.gov.br
To: Eric Youngdale <eric@andante.jic.com>
CC: linux-scsi@vger.rutgers.edu
Eric Youngdale wrote:
>
> ......
>
> Yes, it does negotiate the traffic in an indirect way. The point
> is that each low-level driver tells sr.c whether it needs bounce buffers
> or not. If the driver does need the bounce buffers, then it starts using
> memory from the pool. By the time the request reaches the 1542, the
> buffers that are listed in the request should all be <16Mb.
>
I've made an experiment recompiling the kernel setting the memory usage
limit in 16 Mb.
As a result, the Warning about running low on DMA buffers definitly
disapeared.
>
> The reason I pointed you at the differences between sd.c and sr.c
> is that apparently someone in the past put a fix in so that if a similar
> situation came up with disk drives, that a different recovery strategy
> would be used (that doesn't involve printing a message). The code is
> virtually identical between sd.c and sr.c, so all I am suggesting is that
> you transplant the handling code from sd.c into sr.c.
>
>-Eric
I've been reading the source code. As I can see in sr.c, you Mr. Eric
have made at least part of the distribution's source code yourself :)
Sorry, I'm not so good programmer ... so I couldn't find exactly what to
do ... I'm going to print sr.c and sd.c and take a look there, but I'm
not convinced if I really can deal with the problem myself.
