From: Justin Azoff <JAzoff@albany.edu>
To: b43-dev@lists.infradead.org
Subject: BCM4312 LP-PHY DMA issues
Date: Thu, 24 Nov 2011 10:09:22 -0500 [thread overview]
Message-ID: <20111124150922.GJ6004@datacomm.albany.edu> (raw)
In-Reply-To: <CACna6rw6SnLo=M=NKPzv_yb665aj6WCoR8VBNA9goS9otQB8Lw@mail.gmail.com>
On Thu, Nov 24, 2011 at 07:35:23AM +0100, Rafa? Mi?ecki wrote:
> Huh, that sound interesting. So updating firmware fixed DMA issues for
> you, right? Are you really sure you're using DMA?
Yeah, with the old firmware I had to force pio=1 to get it to work at
all. With the new firmware I removed the module options and it works
great, and there are no DMA errors in dmesg. The cpu usage also went
from 100% to <10%
> I didn't think Broadcom could fix something about DMA errors
> (timeouts?) of LP-PHY in the recent firmware.
Got me :-) Maybe it's not really a DMA error in the first place.. maybe
the old firmware just has issues with this hardware that get detected as
a DMA error but are really caused by a general failure somewhere else?
> Is this still working fine for you? After that ~2 days?
Yes! I built 3 of these laptops to run as wireless probes using
https://github.com/justinazoff/wireless-probes so I have detailed logs..
2011-11-24 08:49:33 check=DL avg_speed=1723
2011-11-24 08:55:01 check=DL avg_speed=2269
2011-11-24 09:00:28 check=DL avg_speed=1880
2011-11-24 09:05:57 check=DL avg_speed=2227
2011-11-24 09:11:24 check=DL avg_speed=1850
2011-11-24 09:16:52 check=DL avg_speed=2518
2011-11-24 09:22:18 check=DL avg_speed=1685
2011-11-24 09:27:48 check=DL avg_speed=1723
2011-11-24 09:33:17 check=DL avg_speed=2233
2011-11-24 09:38:44 check=DL avg_speed=2013
2011-11-24 09:44:11 check=DL avg_speed=1929
2011-11-24 09:49:39 check=DL avg_speed=1551
2011-11-24 09:51:30 check=DL avg_speed=1717
2011-11-24 09:56:59 check=DL avg_speed=1953
Before, it looked like this:
2011-11-19 06:19:41 check=DL avg_speed=856
2011-11-19 06:25:34 check=DL avg_speed=847
2011-11-19 06:31:30 check=DL avg_speed=858
2011-11-19 06:37:26 check=DL avg_speed=857
2011-11-19 06:43:20 check=DL avg_speed=853
2011-11-19 06:49:12 check=DL avg_speed=864
2011-11-19 06:55:08 check=DL avg_speed=857
2011-11-19 07:01:01 check=DL avg_speed=851
2011-11-19 07:06:54 check=DL avg_speed=854
2011-11-19 07:12:47 check=DL avg_speed=848
2011-11-19 07:18:41 check=DL avg_speed=856
2011-11-19 07:24:37 check=DL avg_speed=846
2011-11-19 07:30:32 check=DL avg_speed=854
--
-- Justin Azoff
-- Network Security & Performance Analyst
prev parent reply other threads:[~2011-11-24 15:09 UTC|newest]
Thread overview: 5+ messages / expand[flat|nested] mbox.gz Atom feed top
2011-11-22 0:00 BCM4312 LP-PHY DMA issues Justin Azoff
2011-11-22 16:13 ` Dominique Martinet
2011-11-22 17:45 ` Justin Azoff
2011-11-24 6:35 ` Rafał Miłecki
2011-11-24 15:09 ` Justin Azoff [this message]
Reply instructions:
You may reply publicly to this message via plain-text email
using any one of the following methods:
* Save the following mbox file, import it into your mail client,
and reply-to-all from there: mbox
Avoid top-posting and favor interleaved quoting:
https://en.wikipedia.org/wiki/Posting_style#Interleaved_style
* Reply using the --to, --cc, and --in-reply-to
switches of git-send-email(1):
git send-email \
--in-reply-to=20111124150922.GJ6004@datacomm.albany.edu \
--to=jazoff@albany.edu \
--cc=b43-dev@lists.infradead.org \
/path/to/YOUR_REPLY
https://kernel.org/pub/software/scm/git/docs/git-send-email.html
* If your mail client supports setting the In-Reply-To header
via mailto: links, try the mailto: link
Be sure your reply has a Subject: header at the top and a blank line
before the message body.
This is a public inbox, see mirroring instructions
for how to clone and mirror all data and code used for this inbox