On Mon, Jan 24, 2011 at 12:27:16PM -0000, Pawel Moll wrote:
> So - we'll try to enlarge FIFO. For the moment - playing with interrupts
> affinity seem to be a viable workaround.
I don't think enlarging the FIFO will help too much. The issue is
whether the CPU can keep up with the data rate coming off the card.
If it can't, then no matter how large the FIFO is, it will eventually
overflow.
The real answer is to avoid PIO mode, and use DMA support. However,
I've had problems using DMA on the ARM development boards. You can
find details my DMA issues internally within ARM by talking to Catalin.
The alternative answer, I believe implemented by some of ARMs silicon
partners, is to turn the card clock off when the FIFO becomes full/empty
to stop it sending more data. I think this violates some of the MMC/SD
requirements, but it seems to work for the silicon partners just fine.
Hi,
I am struggling to run perf tool on u8500 as hwpacks for 2.6.35 kernel are
still not out. Can someone help me know if anyone is using perf on arm-based
board such as panda, beagle etc.
Ideally, I would like to start a firefox application, and run command
'perf stat -p <pid_of_firefox> -e cycles sleep 1'
Regards,
Sudip
Enclosed you'll find a link to the agenda, notes and actions from the
Linaro Developer Platforms Weekly Status meeting held on February 2nd
in #linaro-meeting on irc.freenode.net at 16:00 UTC.
https://wiki.linaro.org/Platform/Foundations/2011-02-02
Actions from the meeting where as follows:
* JamieBennett to come up with test assignments for the new developer image
* jcrigby to write up landing team u-boot, kernel workflows and send
for review after first draft is done
* slangasek to review
https://wiki.linaro.org/Platform/DevPlatform/Specs/MemoryFootprintMethodolo…
for dmart
* ppearse to figure out what version number we want for 'helios' to
be in natty
* dmart to send a beagle kernel config to aviksil1
* aviksil1 to send pointer to lttng-enabled tree to slangasek
Regards,
Tom (tgall_foo)
Developer Platforms Team
"We want great men who, when fortune frowns will not be discouraged."
- Colonel Henry Knox
w) tom.gall att linaro.org
w) tom_gall att vnet.ibm.com
h) tom_gall att mac.com
Moving this thread to the linaro-dev mailing list because I'd like it to be
public discussion, and specifically to involve Rob since we talked about his
interest in getting involved with LAVA development and especially the job
dispatcher.
2. One queue TOTAL. One queue may seem like a bottleneck, but I don't think
>> it has to be in practice. One process can monitor that queue, then launch a
>> process or thread to handle each new job that comes in.
>>
> I think RabbitMQ message can have the ability to include the board
> information in it to use one queue, and also we can use different queues for
> different types of boards.
>
Right, but my question was, if you are already encoding information about
which host to run on in the job stream, what is the advantage to having a
queue for each board type, rather than a single queue?
>
>>
>>
>> Job description:
>> I'd like to see some more detail here. Can you provide an example of a
>> job file that would illustrate how you see it working? We also need to
>> specify the underlying mechanisms that will handle parsing what's in the job
>> file, and calling [something?] to do those tasks. What we have here feels
>> like it might be a bit cumbersome.
>>
> I added an detailed one on the spec, like:
>
> 1.
>
> [Beagle-1,
> http://snapshots.linaro.org/11.05-daily/linaro-hwpacks/imx51/20110131/0/ima…,
>
> http://snapshots.linaro.org/11.05-daily/linaro-headless/20110131/0/images/t…,
> 900, ["abrek", "LTP", 180], ["none", "echo 100 > abc", 1], ... ]
> 2.
>
> [IMX51-2, 20100131, 900, ["abrek", "LTP", 180], ["none", "echo 100 >
> abc", 1], ... ]
>
> This looks almost like JSON, which is what Zygmunt was originally pushing
for IIRC. If we are already going down that path, seems it would be
sensible to take it a step further and have defined sections. For example:
Tests:[
{
name:"LTP",
testsuite:"abrek",
subtest:"ltp", <---- not thrilled about that name "subtest", but
can't think of something better to call it at the moment
timeout:180,
reboot_after:True
},
{
name:"echo test",
testsuite:"shell",
timeout:20
reboot_after:False
}
]
What do you think? Obviously, there would be other sections for things like
defining the host characteristics, the image to deploy, etc.
>
>>
>>
> Other questions...
>> What if we have a dependency, how does that get installed on the target
>> image? For example, if I want to do a test that requires bootchart be
>> installed before the system is booted, we should be able to specify that,
>> and have it installed before booting.
>>
>> What about installing necessary test suites? How do we tell it, in
>> advance, what we need to have installed, and how does it get on the image
>> before we boot, or before we start testing?
>>
> I think validation tools, test suites and necessary files are likely to
> install after test image deployment.
>
Yes, clearly they have to be installed after deployment, but we may also
need to consider them installing BEFORE we actually boot the test image.
Thanks,
Paul Larson
Hi there,
Just a thought--- is it worth experimenting with running the kernel wg
meeting on IRC instead of the conf call?
Personally, I find IRC meetings _much_ more digestible than conf calls
(better "audio quality"; ability to scroll back when you don't hear /
don't understand something etc.), but I don't know whether other
people feel the same way -- that may just be my personal preference.
Comparing the dev platform group's weekly IRC meeting with the kernel
conf call, I've found that the IRC format works quite a lot better for
me, but again, that may just be my experience.
Cheers
---Dave
---------- Forwarded message ----------
From: Dave Martin <dave.martin(a)linaro.org>
Date: Wed, Feb 2, 2011 at 4:55 PM
Subject: Re: query regarding perf
To: Sudip Jain <sudip.jain(a)linaro.org>
On Wed, Feb 2, 2011 at 11:09 AM, Sudip Jain <sudip.jain(a)linaro.org> wrote:
> I am getting the error when I execute perf on U8500
> No permission to collect stats.
> Consider tweaking /proc/sys/kernel/perf_event_paranoid.
> The problem I think is perf version and kernel version are not same.On
> ubuntu host x86 machine, if I do sudo apt-get install linux-tools-common,
> then perf runs succesfully. Even I downloaded the source code using sudo
> apt-get source linux-tools-common and re-built perf. It works.
Yes, you'll need the perf tools to be (reasonably) in sync with the kernel.
The linux-linaro-tools package provides the tools for the released
kernels, but if you're working with a development kernel it may be
better to build the tools yourself, as you describe.
> Recently my ubuntu host crashed, I re-installed with 10.04, the kernel
> version is 2.6.32-21 and perf version is 2.6.35.8. So again I am getting
the
> same error (now on ubuntu host) which I mentioned above. Though now I have
> the opportunity to debug the perf code, but that is not my target.
> I am hoping that panda/beagle is fully supported for ubuntu mainstream
AFAIK panda and beagle both ought to work, but please shout if you run
into problems!
Cheers
---Dave