Skip the use of work queue and call musb_dma_completion() directly from
DMA callback context.
Here follows measurements on a Snowball board with ondemand governor active.
Performance using work queue:
(105 MB) copied, 6.23758 s, 16.8 MB/s
(105 MB) copied, 5.7151 s, 18.3 MB/s
(105 MB) copied,
On Mon, 08 Aug 2011 02:22:14 +0200, Per Forlin per.for...@linaro.org
wrote:
FSG_NUM_BUFFERS is set to 2 as default.
Usually 2 buffers are enough to establish a good
double buffering pipeline. But when dealing with expensive
request preparation (i.e. dma_map) there may be benefits of
increasing
this should be fixed now. folks, please use:
umask 002
in your .bashrc - ssh git.linaro.org - change .bashrc there.
I guess from now on we could consider to use gerrit for toolchain etc. too.
Thanks!
On Sun, Aug 7, 2011 at 8:16 PM, James Westby james.wes...@linaro.org wrote:
On Sun, 7 Aug
Hi,
On Mon, Aug 08, 2011 at 10:32:38AM +0200, Per Forlin wrote:
[snip]
-/* Work function invoked from DMA callback to handle rx transfers. */
-static void ux500_rx_work(struct work_struct *data)
+void ux500_dma_callback(void *private_data)
{
- struct ux500_dma_channel *ux500_channel =
On Fri, Aug 5, 2011 at 1:08 PM, James Tunnicliffe
james.tunnicli...@linaro.org wrote:
I just tested two a nano images using ext4 and they didn't find the
root file system. So, we are at least gated on that bug.
I filed https://bugs.launchpad.net/linaro-ubuntu/+bug/822593 to make
ext4 our
Dear Chander Kashyap,
On 28 July 2011 15:36, Chander Kashyap chander.kash...@linaro.org wrote:
Removed dummy functions in mmc_spl/board/samsung/smdkv310/mmc_boot.c,
@mmc_boot.c
void do_undefined_instruction(struct pt_regs *pt_regs);
void do_software_interrupt(struct pt_regs *pt_regs);
void
ok spads from IS gave better suggestion than using umask in .bashrc.
Now, we propose that you set alias for git like:
alias git='UMASK=002 git'
Please update accordingly.
Thanks!
On Mon, Aug 8, 2011 at 11:51 AM, Alexander Sack a...@linaro.org wrote:
this should be fixed now. folks, please use:
Hi Michal,
2011/8/8 Michal Nazarewicz min...@mina86.com:
On Mon, 08 Aug 2011 02:22:14 +0200, Per Forlin per.for...@linaro.org
wrote:
FSG_NUM_BUFFERS is set to 2 as default.
Usually 2 buffers are enough to establish a good
double buffering pipeline. But when dealing with expensive
request
From: Per Forlin per.for...@linaro.org
FSG_NUM_BUFFERS is set to 2 as default.
Usually 2 buffers are enough to establish a good
buffering pipeline. But when dealing with expensive
request preparation (i.e. dma_map) there may be benefits of
increasing the number of buffers. There is an extra cost
From: Per Forlin per.for...@linaro.org
Skip the use of work queue and call musb_dma_completion() directly from
DMA callback context.
Here follows measurements on a Snowball board with ondemand governor active.
Performance using work queue:
(105 MB) copied, 6.23758 s, 16.8 MB/s
(105 MB) copied,
Hi,
I have followed (and updated) the instructions on
https://wiki.linaro.org/Platform/Android/Gerrit .
I can not log in with my launchpad account. I get the message The requested
URL /OpenID was not found on this server.
/Patrik
On 6 August 2011 07:56, James Westby james.wes...@canonical.com
On Mon, Aug 8, 2011 at 1:02 PM, Patrik Ryd patrik@linaro.org wrote:
Hi,
I have followed (and updated) the instructions
on https://wiki.linaro.org/Platform/Android/Gerrit .
I can not log in with my launchpad account. I get the message The requested
URL /OpenID was not found on this server.
On Tue, Jul 05, 2011 at 02:16:23PM +0100, Russell King - ARM Linux wrote:
Looks fine now, and so can go to my patch system. Many thanks.
Ping.
___
linaro-dev mailing list
linaro-dev@lists.linaro.org
http://lists.linaro.org/mailman/listinfo/linaro-dev
On Mon, Aug 08, 2011 at 04:42:42PM +0530, RACHANA TEWARI wrote:
Does anyone know way to initiate a bash script(to run on linux box) from
windows Written in C#?
How to write these Scripts...
This has nothing to do with CPU topology. Please do not topic hijack.
This is also off-topic for
On 8 August 2011 12:09, Russell King - ARM Linux li...@arm.linux.org.uk wrote:
On Tue, Jul 05, 2011 at 02:16:23PM +0100, Russell King - ARM Linux wrote:
Looks fine now, and so can go to my patch system. Many thanks.
Ping.
Yes. Do you have additional comments to the patch ?
Hi,
In the PMWG, we'd like to to be able to run some apps and measure the
power consumption while they run. Since the power measurement
framework currently supports Android, does anybody know of automated
ways to reproduce a test case?
I found Robotium[1] on googling and would like to know if it
On Mon, 08 Aug 2011 02:22:14 +0200, Per Forlin wrote:
There may not be one optimal number for all boards. That is the
reason for adding the number to Kconfig,
2011/8/8 Michal Nazarewicz min...@mina86.com:
It could actually be turned into a run-time configuration, but
that's a bit more
On 8 August 2011 16:34, Alan Stern st...@rowland.harvard.edu wrote:
On Mon, 8 Aug 2011, Per Forlin wrote:
FSG_NUM_BUFFERS is set to 2 as default.
Usually 2 buffers are enough to establish a good
double buffering pipeline. But when dealing with expensive
request preparation (i.e. dma_map)
On 8 August 2011 20:45, Alan Stern st...@rowland.harvard.edu wrote:
On Mon, 8 Aug 2011, Per Forlin wrote:
Okay, 6% is a worthwhile improvement, though not huge. Did you try 6
or 8 buffers? I bet going beyond 4 makes very little difference.
On my board 4 buffers are enough. More buffers
Add description on how to enable random fault injection
for MMC IO
Signed-off-by: Per Forlin per.for...@linaro.org
---
Documentation/fault-injection/fault-injection.txt |5 +
1 files changed, 5 insertions(+), 0 deletions(-)
diff --git a/Documentation/fault-injection/fault-injection.txt
Daniel,
This looks ok. Ack.
/Amit
On Fri, Aug 5, 2011 at 4:03 PM, Daniel Lezcano
daniel.lezc...@linaro.org wrote:
Error messages have to go to the log file
Signed-off-by: Daniel Lezcano daniel.lezc...@linaro.org
---
cpufreq/Makefile | 4 ++--
1 files changed, 2 insertions(+), 2
On 8 August 2011 22:23, Alan Stern st...@rowland.harvard.edu wrote:
On Mon, 8 Aug 2011, Per Forlin wrote:
On 8 August 2011 20:45, Alan Stern st...@rowland.harvard.edu wrote:
On Mon, 8 Aug 2011, Per Forlin wrote:
Okay, 6% is a worthwhile improvement, though not huge. Did you try 6
or
On Mon, 8 Aug 2011, Per Forlin wrote:
On 8 August 2011 20:45, Alan Stern st...@rowland.harvard.edu wrote:
On Mon, 8 Aug 2011, Per Forlin wrote:
Okay, 6% is a worthwhile improvement, though not huge. �Did you try 6
or 8 buffers? �I bet going beyond 4 makes very little difference.
On Mon, 8 Aug 2011, Per Forlin wrote:
Okay, 6% is a worthwhile improvement, though not huge. �Did you try 6
or 8 buffers? �I bet going beyond 4 makes very little difference.
On my board 4 buffers are enough. More buffers will make no difference.
Background study
I started by running dd
On 5 August 2011 14:40, Rob Herring robherri...@gmail.com wrote:
Deepak, Nicolas,
On 07/27/2011 09:58 PM, Nicolas Pitre wrote:
To everyone, and especially to those who are expected to work on this
topic next week, please find below a list of tasks that needs to be
investigated and/or
FSG_NUM_BUFFERS is set to 2 as default.
Usually 2 buffers are enough to establish a good buffering pipeline.
The number may be increased in order to compensate a for bursty VFS
behaviour.
Here follows a description of system that may require more than
2 buffers.
* CPU ondemand governor active
*
26 matches
Mail list logo
