Greetings,
The linux-linaro-core-tracking (llct) tree has been moved to v3.6-rc5 base.
All the topics existed in the 12.08 version of llct have been carried
over into the updated tree with few easy to resolve conflicts. The only
one which needs attention is due to commit "ASoC: Samsung: Fix build
error" [1]. In fact I had to revert it because it doesn't work with the
multiplatform topic (the latter renames all the
arch/arm/mach-<name>/include/mach dirs to
arch/arm/mach-<name>/include/mach-<name>). Sachin or Tushar, could you
take a look please?
Also the big-LITTLE-MP topic has been updated to v3.6-rc5 based
big-LITTLE-MP-v8.
The current list of the llct topics can be found in [2].
12.09 will most probably be v3.6-rc6 based. But for the moment I've
tried rebasing the linux-linaro (ll) tree to the current v3.6-rc5 based
llct, and encountered no merge issues. The current list of the ll topics
can be found in [3]. The plan is to have single topic from the ARM LT
(like the Samsung LT code is represented now) this month vs several
one-per-feature topics.
In 12.08 the linux-linaro-tracking (llt) tree was v3.4 based, and had
recent code from TI LT plus the older code (no changes for couple
months) from ARM and Samsung LTs. Any changes here in 12.09? (Are we on
v3.4 still, are there other LTs to add to this tree?).
And yes, this month llc-3.4 "core stable" tree will be introduced (first
of all, to get the Gator updates for v3.4, and some critical fixes), and
llt will start using it as a base. No more details atm,
should have something in git by the end of this week.
Please let me know if there are any updates to the existing topics, or
new topics missing. And if there are obsoleted topics. The linux-linaro
and linux-linaro-tracking trees will be frozen (only bug fixes would be
accepted afterwards, no new additions) by the end of September 18.
Thanks,
Andrey
[1]
http://git.kernel.org/?p=linux/kernel/git/torvalds/linux.git;a=commitdiff;h…
[2]
http://git.linaro.org/gitweb?p=kernel/linux-linaro-manifest.git;a=blob;f=ma…
[3]
http://git.linaro.org/gitweb?p=kernel/linux-linaro-manifest.git;a=blob;f=ma…
In order to save power, it would be useful to schedule work onto non-IDLE cpus
instead of waking up an IDLE one.
To achieve this, we need scheduler to guide kernel frameworks (like: timers &
workqueues) on which is the most preferred CPU that must be used for these
tasks.
This patchset is about implementing this concept.
The first patch adds sched_select_cpu() routine which returns the preferred cpu
which is non-idle. It accepts max level of sched domain, upto which we can
choose a CPU from. It can accept following options: SD_SIBLING, SD_MC, SD_BOOK,
SD_CPU or SD_NUMA.
Second and Third patch are about adapting this change in workqueue framework.
Earlier discussions over this concept were done at last LPC:
http://summit.linuxplumbersconf.org/lpc-2012/meeting/90/lpc2012-sched-timer…
Figures:
--------
Test case 1:
- Performed on TC2 with ubuntu-devel
- Boot TC2 and run
$ trace-cmd record -e workqueue_execute_start
This will trace only the points, where the work actually runs.
Do, this for 150 seconds.
Results:
---------
Domain 0: CPU 0-1
Domain 1: CPU 2-4
Base Kernel: Without my modifications:
-------------------------------------
CPU No. of works run by CPU
----- -----------------------
CPU0: 7
CPU1: 445
CPU2: 444
CPU3: 315
CPU4: 226
With my modifications:
----------------------
CPU No. of works run by CPU
---- -----------------------
CPU0: 31
CPU2: 797
CPU3: 274
CPU4: 86
Test case 2:
-----------
I have created a small module, which does following:
- Create one work for each CPU (using queue_work_on(), so must schedule on that
cpu)
- Above work, will queue "n" works for each cpu with queue_work(). These works
are tracked within the module and results are printed at the end.
This gave similar results, with n ranging from 10 to 1000.
Viresh Kumar (3):
sched: Create sched_select_cpu() to give preferred CPU for power
saving
workqueue: create __flush_delayed_work to avoid duplicating code
workqueue: Schedule work on non-idle cpu instead of current one
arch/arm/Kconfig | 11 +++++++
include/linux/sched.h | 11 +++++++
kernel/sched/core.c | 88 +++++++++++++++++++++++++++++++++++++++------------
kernel/workqueue.c | 36 ++++++++++++++-------
4 files changed, 115 insertions(+), 31 deletions(-)
--
1.7.12.rc2.18.g61b472e
Hi all,
I Thought I'd let you know that we now have 5 more ST-Ericsson Snowball V11 PDKs in LAVA. They went live yesterday afternoon. In total we now have 10 snowballs but only 8 are available because one of them has been sidelined for staging, and another is not playing ball. I'm working on trying to understand if the board is just dead, or if there there is some other issue. At the moment it's not talking to the outside world at all. I'll keep you posted.
Thanks
Dave
Dave Pigott
Validation Engineer
T: +44 1223 40 00 63 | M +44 7940 45 93 44
Linaro.org │ Open source software for ARM SoCs
Follow Linaro: Facebook | Twitter | Blog
Hi All,
I notice that there are still some jobs being submitted to LAVA with the device-type "vexpress". This device type is now deprecated and has been replaced by the more specific device type vexpress-a9. The jobs seem to be coming from CI and Android. Could someone amend these submissions?
Thanks
Dave
Dave Pigott
Validation Engineer
T: +44 1223 40 00 63 | M +44 7940 45 93 44
Linaro.org │ Open source software for ARM SoCs
Follow Linaro: Facebook | Twitter | Blog
This weekend a test rebuild of quantal quetzal did start for the amd64, i386 and
armhf architectures. The test rebuild is now finished for the main and
restricted components, and continues with the universe and multiverse components.
Results can be seen at
http://people.ubuntuwire.org/~wgrant/rebuild-ftbfs-test/test-rebuild-201209…
The archive for the test rebuild is
https://launchpad.net/ubuntu/+archive/test-rebuild-20120922
Please help fixing the build failures for the final release.
Note that an upload won't show up in the superseded sections, if it is uploaded
to quantal-proposed, but didn't propagate yet to quantal.
Matthias
Just wanted to share this with everyone.
I've attached the "output" folder that the NI instrument creates for
each test session. In the results file you'll see a text doc called
results.txt that lists the comma delimited parameters that get
measured followed by the measurements themselves:
Current Cycle Average,Current Cycle RMS,Current Mean (DC),Current
Negative Peak,Current Peak to Peak,Current Positive Peak,Current
RMS,Volt Cycle Average,Volt Cycle RMS,Volt Mean (DC),Volt Negative
Peak,Volt Peak to Peak,Volt Positive Peak,Volt RMS
See:
https://docs.google.com/a/linaro.org/file/d/0B3pUtxWjZbP9bFhqNGZfYzNSMWs/ed…
Included in each record is a Record Number that indexes into the
"report directory." Each directory is marked with an index and under
that directory is the graph associated with the data for example:
https://docs.google.com/a/linaro.org/file/d/0B3pUtxWjZbP9VnVQS3M4WWx1OVk/ed…
In addition, controlling the instrument is super easy. You connect to
the box over TCP/IP the you can send 5 single character commands in
any order: 1,0,s,e,r
1 turns the power on
0 turns it off
s starts a measurement
e ends a measurement
r records
r is destructive, so if you send an r it erase the previous data
record. The data record does survive instrument restarts (as opposed
to having an implicit r at the start of the measurement.
At any point the existing data set can simply be uploaded.
One minor point. This instrument produces a lot of data, instead of
moving all this data around, the instrument can be configured to do
all the measurement, making the analyzed data set easier to understand
and faster to upload.
Comments and questions welcome.
See it in action at:
https://plus.google.com/u/0/104422661029399872488/posts/NU4pZ36L13U
--
Zach Pfeffer
Android Platform Team Lead, Linaro Platform Teams
Linaro.org | Open source software for ARM SoCs
Follow Linaro: http://www.facebook.com/pages/Linarohttp://twitter.com/#!/linaroorg - http://www.linaro.org/linaro-blog