Should we expect any thermal issues if we leave the Hikeys always on?
Assuming you are running the “release” build and bootloader - no - the thermal control is overly aggressive until we tune it so you should not see any problems (however the cores may only run at 200MHz!). George
On Mar 18, 2015, at 6:22 PM, Jorge Ramirez-Ortiz jorge.ramirez-ortiz@linaro.org wrote:
Should we expect any thermal issues if we leave the Hikeys always on?
Dev mailing list Dev@lists.96boards.org https://lists.96boards.org/mailman/listinfo/dev
On Wed, Mar 18, 2015 at 09:04:15PM +0000, George Grey wrote:
Assuming you are running the “release” build and bootloader - no - the thermal control is overly aggressive until we tune it so you should not see any problems (however the cores may only run at 200MHz!). George
Yes.
If use hisilicon bootloader + v3.18 kernel, the thermal driver with cpu cooling device has been enabled. So if the temperature > 70'c, the cpu frequency will be limited; and if temp > 90'c, the system will be reset, which this condition is hard to meet.
So suppose most case is to downgrade cpu frequency. If debug for performance issue, suggest to check cpufreq info.
On Mar 18, 2015, at 6:22 PM, Jorge Ramirez-Ortiz jorge.ramirez-ortiz@linaro.org wrote:
Should we expect any thermal issues if we leave the Hikeys always on?
Dev mailing list Dev@lists.96boards.org https://lists.96boards.org/mailman/listinfo/dev
Dev mailing list Dev@lists.96boards.org https://lists.96boards.org/mailman/listinfo/dev
On 19 March 2015 at 01:21, Leo Yan leo.yan@linaro.org wrote:
On Wed, Mar 18, 2015 at 09:04:15PM +0000, George Grey wrote:
Assuming you are running the “release” build and bootloader - no - the thermal control is overly aggressive until we tune it so you should not see any problems (however the cores may only run at 200MHz!). George
Yes.
If use hisilicon bootloader + v3.18 kernel, the thermal driver with cpu cooling device has been enabled. So if the temperature > 70'c, the cpu frequency will be limited; and if temp > 90'c, the system will be reset, which this condition is hard to meet.
So suppose most case is to downgrade cpu frequency. If debug for performance issue, suggest to check cpufreq info.
A `make -j8 Image' kernel build on the board triggered the thermal reset mechanism for me, but that's the only time I've ran into it. (a less ambitious `make -j4 Image' worked fine).
Cheers, -- Steve
Hi Steve,
Just curious, does your board have a heat sink on the SoC?
Scott
On Thu, Mar 19, 2015 at 5:26 AM, Steve Capper steve.capper@linaro.org wrote:
On 19 March 2015 at 01:21, Leo Yan leo.yan@linaro.org wrote:
On Wed, Mar 18, 2015 at 09:04:15PM +0000, George Grey wrote:
Assuming you are running the “release” build and bootloader - no - the
thermal control is overly aggressive until we tune it so you should not see any problems (however the cores may only run at 200MHz!).
George
Yes.
If use hisilicon bootloader + v3.18 kernel, the thermal driver with cpu cooling device has been enabled. So if the temperature > 70'c, the cpu frequency will be limited; and if temp > 90'c, the system will be reset, which this condition is hard to meet.
So suppose most case is to downgrade cpu frequency. If debug for performance issue, suggest to check cpufreq info.
A `make -j8 Image' kernel build on the board triggered the thermal reset mechanism for me, but that's the only time I've ran into it. (a less ambitious `make -j4 Image' worked fine).
Cheers,
Steve _______________________________________________ Dev mailing list Dev@lists.96boards.org https://lists.96boards.org/mailman/listinfo/dev
On 19 March 2015 at 16:36, Scott Bambrough scott.bambrough@linaro.org wrote:
Hi Steve,
Just curious, does your board have a heat sink on the SoC?
Scott
Hi Scott, Yes it has a smallish silver one mounted to the chip. I think it's the standard one.
Cheers, -- Steve
On a similar note, I was going to run some of the LKP tests for a baseline last week. Of course the first one I chose, pigz[1], is a pretty good all-cores stress test and during the test run from I observed the thermal warnings and forced shutdowns after about 1-2 minutes. I was going to hit it with some freeze spray, but thought I had better not if I wanted to make sure the system was in good shape for demos.
https://git.kernel.org/cgit/linux/kernel/git/wfg/lkp-tests.git/tree/tests/pi... ..parallel implementation of gzip, is a fully functional replacement for gzip that exploits multiple processors and multiple cores to the hilt when compressing data...
I was running bits from the debian daily build #124, board does have the silver passive heat-sink
alan
On Thu, Mar 19, 2015 at 10:38 AM, Steve Capper steve.capper@linaro.org wrote:
On 19 March 2015 at 16:36, Scott Bambrough scott.bambrough@linaro.org wrote:
Hi Steve,
Just curious, does your board have a heat sink on the SoC?
Scott
Hi Scott, Yes it has a smallish silver one mounted to the chip. I think it's the standard one.
Cheers,
Steve _______________________________________________ Dev mailing list Dev@lists.96boards.org https://lists.96boards.org/mailman/listinfo/dev
On 03/19/2015 02:44 PM, Alan Bennett wrote:
On a similar note, I was going to run some of the LKP tests for a baseline last week. Of course the first one I chose, pigz[1], is a pretty good all-cores stress test and during the test run from I observed the thermal warnings and forced shutdowns after about 1-2 minutes. I was going to hit it with some freeze spray, but thought I had better not if I wanted to make sure the system was in good shape for demos.
https://git.kernel.org/cgit/linux/kernel/git/wfg/lkp-tests.git/tree/tests/pi... ..parallel implementation of gzip, is a fully functional replacement for gzip that exploits multiple processors and multiple cores to the hilt when compressing data...
Just received this from the Energy Aware Scheduler mailing list. I thought it might be of interest.
---
FYI, this week ARM opensourced the Workload Automation suite that is useful for EAS evaluation License is Apache ver 2.0
https://github.com/ARM-software/workload-automation
----
On Thu, Mar 19, 2015 at 09:33:00PM +0000, Jorge Ramirez-Ortiz wrote:
On 03/19/2015 02:44 PM, Alan Bennett wrote:
On a similar note, I was going to run some of the LKP tests for a baseline last week. Of course the first one I chose, pigz[1], is a pretty good all-cores stress test and during the test run from I observed the thermal warnings and forced shutdowns after about 1-2 minutes. I was going to hit it with some freeze spray, but thought I had better not if I wanted to make sure the system was in good shape for demos.
https://git.kernel.org/cgit/linux/kernel/git/wfg/lkp-tests.git/tree/tests/pi... ..parallel implementation of gzip, is a fully functional replacement for gzip that exploits multiple processors and multiple cores to the hilt when compressing data...
Just received this from the Energy Aware Scheduler mailing list. I thought it might be of interest.
FYI, this week ARM opensourced the Workload Automation suite that is useful for EAS evaluation License is Apache ver 2.0
Good inputs for three excellent cases for cpu workload.
Now kernel has not enabled cpuidle, so that this will introduce static power leakage; so even the cpu is in idle state, it still will consume power. If enable the cpuidle, we can get power benefit from cpu idle state.
In the cases which cpus run with 100% busy state, if the thermal is high enough, there mainly have two ways to cool down cpu: - Limit the cpu frequency, so that decrease the dynamic power leakage; Thermal framework has provided cpu cooling device driver for that; - Limit the cpu numbers (or using hotplug governor), the specially case is to hotplug out all cpus in the second cluster so that can easily decrease the static power leakage; I'm not sure EAS/IPA can support for this or not?
So far we need firstly enable PSCI's hotplug/cpuidle functionality, so that it can support furthmore's power profiling/optimization.
Thanks, Leo Yan
-
Alan Bennett -
George Grey -
Jorge Ramirez-Ortiz -
Leo Yan -
Scott Bambrough -
Steve Capper