sched_mc test scenario

Vincent Guittot vincent.guittot at linaro.org
Wed Aug 3 16:25:06 UTC 2011


Hi Daniel,

On 3 August 2011 15:58, Daniel Lezcano <daniel.lezcano at linaro.org> wrote:
>
> -----BEGIN PGP SIGNED MESSAGE-----
> Hash: SHA1
>
>
> Hi all,
>
> here is a few test scenario I would like to add to the pm-qa.
>
> test_01: the sched_mc feature is enabled in the kernel
>
>    check the presence of the 'sched_mc_power_savings' file
>
> test_02: the topology is implemented in the kernel
>
>    check the value of the physical_package_id file is different from "-1"
>
> test_03: the topology files are present
>
>    check the presence of the topology files for each cpu:
>     * core_id
>     * core_siblings
>     * core_siblings_list
>     * physical_package_id
>     * thread_siblings
>     * thread_siblings_list
>
> test_04: the change are effective for sched_mc
>
>    check the ability to change the value [0-2] of the
> 'sched_mc_power_savings' file
>
> test_05: the topology is consistent
>
>    check the consistency of the topology files
>    * for each package:
>      * count the cores
>            -> the number of cores is 2 ^ (nr_cores - 1)
>            -> all core ids are between 0 and nr_cores - 1
>
>

it sounds good for me.

> Concerning the functional tests, I need some hints :)
>
> On the architecture we have, that will be difficult to verify sched_mc
> works as expected.
> If I understood correctly, in order to test that, we should have a
> dual Cortex-A9 to check a program with two processes eating a lot of
> cpu cycles will be bounded in the same socket_id when
> sched_mc_power_savings=2.
> The other processor staying idle or not running any of these
> processes, right ? AFAIK, there is no such hardware, no ?
>
>

you could integrate a non regression test which check that performance
results in both sched_mc_power_savings=0 and  sched_mc_power_savings=2
. I have one which uses cyclictest and sysbench. Then, you're right
that we must wait a bit before adding some functional tests which test
that sched_mc is working as expected (from a power saving point of
view) with sched_mc_power_savings=2

Vincent

> - --
>  <http://www.linaro.org/> Linaro.org ? Open source software for ARM SoCs
>
> Follow Linaro:  <http://www.facebook.com/pages/Linaro> Facebook |
> <http://twitter.com/#!/linaroorg> Twitter |
> <http://www.linaro.org/linaro-blog/> Blog
>
> -----BEGIN PGP SIGNATURE-----
> Version: GnuPG v1.4.11 (GNU/Linux)
> Comment: Using GnuPG with Mozilla - http://enigmail.mozdev.org/
>
> iQEcBAEBAgAGBQJOOWIyAAoJEAKBbMCpUGYAGoEIAL7ETqYPdyCzS3c+4JYMrK72
> AXMLu9W6stMfuTssyGZFBlsSbWsSDKbkqp8uzKc0zr8gw7KgQdVedHkBTn3H8QCi
> enAPoaIonkB7+UDNpg5zvrg4swLIMSJ5wBd7SVmFDnLiGIAf/seJac31ZtoLRV3A
> kT7wnusIQFATWVazlR110zNrLVA1rEdlOXBWudCYj4FPTnTde6mBqkvW1WMRDroP
> XAazklW7e7+NF2xo0/+7T2xT8Mudc3ELY5+KMF7j6YMCh/h8WSaSWh0baES0/Mie
> crFku0w+trXaniW6qnrxAWCyc0BB/MVbd60PJVJ25nnxTGo4JwwOf4hQZ5GHKfc=
> =7lNh
> -----END PGP SIGNATURE-----
>
>



More information about the linaro-dev mailing list