trace power_frequency events on the correct cpu (for Intel x86 CPUs)
in [Kernel]
|
Prev: [PATCH -v2] x86, k8 nb: Enable k8_northbridges unconditionally on AMD
Next: [RFC] resource, PCI: work around pci=use_crs conflicts
From: Arjan van de Ven on 22 Mar 2010 10:00 On 3/22/2010 0:04, Robert Sch�ne wrote: > Am Sonntag, den 21.03.2010, 17:42 -0700 schrieb Arjan van de Ven: >> On 3/20/2010 14:37, Thomas Renninger wrote: >> >>> It also seem to be (hopefully) a minor feature for timechart, so this should >>> not hurt that much (yet). >> >> It's actually a major feature for timechart, and one of the key things I and a bunch of others >> inside Intel use timechart for. >> > It's a major feature for us too. > I suppose, the cpufreq_notify_transition calls are correct (meaning > being called for all related cpus) for every driver. So there's still > the option to include it in the POST_CHANGE section of this function. > Could this be okay for the both of you? post change would work... that gets frequency afaik.. > > -- To unsubscribe from this list: send the line "unsubscribe linux-kernel" in the body of a message to majordomo(a)vger.kernel.org More majordomo info at http://vger.kernel.org/majordomo-info.html Please read the FAQ at http://www.tux.org/lkml/
From: Robert Schöne on 23 Mar 2010 12:30 Am Montag, den 22.03.2010, 06:57 -0700 schrieb Arjan van de Ven: > On 3/22/2010 0:04, Robert Schöne wrote: > > Am Sonntag, den 21.03.2010, 17:42 -0700 schrieb Arjan van de Ven: > >> On 3/20/2010 14:37, Thomas Renninger wrote: > >> > >>> It also seem to be (hopefully) a minor feature for timechart, so this should > >>> not hurt that much (yet). > >> > >> It's actually a major feature for timechart, and one of the key things I and a bunch of others > >> inside Intel use timechart for. > >> > > It's a major feature for us too. > > I suppose, the cpufreq_notify_transition calls are correct (meaning > > being called for all related cpus) for every driver. So there's still > > the option to include it in the POST_CHANGE section of this function. > > Could this be okay for the both of you? > > post change would work... that gets frequency afaik.. Are you ok with this too, Thomas? -- To unsubscribe from this list: send the line "unsubscribe linux-kernel" in the body of a message to majordomo(a)vger.kernel.org More majordomo info at http://vger.kernel.org/majordomo-info.html Please read the FAQ at http://www.tux.org/lkml/
From: Arjan van de Ven on 23 Mar 2010 13:00 On 3/23/2010 9:57, Thomas Renninger wrote: > On Tuesday 23 March 2010 17:28:36 Robert Schöne wrote: >> Am Montag, den 22.03.2010, 06:57 -0700 schrieb Arjan van de Ven: >>> On 3/22/2010 0:04, Robert Schöne wrote: >>>> Am Sonntag, den 21.03.2010, 17:42 -0700 schrieb Arjan van de Ven: >>>>> On 3/20/2010 14:37, Thomas Renninger wrote: >>>>> >>>>>> It also seem to be (hopefully) a minor feature for timechart, so this should >>>>>> not hurt that much (yet). >>>>> >>>>> It's actually a major feature for timechart, and one of the key things I and a bunch of others >>>>> inside Intel use timechart for. >>>>> >>>> It's a major feature for us too. >>>> I suppose, the cpufreq_notify_transition calls are correct (meaning >>>> being called for all related cpus) for every driver. So there's still >>>> the option to include it in the POST_CHANGE section of this function. >>>> Could this be okay for the both of you? >>> >>> post change would work... that gets frequency afaik.. >> Are you ok with this too, Thomas? > You mean hooking it into cpufreq_stat_notifier_trans() in > drivers/cpufreq/cpufreq_stats.c? no hooking into the post frequency change callback that gets done.. which is guaranteed to be on the right cpu afaics. -- To unsubscribe from this list: send the line "unsubscribe linux-kernel" in the body of a message to majordomo(a)vger.kernel.org More majordomo info at http://vger.kernel.org/majordomo-info.html Please read the FAQ at http://www.tux.org/lkml/
From: Robert Schöne on 24 Mar 2010 03:10 Am Dienstag, den 23.03.2010, 09:58 -0700 schrieb Arjan van de Ven: > On 3/23/2010 9:57, Thomas Renninger wrote: > > On Tuesday 23 March 2010 17:28:36 Robert Schöne wrote: > >> Am Montag, den 22.03.2010, 06:57 -0700 schrieb Arjan van de Ven: > >>> On 3/22/2010 0:04, Robert Schöne wrote: > >>>> Am Sonntag, den 21.03.2010, 17:42 -0700 schrieb Arjan van de Ven: > >>>>> On 3/20/2010 14:37, Thomas Renninger wrote: > >>>>> > >>>>>> It also seem to be (hopefully) a minor feature for timechart, so this should > >>>>>> not hurt that much (yet). > >>>>> > >>>>> It's actually a major feature for timechart, and one of the key things I and a bunch of others > >>>>> inside Intel use timechart for. > >>>>> > >>>> It's a major feature for us too. > >>>> I suppose, the cpufreq_notify_transition calls are correct (meaning > >>>> being called for all related cpus) for every driver. So there's still > >>>> the option to include it in the POST_CHANGE section of this function. > >>>> Could this be okay for the both of you? > >>> > >>> post change would work... that gets frequency afaik.. > >> Are you ok with this too, Thomas? > > You mean hooking it into cpufreq_stat_notifier_trans() in > > drivers/cpufreq/cpufreq_stats.c? > > no > > > hooking into the post frequency change callback that gets done.. > which is guaranteed to be on the right cpu afaics. > I don't see where this would be guaranteed. So I'd be fine with a) adding it to cpufreq.c/cpufreq_notify_transition/cpufreq_notify_transition b) adding an item to the cpufreq_transition_notifier_list c) adding it to cpufreq_stats.c/cpufreq_stat_notifier_trans which would imply the usage of smp_call_function_single(...) -- To unsubscribe from this list: send the line "unsubscribe linux-kernel" in the body of a message to majordomo(a)vger.kernel.org More majordomo info at http://vger.kernel.org/majordomo-info.html Please read the FAQ at http://www.tux.org/lkml/
From: Robert Schöne on 30 Mar 2010 01:50
Am Mittwoch, den 24.03.2010, 08:07 +0100 schrieb Robert Schöne: > Am Dienstag, den 23.03.2010, 09:58 -0700 schrieb Arjan van de Ven: > > On 3/23/2010 9:57, Thomas Renninger wrote: > > > On Tuesday 23 March 2010 17:28:36 Robert Schöne wrote: > > >> Am Montag, den 22.03.2010, 06:57 -0700 schrieb Arjan van de Ven: > > >>> On 3/22/2010 0:04, Robert Schöne wrote: > > >>>> Am Sonntag, den 21.03.2010, 17:42 -0700 schrieb Arjan van de Ven: > > >>>>> On 3/20/2010 14:37, Thomas Renninger wrote: > > >>>>> > > >>>>>> It also seem to be (hopefully) a minor feature for timechart, so this should > > >>>>>> not hurt that much (yet). > > >>>>> > > >>>>> It's actually a major feature for timechart, and one of the key things I and a bunch of others > > >>>>> inside Intel use timechart for. > > >>>>> > > >>>> It's a major feature for us too. > > >>>> I suppose, the cpufreq_notify_transition calls are correct (meaning > > >>>> being called for all related cpus) for every driver. So there's still > > >>>> the option to include it in the POST_CHANGE section of this function. > > >>>> Could this be okay for the both of you? > > >>> > > >>> post change would work... that gets frequency afaik.. > > >> Are you ok with this too, Thomas? > > > You mean hooking it into cpufreq_stat_notifier_trans() in > > > drivers/cpufreq/cpufreq_stats.c? > > > > no > > > > > > hooking into the post frequency change callback that gets done.. > > which is guaranteed to be on the right cpu afaics. > > > I don't see where this would be guaranteed. So I'd be fine with > a) adding it to > cpufreq.c/cpufreq_notify_transition/cpufreq_notify_transition > > b) adding an item to the cpufreq_transition_notifier_list > > c) adding it to cpufreq_stats.c/cpufreq_stat_notifier_trans > > which would imply the usage of smp_call_function_single(...) > I really want to keep this diskussion alive until there's a soultion we can all agree. So Arjan and Thomas, are there any comments/preferences to the proposed options? -- To unsubscribe from this list: send the line "unsubscribe linux-kernel" in the body of a message to majordomo(a)vger.kernel.org More majordomo info at http://vger.kernel.org/majordomo-info.html Please read the FAQ at http://www.tux.org/lkml/ |