Re: [PATCH] powercap/rapl: handle domain energy unit

[kazutomo]

On 03/12/2015 04:24 PM, Jacob Pan wrote:
> On Wed, 11 Mar 2015 16:25:52 -0500
> kazutomo <kazutomo.yoshii@xxxxxxxxx> wrote:
>
>> Hi Jacob,
>>
>> Wow, this is a really pitfall for people who are writing their own
>> RAPL tool.
>> Anyway, I've tested your patch on a Haswell system (2699v3), running a
>> dgemm
>> benchmark. NOTE: userspace governor is selected. All core are set to
>> 2.3 GHz.
>> No power cap is set.
>>  
>> # before the patch is applied
>> $ cd /sys/class/powercap/intel-rapl:0:0
>> $ cat name
>> dram
>> $ for i in 1 2 3 ; do a=`cat energy_uj` ; sleep 1 ; b=`cat
>> energy_uj` ; expr $b - $a ; done
>> 16853445
>> 16829355
>> 16666320
>>  
>> # after the patch is applied
>> $ for i in 1 2 3 ; do a=`cat energy_uj` ; sleep 1 ; b=`cat
>> energy_uj` ; expr $b - $a ; done 
>> 69751487
>> 68153897
>> 69689816
>>
> thanks for testing, but i thought the results should be the other way
> around. counting 15uJ vs 61uJ after the patch is applied. I will double
> check once i get a machine again.
It was my mistake.  Somehow I cut and pasted the results in the wrong
order.
e.g., 69751487 is before the patch and  16853445 is after the patch.
>> I have a couple of questions. 
>>  
>> 1. Is it possible to retrieve the DRAM energy unit from some MSRs
>> *eventually* like the domain energy unit? 
>>  
> according to the document, future DRAM energy unit will always be
> hardcoded to 15.3uJ, no enumeration since there is no domain specific
> MSR for energy unit.
Which document are you referring to?
>> 2. Will the Intel software developer's manual (vol3b) be updated
>> accordingly if you know? I'm assuming that you are working at Intel.
>>  
> I don't know. Let me get back to you later. 
Thanks!
>> 3. Is get_max_energy_range_uj still the same as other counters?
>>  
> good catch. max energy is obtained from parent package domain which
> still uses MSR enumerated unit. now it has to be per domain.
>> 4. The current driver maintains the unit as an integer, instead of a
>> shift value, and the multiplier is a relatively small number.  I guess
>> the DRAM energy unit is technically ~15.2587 uJ = (0.5 ** 16) * 1e6,
>> so it always reports a approx. 2 % smaller energy number, while the
>> pkg energy unit is ~61.0351, so the error is ~0.5 %.  An easier
>> solution would be to maintain the unit in pJ, instead of uJ. 
>> or am I worrying too much? I guess the RAPL energy estimation may
>> have some error, so maybe canceling out.
>>
> yes, you are right. using pJ or more precise shift would be a better.
> let me add that also.
cool!

- kaz
>
> Thanks,
>
> Jacob
>> - kaz
>>
>> On 03/11/2015 07:55 AM, Jacob Pan wrote:
>>> The current driver assumes all RAPL domains within a CPU package
>>> have the same energy unit. This is no longer true for HSW server
>>> CPUs since DRAM domain has is own fixed energy unit which can be
>>> different than the package energy unit enumerated by package
>>> power MSR. In fact, the default HSW EP package power unit is 61uJ
>>> whereas DRAM domain unit is 15.3uJ. The result is that DRAM power
>>> consumption is counted 4x more than real power reported by energy
>>> counters.
>>>
>>> This patch adds domain specific energy unit per cpu type, it allows
>>> domain energy unit to override package energy unit if non zero.
>>>
>>> Signed-off-by: Jacob Pan <jacob.jun.pan@xxxxxxxxxxxxxxx>
>>> ---
>>>  drivers/powercap/intel_rapl.c | 35
>>> ++++++++++++++++++++++++++++------- 1 file changed, 28
>>> insertions(+), 7 deletions(-)
>>>
>>> diff --git a/drivers/powercap/intel_rapl.c
>>> b/drivers/powercap/intel_rapl.c index 97b5e4e..af4c61e 100644
>>> --- a/drivers/powercap/intel_rapl.c
>>> +++ b/drivers/powercap/intel_rapl.c
>>> @@ -158,6 +158,7 @@ struct rapl_domain {
>>>  	struct rapl_power_limit rpl[NR_POWER_LIMITS];
>>>  	u64 attr_map; /* track capabilities */
>>>  	unsigned int state;
>>> +	unsigned int domain_energy_unit;
>>>  	int package_id;
>>>  };
>>>  #define power_zone_to_rapl_domain(_zone) \
>>> @@ -190,6 +191,7 @@ struct rapl_defaults {
>>>  	void (*set_floor_freq)(struct rapl_domain *rd, bool mode);
>>>  	u64 (*compute_time_window)(struct rapl_package *rp, u64
>>> val, bool to_raw);
>>> +	unsigned int dram_domain_energy_unit;
>>>  };
>>>  static struct rapl_defaults *rapl_defaults;
>>>  
>>> @@ -227,7 +229,8 @@ static int rapl_read_data_raw(struct
>>> rapl_domain *rd, static int rapl_write_data_raw(struct rapl_domain
>>> *rd, enum rapl_primitives prim,
>>>  			unsigned long long value);
>>> -static u64 rapl_unit_xlate(int package, enum unit_type type, u64
>>> value, +static u64 rapl_unit_xlate(struct rapl_domain *rd, int
>>> package,
>>> +			enum unit_type type, u64 value,
>>>  			int to_raw);
>>>  static void package_power_limit_irq_save(int package_id);
>>>  
>>> @@ -305,7 +308,8 @@ static int get_energy_counter(struct
>>> powercap_zone *power_zone, u64 *energy_raw) 
>>>  static int get_max_energy_counter(struct powercap_zone *pcd_dev,
>>> u64 *energy) {
>>> -	*energy = rapl_unit_xlate(0, ENERGY_UNIT,
>>> ENERGY_STATUS_MASK, 0);
>>> +	/* package domain is the largest */
>>> +	*energy = rapl_unit_xlate(NULL, 0, ENERGY_UNIT,
>>> ENERGY_STATUS_MASK, 0); return 0;
>>>  }
>>>  
>>> @@ -639,6 +643,11 @@ static void rapl_init_domains(struct
>>> rapl_package *rp) rd->msrs[4] = MSR_DRAM_POWER_INFO;
>>>  			rd->rpl[0].prim_id = PL1_ENABLE;
>>>  			rd->rpl[0].name = pl1_name;
>>> +			rd->domain_energy_unit =
>>> +
>>> rapl_defaults->dram_domain_energy_unit;
>>> +			if (rd->domain_energy_unit)
>>> +				pr_info("DRAM domain energy unit
>>> %duj\n",
>>> +					rd->domain_energy_unit);
>>>  			break;
>>>  		}
>>>  		if (mask) {
>>> @@ -648,7 +657,8 @@ static void rapl_init_domains(struct
>>> rapl_package *rp) }
>>>  }
>>>  
>>> -static u64 rapl_unit_xlate(int package, enum unit_type type, u64
>>> value, +static u64 rapl_unit_xlate(struct rapl_domain *rd, int
>>> package,
>>> +			enum unit_type type, u64 value,
>>>  			int to_raw)
>>>  {
>>>  	u64 units = 1;
>>> @@ -663,7 +673,11 @@ static u64 rapl_unit_xlate(int package, enum
>>> unit_type type, u64 value, units = rp->power_unit;
>>>  		break;
>>>  	case ENERGY_UNIT:
>>> -		units = rp->energy_unit;
>>> +		/* per domain unit takes precedence */
>>> +		if (rd && rd->domain_energy_unit)
>>> +			units = rd->domain_energy_unit;
>>> +		else
>>> +			units = rp->energy_unit;
>>>  		break;
>>>  	case TIME_UNIT:
>>>  		return rapl_defaults->compute_time_window(rp,
>>> value, to_raw); @@ -773,7 +787,7 @@ static int
>>> rapl_read_data_raw(struct rapl_domain *rd, final = value & rp->mask;
>>>  	final = final >> rp->shift;
>>>  	if (xlate)
>>> -		*data = rapl_unit_xlate(rd->package_id, rp->unit,
>>> final, 0);
>>> +		*data = rapl_unit_xlate(rd, rd->package_id,
>>> rp->unit, final, 0); else
>>>  		*data = final;
>>>  
>>> @@ -799,7 +813,7 @@ static int rapl_write_data_raw(struct
>>> rapl_domain *rd, "failed to read msr 0x%x on cpu %d\n", msr, cpu);
>>>  		return -EIO;
>>>  	}
>>> -	value = rapl_unit_xlate(rd->package_id, rp->unit, value,
>>> 1);
>>> +	value = rapl_unit_xlate(rd, rd->package_id, rp->unit,
>>> value, 1); msr_val &= ~rp->mask;
>>>  	msr_val |= value << rp->shift;
>>>  	if (wrmsrl_safe_on_cpu(cpu, msr, msr_val)) {
>>> @@ -1017,6 +1031,13 @@ static const struct rapl_defaults
>>> rapl_defaults_core = { .compute_time_window =
>>> rapl_compute_time_window_core, };
>>>  
>>> +static const struct rapl_defaults rapl_defaults_hsw_server = {
>>> +	.check_unit = rapl_check_unit_core,
>>> +	.set_floor_freq = set_floor_freq_default,
>>> +	.compute_time_window = rapl_compute_time_window_core,
>>> +	.dram_domain_energy_unit = 15,
>>> +};
>>> +
>>>  static const struct rapl_defaults rapl_defaults_atom = {
>>>  	.check_unit = rapl_check_unit_atom,
>>>  	.set_floor_freq = set_floor_freq_atom,
>>> @@ -1037,7 +1058,7 @@ static const struct x86_cpu_id rapl_ids[] = {
>>>  	RAPL_CPU(0x3a, rapl_defaults_core),/* Ivy Bridge */
>>>  	RAPL_CPU(0x3c, rapl_defaults_core),/* Haswell */
>>>  	RAPL_CPU(0x3d, rapl_defaults_core),/* Broadwell */
>>> -	RAPL_CPU(0x3f, rapl_defaults_core),/* Haswell */
>>> +	RAPL_CPU(0x3f, rapl_defaults_hsw_server),/* Haswell
>>> servers */ RAPL_CPU(0x45, rapl_defaults_core),/* Haswell ULT */
>>>  	RAPL_CPU(0x4C, rapl_defaults_atom),/* Braswell */
>>>  	RAPL_CPU(0x4A, rapl_defaults_atom),/* Tangier */
> [Jacob Pan]

--
To unsubscribe from this list: send the line "unsubscribe linux-kernel" in
the body of a message to majordomo@xxxxxxxxxxxxxxx
More majordomo info at  http://vger.kernel.org/majordomo-info.html
Please read the FAQ at  http://www.tux.org/lkml/