test procedure

I have deployed batterylog and my own hack to collect metrics. The actual procedure is:

1. resume
2. add/remove modules, change configuration
3. suspend for 60 minutes
4. collect results

At first, the "suspend" was triggered by hitting the power key, which was reconfigured in logind.conf to make systemd suspend the machine instead of shutdown. The timing is done with a "wall clock" (an Android phone timer, technically), and the actual delay will vary between tests. the actual delay used will be the one provided by the tlp-stat -b entry in the log.

We originally set a timer of 5 minutes to expedite the tests, but this was seeing too little variation in the tlp-stat -b output: the first test led to 2 mAh usage (23mA), but that means the margin of error (±1mAh) is basically half of the measurement. batterylog reported 0.36W and it's unclear what its margin of error is.

At one hour, we'd expect 12 times the usage (so 24mAh), and therefore a more reasonable 4% margin of error.

Eventually, we found out about the rtcwake binary (part of util-linux) to automate that part of the procedure. At the end, our test procedure was:

date ; rtcwake -m no -s 3600 && systemctl suspend ; date ;\
sleep 10 ; date ; /opt/batterylog/batterylog.py ; \
journalctl -b | grep charge_now | tail -2

The mAh metrics were computed with the excellent qalculate with a formula like this for the simple, ~1h tests:

> (2205mAh−2150mAh)/3601s

  (((2205 * meter) * ampère * heure) - ((2150 * meter) * ampère * heure)) /
  (3601 * seconde) =
  approx. 54,984726 A*m

For longer tests, some creative time diffs were done because qalculate doesn't support complicated calendar calculations. This run, for example:

oct 12 20:19:01 angela systemd-sleep[149720]: /sys/class/power_supply/BAT1/charge_now                     =   1836 [mAh]
oct 13 08:52:54 angela systemd-sleep[150028]: /sys/class/power_supply/BAT1/charge_now                     =   1636 [mAh]

... would result in the formula:

> (1836mAh-1636mAh)/((20h+52min+54s)-(8h+19min+1s))

(((1836 * meter) * ampère * heure) - ((1636 * meter) * ampère * heure)) /
(((20 * heure) + (52 * minute) + (54 * seconde)) - ((8 * heure) + (19 *
minute) + (1 * seconde))) =
approx. 15,917582 A*m

Tests were performed on a 12th gen Framework laptop with the latest BIOS (3.05, as of 2022-10-13), running Debian bookworm, with powerstat --autotune, and tlp.service enabled. Other tweaks might be relevant here, but see the full review on things that were done to this laptop.

a note on turbostat

I've seen elsewhere people using turbostat to profile the suspend mode, but I couldn't make this work.

This, for example, doesn't give the results I'd expect:

root@angela:/home/anarcat# turbostat --show GFX%rc6,Pkg%pc2,Pkg%pc3,Pkg%pc6,Pkg%pc7,Pkg%pc8,Pkg%pc9,Pk%pc10,SYS%LPI rtcwake -m freeze -s 3600 ; /opt/batterylog/batterylog.py ; journalctl -b | grep charge_now | tail -2 ;\
> turbostat --show GFX%rc6,Pkg%pc2,Pkg%pc3,Pkg%pc6,Pkg%pc7,Pkg%pc8,Pkg%pc9,Pk%pc10,SYS%LPI systemctl suspend ; /opt/batterylog/batterylog.py ; journalctl -b | grep charge_now | tail -2
turbostat version 2022.04.16 - Len Brown <lenb@kernel.org>
CPUID(0): GenuineIntel 0x20 CPUID levels
CPUID(1): family:model:stepping 0x6:9a:3 (6:154:3) microcode 0x421
CPUID(0x80000000): max_extended_levels: 0x80000008
CPUID(1): SSE3 MONITOR SMX EIST TM2 TSC MSR ACPI-TM HT TM
CPUID(6): APERF, TURBO, DTS, PTM, HWP, HWPnotify, HWPwindow, HWPepp, HWPpkg, EPB
cpu4: MSR_IA32_MISC_ENABLE: 0x00850089 (TCC EIST MWAIT PREFETCH TURBO)
CPUID(7): No-SGX
CPUID(0x15): eax_crystal: 2 ebx_tsc: 110 ecx_crystal_hz: 38400000
TSC: 2112 MHz (38400000 Hz * 110 / 2 / 1000000)
CPUID(0x16): base_mhz: 2100 max_mhz: 4400 bus_mhz: 100
cpu4: MSR_MISC_PWR_MGMT: 0x000030c2 (ENable-EIST_Coordination ENable-EPB DISable-OOB)
RAPL: 9362 sec. Joule Counter Range, at 28 Watts
cpu4: MSR_PLATFORM_INFO: 0x804043df0811500
4 * 100.0 = 400.0 MHz max efficiency frequency
21 * 100.0 = 2100.0 MHz base frequency
cpu4: MSR_IA32_POWER_CTL: 0x00e4005b (C1E auto-promotion: ENabled)
cpu4: MSR_TURBO_RATIO_LIMIT: 0x2323232323252c2c
35 * 100.0 = 3500.0 MHz max turbo 8 active cores
35 * 100.0 = 3500.0 MHz max turbo 7 active cores
35 * 100.0 = 3500.0 MHz max turbo 6 active cores
35 * 100.0 = 3500.0 MHz max turbo 5 active cores
35 * 100.0 = 3500.0 MHz max turbo 4 active cores
37 * 100.0 = 3700.0 MHz max turbo 3 active cores
44 * 100.0 = 4400.0 MHz max turbo 2 active cores
44 * 100.0 = 4400.0 MHz max turbo 1 active cores
cpu4: MSR_CONFIG_TDP_NOMINAL: 0x00000011 (base_ratio=17)
cpu4: MSR_CONFIG_TDP_LEVEL_1: 0x000e00a0 (PKG_MIN_PWR_LVL1=0 PKG_MAX_PWR_LVL1=0 LVL1_RATIO=14 PKG_TDP_LVL1=160)
cpu4: MSR_CONFIG_TDP_LEVEL_2: 0x00150118 (PKG_MIN_PWR_LVL2=0 PKG_MAX_PWR_LVL2=0 LVL2_RATIO=21 PKG_TDP_LVL2=280)
cpu4: MSR_CONFIG_TDP_CONTROL: 0x00000000 ( lock=0)
cpu4: MSR_TURBO_ACTIVATION_RATIO: 0x00000010 (MAX_NON_TURBO_RATIO=16 lock=0)
cpu4: MSR_PKG_CST_CONFIG_CONTROL: 0x74008008 (UNdemote-C1, demote-C1, locked, pkg-cstate-limit=8 (unlimited))
/dev/cpu_dma_latency: 2000000000 usec (default)
current_driver: intel_idle
current_governor: menu
current_governor_ro: menu
cpu4: POLL: CPUIDLE CORE POLL IDLE
cpu4: C1E: MWAIT 0x01
cpu4: C6: MWAIT 0x20
cpu4: C8: MWAIT 0x40
cpu4: C10: MWAIT 0x60
cpu4: cpufreq driver: intel_pstate
cpu4: cpufreq governor: powersave
cpufreq intel_pstate no_turbo: 0
cpu4: MSR_MISC_FEATURE_CONTROL: 0x00000000 (L2-Prefetch L2-Prefetch-pair L1-Prefetch L1-IP-Prefetch)
cpu0: MSR_PM_ENABLE: 0x00000001 (HWP)
cpu0: MSR_HWP_CAPABILITIES: 0x01111638 (high 56 guar 22 eff 17 low 1)
cpu0: MSR_HWP_REQUEST: 0xc0003806 (min 6 max 56 des 0 epp 0xc0 window 0x0 pkg 0x0)
cpu0: MSR_HWP_REQUEST_PKG: 0x8000ff01 (min 1 max 255 des 0 epp 0x80 window 0x0)
cpu0: MSR_HWP_INTERRUPT: 0x00000001 (EN_Guaranteed_Perf_Change, Dis_Excursion_Min)
cpu0: MSR_HWP_STATUS: 0x00000000 (No-Guaranteed_Perf_Change, No-Excursion_Min)
cpu0: EPB: 7 (custom)
cpu0: MSR_RAPL_POWER_UNIT: 0x000a0e03 (0.125000 Watts, 0.000061 Joules, 0.000977 sec.)
cpu0: MSR_PKG_POWER_INFO: 0x000000e0 (28 W TDP, RAPL 0 - 0 W, 0.000000 sec.)
cpu0: MSR_PKG_POWER_LIMIT: 0x42820000dd80f0 (UNlocked)
cpu0: PKG Limit #1: ENabled (30.000 Watts, 28.000000 sec, clamp ENabled)
cpu0: PKG Limit #2: ENabled (64.000 Watts, 0.002441* sec, clamp DISabled)
cpu0: MSR_VR_CURRENT_CONFIG: 0x000002d0
cpu0: PKG Limit #4: 90.000000 Watts (UNlocked)
cpu0: MSR_DRAM_POWER_LIMIT: 0x00000000 (UNlocked)
cpu0: DRAM Limit: DISabled (0.000 Watts, 0.000977 sec, clamp DISabled)
cpu0: MSR_PP0_POLICY: 9
cpu0: MSR_PP0_POWER_LIMIT: 0x00000000 (UNlocked)
cpu0: Cores Limit: DISabled (0.000 Watts, 0.000977 sec, clamp DISabled)
cpu0: MSR_PP1_POLICY: 13
cpu0: MSR_PP1_POWER_LIMIT: 0x00000000 (UNlocked)
cpu0: GFX Limit: DISabled (0.000 Watts, 0.000977 sec, clamp DISabled)
cpu0: MSR_IA32_TEMPERATURE_TARGET: 0x80640000 (100 C)
cpu0: MSR_IA32_PACKAGE_THERM_STATUS: 0x88420000 (34 C)
cpu0: MSR_IA32_PACKAGE_THERM_INTERRUPT: 0x02000003 (100 C, 100 C)
cpu4: MSR_PKGC3_IRTL: 0x00000000 (NOTvalid, 0 ns)
cpu4: MSR_PKGC6_IRTL: 0x00000000 (NOTvalid, 0 ns)
cpu4: MSR_PKGC7_IRTL: 0x00000000 (NOTvalid, 0 ns)
cpu4: MSR_PKGC8_IRTL: 0x00000000 (NOTvalid, 0 ns)
cpu4: MSR_PKGC9_IRTL: 0x00000000 (NOTvalid, 0 ns)
cpu4: MSR_PKGC10_IRTL: 0x00000000 (NOTvalid, 0 ns)
rtcwake: assuming RTC uses UTC ...
rtcwake: wakeup from "freeze" using /dev/rtc0 at Wed Oct 12 03:03:31 2022
3601.483927 sec
GFX%rc6 Pkg%pc2 Pkg%pc3 Pkg%pc6 Pkg%pc7 Pkg%pc8 Pkg%pc9 Pk%pc10 SYS%LPI
15.63   0.03    0.01    0.00    0.00    0.00    0.00    100.50  99.80
15.63   0.03    0.01    0.00    0.00    0.00    0.00    100.50  99.80
Slept for 1.01 hours
Used 0.75 Wh, an average rate of 0.75 W
For your 54.53 Wh battery this is 1.38%/hr or 33.03%/day
oct 11 20:19:44 angela systemd-sleep[12975]: /sys/class/power_supply/BAT1/charge_now                     =   3284 [mAh]
oct 11 21:20:04 angela systemd-sleep[13222]: /sys/class/power_supply/BAT1/charge_now                     =   3235 [mAh]
turbostat version 2022.04.16 - Len Brown <lenb@kernel.org>
CPUID(0): GenuineIntel 0x20 CPUID levels
CPUID(1): family:model:stepping 0x6:9a:3 (6:154:3) microcode 0x421
CPUID(0x80000000): max_extended_levels: 0x80000008
CPUID(1): SSE3 MONITOR SMX EIST TM2 TSC MSR ACPI-TM HT TM
CPUID(6): APERF, TURBO, DTS, PTM, HWP, HWPnotify, HWPwindow, HWPepp, HWPpkg, EPB
cpu1: MSR_IA32_MISC_ENABLE: 0x00850089 (TCC EIST MWAIT PREFETCH TURBO)
CPUID(7): No-SGX
CPUID(0x15): eax_crystal: 2 ebx_tsc: 110 ecx_crystal_hz: 38400000
TSC: 2112 MHz (38400000 Hz * 110 / 2 / 1000000)
CPUID(0x16): base_mhz: 2100 max_mhz: 4400 bus_mhz: 100
cpu1: MSR_MISC_PWR_MGMT: 0x000030c2 (ENable-EIST_Coordination ENable-EPB DISable-OOB)
RAPL: 9362 sec. Joule Counter Range, at 28 Watts
cpu1: MSR_PLATFORM_INFO: 0x804043df0811500
4 * 100.0 = 400.0 MHz max efficiency frequency
21 * 100.0 = 2100.0 MHz base frequency
cpu1: MSR_IA32_POWER_CTL: 0x00e4005b (C1E auto-promotion: ENabled)
cpu1: MSR_TURBO_RATIO_LIMIT: 0x2323232323252c2c
35 * 100.0 = 3500.0 MHz max turbo 8 active cores
35 * 100.0 = 3500.0 MHz max turbo 7 active cores
35 * 100.0 = 3500.0 MHz max turbo 6 active cores
35 * 100.0 = 3500.0 MHz max turbo 5 active cores
35 * 100.0 = 3500.0 MHz max turbo 4 active cores
37 * 100.0 = 3700.0 MHz max turbo 3 active cores
44 * 100.0 = 4400.0 MHz max turbo 2 active cores
44 * 100.0 = 4400.0 MHz max turbo 1 active cores
cpu1: MSR_CONFIG_TDP_NOMINAL: 0x00000011 (base_ratio=17)
cpu1: MSR_CONFIG_TDP_LEVEL_1: 0x000e00a0 (PKG_MIN_PWR_LVL1=0 PKG_MAX_PWR_LVL1=0 LVL1_RATIO=14 PKG_TDP_LVL1=160)
cpu1: MSR_CONFIG_TDP_LEVEL_2: 0x00150118 (PKG_MIN_PWR_LVL2=0 PKG_MAX_PWR_LVL2=0 LVL2_RATIO=21 PKG_TDP_LVL2=280)
cpu1: MSR_CONFIG_TDP_CONTROL: 0x00000000 ( lock=0)
cpu1: MSR_TURBO_ACTIVATION_RATIO: 0x00000010 (MAX_NON_TURBO_RATIO=16 lock=0)
cpu1: MSR_PKG_CST_CONFIG_CONTROL: 0x74008008 (UNdemote-C1, demote-C1, locked, pkg-cstate-limit=8 (unlimited))
/dev/cpu_dma_latency: 2000000000 usec (default)
current_driver: intel_idle
current_governor: menu
current_governor_ro: menu
cpu1: POLL: CPUIDLE CORE POLL IDLE
cpu1: C1E: MWAIT 0x01
cpu1: C6: MWAIT 0x20
cpu1: C8: MWAIT 0x40
cpu1: C10: MWAIT 0x60
cpu1: cpufreq driver: intel_pstate
cpu1: cpufreq governor: powersave
cpufreq intel_pstate no_turbo: 0
cpu1: MSR_MISC_FEATURE_CONTROL: 0x00000000 (L2-Prefetch L2-Prefetch-pair L1-Prefetch L1-IP-Prefetch)
cpu0: MSR_PM_ENABLE: 0x00000001 (HWP)
cpu0: MSR_HWP_CAPABILITIES: 0x011c1638 (high 56 guar 22 eff 28 low 1)
cpu0: MSR_HWP_REQUEST: 0xc0003806 (min 6 max 56 des 0 epp 0xc0 window 0x0 pkg 0x0)
cpu0: MSR_HWP_REQUEST_PKG: 0x8000ff01 (min 1 max 255 des 0 epp 0x80 window 0x0)
cpu0: MSR_HWP_INTERRUPT: 0x00000001 (EN_Guaranteed_Perf_Change, Dis_Excursion_Min)
cpu0: MSR_HWP_STATUS: 0x00000000 (No-Guaranteed_Perf_Change, No-Excursion_Min)
cpu0: EPB: 7 (custom)
cpu0: MSR_RAPL_POWER_UNIT: 0x000a0e03 (0.125000 Watts, 0.000061 Joules, 0.000977 sec.)
cpu0: MSR_PKG_POWER_INFO: 0x000000e0 (28 W TDP, RAPL 0 - 0 W, 0.000000 sec.)
cpu0: MSR_PKG_POWER_LIMIT: 0x42820000dd80f0 (UNlocked)
cpu0: PKG Limit #1: ENabled (30.000 Watts, 28.000000 sec, clamp ENabled)
cpu0: PKG Limit #2: ENabled (64.000 Watts, 0.002441* sec, clamp DISabled)
cpu0: MSR_VR_CURRENT_CONFIG: 0x000002d0
cpu0: PKG Limit #4: 90.000000 Watts (UNlocked)
cpu0: MSR_DRAM_POWER_LIMIT: 0x00000000 (UNlocked)
cpu0: DRAM Limit: DISabled (0.000 Watts, 0.000977 sec, clamp DISabled)
cpu0: MSR_PP0_POLICY: 9
cpu0: MSR_PP0_POWER_LIMIT: 0x00000000 (UNlocked)
cpu0: Cores Limit: DISabled (0.000 Watts, 0.000977 sec, clamp DISabled)
cpu0: MSR_PP1_POLICY: 13
cpu0: MSR_PP1_POWER_LIMIT: 0x00000000 (UNlocked)
cpu0: GFX Limit: DISabled (0.000 Watts, 0.000977 sec, clamp DISabled)
cpu0: MSR_IA32_TEMPERATURE_TARGET: 0x80640000 (100 C)
cpu0: MSR_IA32_PACKAGE_THERM_STATUS: 0x884f0000 (21 C)
cpu0: MSR_IA32_PACKAGE_THERM_INTERRUPT: 0x02000003 (100 C, 100 C)
cpu1: MSR_PKGC3_IRTL: 0x00000000 (NOTvalid, 0 ns)
cpu1: MSR_PKGC6_IRTL: 0x00000000 (NOTvalid, 0 ns)
cpu1: MSR_PKGC7_IRTL: 0x00000000 (NOTvalid, 0 ns)
cpu1: MSR_PKGC8_IRTL: 0x00000000 (NOTvalid, 0 ns)
cpu1: MSR_PKGC9_IRTL: 0x00000000 (NOTvalid, 0 ns)
cpu1: MSR_PKGC10_IRTL: 0x00000000 (NOTvalid, 0 ns)
0.012176 sec
GFX%rc6 Pkg%pc2 Pkg%pc3 Pkg%pc6 Pkg%pc7 Pkg%pc8 Pkg%pc9 Pk%pc10 SYS%LPI
82.13   0.00    0.00    0.00    0.00    0.00    0.00    0.00    0.00
90.10   0.00    0.00    0.00    0.00    0.00    0.00    0.00    0.00
Slept for 1.01 hours
Used 0.75 Wh, an average rate of 0.75 W
For your 54.53 Wh battery this is 1.38%/hr or 33.03%/day
oct 11 20:19:44 angela systemd-sleep[12975]: /sys/class/power_supply/BAT1/charge_now                     =   3284 [mAh]
oct 11 21:20:04 angela systemd-sleep[13222]: /sys/class/power_supply/BAT1/charge_now                     =   3235 [mAh]

See how the second suspend didn't correctly run? It looks like rtcwake doesn't correctly trigger the systemd hooks. And indeed, the above it doesn't even go in the correct sleep more (freeze instead of mem).

Another run, with mem:

root@angela:/home/anarcat# turbostat --show GFX%rc6,Pkg%pc2,Pkg%pc3,Pkg%pc6,Pkg%pc7,Pkg%pc8,Pkg%pc9,Pk%pc10,SYS%LPI rtcwake -m mem -s 3600 ; /opt/batterylog/batterylog.py ; journalctl -b | grep charge_now | tail -2
turbostat version 2022.04.16 - Len Brown <lenb@kernel.org>
CPUID(0): GenuineIntel 0x20 CPUID levels
CPUID(1): family:model:stepping 0x6:9a:3 (6:154:3) microcode 0x421
CPUID(0x80000000): max_extended_levels: 0x80000008
CPUID(1): SSE3 MONITOR SMX EIST TM2 TSC MSR ACPI-TM HT TM
CPUID(6): APERF, TURBO, DTS, PTM, HWP, HWPnotify, HWPwindow, HWPepp, HWPpkg, EPB
cpu6: MSR_IA32_MISC_ENABLE: 0x00850089 (TCC EIST MWAIT PREFETCH TURBO)
CPUID(7): No-SGX
CPUID(0x15): eax_crystal: 2 ebx_tsc: 110 ecx_crystal_hz: 38400000
TSC: 2112 MHz (38400000 Hz * 110 / 2 / 1000000)
CPUID(0x16): base_mhz: 2100 max_mhz: 4400 bus_mhz: 100
cpu6: MSR_MISC_PWR_MGMT: 0x000030c2 (ENable-EIST_Coordination ENable-EPB DISable-OOB)
RAPL: 9362 sec. Joule Counter Range, at 28 Watts
cpu6: MSR_PLATFORM_INFO: 0x804043df0811500
4 * 100.0 = 400.0 MHz max efficiency frequency
21 * 100.0 = 2100.0 MHz base frequency
cpu6: MSR_IA32_POWER_CTL: 0x00e4005b (C1E auto-promotion: ENabled)
cpu6: MSR_TURBO_RATIO_LIMIT: 0x2323232323252c2c
35 * 100.0 = 3500.0 MHz max turbo 8 active cores
35 * 100.0 = 3500.0 MHz max turbo 7 active cores
35 * 100.0 = 3500.0 MHz max turbo 6 active cores
35 * 100.0 = 3500.0 MHz max turbo 5 active cores
35 * 100.0 = 3500.0 MHz max turbo 4 active cores
37 * 100.0 = 3700.0 MHz max turbo 3 active cores
44 * 100.0 = 4400.0 MHz max turbo 2 active cores
44 * 100.0 = 4400.0 MHz max turbo 1 active cores
cpu6: MSR_CONFIG_TDP_NOMINAL: 0x00000011 (base_ratio=17)
cpu6: MSR_CONFIG_TDP_LEVEL_1: 0x000e00a0 (PKG_MIN_PWR_LVL1=0 PKG_MAX_PWR_LVL1=0 LVL1_RATIO=14 PKG_TDP_LVL1=160)
cpu6: MSR_CONFIG_TDP_LEVEL_2: 0x00150118 (PKG_MIN_PWR_LVL2=0 PKG_MAX_PWR_LVL2=0 LVL2_RATIO=21 PKG_TDP_LVL2=280)
cpu6: MSR_CONFIG_TDP_CONTROL: 0x00000000 ( lock=0)
cpu6: MSR_TURBO_ACTIVATION_RATIO: 0x00000010 (MAX_NON_TURBO_RATIO=16 lock=0)
cpu6: MSR_PKG_CST_CONFIG_CONTROL: 0x74008008 (UNdemote-C1, demote-C1, locked, pkg-cstate-limit=8 (unlimited))
/dev/cpu_dma_latency: 2000000000 usec (default)
current_driver: intel_idle
current_governor: menu
current_governor_ro: menu
cpu6: POLL: CPUIDLE CORE POLL IDLE
cpu6: C1E: MWAIT 0x01
cpu6: C6: MWAIT 0x20
cpu6: C8: MWAIT 0x40
cpu6: C10: MWAIT 0x60
cpu6: cpufreq driver: intel_pstate
cpu6: cpufreq governor: powersave
cpufreq intel_pstate no_turbo: 0
cpu6: MSR_MISC_FEATURE_CONTROL: 0x00000000 (L2-Prefetch L2-Prefetch-pair L1-Prefetch L1-IP-Prefetch)
cpu0: MSR_PM_ENABLE: 0x00000001 (HWP)
cpu0: MSR_HWP_CAPABILITIES: 0x01141638 (high 56 guar 22 eff 20 low 1)
cpu0: MSR_HWP_REQUEST: 0xc0003806 (min 6 max 56 des 0 epp 0xc0 window 0x0 pkg 0x0)
cpu0: MSR_HWP_REQUEST_PKG: 0x8000ff01 (min 1 max 255 des 0 epp 0x80 window 0x0)
cpu0: MSR_HWP_INTERRUPT: 0x00000001 (EN_Guaranteed_Perf_Change, Dis_Excursion_Min)
cpu0: MSR_HWP_STATUS: 0x00000000 (No-Guaranteed_Perf_Change, No-Excursion_Min)
cpu0: EPB: 7 (custom)
cpu0: MSR_RAPL_POWER_UNIT: 0x000a0e03 (0.125000 Watts, 0.000061 Joules, 0.000977 sec.)
cpu0: MSR_PKG_POWER_INFO: 0x000000e0 (28 W TDP, RAPL 0 - 0 W, 0.000000 sec.)
cpu0: MSR_PKG_POWER_LIMIT: 0x42820000dd80f0 (UNlocked)
cpu0: PKG Limit #1: ENabled (30.000 Watts, 28.000000 sec, clamp ENabled)
cpu0: PKG Limit #2: ENabled (64.000 Watts, 0.002441* sec, clamp DISabled)
cpu0: MSR_VR_CURRENT_CONFIG: 0x000002d0
cpu0: PKG Limit #4: 90.000000 Watts (UNlocked)
cpu0: MSR_DRAM_POWER_LIMIT: 0x00000000 (UNlocked)
cpu0: DRAM Limit: DISabled (0.000 Watts, 0.000977 sec, clamp DISabled)
cpu0: MSR_PP0_POLICY: 9
cpu0: MSR_PP0_POWER_LIMIT: 0x00000000 (UNlocked)
cpu0: Cores Limit: DISabled (0.000 Watts, 0.000977 sec, clamp DISabled)
cpu0: MSR_PP1_POLICY: 13
cpu0: MSR_PP1_POWER_LIMIT: 0x00000000 (UNlocked)
cpu0: GFX Limit: DISabled (0.000 Watts, 0.000977 sec, clamp DISabled)
cpu0: MSR_IA32_TEMPERATURE_TARGET: 0x80640000 (100 C)
cpu0: MSR_IA32_PACKAGE_THERM_STATUS: 0x884b0000 (25 C)
cpu0: MSR_IA32_PACKAGE_THERM_INTERRUPT: 0x02000003 (100 C, 100 C)
cpu6: MSR_PKGC3_IRTL: 0x00000000 (NOTvalid, 0 ns)
cpu6: MSR_PKGC6_IRTL: 0x00000000 (NOTvalid, 0 ns)
cpu6: MSR_PKGC7_IRTL: 0x00000000 (NOTvalid, 0 ns)
cpu6: MSR_PKGC8_IRTL: 0x00000000 (NOTvalid, 0 ns)
cpu6: MSR_PKGC9_IRTL: 0x00000000 (NOTvalid, 0 ns)
cpu6: MSR_PKGC10_IRTL: 0x00000000 (NOTvalid, 0 ns)
rtcwake: assuming RTC uses UTC ...
rtcwake: wakeup from "mem" using /dev/rtc0 at Wed Oct 12 14:11:02 2022

264.737865 sec
GFX%rc6 Pkg%pc2 Pkg%pc3 Pkg%pc6 Pkg%pc7 Pkg%pc8 Pkg%pc9 Pk%pc10 SYS%LPI
0.84    1609.15 1609.15 1609.15 0.00    1609.15 0.00    1609.15 6967928093745.08
0.84    100.57  100.57  100.57  0.00    100.57  0.00    100.57  6968124499895.82
Slept for 9.04 hours
Used 2.09 Wh, an average rate of 0.23 W
For your 54.53 Wh battery this is 0.42%/hr or 10.20%/day
oct 11 23:03:32 angela systemd-sleep[42344]: /sys/class/power_supply/BAT1/charge_now                     =   2969 [mAh]
oct 12 08:05:52 angela systemd-sleep[42611]: /sys/class/power_supply/BAT1/charge_now                     =   2833 [mAh]

That seems to have worked, but then the actual numbers from turbostat are not really that meaningful. It seems we're using 100% of the CPU there, and millions of percent of SYS. Anyways, I don't understand how turbostat could be used that way anyways, since, well, it's suspended...

assumptions

we assume standby battery usage doesn't fluctuate depending on the level of the battery; as of this writing, the battery is at 95% with an estimated 10h remaining
we assume we will get similar results than runtime power usage, that is the SSD and MicroSD expansion cards use a lot of power, HDMI and DisplayPort a little, and USB-A the less, while USB-C should use none at all
we have heard theories that USB-A uses a lot more power on suspend than at runtime
we assume deep sleep provides better power saving
we expect to get close to 14mA drain on suspend

previous work

The previous results were:

System on, locked and screen off, with HDMI & USB expansion cards: around 3W
s2idle sleep with USB-A and HDMI expansion cards: around 1.9 W
s2idle sleep with only USB-C expansion cards: around 0.8 W
deep sleep with USB-A and HDMI expansion cards: around 0.9 W
deep sleep with only USB-C expansion cards: around 0.4 W

no modules

baseline: sleep=deep, nvme.noacpi=1, 0.25W, 16mA, 9 days

this is done by adding mem_sleep_default=deep to grup, rebuilding grub, and rebooting, then sleeping 5 minutes.

Slept for 0.09 hours
Used 0.03 Wh, an average rate of 0.36 W
For your 54.53 Wh battery this is 0.66%/hr or 15.74%/day

oct 11 09:58:51 angela systemd-sleep[3372668]: /sys/class/power_supply/BAT1/charge_now                     =   3317 [mAh]
oct 11 10:04:01 angela systemd-sleep[3372950]: /sys/class/power_supply/BAT1/charge_now                     =   3315 [mAh]

not conclusive, too close (2mAh) to the margin of error (1mAh). redoing with 60 minutes delay:

Slept for 1.00 hours
Used 0.25 Wh, an average rate of 0.25 W
For your 54.53 Wh battery this is 0.45%/hr or 10.83%/day

root@angela:/home/anarcat/wikis/anarc.at# journalctl -b | grep charge_now | tail -2
oct 11 10:10:42 angela systemd-sleep[3377619]: /sys/class/power_supply/BAT1/charge_now                     =   3270 [mAh]
oct 11 11:10:46 angela systemd-sleep[3377936]: /sys/class/power_supply/BAT1/charge_now                     =   3254 [mAh]

So about 0.45% per hour, 0.25W, or 16mA, or about 9 days standby. This is close to our expected 14mA. If the metrics from the two tools match, it would mean a 15.625 volt potential from the battery, which seems reasonable.

sleep=s2idle, nvme.noacpi=1, 0.29W, 18.9mA, ~7 days

same as the above, but with mem_sleep_default=s2idle.

odd result. no power consumption detected in one hour of suspend:

root@angela:/home/anarcat# journalctl -b | grep charge_now | tail -2
oct 11 12:34:48 angela systemd-sleep[13030]: /sys/class/power_supply/BAT1/charge_now                     =   3541 [mAh]
oct 11 13:34:51 angela systemd-sleep[13265]: /sys/class/power_supply/BAT1/charge_now                     =   3541 [mAh]

This even crashed battery log:

root@angela:/home/anarcat# /opt/batterylog/batterylog.py
Traceback (most recent call last):
  File "/opt/batterylog/batterylog.py", line 123, in <module>
    until_empty_h = Decimal(resume['energy_min']/1000000000000)/ power_use_w
decimal.DivisionByZero: [<class 'decimal.DivisionByZero'>]

And no, the laptop was not plugged in. Probably because the battery was recharged between the first test and second, it's possible it was "over charged" and the battery use wasn't detected.

Really odd result, will retry.

root@angela:/home/anarcat# /opt/batterylog/batterylog.py
Slept for 1.00 hours
Used 0.29 Wh, an average rate of 0.29 W
For your 54.53 Wh battery this is 0.54%/hr or 12.86%/day

root@angela:/home/anarcat# journalctl -b | grep charge_now | tail -2
oct 11 14:00:41 angela systemd-sleep[29700]: /sys/class/power_supply/BAT1/charge_now                     =   3497 [mAh]
oct 11 15:00:45 angela systemd-sleep[29983]: /sys/class/power_supply/BAT1/charge_now                     =   3478 [mAh]

That's 18.9mA, 0.29W, 0.54% per hour, or about a week standby.

In here, we could say s2idle costs us 0.04W, or about 5mA, which is pretty small, but still negligible: about two days standby time, out of the 9 days from the baseline.

sleep=s2idle, no nvme config, 0.31W, 20mA, ~7 days

Here, we kept the mem_sleep_default=s2idle kernel parameter but removed the nvme.noacpi=1 flag.

Slept for 1.00 hours
Used 0.31 Wh, an average rate of 0.31 W
For your 54.53 Wh battery this is 0.56%/hr or 13.55%/day

oct 11 15:06:11 angela systemd-sleep[3499]: /sys/class/power_supply/BAT1/charge_now                     =   3447 [mAh]
oct 11 16:06:13 angela systemd-sleep[3793]: /sys/class/power_supply/BAT1/charge_now                     =   3427 [mAh]

That's 19.98mA (let's just call it 20mA), 0.31W, 0.56% per hour, or about a week of standby.

It's only slightly more than with nvme.noacpi=1, but it's basically within the margin of error (1mAh or 0.02W).

1 USB-C: 0.23W, 15mA, ~10 days

baseline configuration (nvme.noacpi=1, mem_sleep_default=deep) with only one USB-C expansion card connected

Slept for 1.00 hours
Used 0.23 Wh, an average rate of 0.23 W
For your 54.53 Wh battery this is 0.42%/hr or 10.15%/day

oct 11 16:15:20 angela systemd-sleep[3637]: /sys/class/power_supply/BAT1/charge_now                     =   3378 [mAh]
oct 11 17:15:25 angela systemd-sleep[3946]: /sys/class/power_supply/BAT1/charge_now                     =   3363 [mAh]

15mA, 0.23W, 0.42%/h, that's 10 days standby, more than without modules??? weeeird... Could it be that USB-C cards do something to the USB-C ports that make them take less power?

1 USB-C, longer suspend: 0.22W, 14.5mA, ~10+ days

Just a spot check.

Slept for 1.93 hours
Used 0.43 Wh, an average rate of 0.22 W
For your 54.53 Wh battery this is 0.41%/hr or 9.82%/day

oct 11 17:18:58 angela systemd-sleep[6788]: /sys/class/power_supply/BAT1/charge_now                     =   3348 [mAh]
oct 11 19:14:58 angela systemd-sleep[7039]: /sys/class/power_supply/BAT1/charge_now                     =   3320 [mAh]

Again, around 14mA (14.5mA), 0.22W, 0.41%/hr. Excellent result.

2 USB-C: 0.23W, 14.9mA, ~10 days

Slept for 1.01 hours
Used 0.23 Wh, an average rate of 0.23 W
For your 54.53 Wh battery this is 0.42%/hr or 10.10%/day

oct 11 19:17:34 angela systemd-sleep[11024]: /sys/class/power_supply/BAT1/charge_now                     =   3307 [mAh]
oct 11 20:17:57 angela systemd-sleep[11277]: /sys/class/power_supply/BAT1/charge_now                     =   3292 [mAh]

14.9mA, 0.23W, 0.42%/hr. Basically similar to one USB-C port, as the above, lower than the baseline.

1 USB-A: 0.75W, 48.7mA, 3 days

Slept for 1.01 hours
Used 0.75 Wh, an average rate of 0.75 W
For your 54.53 Wh battery this is 1.38%/hr or 33.03%/day

oct 11 20:19:44 angela systemd-sleep[12975]: /sys/class/power_supply/BAT1/charge_now                     =   3284 [mAh]
oct 11 21:20:04 angela systemd-sleep[13222]: /sys/class/power_supply/BAT1/charge_now                     =   3235 [mAh]

48.7mAm 0.75W, 1.38%/hre, basically 3 days standby max! That's a three-fold performance decrease from the previous metric.

Okay, here's a problem. That's half a watt, for one USB-A card, doing nothing, during suspend.

Something is definitely wrong with the USB-A connectors.

spot check: redoing baseline, longer test

Redoing the baseline for a longer test, as the first test above gave odd results, where the discharge rate without USB-C cards is higher than with the card(s).

Slept for 9.04 hours
Used 2.09 Wh, an average rate of 0.23 W
For your 54.53 Wh battery this is 0.42%/hr or 10.20%/day
oct 11 23:03:32 angela systemd-sleep[42344]: /sys/class/power_supply/BAT1/charge_now                     =   2969 [mAh]
oct 12 08:05:52 angela systemd-sleep[42611]: /sys/class/power_supply/BAT1/charge_now                     =   2833 [mAh]

That's 15mA and 0.23W, closer to the "only USB-C" metric. So this is our new baseline.

2 USB-A: 1.11W, 72mA, 2 days

Slept for 1.00 hours
Used 1.11 Wh, an average rate of 1.11 W
For your 54.53 Wh battery this is 2.03%/hr or 48.79%/day
oct 12 09:16:35 angela systemd-sleep[47702]: /sys/class/power_supply/BAT1/charge_now                     =   2775 [mAh]
oct 12 10:16:36 angela systemd-sleep[47962]: /sys/class/power_supply/BAT1/charge_now                     =   2703 [mAh]

72mA, 1.11W, another ~500mW (360mW, actually) for the extra USB-A card. ouch. Barely two days standby with this configuration.

3 USB-A: 1.48W, 96mA, < 2 days

Slept for 1.00 hours
Used 1.48 Wh, an average rate of 1.48 W
For your 54.53 Wh battery this is 2.71%/hr or 65.05%/day
oct 12 11:47:43 angela systemd-sleep[100669]: /sys/class/power_supply/BAT1/charge_now                     =   2460 [mAh]
oct 12 12:47:44 angela systemd-sleep[100986]: /sys/class/power_supply/BAT1/charge_now                     =   2364 [mAh]

96mA, 1.48W, another 370mW. Seems to confirm there's about 360mW per USB-A card, with a base 150mW cost once any is plugged. That's a total of 1.25W for three USB-A cards, or about 420mW per card on average.

Less than two days standby.

1TB SSD: 0.49W, 32mA, <5 days

Slept for 1.00 hours
Used 0.49 Wh, an average rate of 0.49 W
For your 54.53 Wh battery this is 0.90%/hr or 21.68%/day
oct 12 13:01:15 angela systemd-sleep[110500]: /sys/class/power_supply/BAT1/charge_now                     =   2304 [mAh]
oct 12 14:01:16 angela systemd-sleep[110779]: /sys/class/power_supply/BAT1/charge_now                     =   2272 [mAh]

MicroSD: 0.52W, 34mA, ~4 days

Slept for 1.00 hours
Used 0.52 Wh, an average rate of 0.52 W
For your 54.53 Wh battery this is 0.96%/hr or 23.04%/day
oct 12 14:04:38 angela systemd-sleep[113632]: /sys/class/power_supply/BAT1/charge_now                     =   2254 [mAh]
oct 12 15:04:38 angela systemd-sleep[113882]: /sys/class/power_supply/BAT1/charge_now                     =   2220 [mAh]

1 DisplayPort: 0.85W, 55mA, <3 days

Slept for 1.00 hours
Used 0.85 Wh, an average rate of 0.85 W
For your 54.53 Wh battery this is 1.55%/hr or 37.27%/day
oct 12 15:07:49 angela systemd-sleep[116530]: /sys/class/power_supply/BAT1/charge_now                     =   2205 [mAh]
oct 12 16:07:50 angela systemd-sleep[116797]: /sys/class/power_supply/BAT1/charge_now                     =   2150 [mAh]

1 HDMI: 0.58W, 38mA, ~4 days

Slept for 1.00 hours
Used 0.59 Wh, an average rate of 0.58 W
For your 54.53 Wh battery this is 1.07%/hr or 25.74%/day
oct 12 16:14:23 angela systemd-sleep[122142]: /sys/class/power_supply/BAT1/charge_now                     =   2123 [mAh]
oct 12 17:14:25 angela systemd-sleep[122476]: /sys/class/power_supply/BAT1/charge_now                     =   2085 [mAh]

2 HDMI: 0.65W, 42mA, <4 days

Slept for 1.00 hours
Used 0.65 Wh, an average rate of 0.65 W
For your 54.53 Wh battery this is 1.19%/hr or 28.46%/day
oct 12 17:53:19 angela systemd-sleep[125049]: /sys/class/power_supply/BAT1/charge_now                     =   2054 [mAh]
oct 12 18:53:20 angela systemd-sleep[125304]: /sys/class/power_supply/BAT1/charge_now                     =   2012 [mAh]

last spot check, no cards: 0.25W, 16mA, >9 days

Slept for 12.56 hours
Used 3.08 Wh, an average rate of 0.25 W
For your 54.53 Wh battery this is 0.45%/hr or 10.79%/day
oct 12 20:19:01 angela systemd-sleep[149720]: /sys/class/power_supply/BAT1/charge_now                     =   1836 [mAh]
oct 13 08:52:54 angela systemd-sleep[150028]: /sys/class/power_supply/BAT1/charge_now                     =   1636 [mAh]

Interestingly, this is the same as the original baseline, which is higher than the "USB-C" case. This posibly confirms that having USB-C cards plugged in helps with power consumption, but further tests would be required to confirm this hypothesis.

At the end of the run, the battery was at 45%, with 4h26m remaining according to py3status. Almost all the tests here were done on a single charge, although there was one charge earlier in the test (in sleep=s2idle, nvme.noacpi=1). It doesn't seem like charge level influences battery consumption apart from the "full battery" case.

Created 2022-10-11 14:00. Edited 2022-10-13 21:25.