[lm-sensors] Sensors shows only 8 of 10 cores on 4-Socket Intel(R) Xeon(R) CPU E7- 4850 machine

[lm-sensors] Sensors shows only 8 of 10 cores on 4-Socket Intel(R) Xeon(R) CPU E7- 4850 machine

[Andreas Hollmann]

Hi,

2 cores are missing per socket in the sensors output.

Is there a hard coded number of max CPUs that limits
to output more then 8 CPUs?

CPUs are

4 x CPU0: Intel(R) Xeon(R) CPU E7- 4850  @ 2.00GHz
(10 cores with hyperthreading)

Mainboard:

Supermicro X8QB6-F

http://www.supermicro.com/products/motherboard/Xeon7000/7500/X8QB6.cfm?SAS=Y

sensors gives me following output

$: sensors
coretemp-isa-0000
Adapter: ISA adapter
Core 0:       +43.0 C  (high = +86.0 C, crit = +94.0 C)
Core 1:       +45.0 C  (high = +86.0 C, crit = +94.0 C)
Core 2:       +43.0 C  (high = +86.0 C, crit = +94.0 C)
Core 8:       +42.0 C  (high = +86.0 C, crit = +94.0 C)
Core 9:       +42.0 C  (high = +86.0 C, crit = +94.0 C)
Core 16:      +45.0 C  (high = +86.0 C, crit = +94.0 C)
Core 17:      +38.0 C  (high = +86.0 C, crit = +94.0 C)
Core 18:      +43.0 C  (high = +86.0 C, crit = +94.0 C)

coretemp-isa-0001
Adapter: ISA adapter
Core 0:       +36.0 C  (high = +86.0 C, crit = +94.0 C)
Core 1:       +47.0 C  (high = +86.0 C, crit = +94.0 C)
Core 2:       +33.0 C  (high = +86.0 C, crit = +94.0 C)
Core 8:       +36.0 C  (high = +86.0 C, crit = +94.0 C)
Core 9:       +39.0 C  (high = +86.0 C, crit = +94.0 C)
Core 16:      +40.0 C  (high = +86.0 C, crit = +94.0 C)
Core 17:      +39.0 C  (high = +86.0 C, crit = +94.0 C)
Core 18:      +37.0 C  (high = +86.0 C, crit = +94.0 C)

coretemp-isa-0002
Adapter: ISA adapter
Core 0:       +37.0 C  (high = +86.0 C, crit = +94.0 C)
Core 1:       +39.0 C  (high = +86.0 C, crit = +94.0 C)
Core 2:       +46.0 C  (high = +86.0 C, crit = +94.0 C)
Core 8:       +41.0 C  (high = +86.0 C, crit = +94.0 C)
Core 9:       +37.0 C  (high = +86.0 C, crit = +94.0 C)
Core 16:      +35.0 C  (high = +86.0 C, crit = +94.0 C)
Core 17:      +37.0 C  (high = +86.0 C, crit = +94.0 C)
Core 18:      +37.0 C  (high = +86.0 C, crit = +94.0 C)

coretemp-isa-0003
Adapter: ISA adapter
Core 0:       +40.0 C  (high = +86.0 C, crit = +94.0 C)
Core 1:       +42.0 C  (high = +86.0 C, crit = +94.0 C)
Core 2:       +44.0 C  (high = +86.0 C, crit = +94.0 C)
Core 8:       +41.0 C  (high = +86.0 C, crit = +94.0 C)
Core 9:       +41.0 C  (high = +86.0 C, crit = +94.0 C)
Core 16:      +40.0 C  (high = +86.0 C, crit = +94.0 C)
Core 17:      +41.0 C  (high = +86.0 C, crit = +94.0 C)
Core 18:      +43.0 C  (high = +86.0 C, crit = +94.0 C)

w83795adg-i2c-0-2f
Adapter: SMBus I801 adapter at 0400
in0:          +1.09 V  (min =  +0.54 V, max =  +1.49 V)
in1:          +1.01 V  (min =  +0.90 V, max =  +1.11 V)
in2:          +1.22 V  (min =  +1.08 V, max =  +1.33 V)
in3:          +1.82 V  (min =  +1.62 V, max =  +1.99 V)
in4:          +1.13 V  (min =  +0.98 V, max =  +1.21 V)
in5:          +1.11 V  (min =  +0.54 V, max =  +1.49 V)
in6:          +1.07 V  (min =  +0.54 V, max =  +1.49 V)
in7:          +1.10 V  (min =  +0.54 V, max =  +1.49 V)
in11:         +1.12 V  (min =  +0.92 V, max =  +1.35 V)
+3.3V:        +3.20 V  (min =  +2.96 V, max =  +3.63 V)
3VSB:         +3.19 V  (min =  +2.96 V, max =  +3.63 V)
Vbat:         +3.33 V  (min =  +2.70 V, max =  +3.63 V)
in15:         +1.87 V  (min =  +1.63 V, max =  +1.99 V)
in16:         +1.52 V  (min =  +1.35 V, max =  +1.65 V)
fan1:        4397 RPM  (min =  709 RPM)
fan2:           0 RPM  (min =  709 RPM)  ALARM
fan3:        4313 RPM  (min =  709 RPM)
fan4:           0 RPM  (min =  709 RPM)  ALARM
fan5:        4455 RPM  (min =  709 RPM)
fan6:           0 RPM  (min =  709 RPM)  ALARM
fan7:           0 RPM  (min =  709 RPM)  ALARM
fan8:        4671 RPM  (min =  709 RPM)
fan9:        4856 RPM  (min =  709 RPM)
fan10:       4856 RPM  (min =  709 RPM)
fan11:          0 RPM  (min =  329 RPM)  ALARM
fan12:       5793 RPM  (min =  709 RPM)
temp1:        +50.5 C  (high = +85.0 C, hyst = +80.0 C)
                       (crit = +75.0 C, hyst = +70.0 C)  sensor = thermal diode
temp2:        +44.2 C  (high = +85.0 C, hyst = +80.0 C)
                       (crit = +75.0 C, hyst = +70.0 C)  sensor = thermal diode
temp3:        +52.0 C  (high = +85.0 C, hyst = +80.0 C)
                       (crit = +75.0 C, hyst = +70.0 C)  sensor = thermal diode
temp4:        +43.8 C  (high = +85.0 C, hyst = +80.0 C)
                       (crit = +75.0 C, hyst = +70.0 C)  sensor = thermal diode
temp7:        +52.2 C  (high = +95.0 C, hyst = +92.0 C)
                       (crit = +95.0 C, hyst = +92.0 C)  sensor = Intel PECI
temp8:        +52.0 C  (high = +95.0 C, hyst = +92.0 C)
                       (crit = +95.0 C, hyst = +92.0 C)  sensor = Intel PECI
temp9:        +50.0 C  (high = +95.0 C, hyst = +92.0 C)
                       (crit = +95.0 C, hyst = +92.0 C)  sensor = Intel PECI
temp10:       +50.0 C  (high = +95.0 C, hyst = +92.0 C)
                       (crit = +95.0 C, hyst = +92.0 C)  sensor = Intel PECI
intrusion0:  OK

Best regards and thanks for the great tool,
Andreas

_______________________________________________
lm-sensors mailing list
lm-sensors@lm-sensors.org
http://lists.lm-sensors.org/mailman/listinfo/lm-sensors

Re: [lm-sensors] Sensors shows only 8 of 10 cores on 4-Socket Intel(R) Xeon(R) CPU E7- 4850 machine

[Jean Delvare]

Hi Andreas,

On Tue, 14 Jan 2014 14:01:19 +0100, Andreas Hollmann wrote:
> 2 cores are missing per socket in the sensors output.
> 
> Is there a hard coded number of max CPUs that limits
> to output more then 8 CPUs?

Which kernel version? Which version of "sensors" and libsensors
("sensors -v" will tell you)?

The non-linear numbering of the cores might be the cause.

-- 
Jean Delvare

_______________________________________________
lm-sensors mailing list
lm-sensors@lm-sensors.org
http://lists.lm-sensors.org/mailman/listinfo/lm-sensors

Re: [lm-sensors] Sensors shows only 8 of 10 cores on 4-Socket Intel(R) Xeon(R) CPU E7- 4850 machine

[Andreas Hollmann]

Hi Jean,

sorry for the missing information.

$ sensors -v
sensors version 3.3.4 with libsensors version 3.3.4
$ uname -a
Linux inwest 3.10.25-1-lts #1 SMP Sat Dec 21 13:31:14 CET 2013 x86_64 GNU/Linux

Best regards,
Andreas

2014/1/14 Jean Delvare <khali@linux-fr.org>:
> Hi Andreas,
>
> On Tue, 14 Jan 2014 14:01:19 +0100, Andreas Hollmann wrote:
>> 2 cores are missing per socket in the sensors output.
>>
>> Is there a hard coded number of max CPUs that limits
>> to output more then 8 CPUs?
>
> Which kernel version? Which version of "sensors" and libsensors
> ("sensors -v" will tell you)?
>
> The non-linear numbering of the cores might be the cause.
>
> --
> Jean Delvare

_______________________________________________
lm-sensors mailing list
lm-sensors@lm-sensors.org
http://lists.lm-sensors.org/mailman/listinfo/lm-sensors

Re: [lm-sensors] Sensors shows only 8 of 10 cores on 4-Socket Intel(R) Xeon(R) CPU E7- 4850 machine

[Jean Delvare]

Please also provide the output of:
$ strace sensors "coretemp-isa-0000"

-- 
Jean Delvare

_______________________________________________
lm-sensors mailing list
lm-sensors@lm-sensors.org
http://lists.lm-sensors.org/mailman/listinfo/lm-sensors

Re: [lm-sensors] Sensors shows only 8 of 10 cores on 4-Socket Intel(R) Xeon(R) CPU E7- 4850 machine

[Jean Delvare]

Hi Andreas,

On Tue, 14 Jan 2014 14:34:15 +0100, Andreas Hollmann wrote:
> 2014/1/14 Jean Delvare <khali@linux-fr.org>:
> > Please also provide the output of:
> > $ strace sensors "coretemp-isa-0000"
>
> (...)
> openat(AT_FDCWD, "/sys/class/hwmon/hwmon0/device", O_RDONLY|O_NONBLOCK|O_DIRECTORY|O_CLOEXEC) = 4
> brk(0x652000)                           = 0x652000
> getdents(4, /* 59 entries */, 32768)    = 1944
> stat("/sys/class/hwmon/hwmon0/device/temp2_input", {st_mode=S_IFREG|0444, st_size@96, ...}) = 0
> stat("/sys/class/hwmon/hwmon0/device/temp2_max", {st_mode=S_IFREG|0444, st_size@96, ...}) = 0
> stat("/sys/class/hwmon/hwmon0/device/temp2_crit", {st_mode=S_IFREG|0444, st_size@96, ...}) = 0
> stat("/sys/class/hwmon/hwmon0/device/temp2_crit_alarm", {st_mode=S_IFREG|0444, st_size@96, ...}) = 0

I'm reordering the entries to make it easier to read... This is Core 0.

> stat("/sys/class/hwmon/hwmon0/device/temp3_input", {st_mode=S_IFREG|0444, st_size@96, ...}) = 0
> stat("/sys/class/hwmon/hwmon0/device/temp3_max", {st_mode=S_IFREG|0444, st_size@96, ...}) = 0
> stat("/sys/class/hwmon/hwmon0/device/temp3_crit", {st_mode=S_IFREG|0444, st_size@96, ...}) = 0
> stat("/sys/class/hwmon/hwmon0/device/temp3_crit_alarm", {st_mode=S_IFREG|0444, st_size@96, ...}) = 0

This is Core 1.

> stat("/sys/class/hwmon/hwmon0/device/temp4_input", {st_mode=S_IFREG|0444, st_size@96, ...}) = 0
> stat("/sys/class/hwmon/hwmon0/device/temp4_max", {st_mode=S_IFREG|0444, st_size@96, ...}) = 0
> stat("/sys/class/hwmon/hwmon0/device/temp4_crit", {st_mode=S_IFREG|0444, st_size@96, ...}) = 0
> stat("/sys/class/hwmon/hwmon0/device/temp4_crit_alarm", {st_mode=S_IFREG|0444, st_size@96, ...}) = 0

This is Core 2.

> stat("/sys/class/hwmon/hwmon0/device/temp10_input", {st_mode=S_IFREG|0444, st_size@96, ...}) = 0
> stat("/sys/class/hwmon/hwmon0/device/temp10_max", {st_mode=S_IFREG|0444, st_size@96, ...}) = 0
> stat("/sys/class/hwmon/hwmon0/device/temp10_crit", {st_mode=S_IFREG|0444, st_size@96, ...}) = 0

This is Core 8, alarm flag is missing.

> stat("/sys/class/hwmon/hwmon0/device/temp11_input", {st_mode=S_IFREG|0444, st_size@96, ...}) = 0
> stat("/sys/class/hwmon/hwmon0/device/temp11_max", {st_mode=S_IFREG|0444, st_size@96, ...}) = 0
> stat("/sys/class/hwmon/hwmon0/device/temp11_crit", {st_mode=S_IFREG|0444, st_size@96, ...}) = 0

This is Core 9, alarm flag is missing.

> stat("/sys/class/hwmon/hwmon0/device/temp18_input", {st_mode=S_IFREG|0444, st_size@96, ...}) = 0
> stat("/sys/class/hwmon/hwmon0/device/temp18_max", {st_mode=S_IFREG|0444, st_size@96, ...}) = 0
> stat("/sys/class/hwmon/hwmon0/device/temp18_crit", {st_mode=S_IFREG|0444, st_size@96, ...}) = 0

This is Core 16, alarm flag is missing.

> stat("/sys/class/hwmon/hwmon0/device/temp19_input", {st_mode=S_IFREG|0444, st_size@96, ...}) = 0
> stat("/sys/class/hwmon/hwmon0/device/temp19_max", {st_mode=S_IFREG|0444, st_size@96, ...}) = 0
> stat("/sys/class/hwmon/hwmon0/device/temp19_crit", {st_mode=S_IFREG|0444, st_size@96, ...}) = 0

This is Core 17, alarm flag is missing.

> stat("/sys/class/hwmon/hwmon0/device/temp20_input", {st_mode=S_IFREG|0444, st_size@96, ...}) = 0
> stat("/sys/class/hwmon/hwmon0/device/temp20_max", {st_mode=S_IFREG|0444, st_size@96, ...}) = 0
> stat("/sys/class/hwmon/hwmon0/device/temp20_crit", {st_mode=S_IFREG|0444, st_size@96, ...}) = 0
> getdents(4, /* 0 entries */, 32768)     = 0
> close(4)                                = 0

This is Core 18, alarm flag is missing.

This matches the output of sensors, but raises two questions:
1* Why are the alarm flags missing for 5 inputs?
2* getdents says 59 entries, but the above are only 27. Even adding 2
for . and .. and 8 for the label files, we're only at 37. So there must
be more files to read than libsensors is actually reading - presumably
your two missing cores are there.

So please provide the output of:

$ ls -l /sys/devices/platform/coretemp.0

I suspect this constant in libsensors is causing the problem:

#define MAX_SENSORS_PER_TYPE	24

The library assumes linear numbering, so anything beyond temp23 would
be ignored, which I suspect is the problem here.

This however doesn't explain the missing alarm files. I'm curious if
the "ls" command above will show them.

I would also like to see the output of:

$ grep '^\(processor\|core id\)' /proc/cpuinfo

-- 
Jean Delvare
http://jdelvare.nerim.net/wishlist.html

_______________________________________________
lm-sensors mailing list
lm-sensors@lm-sensors.org
http://lists.lm-sensors.org/mailman/listinfo/lm-sensors

Re: [lm-sensors] Sensors shows only 8 of 10 cores on 4-Socket Intel(R) Xeon(R) CPU E7- 4850 machine

[Andreas Hollmann]

Thanks for your quick response.


Here is the requested output and if there is anything missing I willy reply as
quick as possible.

[hollmann@inwest ~]$ ls -l /sys/devices/platform/coretemp.0
total 0
lrwxrwxrwx 1 root root    0 Jan 14 15:05 driver ->
../../../bus/platform/drivers/coretemp
drwxr-xr-x 3 root root    0 Jan 10 18:51 hwmon
-r--r--r-- 1 root root 4096 Jan 14 14:43 modalias
-r--r--r-- 1 root root 4096 Jan 10 18:51 name
drwxr-xr-x 2 root root    0 Jan 14 11:54 power
lrwxrwxrwx 1 root root    0 Jan 10 18:51 subsystem -> ../../../bus/platform
-r--r--r-- 1 root root 4096 Jan 10 18:51 temp10_crit
-r--r--r-- 1 root root 4096 Jan 14 14:43 temp10_crit_alar
-r--r--r-- 1 root root 4096 Jan 10 18:51 temp10_input
-r--r--r-- 1 root root 4096 Jan 13 15:42 temp10_label
-r--r--r-- 1 root root 4096 Jan 10 18:51 temp10_max
-r--r--r-- 1 root root 4096 Jan 10 18:51 temp11_crit
-r--r--r-- 1 root root 4096 Jan 14 14:43 temp11_crit_alar
-r--r--r-- 1 root root 4096 Jan 10 18:51 temp11_input
-r--r--r-- 1 root root 4096 Jan 13 15:42 temp11_label
-r--r--r-- 1 root root 4096 Jan 10 18:51 temp11_max
-r--r--r-- 1 root root 4096 Jan 10 18:51 temp18_crit
-r--r--r-- 1 root root 4096 Jan 14 14:43 temp18_crit_alar
-r--r--r-- 1 root root 4096 Jan 10 18:51 temp18_input
-r--r--r-- 1 root root 4096 Jan 13 15:42 temp18_label
-r--r--r-- 1 root root 4096 Jan 10 18:51 temp18_max
-r--r--r-- 1 root root 4096 Jan 10 18:51 temp19_crit
-r--r--r-- 1 root root 4096 Jan 14 14:43 temp19_crit_alar
-r--r--r-- 1 root root 4096 Jan 10 18:51 temp19_input
-r--r--r-- 1 root root 4096 Jan 13 15:42 temp19_label
-r--r--r-- 1 root root 4096 Jan 10 18:51 temp19_max
-r--r--r-- 1 root root 4096 Jan 10 18:51 temp20_crit
-r--r--r-- 1 root root 4096 Jan 14 14:43 temp20_crit_alar
-r--r--r-- 1 root root 4096 Jan 10 18:51 temp20_input
-r--r--r-- 1 root root 4096 Jan 13 15:42 temp20_label
-r--r--r-- 1 root root 4096 Jan 10 18:51 temp20_max
-r--r--r-- 1 root root 4096 Jan 14 14:43 temp26_crit
-r--r--r-- 1 root root 4096 Jan 14 14:43 temp26_crit_alar
-r--r--r-- 1 root root 4096 Jan 14 14:43 temp26_input
-r--r--r-- 1 root root 4096 Jan 14 14:43 temp26_label
-r--r--r-- 1 root root 4096 Jan 14 14:43 temp26_max
-r--r--r-- 1 root root 4096 Jan 14 14:43 temp27_crit
-r--r--r-- 1 root root 4096 Jan 14 14:43 temp27_crit_alar
-r--r--r-- 1 root root 4096 Jan 14 14:43 temp27_input
-r--r--r-- 1 root root 4096 Jan 14 14:43 temp27_label
-r--r--r-- 1 root root 4096 Jan 14 14:43 temp27_max
-r--r--r-- 1 root root 4096 Jan 10 18:51 temp2_crit
-r--r--r-- 1 root root 4096 Jan 10 18:51 temp2_crit_alarm
-r--r--r-- 1 root root 4096 Jan 10 18:51 temp2_input
-r--r--r-- 1 root root 4096 Jan 13 15:42 temp2_label
-r--r--r-- 1 root root 4096 Jan 10 18:51 temp2_max
-r--r--r-- 1 root root 4096 Jan 10 18:51 temp3_crit
-r--r--r-- 1 root root 4096 Jan 10 18:51 temp3_crit_alarm
-r--r--r-- 1 root root 4096 Jan 10 18:51 temp3_input
-r--r--r-- 1 root root 4096 Jan 13 15:42 temp3_label
-r--r--r-- 1 root root 4096 Jan 10 18:51 temp3_max
-r--r--r-- 1 root root 4096 Jan 10 18:51 temp4_crit
-r--r--r-- 1 root root 4096 Jan 10 18:51 temp4_crit_alarm
-r--r--r-- 1 root root 4096 Jan 10 18:51 temp4_input
-r--r--r-- 1 root root 4096 Jan 13 15:42 temp4_label
-r--r--r-- 1 root root 4096 Jan 10 18:51 temp4_max
-rw-r--r-- 1 root root 4096 Jan 10 18:51 uevent

[hollmann@inwest ~]$ grep '^\(processor\|core id\)' /proc/cpuinfo
processor       : 0
core id         : 0
processor       : 1
core id         : 1
processor       : 2
core id         : 2
processor       : 3
core id         : 8
processor       : 4
core id         : 9
processor       : 5
core id         : 16
processor       : 6
core id         : 17
processor       : 7
core id         : 18
processor       : 8
core id         : 24
processor       : 9
core id         : 25
processor       : 10
core id         : 0
processor       : 11
core id         : 1
processor       : 12
core id         : 2
processor       : 13
core id         : 8
processor       : 14
core id         : 9
processor       : 15
core id         : 16
processor       : 16
core id         : 17
processor       : 17
core id         : 18
processor       : 18
core id         : 24
processor       : 19
core id         : 25
processor       : 20
core id         : 0
processor       : 21
core id         : 1
processor       : 22
core id         : 2
processor       : 23
core id         : 8
processor       : 24
core id         : 9
processor       : 25
core id         : 16
processor       : 26
core id         : 17
processor       : 27
core id         : 18
processor       : 28
core id         : 24
processor       : 29
core id         : 25
processor       : 30
core id         : 0
processor       : 31
core id         : 1
processor       : 32
core id         : 2
processor       : 33
core id         : 8
processor       : 34
core id         : 9
processor       : 35
core id         : 16
processor       : 36
core id         : 17
processor       : 37
core id         : 18
processor       : 38
core id         : 24
processor       : 39
core id         : 25
processor       : 40
core id         : 0
processor       : 41
core id         : 1
processor       : 42
core id         : 2
processor       : 43
core id         : 8
processor       : 44
core id         : 9
processor       : 45
core id         : 16
processor       : 46
core id         : 17
processor       : 47
core id         : 18
processor       : 48
core id         : 24
processor       : 49
core id         : 25
processor       : 50
core id         : 0
processor       : 51
core id         : 1
processor       : 52
core id         : 2
processor       : 53
core id         : 8
processor       : 54
core id         : 9
processor       : 55
core id         : 16
processor       : 56
core id         : 17
processor       : 57
core id         : 18
processor       : 58
core id         : 24
processor       : 59
core id         : 25
processor       : 60
core id         : 0
processor       : 61
core id         : 1
processor       : 62
core id         : 2
processor       : 63
core id         : 8
processor       : 64
core id         : 9
processor       : 65
core id         : 16
processor       : 66
core id         : 17
processor       : 67
core id         : 18
processor       : 68
core id         : 24
processor       : 69
core id         : 25
processor       : 70
core id         : 0
processor       : 71
core id         : 1
processor       : 72
core id         : 2
processor       : 73
core id         : 8
processor       : 74
core id         : 9
processor       : 75
core id         : 16
processor       : 76
core id         : 17
processor       : 77
core id         : 18
processor       : 78
core id         : 24
processor       : 79
core id         : 25
[hollmann@inwest ~]$

2014/1/14 Jean Delvare <khali@linux-fr.org>:
> Hi Andreas,
>
> On Tue, 14 Jan 2014 14:34:15 +0100, Andreas Hollmann wrote:
>> 2014/1/14 Jean Delvare <khali@linux-fr.org>:
>> > Please also provide the output of:
>> > $ strace sensors "coretemp-isa-0000"
>>
>> (...)
>> openat(AT_FDCWD, "/sys/class/hwmon/hwmon0/device", O_RDONLY|O_NONBLOCK|O_DIRECTORY|O_CLOEXEC) = 4
>> brk(0x652000)                           = 0x652000
>> getdents(4, /* 59 entries */, 32768)    = 1944
>> stat("/sys/class/hwmon/hwmon0/device/temp2_input", {st_mode=S_IFREG|0444, st_size@96, ...}) = 0
>> stat("/sys/class/hwmon/hwmon0/device/temp2_max", {st_mode=S_IFREG|0444, st_size@96, ...}) = 0
>> stat("/sys/class/hwmon/hwmon0/device/temp2_crit", {st_mode=S_IFREG|0444, st_size@96, ...}) = 0
>> stat("/sys/class/hwmon/hwmon0/device/temp2_crit_alarm", {st_mode=S_IFREG|0444, st_size@96, ...}) = 0
>
> I'm reordering the entries to make it easier to read... This is Core 0.
>
>> stat("/sys/class/hwmon/hwmon0/device/temp3_input", {st_mode=S_IFREG|0444, st_size@96, ...}) = 0
>> stat("/sys/class/hwmon/hwmon0/device/temp3_max", {st_mode=S_IFREG|0444, st_size@96, ...}) = 0
>> stat("/sys/class/hwmon/hwmon0/device/temp3_crit", {st_mode=S_IFREG|0444, st_size@96, ...}) = 0
>> stat("/sys/class/hwmon/hwmon0/device/temp3_crit_alarm", {st_mode=S_IFREG|0444, st_size@96, ...}) = 0
>
> This is Core 1.
>
>> stat("/sys/class/hwmon/hwmon0/device/temp4_input", {st_mode=S_IFREG|0444, st_size@96, ...}) = 0
>> stat("/sys/class/hwmon/hwmon0/device/temp4_max", {st_mode=S_IFREG|0444, st_size@96, ...}) = 0
>> stat("/sys/class/hwmon/hwmon0/device/temp4_crit", {st_mode=S_IFREG|0444, st_size@96, ...}) = 0
>> stat("/sys/class/hwmon/hwmon0/device/temp4_crit_alarm", {st_mode=S_IFREG|0444, st_size@96, ...}) = 0
>
> This is Core 2.
>
>> stat("/sys/class/hwmon/hwmon0/device/temp10_input", {st_mode=S_IFREG|0444, st_size@96, ...}) = 0
>> stat("/sys/class/hwmon/hwmon0/device/temp10_max", {st_mode=S_IFREG|0444, st_size@96, ...}) = 0
>> stat("/sys/class/hwmon/hwmon0/device/temp10_crit", {st_mode=S_IFREG|0444, st_size@96, ...}) = 0
>
> This is Core 8, alarm flag is missing.
>
>> stat("/sys/class/hwmon/hwmon0/device/temp11_input", {st_mode=S_IFREG|0444, st_size@96, ...}) = 0
>> stat("/sys/class/hwmon/hwmon0/device/temp11_max", {st_mode=S_IFREG|0444, st_size@96, ...}) = 0
>> stat("/sys/class/hwmon/hwmon0/device/temp11_crit", {st_mode=S_IFREG|0444, st_size@96, ...}) = 0
>
> This is Core 9, alarm flag is missing.
>
>> stat("/sys/class/hwmon/hwmon0/device/temp18_input", {st_mode=S_IFREG|0444, st_size@96, ...}) = 0
>> stat("/sys/class/hwmon/hwmon0/device/temp18_max", {st_mode=S_IFREG|0444, st_size@96, ...}) = 0
>> stat("/sys/class/hwmon/hwmon0/device/temp18_crit", {st_mode=S_IFREG|0444, st_size@96, ...}) = 0
>
> This is Core 16, alarm flag is missing.
>
>> stat("/sys/class/hwmon/hwmon0/device/temp19_input", {st_mode=S_IFREG|0444, st_size@96, ...}) = 0
>> stat("/sys/class/hwmon/hwmon0/device/temp19_max", {st_mode=S_IFREG|0444, st_size@96, ...}) = 0
>> stat("/sys/class/hwmon/hwmon0/device/temp19_crit", {st_mode=S_IFREG|0444, st_size@96, ...}) = 0
>
> This is Core 17, alarm flag is missing.
>
>> stat("/sys/class/hwmon/hwmon0/device/temp20_input", {st_mode=S_IFREG|0444, st_size@96, ...}) = 0
>> stat("/sys/class/hwmon/hwmon0/device/temp20_max", {st_mode=S_IFREG|0444, st_size@96, ...}) = 0
>> stat("/sys/class/hwmon/hwmon0/device/temp20_crit", {st_mode=S_IFREG|0444, st_size@96, ...}) = 0
>> getdents(4, /* 0 entries */, 32768)     = 0
>> close(4)                                = 0
>
> This is Core 18, alarm flag is missing.
>
> This matches the output of sensors, but raises two questions:
> 1* Why are the alarm flags missing for 5 inputs?
> 2* getdents says 59 entries, but the above are only 27. Even adding 2
> for . and .. and 8 for the label files, we're only at 37. So there must
> be more files to read than libsensors is actually reading - presumably
> your two missing cores are there.
>
> So please provide the output of:
>
> $ ls -l /sys/devices/platform/coretemp.0
>
> I suspect this constant in libsensors is causing the problem:
>
> #define MAX_SENSORS_PER_TYPE    24
>
> The library assumes linear numbering, so anything beyond temp23 would
> be ignored, which I suspect is the problem here.
>
> This however doesn't explain the missing alarm files. I'm curious if
> the "ls" command above will show them.
>
> I would also like to see the output of:
>
> $ grep '^\(processor\|core id\)' /proc/cpuinfo
>
> --
> Jean Delvare
> http://jdelvare.nerim.net/wishlist.html

_______________________________________________
lm-sensors mailing list
lm-sensors@lm-sensors.org
http://lists.lm-sensors.org/mailman/listinfo/lm-sensors

Re: [lm-sensors] Sensors shows only 8 of 10 cores on 4-Socket Intel(R) Xeon(R) CPU E7- 4850 machine

[Guenter Roeck]

On 01/14/2014 06:09 AM, Andreas Hollmann wrote:
> Thanks for your quick response.
>
>
> Here is the requested output and if there is anything missing I willy reply as
> quick as possible.
>

> -r--r--r-- 1 root root 4096 Jan 14 14:43 temp11_crit_alar
> -r--r--r-- 1 root root 4096 Jan 14 14:43 temp18_crit_alar
> -r--r--r-- 1 root root 4096 Jan 14 14:43 temp19_crit_alar

Name too long. Jean, any idea how we can fix this ?

Guenter


_______________________________________________
lm-sensors mailing list
lm-sensors@lm-sensors.org
http://lists.lm-sensors.org/mailman/listinfo/lm-sensors

Re: [lm-sensors] Sensors shows only 8 of 10 cores on 4-Socket Intel(R) Xeon(R) CPU E7- 4850 machine

[Jean Delvare]

Hi Andreas,

On Tue, 14 Jan 2014 15:09:36 +0100, Andreas Hollmann wrote:
> Thanks for your quick response.
> 
> 
> Here is the requested output and if there is anything missing I willy reply as
> quick as possible.
> 
> [hollmann@inwest ~]$ ls -l /sys/devices/platform/coretemp.0
> total 0
> lrwxrwxrwx 1 root root    0 Jan 14 15:05 driver -> ../../../bus/platform/drivers/coretemp
> drwxr-xr-x 3 root root    0 Jan 10 18:51 hwmon
> -r--r--r-- 1 root root 4096 Jan 14 14:43 modalias
> -r--r--r-- 1 root root 4096 Jan 10 18:51 name
> drwxr-xr-x 2 root root    0 Jan 14 11:54 power
> lrwxrwxrwx 1 root root    0 Jan 10 18:51 subsystem -> ../../../bus/platform
> -r--r--r-- 1 root root 4096 Jan 10 18:51 temp10_crit
> -r--r--r-- 1 root root 4096 Jan 14 14:43 temp10_crit_alar

We have a first bug here, apparently some buffer isn't large enough so
the dynamic attribute name doesn't fit. The (trivial) fix is in the
coretemp kernel driver, I'll send a patch in a minute.

> -r--r--r-- 1 root root 4096 Jan 10 18:51 temp10_input
> -r--r--r-- 1 root root 4096 Jan 13 15:42 temp10_label
> -r--r--r-- 1 root root 4096 Jan 10 18:51 temp10_max
> -r--r--r-- 1 root root 4096 Jan 10 18:51 temp11_crit
> -r--r--r-- 1 root root 4096 Jan 14 14:43 temp11_crit_alar
> -r--r--r-- 1 root root 4096 Jan 10 18:51 temp11_input
> -r--r--r-- 1 root root 4096 Jan 13 15:42 temp11_label
> -r--r--r-- 1 root root 4096 Jan 10 18:51 temp11_max
> -r--r--r-- 1 root root 4096 Jan 10 18:51 temp18_crit
> -r--r--r-- 1 root root 4096 Jan 14 14:43 temp18_crit_alar
> -r--r--r-- 1 root root 4096 Jan 10 18:51 temp18_input
> -r--r--r-- 1 root root 4096 Jan 13 15:42 temp18_label
> -r--r--r-- 1 root root 4096 Jan 10 18:51 temp18_max
> -r--r--r-- 1 root root 4096 Jan 10 18:51 temp19_crit
> -r--r--r-- 1 root root 4096 Jan 14 14:43 temp19_crit_alar
> -r--r--r-- 1 root root 4096 Jan 10 18:51 temp19_input
> -r--r--r-- 1 root root 4096 Jan 13 15:42 temp19_label
> -r--r--r-- 1 root root 4096 Jan 10 18:51 temp19_max
> -r--r--r-- 1 root root 4096 Jan 10 18:51 temp20_crit
> -r--r--r-- 1 root root 4096 Jan 14 14:43 temp20_crit_alar
> -r--r--r-- 1 root root 4096 Jan 10 18:51 temp20_input
> -r--r--r-- 1 root root 4096 Jan 13 15:42 temp20_label
> -r--r--r-- 1 root root 4096 Jan 10 18:51 temp20_max
> -r--r--r-- 1 root root 4096 Jan 14 14:43 temp26_crit
> -r--r--r-- 1 root root 4096 Jan 14 14:43 temp26_crit_alar
> -r--r--r-- 1 root root 4096 Jan 14 14:43 temp26_input
> -r--r--r-- 1 root root 4096 Jan 14 14:43 temp26_label
> -r--r--r-- 1 root root 4096 Jan 14 14:43 temp26_max
> -r--r--r-- 1 root root 4096 Jan 14 14:43 temp27_crit
> -r--r--r-- 1 root root 4096 Jan 14 14:43 temp27_crit_alar
> -r--r--r-- 1 root root 4096 Jan 14 14:43 temp27_input
> -r--r--r-- 1 root root 4096 Jan 14 14:43 temp27_label
> -r--r--r-- 1 root root 4096 Jan 14 14:43 temp27_max

Here's the second issue, these indexes are too high for libsensors,
which stops at temp23. We can raise the limit to cover this case (and
I'll probably do that as an immediate fix) but in the long run it would
be great to have it computed dynamically at run-time so that the
problem doesn't ever happen again.

Fixes are coming, stay tuned.

-- 
Jean Delvare
http://jdelvare.nerim.net/wishlist.html

_______________________________________________
lm-sensors mailing list
lm-sensors@lm-sensors.org
http://lists.lm-sensors.org/mailman/listinfo/lm-sensors

Re: [lm-sensors] Sensors shows only 8 of 10 cores on 4-Socket Intel(R) Xeon(R) CPU E7- 4850 machine

[Andreas Hollmann]

Hi Jean,

thanks for the great support and fast responses. I'm really amazed.

Best regards,
Andreas

2014/1/14 Jean Delvare <khali@linux-fr.org>:
> Hi Andreas,
>
> On Tue, 14 Jan 2014 15:09:36 +0100, Andreas Hollmann wrote:
>> Thanks for your quick response.
>>
>>
>> Here is the requested output and if there is anything missing I willy reply as
>> quick as possible.
>>
>> [hollmann@inwest ~]$ ls -l /sys/devices/platform/coretemp.0
>> total 0
>> lrwxrwxrwx 1 root root    0 Jan 14 15:05 driver -> ../../../bus/platform/drivers/coretemp
>> drwxr-xr-x 3 root root    0 Jan 10 18:51 hwmon
>> -r--r--r-- 1 root root 4096 Jan 14 14:43 modalias
>> -r--r--r-- 1 root root 4096 Jan 10 18:51 name
>> drwxr-xr-x 2 root root    0 Jan 14 11:54 power
>> lrwxrwxrwx 1 root root    0 Jan 10 18:51 subsystem -> ../../../bus/platform
>> -r--r--r-- 1 root root 4096 Jan 10 18:51 temp10_crit
>> -r--r--r-- 1 root root 4096 Jan 14 14:43 temp10_crit_alar
>
> We have a first bug here, apparently some buffer isn't large enough so
> the dynamic attribute name doesn't fit. The (trivial) fix is in the
> coretemp kernel driver, I'll send a patch in a minute.
>
>> -r--r--r-- 1 root root 4096 Jan 10 18:51 temp10_input
>> -r--r--r-- 1 root root 4096 Jan 13 15:42 temp10_label
>> -r--r--r-- 1 root root 4096 Jan 10 18:51 temp10_max
>> -r--r--r-- 1 root root 4096 Jan 10 18:51 temp11_crit
>> -r--r--r-- 1 root root 4096 Jan 14 14:43 temp11_crit_alar
>> -r--r--r-- 1 root root 4096 Jan 10 18:51 temp11_input
>> -r--r--r-- 1 root root 4096 Jan 13 15:42 temp11_label
>> -r--r--r-- 1 root root 4096 Jan 10 18:51 temp11_max
>> -r--r--r-- 1 root root 4096 Jan 10 18:51 temp18_crit
>> -r--r--r-- 1 root root 4096 Jan 14 14:43 temp18_crit_alar
>> -r--r--r-- 1 root root 4096 Jan 10 18:51 temp18_input
>> -r--r--r-- 1 root root 4096 Jan 13 15:42 temp18_label
>> -r--r--r-- 1 root root 4096 Jan 10 18:51 temp18_max
>> -r--r--r-- 1 root root 4096 Jan 10 18:51 temp19_crit
>> -r--r--r-- 1 root root 4096 Jan 14 14:43 temp19_crit_alar
>> -r--r--r-- 1 root root 4096 Jan 10 18:51 temp19_input
>> -r--r--r-- 1 root root 4096 Jan 13 15:42 temp19_label
>> -r--r--r-- 1 root root 4096 Jan 10 18:51 temp19_max
>> -r--r--r-- 1 root root 4096 Jan 10 18:51 temp20_crit
>> -r--r--r-- 1 root root 4096 Jan 14 14:43 temp20_crit_alar
>> -r--r--r-- 1 root root 4096 Jan 10 18:51 temp20_input
>> -r--r--r-- 1 root root 4096 Jan 13 15:42 temp20_label
>> -r--r--r-- 1 root root 4096 Jan 10 18:51 temp20_max
>> -r--r--r-- 1 root root 4096 Jan 14 14:43 temp26_crit
>> -r--r--r-- 1 root root 4096 Jan 14 14:43 temp26_crit_alar
>> -r--r--r-- 1 root root 4096 Jan 14 14:43 temp26_input
>> -r--r--r-- 1 root root 4096 Jan 14 14:43 temp26_label
>> -r--r--r-- 1 root root 4096 Jan 14 14:43 temp26_max
>> -r--r--r-- 1 root root 4096 Jan 14 14:43 temp27_crit
>> -r--r--r-- 1 root root 4096 Jan 14 14:43 temp27_crit_alar
>> -r--r--r-- 1 root root 4096 Jan 14 14:43 temp27_input
>> -r--r--r-- 1 root root 4096 Jan 14 14:43 temp27_label
>> -r--r--r-- 1 root root 4096 Jan 14 14:43 temp27_max
>
> Here's the second issue, these indexes are too high for libsensors,
> which stops at temp23. We can raise the limit to cover this case (and
> I'll probably do that as an immediate fix) but in the long run it would
> be great to have it computed dynamically at run-time so that the
> problem doesn't ever happen again.
>
> Fixes are coming, stay tuned.
>
> --
> Jean Delvare
> http://jdelvare.nerim.net/wishlist.html

_______________________________________________
lm-sensors mailing list
lm-sensors@lm-sensors.org
http://lists.lm-sensors.org/mailman/listinfo/lm-sensors

Re: [lm-sensors] Sensors shows only 8 of 10 cores on 4-Socket Intel(R) Xeon(R) CPU E7- 4850 machine

[Jean Delvare]

On Tue, 14 Jan 2014 16:07:24 +0100, Andreas Hollmann wrote:
> Hi Jean,
> 
> thanks for the great support and fast responses. I'm really amazed.

You're welcome :-)

> 2014/1/14 Jean Delvare <khali@linux-fr.org>:
> > Fixes are coming, stay tuned.

Libsensors fix is here:
  http://www.lm-sensors.org/changeset/6208

An updated standalone coretemp driver is available for download from:
  http://jdelvare.nerim.net/devel/lm-sensors/drivers/coretemp/
Generic instructions at:
  http://jdelvare.nerim.net/devel/lm-sensors/drivers/INSTALL

-- 
Jean Delvare
http://jdelvare.nerim.net/wishlist.html

_______________________________________________
lm-sensors mailing list
lm-sensors@lm-sensors.org
http://lists.lm-sensors.org/mailman/listinfo/lm-sensors