[Date Prev][Date Next] [Thread Prev][Thread Next] [Date Index] [Thread Index]

Re: Debian CPU heating up <no apparent cpu activity>



could it be because with USB-SSD the kernel detects it as drive (smart
works and also does hdparm) and uses DMA whereas in USB-SD kernel
detects and attaches to usbstor but then has to do pio and cpu
intensive low efficency transfer methods rather than DMA ?
This means that kernel is doing a lot of job to write/read to usb and
will not show up in top ... but still since CPU is being used
constantly CPU gets heated up ....
just a hypothesis ... someone can comment on this

if that is the case how to force UDMA for usb memorystick kind of devices ?
tried googling ... no answer


On 2/6/15, Bhasker C V <bhasker@unixindia.com> wrote:
> could it be because with USB-SSD the kernel detects it as drive (smart
> works and also does hdparm) and uses DMA whereas in USB-SD kernel
> detects and attaches to usbstor but then has to do pio and cpu
> intensive low efficency transfer methods rather than DMA ?
> This means that kernel is doing a lot of job to write/read to usb and
> will not show up in top ... but still since CPU is being used
> constantly CPU gets heated up ....
> just a hypothesis ... someone can comment on this
>
>
>
>
> On 2/6/15, Bhasker C V <bhasker@unixindia.com> wrote:
>> Hi,
>>
>>  The same system running on the USB-SSD behaves nicely. Less than 60C
>> always even when watching videos on youtube.  However when I boot from
>> USB-SD adapter then CPU starts heating to 80C
>> There is no apparent message I can see in dmesg or syslog
>>
>>
>> On 2/5/15, Burhan Hanoglu <burhanoglu@gmail.com> wrote:
>>> Hi,
>>>
>>> Does it happen only when the OS is running on microSD? Have you tried to
>>> boot using a live iso either on a CD or on a usb stick? Have you looked
>>> thru /var/log/syslog and dmesg to see if there is anything relevant?
>>>
>>> Regards,
>>> Burhan
>>>
>>> On Fri, Feb 6, 2015 at 12:18 AM, Bhasker C V <bhasker@unixindia.com>
>>> wrote:
>>>
>>>> Hi,
>>>>
>>>>  I am trying to create 2 systems (both are portable and works on USB)
>>>>
>>>> 1. USB<->SATA bridge SSD with linux kernel 3.19.0 (self compiled).
>>>>    this systems works fine and the operating temperature on the DELL
>>>> machine I am using is about 54C to 60C
>>>>
>>>> 2. USB<->microSD with MicroSD card (sandisk 32GB).
>>>>    this system when it works starts heating up !!! temperatures sore
>>>> to 80C.(in a matter of 2-3 minutes)
>>>>
>>>> BASE CONDITIONS (common for both systems):
>>>> * Both the systems are jessie
>>>> * Both are running idential kernel and initrd (infact exact binary
>>>> copies on both)
>>>> * top shows very low CPU utilisation
>>>> * iotop shows occasional  R/W but not too much of write/read (less
>>>> than 0.1 kb/sec)
>>>> * both are currently text mode only
>>>> * system is DELL Q15R core-i7-2630QM (see cpuinfo in the end)
>>>>
>>>> on SSD: vmstat
>>>>
>>>>  0  0      0 7003648  44012 896832    0    0     0    12  157  583  1
>>>> 0 99  0  0
>>>>  0  0      0 7003532  44012 896840    0    0     0     0  136  429  0
>>>> 0 100  0  0
>>>>  0  0      0 7003760  44012 896840    0    0     0     0  205  510  0
>>>> 0 100  0  0
>>>>  0  0      0 7003904  44012 896840    0    0     0     0  152  513  0
>>>> 0 100  0  0
>>>> (using graphics and so sligtly low in mem but this is on the system
>>>> which does not heat up)
>>>>
>>>> on SDCARD: vmstat
>>>>
>>>>  0  0      0 7935012  20884 184812    0    0     0     0  110  313  0
>>>> 0 100  0  0
>>>>  0  0      0 7935012  20884 184812    0    0     0     0   97  286  0
>>>> 0 100  0  0
>>>>  0  0      0 7935012  20884 184812    0    0     0     0   99  275  0
>>>> 0 100  0  0
>>>>  0  0      0 7935012  20884 184812    0    0     0     0  103  280  0
>>>> 0 100  0  0
>>>>  0  0      0 7934864  20892 184804    0    0     0    20  176  470  0
>>>> 0 100  0  0
>>>>
>>>>
>>>> I even applied all CPU microcodes and got the message
>>>> perf_event_intel: PEBS enabled due to microcode update
>>>>
>>>>
>>>> Has someone encountered this before ? I am not sure what is causing
>>>> the fans to run fast and CPU to heatup when I use the OS on SD card ?
>>>> I agree SD is slow but that will be IO rather than CPU right ? will
>>>> that cause heatup ?
>>>>
>>>> iotop also shows READ/WRITE only occasionally SSD for
>>>> I am fully  exhausted not kwowing  what to do. Can anyone help please ?
>>>>
>>>>
>>>> -------------------- CPU INFO -----------------------
>>>> processor       : 7
>>>> vendor_id       : GenuineIntel
>>>> cpu family      : 6
>>>> model           : 42
>>>> model name      : Intel(R) Core(TM) i7-2630QM CPU @ 2.00GHz
>>>> stepping        : 7
>>>> microcode       : 0x29
>>>> cpu MHz         : 1900.000
>>>> cache size      : 6144 KB
>>>> physical id     : 0
>>>> siblings        : 8
>>>> core id         : 3
>>>> cpu cores       : 4
>>>> apicid          : 7
>>>> initial apicid  : 7
>>>> fdiv_bug        : no
>>>> f00f_bug        : no
>>>> coma_bug        : no
>>>> fpu             : yes
>>>> fpu_exception   : yes
>>>> cpuid level     : 13
>>>> wp              : yes
>>>> flags           : fpu vme de pse tsc msr pae mce cx8 apic sep mtrr pge
>>>> mca
>>>> cmov
>>>> pat pse36 clflush dts acpi mmx fxsr sse sse2 ss ht tm pbe nx rdtscp lm
>>>> constant_tsc arch_perfmon pebs bts xtopology nonstop_tsc aperfmperf
>>>> eagerfpu pni pclmulqdq dtes64 monitor ds_cpl vmx est tm2 ssse3 cx16
>>>> xtpr pdcm pcid sse4_1 sse4_2 x2apic popcnt tsc_deadline_timer aes
>>>> xsave avx lahf_lm ida arat epb pln pts dtherm tpr_shadow vnmi
>>>> flexpriority ept vpid xsaveopt
>>>> bugs            :
>>>> bogomips        : 3990.87
>>>> clflush size    : 64
>>>> cache_alignment : 64
>>>> address sizes   : 36 bits physical, 48 bits virtual
>>>> power management:
>>>>
>>>>
>>>> --
>>>> To UNSUBSCRIBE, email to debian-user-REQUEST@lists.debian.org
>>>> with a subject of "unsubscribe". Trouble? Contact
>>>> listmaster@lists.debian.org
>>>> Archive:
>>>> [🔎] CAPLCSGCA3+NXH3o07Zz9G+=CCVbYMWjnRnLzdWJf44H1xHc=Kg@mail.gmail.com">https://lists.debian.org/[🔎] CAPLCSGCA3+NXH3o07Zz9G+=CCVbYMWjnRnLzdWJf44H1xHc=Kg@mail.gmail.com
>>>>
>>>>
>>>
>>
>


Reply to: