And this is log from /sys/kernel/debug/tracing/trace

# entries-in-buffer/entries-written: 32410/32410   #P:64
#
#                              _-----=> irqs-off
#                             / _----=> need-resched
#                            | / _---=> hardirq/softirq
#                            || / _--=> preempt-depth
#                            ||| /     delay
#           TASK-PID   CPU#  ||||    TIMESTAMP  FUNCTION
#              | |       |   ||||       |         |
           <...>-57259 [005] .... 29619.680698: workqueue_execute_start: work 
struct 00000000ef22e4b8: function gc_worker [nf_conntrack]
           <...>-57259 [005] .... 29623.811407: workqueue_execute_end: work 
struct 00000000ef22e4b8: function gc_worker [nf_conntrack]
           <...>-57259 [005] .... 29623.811410: workqueue_execute_start: work 
struct 0000000000aeec55: function fb_flashcursor
           <...>-57259 [005] .... 29623.811421: workqueue_execute_end: work 
struct 0000000000aeec55: function fb_flashcursor
           <...>-57259 [005] .... 29623.811422: workqueue_execute_start: work 
struct 00000000a6d382bb: function vmstat_update
           <...>-57259 [005] .... 29623.811435: workqueue_execute_end: work 
struct 00000000a6d382bb: function vmstat_update

> On 7 Jul 2020, at 22:44, Martin Zaharinov <micro...@gmail.com> wrote:
> 
> the problem is hear with kernel 5.7.7 
> 
> last work kernel without this problem is 5.6.7
> 
> hear is more info:
> 
> cat /proc/57259/stack
> root@megacableamarilis:~# cat /proc/57259/stack
> [<0>] gc_worker+0x1be/0x380 [nf_conntrack]
> [<0>] process_one_work+0x1bc/0x3b0
> [<0>] worker_thread+0x4d/0x460
> [<0>] kthread+0x10d/0x130
> [<0>] ret_from_fork+0x1f/0x30
> 
> PID USER      PR  NI    VIRT    RES    SHR S  %CPU  %MEM     TIME+ COMMAND    
>                         57259 root      28   0       0      0      0 R  69.8  
>  0.0  82:42.14 kworker/5:2+events_power_efficient                             
>                              
> 32 root      21   0       0      0      0 R  31.0   0.0  87:06.33 ksoftirqd/4
> 
> 
> Please help to fix this problem
> 
>> On 22 Apr 2020, at 15:55, Martin Zaharinov <micro...@gmail.com> wrote:
>> 
>> Hello Qian and Greg 
>> With latest 5.6.x kernel have problem with events_power_efficient 28488 root 
>>      28   0       0      0      0 R  95.5   0.0 101:38.19 
>> kworker/2:1+events_power_efficient Process start to load machine after 3-4 
>> hour and load not stop only reboot machine remove process . Server runing on 
>> AMD EPIC CPU 2x 7301 32Gb Ram Have 2 x 10G card Intel when machine load over 
>> 1G traffic machine locked and only restart fix problem to next load . After 
>> move traffic and server stop load process still hear and load server ?
>> And after reboot process move to other core .
>> 
>> Best Regards,
>> Martin
> 

Reply via email to