|
Why the smp version of zephyr kernel "idle" task implent the "k_busy_wait(100)" delay?
Hi everyone: whey the SMP version of zephyr kernel idle task has involke the "k_busy_wait"? and it is especially unreasonable to pass the delay time with 100. why not 200, 300, 400..... and so on? i c
Hi everyone: whey the SMP version of zephyr kernel idle task has involke the "k_busy_wait"? and it is especially unreasonable to pass the delay time with 100. why not 200, 300, 400..... and so on? i c
|
By
"曹子龙
· #6142
·
|
|
About the Behavior of "z_clock_announce" in SMP?
Hi folks: a puzzle in the timer tick interrupt handler in SMP mode. look at below, the SMP mult cores share the same "cur_tick" object to remeber the current time, each cpu would increment it when the
Hi folks: a puzzle in the timer tick interrupt handler in SMP mode. look at below, the SMP mult cores share the same "cur_tick" object to remeber the current time, each cpu would increment it when the
|
By
"曹子龙
· #6166
·
|
|
About the Behavior of "z_clock_announce" in SMP, Is it dupulicate caculated?
Hi folks:
By
"曹子龙
· #6169
·
|
|
Is The tick handler "z_clock_announce" in SMP mode dupulicate caculated?
Hi friends: a puzzle in the timer tick interrupt handler in SMP mode. look at below, the SMP mult cores share the same "cur_tick" object to remeber the current time, each cpu would increment it when t
Hi friends: a puzzle in the timer tick interrupt handler in SMP mode. look at below, the SMP mult cores share the same "cur_tick" object to remeber the current time, each cpu would increment it when t
|
By
"曹子龙
· #6192
·
|
|
回复: [Zephyr-devel] Is The tick handler "z_clock_announce" in SMP mode dupulicate caculated?
could you show me where the logic you said locates? i still cant catches it, thank you
could you show me where the logic you said locates? i still cant catches it, thank you
|
By
"曹子龙
· #6194
·
|
|
回复:[Zephyr-devel] Is The tick handler "z_clock_announce" in SMP mode dupulicate caculated?
I still cant understand this flow after read the code. take cortex-m arch for exmaple, z_clock_isr, is hooked for NVIC vector table, so each cores would call this following the frequency. so, there mu
I still cant understand this flow after read the code. take cortex-m arch for exmaple, z_clock_isr, is hooked for NVIC vector table, so each cores would call this following the frequency. so, there mu
|
By
"曹子龙
· #6196
·
|
|
回复:[Zephyr-devel] Is The tick handler "z_clock_announce" in SMP mode dupulicate caculated?
Hi andrew: i find the place you said laste emai, it seems only xtensa and x84 arch supports the SMP mode, so take xtensa for exmaple. it seems the mechanism you said in the laste email only effect whe
Hi andrew: i find the place you said laste emai, it seems only xtensa and x84 arch supports the SMP mode, so take xtensa for exmaple. it seems the mechanism you said in the laste email only effect whe
|
By
"曹子龙
· #6200
·
|
|
why the reschrdule not permitted if lock key nested ?
HI guys: in kerne impl. many scenarios would call the z_reschedule to yield volunteer if the thread`s resource request did not meets. but the "resched" condition check confuse me, it seems only the ca
HI guys: in kerne impl. many scenarios would call the z_reschedule to yield volunteer if the thread`s resource request did not meets. but the "resched" condition check confuse me, it seems only the ca
|
By
"曹子龙
· #6254
·
|
|
how to get the verbose output the check the compile details using west?
Hi folks: i want to get the compiler process details output when using west build command, so, how to get this? 曹子龙 珠海全志科技股份有限公司 BU1-PSW 地址:广东省珠海市高新区唐家湾镇科技2路9号 TEL:13824125580 Email:caozilong@allwinne
Hi folks: i want to get the compiler process details output when using west build command, so, how to get this? 曹子龙 珠海全志科技股份有限公司 BU1-PSW 地址:广东省珠海市高新区唐家湾镇科技2路9号 TEL:13824125580 Email:caozilong@allwinne
|
By
"曹子龙
· #6352
·
|
|
Is the devicetree in zephyr sdk supports the dynamic running time flow control ?
Hi folks: I know the device three mechanism is also applied in zephyr sdk, but it seems something diffferent compare with in linux. in linux, the dtsi script file would be compiled to a binary blob wh
Hi folks: I know the device three mechanism is also applied in zephyr sdk, but it seems something diffferent compare with in linux. in linux, the dtsi script file would be compiled to a binary blob wh
|
By
"曹子龙
· #6490
·
|
|
about the difference of device tree use method compare with linux?
Hi folks: I know the device tree mechanism is also applied in zephyr sdk, but it seems something diffferent compare with in linux. in linux, the dtsi script file would be compiled to a binary blob whi
Hi folks: I know the device tree mechanism is also applied in zephyr sdk, but it seems something diffferent compare with in linux. in linux, the dtsi script file would be compiled to a binary blob whi
|
By
"曹子龙
· #6497
·
|
|
about the SMP implement ion, did the zephyr SMP support cpu affinity settings?
Hi folks: Did the SMP impl. of zephyr support the cpu affinity settings? i have not seen the related members in k_thread structure. Thanks for your kindly help.! 曹子龙 珠海全志科技股份有限公司 BU1-PSW 地址:广东省珠海市高新区唐
Hi folks: Did the SMP impl. of zephyr support the cpu affinity settings? i have not seen the related members in k_thread structure. Thanks for your kindly help.! 曹子龙 珠海全志科技股份有限公司 BU1-PSW 地址:广东省珠海市高新区唐
|
By
"曹子龙
· #6654
·
|
|
where is the "z_smp_reacquire_global_lock" called to restore the lock state to whatever the thread's counter?
Hi folks: throught the docment of zephyr smp imple. a task take the irq_lock can be yield to another thread, but would restore the spinlock own status when it comes back but, throught the code, i just
Hi folks: throught the docment of zephyr smp imple. a task take the irq_lock can be yield to another thread, but would restore the spinlock own status when it comes back but, throught the code, i just
|
By
"曹子龙
· #6655
·
|
|
Did the SMP support arm architecture boards presents? if yes, which one?
HI folks: Did the SMP support arm architecture boards presents? if yes, which one? Thank you! 曹子龙 珠海全志科技股份有限公司 BU1-PSW 地址:广东省珠海市高新区唐家湾镇科技2路9号 TEL:13824125580 Email:caozilong@... 网址: http
HI folks: Did the SMP support arm architecture boards presents? if yes, which one? Thank you! 曹子龙 珠海全志科技股份有限公司 BU1-PSW 地址:广东省珠海市高新区唐家湾镇科技2路9号 TEL:13824125580 Email:caozilong@... 网址: http
|
By
"曹子龙
· #6656
·
|
|
What is the difference "z_reschedule_irqlock" and "z_reschedule“? why two implementations?
Hi folks: why there are two implmentations of schedule? What is the difference "z_reschedule_irqlock" and "z_reschedule“? why two implementations? 曹子龙 珠海全志科技股份有限公司 BU1-PSW 地址:广东省珠海市高新区唐家湾镇科技2路9号 TEL:1
Hi folks: why there are two implmentations of schedule? What is the difference "z_reschedule_irqlock" and "z_reschedule“? why two implementations? 曹子龙 珠海全志科技股份有限公司 BU1-PSW 地址:广东省珠海市高新区唐家湾镇科技2路9号 TEL:1
|
By
"曹子龙
· #6660
·
|
|
Is this a bug? how to guarantee the "atomic semantics access of readyqueue" in "do_swap" function during context switch in SMP mode?
HI folks: if from the call pass of z_swap, which with parameter, do_swap(key.key, lock, 1); because is_spinlock is 1, so the lock would be released before invoke the actual switch function "arch_switc
HI folks: if from the call pass of z_swap, which with parameter, do_swap(key.key, lock, 1); because is_spinlock is 1, so the lock would be released before invoke the actual switch function "arch_switc
|
By
"曹子龙
· #6661
·
|
|
回复:[Zephyr-devel] Is this a bug? how to guarantee the "atomic semantics access of readyqueue" in "do_swap" function during context switch in SMP mode?
Hi andy: so, this is turely a issue that i have illustrated in last emai? is that true? so the mainline code still has this issue, right? thank you. 曹子龙 珠海全志科技股份有限公司 BU1-PSW 地址:广东省珠海市高新区唐家湾镇科技2路9号 TEL
Hi andy: so, this is turely a issue that i have illustrated in last emai? is that true? so the mainline code still has this issue, right? thank you. 曹子龙 珠海全志科技股份有限公司 BU1-PSW 地址:广东省珠海市高新区唐家湾镇科技2路9号 TEL
|
By
"曹子龙
· #6669
·
|
|
回复:回复:[Zephyr-devel] Is this a bug? how to guarantee the "atomic semantics access of readyqueue" in "do_swap" function during context switch in SMP mode?
HI folks: i still belive there are race conditions exist. in "do_swap" function, what would happen if others cpus pick up the "old" thread to run before it do the actual context backup? because if "is
HI folks: i still belive there are race conditions exist. in "do_swap" function, what would happen if others cpus pick up the "old" thread to run before it do the actual context backup? because if "is
|
By
"曹子龙
· #6674
·
|
|
回复:回复:[Zephyr-devel] Is this a bug? how to guarantee the "atomic semantics access of readyqueue" in "do_swap" function during context switch in SMP mode?
hi : would the "wait_for_switch(new_thread)" would aggravate the race condition not fix the race condition? the old thread save state still cant guarantee to be saved before it pick up by other cpus t
hi : would the "wait_for_switch(new_thread)" would aggravate the race condition not fix the race condition? the old thread save state still cant guarantee to be saved before it pick up by other cpus t
|
By
"曹子龙
· #6675
·
|
|
is there any gudeline on how to run SMP mode kernel on X86 architecture?
Now SMP only supported on xtensa, arc and x86 arch, but it seems more diffculte to run on xtensa and arc becasue of no boards. so anybody can tell me how to launch a smp run environment on x86 arch? t
Now SMP only supported on xtensa, arc and x86 arch, but it seems more diffculte to run on xtensa and arc becasue of no boards. so anybody can tell me how to launch a smp run environment on x86 arch? t
|
By
"曹子龙
· #6677
·
|