* xenomai.supported_cpus not working as intended?
@ 2020-07-13 13:37 Lange Norbert
2020-07-13 17:52 ` Jan Kiszka
0 siblings, 1 reply; 3+ messages in thread
From: Lange Norbert @ 2020-07-13 13:37 UTC (permalink / raw)
To: Xenomai (xenomai@xenomai.org)
Hello,
I am using Xenomai 3.1 and I tried once more to tie Linux to Core0, and RT to the remaining Cores.
It seems that both Linux and Xenomai favor Core0, as rtnet-stack rtnet-rtpc seem to always run on that.
Network drivers will process the IRQs on all cores, but realistally all are handles at Core0.
I tries the commandline xenomai.supported_cpus=0xFFFE, but this doesn’t seem to work right.
I get stuck Xenomai processes, and entries in dmesg (both with and without the isolcpus parameter).
Kernel cmdline is like this: irqaffinity=0 xenomai.smi=disabled isolcpus=1-3 xenomai.supported_cpus=0xFFFE
Running a Xenomai Process looks like this:
# /usr/xenomai/bin/clocktest
[ 191.759690] [Xenomai] thread clocktest[575] switched to non-rt CPU0, aborted.
== Testing built-in CLOCK_REALTIME (0)
CPU ToD offset [us] ToD drift [us/s] warps max delta [us]
--- -------------------- ---------------- ---------- --------------
0 0.0 0.000 0 0.0
1 -1450249.3 -36.240 0 0.0
2 -1450249.8 -36.040 0 0.0
3 -1450249.4 -35.292 0 0.0
And similar stuff happens when booting, Kernel dmesg is following.
So I don’t see how xenomai.supported_cpus can be safely used,
It more or less works by chance for me (processes not getting stuck)
Kind regards,
Norbert
[ 2.284754] clocksource: tsc: mask: 0xffffffffffffffff max_cycles: 0x16f8873b2b5, max_idle_ns: 440795270785 ns
[ 2.294855] clocksource: Switched to clocksource tsc
[ 2.307865] [Xenomai] scheduling class idle registered.
[ 2.313104] [Xenomai] scheduling class tp registered.
[ 2.318242] [Xenomai] scheduling class rt registered.
[ 2.323445] I-pipe: head domain Xenomai registered.
[ 2.330836] ------------[ cut here ]------------
[ 2.335675] WARNING: CPU: 0 PID: 1 at kernel/xenomai/timer.c:509 __xntimer_migrate.cold+0xc/0x14
[ 2.344470] Modules linked in:
[ 2.345470] CPU: 0 PID: 1 Comm: swapper/0 Not tainted 4.19.124-cip27-xeno13-static #2
[ 2.345470] Hardware name: TQ-Group TQMxE39M/Type2 - Board Product Name, BIOS 5.12.30.21.18 04/12/2019
[ 2.345470] I-pipe domain: Linux
[ 2.345470] RIP: 0010:__xntimer_migrate.cold+0xc/0x14
[ 2.345470] Code: 24 e8 ac 2f 5c 00 48 8b 3c 24 48 8d 50 f0 48 85 c0 48 0f 45 c2 49 89 46 08 e9 42 ff ff ff 48 c7 c7 f0 2a e0 9d e8 bc fd f3 ff <0f> 0b e9 80 f1 ff ff 90 e8 0b 45 69 00 41 55 49 89 f5 41 54 49 89
[ 2.345470] RSP: 0018:ffffb6cf0004bd20 EFLAGS: 00010246
[ 2.345470] RAX: 0000000000000024 RBX: ffffa038bba30450 RCX: 000000000000019c
[ 2.345470] RDX: 0000000000000000 RSI: 0000000000000000 RDI: 0000000000000000
[ 2.345470] RBP: ffffa038bba30450 R08: 000000000000019c R09: 0000000000000001
[ 2.345470] R10: ffffdc8dc5e993c0 R11: 0000000000000300 R12: ffffa038bbab0380
[ 2.345470] R13: ffffb6cf0004be18 R14: 0000000000000000 R15: 0000000000000000
[ 2.345470] FS: 0000000000000000(0000) GS:ffffa038bba00000(0000) knlGS:0000000000000000
[ 2.345470] CS: 0010 DS: 0000 ES: 0000 CR0: 0000000080050033
[ 2.345470] CR2: 000000000044ecd3 CR3: 000000012f608000 CR4: 00000000003406f0
[ 2.345470] Call Trace:
[ 2.345470] __xntimer_init+0x5c/0x210
[ 2.345470] xnsched_tp_init+0xa8/0xde
[ 2.345470] xnsched_init+0x9d/0x2a0
[ 2.345470] ? vsnprintf+0x2d7/0x480
[ 2.345470] ? xnheap_set_name+0x63/0x90
[ 2.345470] xnsched_init_all+0x2a/0x70
[ 2.345470] ? xnclock_init+0x42/0x42
[ 2.345470] xenomai_init+0x32e/0x452
[ 2.345470] do_one_initcall+0x4c/0x1d6
[ 2.345470] kernel_init_freeable+0x12a/0x1b2
[ 2.345470] ? rest_init+0x9a/0x9a
[ 2.345470] kernel_init+0xa/0xf2
[ 2.345470] ret_from_fork+0x20/0x30
[ 2.345470] ---[ end trace a8efbd6dc99f41b6 ]---
[ 2.509099] ------------[ cut here ]------------
[ 2.513797] WARNING: CPU: 0 PID: 1 at kernel/xenomai/timer.c:509 __xntimer_migrate.cold+0xc/0x14
[ 2.519076] Modules linked in:
[ 2.519076] CPU: 0 PID: 1 Comm: swapper/0 Tainted: G W 4.19.124-cip27-xeno13-static #2
[ 2.519076] Hardware name: TQ-Group TQMxE39M/Type2 - Board Product Name, BIOS 5.12.30.21.18 04/12/2019
[ 2.519076] I-pipe domain: Linux
[ 2.519076] RIP: 0010:__xntimer_migrate.cold+0xc/0x14
[ 2.519076] Code: 24 e8 ac 2f 5c 00 48 8b 3c 24 48 8d 50 f0 48 85 c0 48 0f 45 c2 49 89 46 08 e9 42 ff ff ff 48 c7 c7 f0 2a e0 9d e8 bc fd f3 ff <0f> 0b e9 80 f1 ff ff 90 e8 0b 45 69 00 41 55 49 89 f5 41 54 49 89
[ 2.519076] RSP: 0018:ffffb6cf0004bcd0 EFLAGS: 00010246
[ 2.519076] RAX: 0000000000000024 RBX: ffffa038bba31970 RCX: 00000000000001bc
[ 2.519076] RDX: 0000000000000000 RSI: 0000000000000000 RDI: 0000000000000000
[ 2.519076] RBP: ffffa038bba31970 R08: 00000000000001bc R09: 0000000000000005
[ 2.519076] R10: 0000000000000000 R11: ffffffff9e69960d R12: ffffa038bbab0380
[ 2.519076] R13: ffffa038bba30700 R14: ffffa038bba31970 R15: ffffa038bba31a38
[ 2.519076] FS: 0000000000000000(0000) GS:ffffa038bba00000(0000) knlGS:0000000000000000
[ 2.519076] CS: 0010 DS: 0000 ES: 0000 CR0: 0000000080050033
[ 2.519076] CR2: 000000000044ecd3 CR3: 000000012f608000 CR4: 00000000003406f0
[ 2.519076] Call Trace:
[ 2.519076] __xntimer_init+0x5c/0x210
[ 2.519076] __xnthread_init+0x1e8/0x360
[ 2.519076] ? __ipipe_restore_head+0x16/0xb0
[ 2.519076] xnsched_init+0x122/0x2a0
[ 2.519076] ? xnheap_set_name+0x63/0x90
[ 2.519076] xnsched_init_all+0x2a/0x70
[ 2.519076] ? xnclock_init+0x42/0x42
[ 2.519076] xenomai_init+0x32e/0x452
[ 2.519076] do_one_initcall+0x4c/0x1d6
[ 2.519076] kernel_init_freeable+0x12a/0x1b2
[ 2.519076] ? rest_init+0x9a/0x9a
[ 2.519076] kernel_init+0xa/0xf2
[ 2.519076] ret_from_fork+0x20/0x30
[ 2.519076] ---[ end trace a8efbd6dc99f41b7 ]---
[ 2.689649] ------------[ cut here ]------------
[ 2.694339] WARNING: CPU: 0 PID: 1 at kernel/xenomai/timer.c:509 __xntimer_migrate.cold+0xc/0x14
[ 2.699639] Modules linked in:
[ 2.699639] CPU: 0 PID: 1 Comm: swapper/0 Tainted: G W 4.19.124-cip27-xeno13-static #2
[ 2.699639] Hardware name: TQ-Group TQMxE39M/Type2 - Board Product Name, BIOS 5.12.30.21.18 04/12/2019
[ 2.699639] I-pipe domain: Linux
[ 2.699639] RIP: 0010:__xntimer_migrate.cold+0xc/0x14
[ 2.699639] Code: 24 e8 ac 2f 5c 00 48 8b 3c 24 48 8d 50 f0 48 85 c0 48 0f 45 c2 49 89 46 08 e9 42 ff ff ff 48 c7 c7 f0 2a e0 9d e8 bc fd f3 ff <0f> 0b e9 80 f1 ff ff 90 e8 0b 45 69 00 41 55 49 89 f5 41 54 49 89
[ 2.699639] RSP: 0018:ffffb6cf0004bcd0 EFLAGS: 00010246
[ 2.699639] RAX: 0000000000000024 RBX: ffffa038bba31a38 RCX: 00000000000001dc
[ 2.699639] RDX: 0000000000000000 RSI: 0000000000000000 RDI: 0000000000000000
[ 2.699639] RBP: ffffa038bba31a38 R08: 00000000000001dc R09: 0000000000000005
[ 2.699639] R10: 0000000000000000 R11: ffffffff9e69960d R12: ffffa038bbab0380
[ 2.699639] R13: ffffa038bba30700 R14: ffffa038bba31970 R15: ffffa038bba31a38
[ 2.699639] FS: 0000000000000000(0000) GS:ffffa038bba00000(0000) knlGS:0000000000000000
[ 2.699639] CS: 0010 DS: 0000 ES: 0000 CR0: 0000000080050033
[ 2.699639] CR2: 000000000044ecd3 CR3: 000000012f608000 CR4: 00000000003406f0
[ 2.699639] Call Trace:
[ 2.699639] __xntimer_init+0x5c/0x210
[ 2.699639] __xnthread_init+0x22d/0x360
[ 2.699639] ? __ipipe_restore_head+0x16/0xb0
[ 2.699639] xnsched_init+0x122/0x2a0
[ 2.699639] ? xnheap_set_name+0x63/0x90
[ 2.699639] xnsched_init_all+0x2a/0x70
[ 2.699639] ? xnclock_init+0x42/0x42
[ 2.699639] xenomai_init+0x32e/0x452
[ 2.699639] do_one_initcall+0x4c/0x1d6
[ 2.699639] kernel_init_freeable+0x12a/0x1b2
[ 2.699639] ? rest_init+0x9a/0x9a
[ 2.699639] kernel_init+0xa/0xf2
[ 2.699639] ret_from_fork+0x20/0x30
[ 2.699639] ---[ end trace a8efbd6dc99f41b8 ]---
[ 2.870177] ------------[ cut here ]------------
[ 2.874865] WARNING: CPU: 0 PID: 1 at kernel/xenomai/timer.c:509 __xntimer_migrate.cold+0xc/0x14
[ 2.880167] Modules linked in:
[ 2.880167] CPU: 0 PID: 1 Comm: swapper/0 Tainted: G W 4.19.124-cip27-xeno13-static #2
[ 2.880167] Hardware name: TQ-Group TQMxE39M/Type2 - Board Product Name, BIOS 5.12.30.21.18 04/12/2019
[ 2.880167] I-pipe domain: Linux
[ 2.880167] RIP: 0010:__xntimer_migrate.cold+0xc/0x14
[ 2.880167] Code: 24 e8 ac 2f 5c 00 48 8b 3c 24 48 8d 50 f0 48 85 c0 48 0f 45 c2 49 89 46 08 e9 42 ff ff ff 48 c7 c7 f0 2a e0 9d e8 bc fd f3 ff <0f> 0b e9 80 f1 ff ff 90 e8 0b 45 69 00 41 55 49 89 f5 41 54 49 89
[ 2.880167] RSP: 0018:ffffb6cf0004bd58 EFLAGS: 00010246
[ 2.880167] RAX: 0000000000000024 RBX: ffffa038bba30548 RCX: 00000000000001fc
[ 2.880167] RDX: 0000000000000000 RSI: 0000000000000000 RDI: 0000000000000000
[ 2.880167] RBP: ffffa038bba30548 R08: 00000000000001fc R09: 0000000000000005
[ 2.880167] R10: 0000000000000000 R11: ffffffff9e69960d R12: ffffa038bbab0380
[ 2.880167] R13: ffffb6cf0004be18 R14: 0000000000000000 R15: 0000000000000000
[ 2.880167] FS: 0000000000000000(0000) GS:ffffa038bba00000(0000) knlGS:0000000000000000
[ 2.880167] CS: 0010 DS: 0000 ES: 0000 CR0: 0000000080050033
[ 2.880167] CR2: 000000000044ecd3 CR3: 000000012f608000 CR4: 00000000003406f0
[ 2.880167] Call Trace:
[ 2.880167] __xntimer_init+0x5c/0x210
[ 2.880167] xnsched_init+0x13d/0x2a0
[ 2.880167] ? xnheap_set_name+0x63/0x90
[ 2.880167] xnsched_init_all+0x2a/0x70
[ 2.880167] ? xnclock_init+0x42/0x42
[ 2.880167] xenomai_init+0x32e/0x452
[ 2.880167] do_one_initcall+0x4c/0x1d6
[ 2.880167] kernel_init_freeable+0x12a/0x1b2
[ 2.880167] ? rest_init+0x9a/0x9a
[ 2.880167] kernel_init+0xa/0xf2
[ 2.880167] ret_from_fork+0x20/0x30
[ 2.880167] ---[ end trace a8efbd6dc99f41b9 ]---
[ 3.042369] ------------[ cut here ]------------
[ 3.047067] WARNING: CPU: 0 PID: 1 at kernel/xenomai/timer.c:509 __xntimer_migrate.cold+0xc/0x14
[ 3.055855] Modules linked in:
[ 3.056996] CPU: 0 PID: 1 Comm: swapper/0 Tainted: G W 4.19.124-cip27-xeno13-static #2
[ 3.056996] Hardware name: TQ-Group TQMxE39M/Type2 - Board Product Name, BIOS 5.12.30.21.18 04/12/2019
[ 3.056996] I-pipe domain: Linux
[ 3.056996] RIP: 0010:__xntimer_migrate.cold+0xc/0x14
[ 3.056996] Code: 24 e8 ac 2f 5c 00 48 8b 3c 24 48 8d 50 f0 48 85 c0 48 0f 45 c2 49 89 46 08 e9 42 ff ff ff 48 c7 c7 f0 2a e0 9d e8 bc fd f3 ff <0f> 0b e9 80 f1 ff ff 90 e8 0b 45 69 00 41 55 49 89 f5 41 54 49 89
[ 3.056996] RSP: 0018:ffffb6cf0004bd58 EFLAGS: 00010246
[ 3.056996] RAX: 0000000000000024 RBX: ffffa038bba30610 RCX: 000000000000021a
[ 3.056996] RDX: 0000000000000000 RSI: 0000000000000000 RDI: 0000000000000000
[ 3.056996] RBP: ffffa038bba30610 R08: 000000000000021a R09: ffffa038bba1a568
[ 3.056996] R10: 00000000839a74d3 R11: 0000000000000651 R12: ffffa038bbab0380
[ 3.056996] R13: ffffb6cf0004be18 R14: 0000000000000000 R15: 0000000000000000
[ 3.056996] FS: 0000000000000000(0000) GS:ffffa038bba00000(0000) knlGS:0000000000000000
[ 3.056996] CS: 0010 DS: 0000 ES: 0000 CR0: 0000000080050033
[ 3.056996] CR2: 000000000044ecd3 CR3: 000000012f608000 CR4: 00000000003406f0
[ 3.056996] Call Trace:
[ 3.056996] __xntimer_init+0x5c/0x210
[ 3.056996] xnsched_init+0x184/0x2a0
[ 3.056996] ? xnheap_set_name+0x63/0x90
[ 3.056996] xnsched_init_all+0x2a/0x70
[ 3.056996] ? xnclock_init+0x42/0x42
[ 3.056996] xenomai_init+0x32e/0x452
[ 3.056996] do_one_initcall+0x4c/0x1d6
[ 3.056996] kernel_init_freeable+0x12a/0x1b2
[ 3.056996] ? rest_init+0x9a/0x9a
[ 3.056996] kernel_init+0xa/0xf2
[ 3.056996] ret_from_fork+0x20/0x30
[ 3.056996] ---[ end trace a8efbd6dc99f41ba ]---
[ 3.214589] ------------[ cut here ]------------
[ 3.219330] WARNING: CPU: 0 PID: 1 at kernel/xenomai/timer.c:509 __xntimer_migrate.cold+0xc/0x14
[ 3.228116] Modules linked in:
[ 3.229215] CPU: 0 PID: 1 Comm: swapper/0 Tainted: G W 4.19.124-cip27-xeno13-static #2
[ 3.229215] Hardware name: TQ-Group TQMxE39M/Type2 - Board Product Name, BIOS 5.12.30.21.18 04/12/2019
[ 3.229215] I-pipe domain: Linux
[ 3.229215] RIP: 0010:__xntimer_migrate.cold+0xc/0x14
[ 3.229215] Code: 24 e8 ac 2f 5c 00 48 8b 3c 24 48 8d 50 f0 48 85 c0 48 0f 45 c2 49 89 46 08 e9 42 ff ff ff 48 c7 c7 f0 2a e0 9d e8 bc fd f3 ff <0f> 0b e9 80 f1 ff ff 90 e8 0b 45 69 00 41 55 49 89 f5 41 54 49 89
[ 3.229215] RSP: 0018:ffffb6cf0004bd58 EFLAGS: 00010246
[ 3.229215] RAX: 0000000000000024 RBX: ffffa038bba31c08 RCX: 0000000000000238
[ 3.229215] RDX: 0000000000000000 RSI: 0000000000000000 RDI: 0000000000000000
[ 3.229215] RBP: ffffa038bba31c08 R08: 0000000000000238 R09: ffffffff9d0c1065
[ 3.229215] R10: ffffdc8dc5e80800 R11: 0000000000000600 R12: ffffa038bbab0380
[ 3.229215] R13: ffffb6cf0004be18 R14: 0000000000000000 R15: 0000000000000000
[ 3.229215] FS: 0000000000000000(0000) GS:ffffa038bba00000(0000) knlGS:0000000000000000
[ 3.229215] CS: 0010 DS: 0000 ES: 0000 CR0: 0000000080050033
[ 3.229215] CR2: 000000000044ecd3 CR3: 000000012f608000 CR4: 00000000003406f0
[ 3.229215] Call Trace:
[ 3.229215] __xntimer_init+0x5c/0x210
[ 3.229215] xnsched_init+0x219/0x2a0
[ 3.229215] ? xnheap_set_name+0x63/0x90
[ 3.229215] xnsched_init_all+0x2a/0x70
[ 3.229215] ? xnclock_init+0x42/0x42
[ 3.229215] xenomai_init+0x32e/0x452
[ 3.229215] do_one_initcall+0x4c/0x1d6
[ 3.229215] kernel_init_freeable+0x12a/0x1b2
[ 3.229215] ? rest_init+0x9a/0x9a
[ 3.229215] kernel_init+0xa/0xf2
[ 3.229215] ret_from_fork+0x20/0x30
[ 3.229215] ---[ end trace a8efbd6dc99f41bb ]---
[ 3.387387] [Xenomai] Cobalt v3.1 [DEBUG]
[ 3.391471] workingset: timestamp_bits=62 max_order=20 bucket_order=0
________________________________
This message and any attachments are solely for the use of the intended recipients. They may contain privileged and/or confidential information or other information protected from disclosure. If you are not an intended recipient, you are hereby notified that you received this email in error and that any review, dissemination, distribution or copying of this email and any attachment is strictly prohibited. If you have received this email in error, please contact the sender and delete the message and any attachment from your system.
ANDRITZ HYDRO GmbH
Rechtsform/ Legal form: Gesellschaft mit beschränkter Haftung / Corporation
Firmensitz/ Registered seat: Wien
Firmenbuchgericht/ Court of registry: Handelsgericht Wien
Firmenbuchnummer/ Company registration: FN 61833 g
DVR: 0605077
UID-Nr.: ATU14756806
Thank You
________________________________
^ permalink raw reply [flat|nested] 3+ messages in thread
* Re: xenomai.supported_cpus not working as intended?
2020-07-13 13:37 xenomai.supported_cpus not working as intended? Lange Norbert
@ 2020-07-13 17:52 ` Jan Kiszka
2020-07-14 7:41 ` Lange Norbert
0 siblings, 1 reply; 3+ messages in thread
From: Jan Kiszka @ 2020-07-13 17:52 UTC (permalink / raw)
To: Lange Norbert, Xenomai (xenomai@xenomai.org)
On 13.07.20 15:37, Lange Norbert via Xenomai wrote:
> Hello,
>
> I am using Xenomai 3.1 and I tried once more to tie Linux to Core0, and RT to the remaining Cores.
> It seems that both Linux and Xenomai favor Core0, as rtnet-stack rtnet-rtpc seem to always run on that.
> Network drivers will process the IRQs on all cores, but realistally all are handles at Core0.
>
> I tries the commandline xenomai.supported_cpus=0xFFFE, but this doesn’t seem to work right.
>
> I get stuck Xenomai processes, and entries in dmesg (both with and without the isolcpus parameter).
> Kernel cmdline is like this: irqaffinity=0 xenomai.smi=disabled isolcpus=1-3 xenomai.supported_cpus=0xFFFE
>
> Running a Xenomai Process looks like this:
>
> # /usr/xenomai/bin/clocktest
> [ 191.759690] [Xenomai] thread clocktest[575] switched to non-rt CPU0, aborted.
> == Testing built-in CLOCK_REALTIME (0)
> CPU ToD offset [us] ToD drift [us/s] warps max delta [us]
> --- -------------------- ---------------- ---------- --------------
> 0 0.0 0.000 0 0.0
> 1 -1450249.3 -36.240 0 0.0
> 2 -1450249.8 -36.040 0 0.0
> 3 -1450249.4 -35.292 0 0.0
>
> And similar stuff happens when booting, Kernel dmesg is following.
>
> So I don’t see how xenomai.supported_cpus can be safely used,
> It more or less works by chance for me (processes not getting stuck)
IIRC, we had troubles with starting off RTDM kernel tasks (like RTnet
uses) when supported_cpus is used. There is no good control over where a
kernel task comes up, specifically when it started by a built-in driver.
Or are you seeing issues even without RTnet in the picture?
cpus_supported is one of those "would be nice but usually broken when
needed" feature because we do not consistently test it.
Jan
--
Siemens AG, Corporate Technology, CT RDA IOT SES-DE
Corporate Competence Center Embedded Linux
^ permalink raw reply [flat|nested] 3+ messages in thread
* RE: xenomai.supported_cpus not working as intended?
2020-07-13 17:52 ` Jan Kiszka
@ 2020-07-14 7:41 ` Lange Norbert
0 siblings, 0 replies; 3+ messages in thread
From: Lange Norbert @ 2020-07-14 7:41 UTC (permalink / raw)
To: Jan Kiszka, Xenomai (xenomai@xenomai.org)
> -----Original Message-----
> From: Jan Kiszka <jan.kiszka@siemens.com>
> Sent: Montag, 13. Juli 2020 19:52
> To: Lange Norbert <norbert.lange@andritz.com>; Xenomai
> (xenomai@xenomai.org) <xenomai@xenomai.org>
> Subject: Re: xenomai.supported_cpus not working as intended?
>
> NON-ANDRITZ SOURCE: BE CAUTIOUS WITH CONTENT, LINKS OR
> ATTACHMENTS.
>
>
> On 13.07.20 15:37, Lange Norbert via Xenomai wrote:
> > Hello,
> >
> > I am using Xenomai 3.1 and I tried once more to tie Linux to Core0, and RT
> to the remaining Cores.
> > It seems that both Linux and Xenomai favor Core0, as rtnet-stack rtnet-rtpc
> seem to always run on that.
> > Network drivers will process the IRQs on all cores, but realistally all are
> handles at Core0.
> >
> > I tries the commandline xenomai.supported_cpus=0xFFFE, but this doesn’t
> seem to work right.
> >
> > I get stuck Xenomai processes, and entries in dmesg (both with and
> without the isolcpus parameter).
> > Kernel cmdline is like this: irqaffinity=0 xenomai.smi=disabled
> > isolcpus=1-3 xenomai.supported_cpus=0xFFFE
> >
> > Running a Xenomai Process looks like this:
> >
> > # /usr/xenomai/bin/clocktest
> > [ 191.759690] [Xenomai] thread clocktest[575] switched to non-rt CPU0,
> aborted.
> > == Testing built-in CLOCK_REALTIME (0)
> > CPU ToD offset [us] ToD drift [us/s] warps max delta [us]
> > --- -------------------- ---------------- ---------- --------------
> > 0 0.0 0.000 0 0.0
> > 1 -1450249.3 -36.240 0 0.0
> > 2 -1450249.8 -36.040 0 0.0
> > 3 -1450249.4 -35.292 0 0.0
> >
> > And similar stuff happens when booting, Kernel dmesg is following.
> >
> > So I don’t see how xenomai.supported_cpus can be safely used, It more
> > or less works by chance for me (processes not getting stuck)
>
> IIRC, we had troubles with starting off RTDM kernel tasks (like RTnet
> uses) when supported_cpus is used. There is no good control over where a
> kernel task comes up, specifically when it started by a built-in driver.
>
> Or are you seeing issues even without RTnet in the picture?
I guess clocktest is not really RTnet. Or would I need a kernel with no traces of RTnet?
>
> cpus_supported is one of those "would be nice but usually broken when
> needed" feature because we do not consistently test it.
I got repeatedly told, locking Linux to some cores and RT to others is a good idea.
Last time it was a MMC driver that ran into a timeout as it got preempted ( = no IO on the rootfs anymore).
Seems pretty much needed instead of an optional goodie to me.
I can bind Linux to Core0, I can bind my RT task to other cores, but RT drivers IRQS and rtnet stack still remains there.
Norbert
________________________________
This message and any attachments are solely for the use of the intended recipients. They may contain privileged and/or confidential information or other information protected from disclosure. If you are not an intended recipient, you are hereby notified that you received this email in error and that any review, dissemination, distribution or copying of this email and any attachment is strictly prohibited. If you have received this email in error, please contact the sender and delete the message and any attachment from your system.
ANDRITZ HYDRO GmbH
Rechtsform/ Legal form: Gesellschaft mit beschränkter Haftung / Corporation
Firmensitz/ Registered seat: Wien
Firmenbuchgericht/ Court of registry: Handelsgericht Wien
Firmenbuchnummer/ Company registration: FN 61833 g
DVR: 0605077
UID-Nr.: ATU14756806
Thank You
________________________________
^ permalink raw reply [flat|nested] 3+ messages in thread
end of thread, other threads:[~2020-07-14 7:41 UTC | newest]
Thread overview: 3+ messages (download: mbox.gz / follow: Atom feed)
-- links below jump to the message on this page --
2020-07-13 13:37 xenomai.supported_cpus not working as intended? Lange Norbert
2020-07-13 17:52 ` Jan Kiszka
2020-07-14 7:41 ` Lange Norbert
This is an external index of several public inboxes,
see mirroring instructions on how to clone and mirror
all data and code used by this external index.