[PlanetCCRMA] XRUNS and more
Etienne Rouge
etiennerouge at yahoo.com
Mon May 16 10:11:48 PDT 2016
Hi ! Here are all the commands related to IRQ :
_*rtirq status*_
PID CLS RTPRIO NI PRI %CPU STAT COMMAND
699 FF 50 - 90 0.0 S irq/36-mei_me
3 TS - 0 19 0.0 S ksoftirqd/0
15 TS - 0 19 0.0 S ksoftirqd/1
22 TS - 0 19 0.0 S ksoftirqd/2
29 TS - 0 19 0.0 S ksoftirqd/3
*cat /proc/interrupts*
CPU0 CPU1 CPU2 CPU3
0: 27 0 0 0 IO-APIC 2-edge
timer
1: 2 0 0 0 IO-APIC 1-edge
i8042
8: 1 0 0 0 IO-APIC 8-edge rtc0
9: 0 0 0 0 IO-APIC 9-fasteoi acpi
12: 4 0 0 0 IO-APIC 12-edge
i8042
14: 0 0 0 0 IO-APIC 14-edge
ata_piix
15: 30394 0 0 0 IO-APIC 15-edge
ata_piix
16: 916 0 0 0 IO-APIC 16-fasteoi
ehci_hcd:usb1
17: 877 0 0 0 IO-APIC 17-fasteoi
snd_hda_intel
18: 0 0 0 0 IO-APIC 18-fasteoi
i801_smbus
19: 71018 0 0 0 IO-APIC 19-fasteoi
ata_piix, firewire_ohci
23: 12208 0 0 0 IO-APIC 23-fasteoi
ehci_hcd:usb2
25: 0 0 0 0 PCI-MSI
1572864-edge xhci_hcd
26: 0 0 0 0 PCI-MSI
1572865-edge xhci_hcd
27: 0 0 0 0 PCI-MSI
1572866-edge xhci_hcd
28: 0 0 0 0 PCI-MSI
1572867-edge xhci_hcd
29: 0 0 0 0 PCI-MSI
1572868-edge xhci_hcd
30: 0 0 0 0 PCI-MSI
3145728-edge xhci_hcd
31: 0 0 0 0 PCI-MSI
3145729-edge xhci_hcd
32: 0 0 0 0 PCI-MSI
3145730-edge xhci_hcd
33: 0 0 0 0 PCI-MSI
3145731-edge xhci_hcd
34: 0 0 0 0 PCI-MSI
3145732-edge xhci_hcd
35: 12841 0 0 0 PCI-MSI
3670016-edge enp7s0
36: 11 0 0 0 PCI-MSI
360448-edge mei_me
37: 811 0 0 0 PCI-MSI
442368-edge snd_hda_intel
38: 14631 0 0 0 PCI-MSI
524288-edge nvidia
NMI: 4 3 3 3 Non-maskable interrupts
LOC: 91745 78005 78657 79401 Local timer interrupts
SPU: 0 0 0 0 Spurious interrupts
PMI: 4 3 3 3 Performance
monitoring interrupts
IWI: 1 0 0 0 IRQ work interrupts
RTR: 0 0 0 0 APIC ICR read retries
RES: 4562 6455 4625 4002 Rescheduling interrupts
CAL: 1402 1274 1271 970 Function call interrupts
TLB: 33470 28308 28856 28427 TLB shootdowns
TRM: 0 0 0 0 Thermal event interrupts
THR: 0 0 0 0 Threshold APIC interrupts
DFR: 0 0 0 0 Deferred Error APIC
interrupts
MCE: 0 0 0 0 Machine check exceptions
MCP: 4 4 4 4 Machine check polls
ERR: 0
MIS: 0
PIN: 0 0 0 0 Posted-interrupt
notification event
PIW: 0 0 0 0 Posted-interrupt wakeup
event
*/etc/sysconfig/rtirq*
RTIRQ_NAME_LIST="rtc firewire_ohci" <- the only line I've changed
RTIRQ_PRIO_HIGH=70
RTIRQ_PRIO_DECR=1
RTIRQ_PRIO_LOW=65
RTIRQ_PRIO_UDEV=70
RTIRQ_PRIO_DEFAULT=50
RTIRQ_RESET_ALL=0
RTIRQ_NON_THREADED="rtc snd"
rtirq status seems really odd to me, but once again I understand very
little of this…
Thanks !
É
Le 14/05/2016 à 05:36, Fernando Lopez-Lezcano a écrit :
> On 05/13/2016 09:14 AM, Etienne Rouge wrote:
>>
>> Thanks for the quick reply. I really appreciate !
>>
>> I run Renoise with vanilla plugins.
>>
>> - CPU Intel(R) Core(TM) i5-2500 CPU @ (quad 3.30GHz)
>> - 16gb ram
>>
>> It should be more than enough.
>>
>> I have edited /etc/sysconfig/rtirq with :
>> RTIRQ_NAME_LIST="rtc firewire_ohci" (and haven't touched the rest made
>> by rncbc)
>>
>> I'm not sure it has done anything...
>
> See what priorities you have with "rtirq status"...
>
>> I'll try your script and I'll tell you how it goes.
>
> You have an i5 cpu so you do not have hyperthreading. Don't run the
> examples that I sent blindly, you have to understand what you are
> doing (if you turn off all 4 cores you are left with nothing :-)
>
> -- Fernando
>
>
>> Le 13/05/2016 à 17:43, Fernando Lopez-Lezcano a écrit :
>>> On 05/13/2016 05:15 AM, Etienne Rouge wrote:
>>>> Hello,
>>>
>>> Hi Etienne,
>>>
>>>> I've recently switched back to CCRMA and I'm rather happy with it.
>>>>
>>>> However I still have xruns when I really shouldn't (powerfull computer
>>>> and reasonnable amount of tracks/effects).
>>>>
>>>> I've set up PAM… added "rtc firewire_ohci" to the irq file.
>>>> Honestly, I
>>>> don't quite understand the few tuts I find online and the fact they
>>>> are
>>>> not fedora-oriented don't help.
>>>>
>>>> Is there a crucial step I've missed ? A tutorial I can follow ?
>>>
>>> Could you tell us what hardware is this? What software are you
>>> running? I presume you are running rtirq and you have access to
>>> SCHED_FIFO rt scheduling in your account.
>>>
>>> I have found that for critical low latency work using recent hardware
>>> I need to disable hyperthreading (the fake cores on Intel processors
>>> that can't do much) and also set the intel_pstate driver to try to use
>>> all cores at high speed. Also disable thermald if you are using it (it
>>> could also be throttling the processors). Maybe this would help?
>>>
>>> I have this in a script I run when needed (this is on a four core
>>> Intel laptop with HT):
>>>
>>> # get all processors to run fast all the time...
>>> echo "100" > /sys/devices/system/cpu/intel_pstate/min_perf_pct
>>>
>>> # turn off hyperthreading which only makes things worse most of the
>>> time
>>> # we do this by turning off cpus that have the same "proc id"
>>> echo 0 > /sys/devices/system/cpu/cpu1/online
>>> echo 0 > /sys/devices/system/cpu/cpu3/online
>>> echo 0 > /sys/devices/system/cpu/cpu5/online
>>> echo 0 > /sys/devices/system/cpu/cpu7/online
>>>
>>> Best luck! And let us know how it works out...
>>> -- Fernando
>>>
>>
>> _______________________________________________
>> PlanetCCRMA mailing list
>> PlanetCCRMA at ccrma.stanford.edu
>> https://cm-mail.stanford.edu/mailman/listinfo/planetccrma
>
-------------- next part --------------
An HTML attachment was scrubbed...
URL: <https://cm-mail.stanford.edu/pipermail/planetccrma/attachments/20160516/69329857/attachment.html>
More information about the PlanetCCRMA
mailing list