Hello, Lev.
You wrote 12 января 2012 г., 15:00:20:
>> But what mav says makes sense.
> It is it -- stack size. Setting KSTACK_PAGES=6 fixes situation.
OOOPS. Not. After another 5 minutes ng_queue again consumes 100% CPU
:(
--
// Black Lion AKA Lev Serebryakov
___
Hello, Andriy.
You wrote 12 января 2012 г., 14:29:57:
> But what mav says makes sense.
It is it -- stack size. Setting KSTACK_PAGES=6 fixes situation.
Feature request: warn user when ng_queue is used due to stack
limitations :) I know from mav, that sometime it is unavoidable (with
protocols
Hello, Andriy.
You wrote 12 января 2012 г., 14:29:57:
> Well, I mostly meant things like uptime, load level and pattern, etc.
These are identical too -- freshly boot system, same load (torrent
client on other box), only load -- traffic, as it is router, same
upload/download speeds and peer cou
on 12/01/2012 12:05 Lev Serebryakov said the following:
> Hello, Andriy.
> You wrote 12 января 2012 г., 13:54:41:
>
>>> Switching to 4BSD helps. 4BSD works as usual: all CPU time is
>>> interrupts and network thread, system is responsive under heaviest load,
>>> normal operations of DNS, DHCP a
Hello, Andriy.
You wrote 12 января 2012 г., 13:54:41:
>> Switching to 4BSD helps. 4BSD works as usual: all CPU time is
>> interrupts and network thread, system is responsive under heaviest load,
>> normal operations of DNS, DHCP and hostapd.
> How reproducible is this result?
100%
> In other
on 12/01/2012 11:31 Lev Serebryakov said the following:
> Switching to 4BSD helps. 4BSD works as usual: all CPU time is
> interrupts and network thread, system is responsive under heaviest load,
> normal operations of DNS, DHCP and hostapd.
How reproducible is this result?
In other words, have
Hello, Freebsd-current.
I have router, which connects to upstream ISP with mpd5 from ports
using PPPoE.
I've used SCHED_ULE for long time without nay problems. Under heavy
network load (router is not the fastest one -- 500Mhz Geode CPU) main
consumer of CPU was "intr{swi1: netisr 0}" threa
