Request for information - timers, hz, interrupts
For a long time, at least in the 6-stable timeframe, I was used to
seeing timer interrupts going at the frequency of 2*HZ, e.g. this is
from 6.4-RELEASE:
kern.clockrate: { hz = 250, tick = 4000, profhz = 166, stathz = 33 }
debug.psm.hz: 20
cpu0: timer 6789885563499
cpu2: timer 6789885538499
cpu1: timer 6789885538499
cpu3: timer 6789885537499
Then sometime in 7.x this changed to 4*HZ, which continues in 8.x, e.g.
from 7.2-RELEASE:
kern.clockrate: { hz = 250, tick = 4000, profhz = 1000, stathz = 142 }
kern.hz: 250
cpu0: timer 1368329715988
cpu1: timer 1368324640988
cpu2: timer 1367642854988
cpu3: timer 1367642874988
I'm not very worried about it (though maybe laptop users might be
because of potential power drainage) but would like to know the
explanation behind it.
Presumably it has something to do with profhz but what and why? There
isn't an obvious correlation between profhz frequency in 6.x and HZ and
in 7.x. and HZ.
___
freebsd-hackers@freebsd.org mailing list
http://lists.freebsd.org/mailman/listinfo/freebsd-hackers
To unsubscribe, send any mail to "freebsd-hackers-unsubscr...@freebsd.org"
Re: Request for information - timers, hz, interrupts
On Friday 04 December 2009 9:52:39 am Ivan Voras wrote:
> For a long time, at least in the 6-stable timeframe, I was used to
> seeing timer interrupts going at the frequency of 2*HZ, e.g. this is
> from 6.4-RELEASE:
>
> kern.clockrate: { hz = 250, tick = 4000, profhz = 166, stathz = 33 }
> debug.psm.hz: 20
>
> cpu0: timer 6789885563499
> cpu2: timer 6789885538499
> cpu1: timer 6789885538499
> cpu3: timer 6789885537499
>
> Then sometime in 7.x this changed to 4*HZ, which continues in 8.x, e.g.
> from 7.2-RELEASE:
>
> kern.clockrate: { hz = 250, tick = 4000, profhz = 1000, stathz = 142 }
> kern.hz: 250
>
> cpu0: timer 1368329715988
> cpu1: timer 1368324640988
> cpu2: timer 1367642854988
> cpu3: timer 1367642874988
>
> I'm not very worried about it (though maybe laptop users might be
> because of potential power drainage) but would like to know the
> explanation behind it.
>
> Presumably it has something to do with profhz but what and why? There
> isn't an obvious correlation between profhz frequency in 6.x and HZ and
> in 7.x. and HZ.
It actually was changed to provide saner behavior when you use low hz values
like 'hz=100'. Note that your stathz is now 142 instead of 33. The scheduler
is likely far happier with that stathz. There is more detail in the commit
log I believe (just look at the logs for local_apic.c in either svn or
cvsweb).
--
John Baldwin
___
freebsd-hackers@freebsd.org mailing list
http://lists.freebsd.org/mailman/listinfo/freebsd-hackers
To unsubscribe, send any mail to "freebsd-hackers-unsubscr...@freebsd.org"
won't boot after 8.0-RELEASE upgrade
i sent the following to -questions yesterday morning but had no luck. can anyone where give me tips or pointers? tia tom after running freebsd-update -r 8.0-RELEASE upgrade my system won't boot. it gets stuck on mountroot and i can't find the magic word it wants. the system used to have two sata drives /dev/ad4 and ad6. they were partitioned and sliced using the deafaults that sysinstall suggested. at the boot prompt, lsdev says: disk devices disk0: BIOS drive C: disk0s1a: FFS disk0s1b: swap disk0s1d: FFS disk0s1e: FFS disk0s1f: FFS disk1: BIOS drive D: disk1s1a: FFS disk1s1b: swap disk1s1d: FFS disk1s1e: FFS disk1s1f: FFS which looks right, although i'm not familiar with the "disk" nomenclature. entering ? at mountroot mentions ad4 and ad6. geom_mirror was being used. i've tried saying "load geom_mirror" and/or "enable-module geom_mirror" at the boot prompt. neither made any difference. nothing i've said to mountroot works: ufs:/dev/ad4s1a ufs:/dev/ad6s1a ufs:/dev/mirror/gm0s1a ufs:/dev/disk0s1a ufs:/dev/disk1s1a does anyone know the magic word? i'd be very grateful. tom ___ freebsd-hackers@freebsd.org mailing list http://lists.freebsd.org/mailman/listinfo/freebsd-hackers To unsubscribe, send any mail to "freebsd-hackers-unsubscr...@freebsd.org"
Re: won't boot after 8.0-RELEASE upgrade
On Fri, 4 Dec 2009, Tom Worster wrote: i sent the following to -questions yesterday morning but had no luck. can anyone where give me tips or pointers? I had this problem with a Dell M600 blade. I was able to install from a 6.4 ISO, then binary update to 7.0, but when I tried to get to 8.0 I couldn't boot either. I gave up trying to fix the issue and installed VMWare ESXi on the blade and installed FreeBSD 8 on top of that. Not ideal, but I had to get it working. Here's what I posted: http://lists.freebsd.org/pipermail/freebsd-hackers/2009-November/030013.html http://lists.freebsd.org/pipermail/freebsd-hackers/2009-November/030022.html On http://drop.io/rk0eoap there is a video of the boot process and where it died for me: It hung just after isab0, isa0 and atrtc0 loaded. The last line: atrtc0: registered as a time-of-day clock (resolution 100us) Beckman --- Peter Beckman Internet Guy beck...@angryox.com http://www.angryox.com/ --- ___ freebsd-hackers@freebsd.org mailing list http://lists.freebsd.org/mailman/listinfo/freebsd-hackers To unsubscribe, send any mail to "freebsd-hackers-unsubscr...@freebsd.org"
Re: Request for information - timers, hz, interrupts
2009/12/4 John Baldwin :
> On Friday 04 December 2009 9:52:39 am Ivan Voras wrote:
>> For a long time, at least in the 6-stable timeframe, I was used to
>> seeing timer interrupts going at the frequency of 2*HZ, e.g. this is
>> from 6.4-RELEASE:
>>
>> kern.clockrate: { hz = 250, tick = 4000, profhz = 1000, stathz = 142 }
>> kern.hz: 250
> It actually was changed to provide saner behavior when you use low hz values
> like 'hz=100'. Note that your stathz is now 142 instead of 33. The scheduler
> is likely far happier with that stathz. There is more detail in the commit
> log I believe (just look at the logs for local_apic.c in either svn or
> cvsweb).
Ok. Some more questions:
What does "ticks" do in the above sysctl output?
So 4000 interrupts/s per CPU in the default configuration isn't
considered excessive? :)
I see stathz isn't a divisor of any number in kern.clockrate, which
probably means it's not triggered from one of them firing; can't it be
a separately configurable value?
___
freebsd-hackers@freebsd.org mailing list
http://lists.freebsd.org/mailman/listinfo/freebsd-hackers
To unsubscribe, send any mail to "freebsd-hackers-unsubscr...@freebsd.org"
Re: Request for information - timers, hz, interrupts
On Friday 04 December 2009 4:09:59 pm Ivan Voras wrote:
> 2009/12/4 John Baldwin :
> > On Friday 04 December 2009 9:52:39 am Ivan Voras wrote:
> >> For a long time, at least in the 6-stable timeframe, I was used to
> >> seeing timer interrupts going at the frequency of 2*HZ, e.g. this is
> >> from 6.4-RELEASE:
> >>
> >> kern.clockrate: { hz = 250, tick = 4000, profhz = 1000, stathz = 142 }
> >> kern.hz: 250
>
> > It actually was changed to provide saner behavior when you use low hz values
> > like 'hz=100'. Note that your stathz is now 142 instead of 33. The
> > scheduler
> > is likely far happier with that stathz. There is more detail in the commit
> > log I believe (just look at the logs for local_apic.c in either svn or
> > cvsweb).
>
> Ok. Some more questions:
>
> What does "ticks" do in the above sysctl output?
'tick' is the number of microseconds per clock tick. Since you run hz at 250,
that gives you 4ms = 4000us per clock tick.
> So 4000 interrupts/s per CPU in the default configuration isn't
> considered excessive? :)
The default configuration is hz = 1000 which gives you an interrupt rate of
2000 interrupts/s per CPU and a stathz of 133. With your setting of hz=250,
you have an interrupt rate of 1000 interrupts/s per CPU.
> I see stathz isn't a divisor of any number in kern.clockrate, which
> probably means it's not triggered from one of them firing; can't it be
> a separately configurable value?
No, it is driven by the tick timer. It ends up running at something more
like 142.8571428571 when you have hz = 250. (So some seconds it will fire
143 times rather than 142.)
The kernel tries to run stathz as close to 128 as possible, but ~142 is
what it comes up with. It should probably try the next divisor "up" and
take the resulting stathz that is the closest to 128. That would let stathz
run at 125 on your machine instead of ~142.
--
John Baldwin
___
freebsd-hackers@freebsd.org mailing list
http://lists.freebsd.org/mailman/listinfo/freebsd-hackers
To unsubscribe, send any mail to "freebsd-hackers-unsubscr...@freebsd.org"
Re: won't boot after 8.0-RELEASE upgrade
i finally got a 7.1 livefs fixit shell to work and i was able to mount ad4s1a. i fscb'ed all the slices on ad4 and they look ok. i changed fstab to refer to /dev/ad4* instead of /dev/ mirror/gm0* and got rid of geom_mirror_load="YES" from /boot/loader.conf. and i ran gmirror clear. none of this did any good. 8.0 just won't mount root from the disk. any final suggestions before i try dumping the data out on another system and use the old windows technique (reformat and reinstall the os)? On 12/4/09 11:58 AM, "Tom Worster" wrote: > i sent the following to -questions yesterday morning but had no luck. can > anyone where give me tips or pointers? > > tia > tom > > > after running freebsd-update -r 8.0-RELEASE upgrade my system won't boot. it > gets stuck on mountroot and i can't find the magic word it wants. > > the system used to have two sata drives /dev/ad4 and ad6. they were > partitioned and sliced using the deafaults that sysinstall suggested. > > at the boot prompt, lsdev says: > > disk devices > disk0: BIOS drive C: > disk0s1a: FFS > disk0s1b: swap > disk0s1d: FFS > disk0s1e: FFS > disk0s1f: FFS >disk1: BIOS drive D: > disk1s1a: FFS > disk1s1b: swap > disk1s1d: FFS > disk1s1e: FFS > disk1s1f: FFS > > which looks right, although i'm not familiar with the "disk" nomenclature. > > entering ? at mountroot mentions ad4 and ad6. > > geom_mirror was being used. > > i've tried saying "load geom_mirror" and/or "enable-module geom_mirror" at > the boot prompt. neither made any difference. > > nothing i've said to mountroot works: > > ufs:/dev/ad4s1a > ufs:/dev/ad6s1a > ufs:/dev/mirror/gm0s1a > ufs:/dev/disk0s1a > ufs:/dev/disk1s1a > > does anyone know the magic word? i'd be very grateful. > > tom > > > ___ > freebsd-hackers@freebsd.org mailing list > http://lists.freebsd.org/mailman/listinfo/freebsd-hackers > To unsubscribe, send any mail to "freebsd-hackers-unsubscr...@freebsd.org" ___ freebsd-hackers@freebsd.org mailing list http://lists.freebsd.org/mailman/listinfo/freebsd-hackers To unsubscribe, send any mail to "freebsd-hackers-unsubscr...@freebsd.org"
