Here's the latest (note I didn't update my release.iso with the latest, at
this point I'm still running a slightly earlier (cd /usr/src/release ; make release) copy from 248935 below. Also,
the kernel that the VM is running I actually built while in uni-processor mode
which shows how well
beh
Hi Dan,
On Sat, Mar 30, 2013 at 12:17 PM, Dan Mack wrote:
> Here you go:
>
> - uni-processor output:
>
>
> root@olive:~ # bhyvectl --vm=coco --get-stats --cpu=0
> vcpu0
> vm exits due to external interrupt 1330
> number of times hlt was intercepted 676
> number of times
Here you go:
- uni-processor output:
root@olive:~ # bhyvectl --vm=coco --get-stats --cpu=0
vcpu0
vm exits due to external interrupt 1330
number of times hlt was intercepted 676
number of times %cr access was intercepted 1
number of times rdmsr was intercepted
Yep, no problem. I saw the checkin and started a rebuild a few minutes
ago :-)
Thanks,
Dan
On Sat, 30 Mar 2013, Neel Natu wrote:
Hi Dan,
On Fri, Mar 29, 2013 at 3:20 PM, Dan Mack wrote:
Here you go Neel:
root@olive:~ # bhyvectl --vm=coco --get-stats --cpu=0
vcpu0
vm exits due to ex
Hi Dan,
On Fri, Mar 29, 2013 at 3:20 PM, Dan Mack wrote:
>
>
> Here you go Neel:
>
> root@olive:~ # bhyvectl --vm=coco --get-stats --cpu=0
> vcpu0
> vm exits due to external interrupt 45051
> number of times hlt was intercepted 2277
> number of NMIs delivered to vcpu0
> vcpu tot
Here you go Neel:
root@olive:~ # bhyvectl --vm=coco --get-stats --cpu=0
vcpu0
vm exits due to external interrupt 45051
number of times hlt was intercepted 2277
number of NMIs delivered to vcpu0
vcpu total runtime 105001652482
number of ticks vcpu was idle
Hi Dan,
On Fri, Mar 29, 2013 at 12:38 PM, Dan Mack wrote:
>
> I ran the procsystime dtrace script on bhyve when it was chewing up all
> the CPU in vCPU=2 mode, and this is what I see for about 10s of runtime:
>
> root@olive:/usr/share/dtrace/**toolkit # ./procsystime -n bhyve -aT
> Tracing... Hi
I ran the procsystime dtrace script on bhyve when it was chewing up all
the CPU in vCPU=2 mode, and this is what I see for about 10s of runtime:
root@olive:/usr/share/dtrace/toolkit # ./procsystime -n bhyve -aT
Tracing... Hit Ctrl-C to end...
dtrace: 158536 dynamic variable drops with non-empt
On Thu, 28 Mar 2013, Peter Grehan wrote:
Hi Dan,
Any ideas?
Just to confirm: your host system is an i7 3930k, which looks like a 6 core
system. Should be plenty beefy enough for a 2 vCPU guest.
That's what I thought, 6 cores, 12 threads, 64 GB RAM.
The issue you are seeing looks a bit li
Hi Dan,
Any ideas?
Just to confirm: your host system is an i7 3930k, which looks like a 6
core system. Should be plenty beefy enough for a 2 vCPU guest.
The issue you are seeing looks a bit like what happens when systems
are heavily oversubscribed and vCPUs can't get enough run time.
Update#1: I was using the default of 2 virtual CPUs. When I switched to
1 CPU via vmrun.sh, the system booted clean and let me login.
Also, when running with two vCPUs, the bhyve process is spinning at 100%
even when the guest is doing nothing.
When running with one CPU, bhyve is mostly
I haven't spent too much time debugging this yet but I'd thought I'd ask
just in case someone else has seen this:
- fresh 10.x system (248804) , standard FreeBSD iso image I made with
make release
- latest vmrun.sh release.iso ...
- install went okay, everything seemed normal
- boot s
12 matches
Mail list logo
