Hi Jason,
I've tried to do enable the lttng tracing but no success.
I have done the steps from [1] and [2] but nothing happened ...
It's difficult to catch the event to dump the objecter requests because when we
observe the event, this is already past away.
Kind regards,
Laszlo
On 04.04.2017
Couple options:
1) you can enable LTTng-UST tracing [1][2] against your VM for an
extremely light-weight way to track IO latencies.
2) you can enable "debug rbd = 20" and grep through the logs for
matching "AioCompletion.*(set_request_count|finalize)" log entries
3) use the asok file during one of
Hello cephers,
I have a situation where from time to time the write operation to the seph
storage hangs for 3-5 seconds. For testing we have a simple line like:
while sleep 1; date >> logfile; done &
with this we can see that rarely there are 3 seconds or more differences
between the consecuti
In that case, live migration or power off/power on of the VMs is the
only alternative (after you verify that your directories are properly
created and that QEMU is able to write to them).
On Tue, Feb 28, 2017 at 3:41 AM, Laszlo Budai wrote:
> Hello,
>
> Thank you for the answer.
> I don't have th
Hi,
please check if you have SElinux enabled on your system(s) (CentOS/RHEL are
good candidates for that).
AFAIK I had to write my own pp file to support the socket file generation.
You could also try to use "setenforce 0" to set SElinux to permissive mode
and restart ceph (on that node).
HTH
Be
Hello,
Thank you for the answer.
I don't have the admin socket either :(
the ceph subdirectory is missing in /var/run.
What would be the steps to get the socket?
Kind regards,
Laszlo
On 28.02.2017 05:32, Jason Dillaman wrote:
On Mon, Feb 27, 2017 at 12:36 PM, Laszlo Budai wrote:
Currently m
On Mon, Feb 27, 2017 at 12:36 PM, Laszlo Budai wrote:
> Currently my system does not have the /var/log/quemu directory. Is it enough
> to create that directory in order to have some logs from librbd? Or I need
> to restart the vm?
If you have the admin socket file, you can run "ceph --admin-daem
Hello,
I have these settings in my /etc/ceph/ceph.conf:
[client]
rbd cache = true
rbd cache writethrough until flush = true
admin socket = /var/run/ceph/guests/$cluster-$type.$id.$pid.$cctid.asok
log file = /var/log/qemu/qemu-guest-$pid.log
rbd concurrent management ops = 20
Currently
