[ovirt-users] Performance of cloning

[Gianluca Cecchi]

On Thu, Sep 28, 2017 at 11:02 AM, Gianluca Cecchi <gianluca.cecchi at gmail.com
> wrote:

> Hello,
> I'm on 4.1.5 and I'm cloning a snapshot of a VM with 3 disks for a total
> of about 200Gb to copy
> The target I choose is on a different domain than the source one.
> They are both FC storage domains, with the source on SSD disks and the
> target on SAS disks.
>
> The disks are preallocated
>
> Now I have 3 processes of kind:
> /usr/bin/qemu-img convert -p -t none -T none -f raw
> /rhev/data-center/59b7af54-0155-01c2-0248-000000000195/
> fad05d79-254d-4f40-8201-360757128ede/images/8f62600a-
> 057d-4d59-9655-631f080a73f6/21a8812f-6a89-4015-a79e-150d7e202450 -O raw
> /rhev/data-center/mnt/blockSD/6911716c-aa99-4750-a7fe-
> f83675a2d676/images/c3973d1b-a168-4ec5-8c1a-630cfc4b66c4/
> 27980581-5935-4b23-989a-4811f80956ca
>
> but despite capabilities it seems it is copying using very low system
> resources.
>
> [snip]

>
> Is it expected? Any way to speed up the process?
>
> Thanks,
> Gianluca
>

The cloning process elapsed was 101'
The 3 disks are 85Gb, 20Gb and 80Gb so at the end an average of 30MB/s

At this moment I have only one host with self hosted engine VM running in
this environment, planning to add another host in short time.
So not yet configured power mgmt for fencing on it
During the cloning I saw these kind of events

Sep 28, 2017 10:31:30 AM VM vmclone1 creation was initiated by
admin at internal-authz.
Sep 28, 2017 11:16:38 AM VDSM command SetVolumeDescriptionVDS failed:
Message timeout which can be caused by communication issues

Sep 28, 2017 11:19:43 AM VDSM command SetVolumeDescriptionVDS failed:
Message timeout which can be caused by communication issues
Sep 28, 2017 11:19:43 AM Failed to update OVF disks
1504a878-4fe2-40df-a88f-6f073be0bd7b, 4ddac3ed-2bb9-485c-bf57-1750ac1fd761,
OVF data isn't updated on those OVF stores (Data Center DC1, Storage Domain
SDTEST).
At 11:24 I then start a pre-existing VM named benchvm and run a cpu / I/O
benchmark (HammerDB with 13 concurrent users; the VM is configured with 12
vcpus (1:6:2) and 64Gb of ram; it is not the one I'm cloning) that runs
from 11:40 to 12:02
Sep 28, 2017 11:24:29 AM VM benchvm started on Host host1
Sep 28, 2017 11:45:18 AM Host host1 is not responding. Host cannot be
fenced automatically because power management for the host is disabled.
Sep 28, 2017 11:45:28 AM Failed to update OVF disks
1504a878-4fe2-40df-a88f-6f073be0bd7b, 4ddac3ed-2bb9-485c-bf57-1750ac1fd761,
OVF data isn't updated on those OVF stores (Data Center DC1, Storage Domain
SDTEST).
Sep 28, 2017 11:45:39 AM Status of host host1 was set to Up.
Sep 28, 2017 12:12:31 PM VM vmclone1 creation has been completed.

Any hint on the failures detected, both when only the cloning process was
in place and when a bench was running inside a VM?

Thanks,
Gianluca
-------------- next part --------------
An HTML attachment was scrubbed...
URL: <http://lists.ovirt.org/pipermail/users/attachments/20170928/800c143e/attachment.html>