zfs discuss - Sep 2010 - way to find out of a dataset has children

Is there a way to find out if a dataset has children or not using zfs
properties or other scriptable method?  

I am looking for a more efficient way to delete datasets after they are
finished being used.  Right now I use custom property to set delete=1 on a
dataset, and then I have a script that runs async to clean them up.  If
there are children then the delete will fail. 

This method works, but I would rather filter it again so it only tries to
delete a dataset which can actually be deleted. 

I have looked at the usedbychildren and usedbysnapshots, but they are just
showing "0" in the columns.

Thanks,

Geoff

On 27/09/2010 18:14, Geoff Nordli wrote:
> Is there a way to find out if a dataset has children or not using zfs
> properties or other scriptable method?
>
> I am looking for a more efficient way to delete datasets after they are
> finished being used.  Right now I use custom property to set delete=1 on a
> dataset, and then I have a script that runs async to clean them up.  If
> there are children then the delete will fail.
>
> This method works, but I would rather filter it again so it only tries to
> delete a dataset which can actually be deleted.
This sounds very like what ''zfs hold'' and ''zfs
destroy -d'' were designed
for.  When using ''zfs send'' holds will automatically be taken
out for
pool versions 18 and higher.

-- 
Darren J Moffat

>From: Darren J Moffat 
>Sent: Monday, September 27, 2010 11:03 AM
>
>
>On 27/09/2010 18:14, Geoff Nordli wrote:
>> Is there a way to find out if a dataset has children or not using zfs
>> properties or other scriptable method?
>>
>> I am looking for a more efficient way to delete datasets after they
>> are finished being used.  Right now I use custom property to set
>> delete=1 on a dataset, and then I have a script that runs async to
>> clean them up.  If there are children then the delete will fail.
>>
>> This method works, but I would rather filter it again so it only tries
>> to delete a dataset which can actually be deleted.
>
>This sounds very like what ''zfs hold'' and ''zfs
destroy -d'' were designed
for.  When
>using ''zfs send'' holds will automatically be taken out for
pool versions 18
and
>higher.
>
Darren, thanks for this tip.  It this looks like it will work well for
snapshots, but I can''t apply the property to a clone.

Are there any properties I can set on the clone side?

I could definitely do a zfs list, and look for same name as the clone which
I am trying to delete, but I am looking for a better way. 

Geoff

On Sep 27, 2010, at 11:54 AM, Geoff Nordli wrote:
> 
> Are there any properties I can set on the clone side?
Each clone records its origin snapshot in the "origin" property.

$ zfs get origin syspool/rootfs-nmu-001
NAME                    PROPERTY  VALUE                           SOURCE
syspool/rootfs-nmu-001  origin    syspool/rootfs-nmu-000 at nmu-001  -

Enjoy
 -- richard

-- 
OpenStorage Summit, October 25-27, Palo Alto, CA
http://nexenta-summit2010.eventbrite.com

Richard Elling
richard at nexenta.com   +1-760-896-4422
Enterprise class storage for everyone
www.nexenta.com

>From: Richard Elling  
>Sent: Monday, September 27, 2010 1:01 PM
>
>On Sep 27, 2010, at 11:54 AM, Geoff Nordli wrote:
>>
>> Are there any properties I can set on the clone side?
>
>Each clone records its origin snapshot in the "origin" property.
>
>$ zfs get origin syspool/rootfs-nmu-001
>NAME                    PROPERTY  VALUE                           SOURCE
>syspool/rootfs-nmu-001  origin    syspool/rootfs-nmu-000 at nmu-001  -
>
>Enjoy
> -- richard
Hi Richard.

Yes, we can use the origin, but that tells me where it came from, not how
many snapshots are built from it.  

Before I can delete it, the clone can''t have any snapshots under it.  

This isn''t hard to solve, I can just do a regex on the clone name
looking
for snapshots name, but I was hoping there was a simple zfs property I can
query.

Thanks,

Geoff