For performance reason, the MDT creates objects on OSTs in batch with a
technology called `precreate’. The MDT caches the `precreated’ objects in cache
and whenever a client is creating a file on the MDT, it will allocate objects
from cache. This is why you can’t see the inode count on OSTs
ease let me know if I can provide any additional
data.
-Tom
On Sep 15, 2016, at 16:55, Xiong, Jinshan
<jinshan.xi...@intel.com<mailto:jinshan.xi...@intel.com>> wrote:
Hi Tom,
Just to narrow down the problem, when you saw the space was not freed from
zpool, were you seeing this from
It turned out that the object 136 are an internal object for object accounting.
Therefore, the results you posted seem to be normal.
Jinshan
On Sep 15, 2016, at 6:27 PM, Xiong, Jinshan
<jinshan.xi...@intel.com<mailto:jinshan.xi...@intel.com>> wrote:
Thanks for the info. It make
You can lfsck to see if there exists any orphan objects.
I’m adding nasf into cc list and hopefully he can provide specific commands to
run.
Jinshan
On Sep 15, 2016, at 11:23 PM, Xiong, Jinshan
<jinshan.xi...@intel.com<mailto:jinshan.xi...@intel.com>> wrote:
It turned out that th
> On Oct 6, 2016, at 2:04 AM, Phill Harvey-Smith
> wrote:
>
> Hi all,
>
> Having tested a simple setup for lustre / zfs, I'd like to trey and replicate
> on the test system what we currently have on the production system, which
> uses a much older version of
Hi Tom,
Just to narrow down the problem, when you saw the space was not freed from
zpool, were you seeing this from MDT or OST zpool?
It seems that the objects you dumped were from MDT pool. The object 138 should
belong to a Lustre file, and it has a spilled block attached.
Jinshan
On Sep 9,
It’s LU-9574.
Jinshan
On May 30, 2017, at 12:24 PM, Jones, Peter A
> wrote:
Darby
Can you please open a JIRA ticket with this information?
Thanks
Peter
On 5/30/17, 12:10 PM, "lustre-discuss on behalf of Vicker, Darby (JSC-EG311)"