> On Apr 12, 2016, at 12:16 PM, Massimo Sgaravatto
> wrote:
>
>
> So when a user has to write a new file, if Lustre chooses OST-0, it checks if
> the quota is ok, while if it chooses OST-2, no quota limits are enforced.
>
Ah, I see now. I didn’t realize you were talking about quota enforce
Bingo !
I re-issued the commands:
lctl conf_param cmshome.quota.ost=u
lctl conf_param cmshome.quota.mdt=u
on the MDS, and now I see that the quota is enforced on both OSTs !
Thanks a lot !
Cheers, Massimo
On 12/04/2016 18:44, Philippe Weill wrote:
on lustre 2.5.3 here after adding some o
on lustre 2.5.3 here after adding some ost to a filesystem we found that quota
are present but not enforced on new ost
we had to reenforce quota after
Le 08/04/2016 18:40, Massimo Sgaravatto a écrit :
Hi
We are running Lustre 2.7.0. We have problems with quota on a filesystem.
This filesy
Hi
Thanks for spending your time with my problem ...
Let's consider this [*] output. So I set a quota on 110 for that
user and this got exceeded.
If I use the -v flag [**] I see that on OST-0 it is using a quota limit
of 747152, but no quota for OST-2 !
So when a user has to write a
Based on the output of your “lfs quota” command, I am not sure that I see a
problem with it. Both active osts (OST and OST0002) and the MDT seem to be
returning quota information. Can you explain what you were expecting to see
and how the output differs from your expectations?
--
Rick Mo
> On Apr 12, 2016, at 12:36 AM, Massimo Sgaravatto
> wrote:
>
> Should I try to change (using lctl conf_param) the attribute:
>
> osd-ldiskfs.cmshome-OST0002.quota_slave.enabled
>
I don’t think that should be necessary. On my file system, quotas are enabled
but the value of quota_slave.ena
Indeed when I created that filesystem I simply ran on the MDS:
lctl conf_param cmshome.quota.ost=u
lctl conf_param cmshome.quota.mdt=u
and this was enough.
As I tried to explain in my mail, the problem started when I added
another OST to this filesystem.
And now I have an OST with quota, and
Hi Massimo,
Since lustre 2.5 (I guess) formatting the OST using the specific parameter
it's no more necessary. You should simply enable it using the lctl command.
On Tuesday, 12 April 2016, Massimo Sgaravatto
wrote:
> Any hints ?
>
> Should I try to change (using lctl conf_param) the attribute:
Any hints ?
Should I try to change (using lctl conf_param) the attribute:
osd-ldiskfs.cmshome-OST0002.quota_slave.enabled
on the new OST from 'none' to 'u' to fix the problem ?
Thanks, Massimo
On 08/04/2016 18:40, Massimo Sgaravatto wrote:
Hi
We are running Lustre 2.7.0. We have problems
Hi
We are running Lustre 2.7.0. We have problems with quota on a filesystem.
This filesystem was initially composed of a single OST, and at that time
quota was enable on the MDT simply doing:
lctl conf_param cmshome.quota.ost=u
lctl conf_param cmshome.quota.mdt=u
Nothing was needed on the OS
10 matches
Mail list logo
