Hi Stephen,
> As I already said, sites can't be pushed to maintenance from the
> outside, it has to be done by the local admin, and in many cases once
> the admin knows that a problem exists they can fix it anyway. Also you
> don't want to stop dteam jobs going to a broken site, otherwise you
> couldn't tell when it was fixed.
I don't really mean taking the site out of Dteam/Testzone BDII. Nope!
All I mean is, tag the site in question as being in "Maintenance Mode".
Let me repeat this once more: even for the sites which are under my control,
I find it a great feature if the CIC, or my ROC, does this automatically.
>>Quickly or not, the grid is no longer a party of people in a
>>single room,
>>so there should be some more formal way of telling the other
>>poor admins
>>that something is not optimal with that site's maintenance.
>
>
> There is, the results of the functional tests are public.
I think this way of communicating information in unsufficient, since
it puts the burdain of debugging on the shoulders of the other admins,
rather than on those responsible for the site. The SFTs are good,
once you know that a site *IS* meant to be working well and
you wish to crosscheck & help the other sysadmins with cluefull information.
Eg. Why should 100s of sysadmins go each and check the SFTs of GR-03-HEPNTUA?
FYI,
I got no single response from plenty of problematic sites during RB tests.
The question for me is:
Is it *my* fault to assume that those sites should be operative? or whose?
How do I know as a sysadmin if chasing/debugging a problem is worthwhile?
--
echo "sysadmin know better bash than english" | sed s/min/mins/ \
| sed 's/better bash/bash better/' # Yelling in a CERN forum
