On 11/09/13 08:45, Brian Davies wrote:
> Bristol and se01@QMUL are still showing up using lcg-stmd command. (This is using a production role.)
>
> heplnx204.pp.rl.ac.uk - Total Size: 1500000000000
> lcgse02.phy.bris.ac.uk - Total Size: 1073741824
> se01.dur.scotgrid.ac.uk - Total Size: 805306368000
> se01.esc.qmul.ac.uk - Total Size: 1000000000000
QMUL should now be fixed - apologies - I thought I'd done this before.
Chris
>
> Brain
>
> -----Original Message-----
> From: Testbed Support for GridPP member institutes [mailto:[log in to unmask]] On Behalf Of Alessandra Forti
> Sent: 10 September 2013 17:58
> To: [log in to unmask]
> Subject: Re: Atlas news
>
> Hi Chris,
>
> I just checked the replies to Brian thread.
>
> Checking the BDII shows only RALPP and Durham publishing the ATLASHOTDISK space token now. Manchester is still cached but HOTDISK has gone. Maybe Durham and RALPP are in the same position.
>
> cheers
> alessandra
>
>
> On 10/09/2013 17:33, Christopher J. Walker wrote:
>> On 10/09/13 15:40, Alessandra Forti wrote:
>>> Hi,
>>>
>>> today I said I'd send a more detailed email about what I said today
>>> maybe also repeating some of the things Brian and Elena have said
>>> already
>>>
>>> 1) ATLASHOTDISK space token needs to be eliminated. The directory
>>> hotdisk needs also to be cleaned as it is full of empty subdirs. On DPM:
>>>
>>> Sites still with hotdisk from Brian's email last week (minus
>>> Manchester and Brunel which deleted it)
>>>
>>> fal-pygrid-30.lancs.ac.uk - Total Size: 268435456000
>>> heplnx204.pp.rl.ac.uk - Total Size: 1500000000000
>>> lcg-dpm01.hep.ucl.ac.uk - Total Size: 3298534883328
>>> lcgse02.phy.bris.ac.uk - Total Size: 1073741824
>>> se01.dur.scotgrid.ac.uk - Total Size: 805306368000
>>> se01.esc.qmul.ac.uk - Total Size: 1000000000000 se04.esc.qmul.ac.uk -
>>> Total Size: 1000000000000
>>>
>>> QMUL and Bristol might want to delete from their test SE and in
>>> general respectively to avoid confusion in the future.
>> I thought I had deleted hotdisk from these test SEs (after Brian's
>> post). Has this not stuck?
>>
>> Can you give me the command to check this please.
>>
>>
>>> 2) ATLASPRODDISK from Elena's email
>>>
>>> T2s are asked to keep only .../atlasproddisk/rucio/ and
>>> .../atlasproddisk/ and ... /atlasproddisk/SAM/. Files in
>>> subdirectories other than rucio/ and SAM/ are dark data and should be also removed.
>> I've sent a list of 3260 files to cloud-support for deletion. I'll
>> then delete the directories once they are empty.
>>
>>
>> Chris
>>
>
>
> --
> Facts aren't facts if they come from the wrong people. (Paul Krugman)
>
|