Hi Greig
I thought the meeting was all about storage class implementation issues
(i.e. how you configure and run a site to get storage classes working
and not about SRM specifications). Draining pools would be a legitimate
issue to bring up in the wider context.
Jeremy
> -----Original Message-----
> From: Greig A Cowan [mailto:[log in to unmask]]
> Sent: 02 October 2006 12:00
> To: GridPP Dteam
> Cc: [log in to unmask]
> Subject: Re: pre-GDB storage classes meeting
>
>
> Hi Olivier,
>
> I would say that draining is an implementation specific issue and is
not
> related to the discussions of the SRM specification.
>
> Greig
>
>
> On Mon, 2 Oct 2006, Olivier van der Aa wrote:
>
> > Greig A Cowan wrote:
> >
> > Hi Greig,
> >
> > I see on the agenda that quotas will be discussed. Will the draining
> > also be on the topic ? Maybe this is not srm related.
> >
> > Cheers, Olivier.
> >
> > > Hi everyone (apologies to those who get this twice),
> > >
> > > I am going to attend a meeting next week [1] that will discuss how
the
> SRM
> > > 2.2 storage classes should be implemented at Tier-1 and -2 sites
(i.e.
> > > if any special configuration of the SRM and storage hardware is
needed
> > > beyond what is already deployed). For those who haven't heard of
the
> > > storage classes before, they can be summarised by the terms:
> > >
> > > Tape1Disk1
> > > Tape1Disk0
> > > Tape0Disk1
> > >
> > > which represent how the LHC experiments want to be able to store
and
> > > manage their data.
> > >
> > > In the UK, Tape0Disk1 will likely be the only one to affect the
Tier-
> 2s.
> > >
> > > Jeremy suggested that I ask for input from people before the
meeting
> so
> > > that we can ensure all relevant issues/concerns are raised. Does
> anyone
> > > have any questions that they would like me to raise on their
behalf?
> The
> > > meeting is on Tuesday afternoon.
> > >
> > > Cheers,
> > > Greig
> > >
> > > [1] http://agenda.cern.ch/fullAgenda.php?ida=a058490
> > >
> > >
> > >
> > >
> > >
> > > On Thu, 21 Sep 2006, Coles, J (Jeremy) wrote:
> > >
> > >> Thanks Greig
> > >>
> > >> I would attend since I am going to the GDB but I have to be at
RAL in
> > >> the morning. Please do canvass others on the list for input prior
to
> the
> > >> meeting.
> > >>
> > >> Cheers,
> > >> Jeremy
> > >>
> > >>> -----Original Message-----
> > >>> From: Greig A Cowan [mailto:[log in to unmask]]
> > >>> Sent: 21 September 2006 13:11
> > >>> To: Graeme Stewart
> > >>> Cc: Coles, J (Jeremy); GridPP Dteam
> > >>> Subject: Re: pre-GDB meeting
> > >>>
> > >>>
> > >>> Hi Jeremy,
> > >>>
> > >>> I meant to reply to you about this. I've not been directly
involved
> > >> with
> > >>> the working group so far, but am aware of the ongoing
discussions
> and
> > >>> reports that they have generated. According to the agenda
Tier-2s
> are
> > >> now
> > >>> getting a mention, so I think it would be useful if I attended.
> > >>>
> > >>> http://agenda.cern.ch/fullAgenda.php?ida=a058490
> > >>>
> > >>> Cheers,
> > >>> Greig
> > >>>
> > >>> On Thu, 21 Sep 2006, Graeme Stewart wrote:
> > >>>
> > >>>> I suspect I'll still be mired in the new Glasgow cluster at
this
> > >>>> rate. Perhaps Greig would want to go?
> > >>>>
> > >>>> Graeme
> > >>>>
> > >>>> On 18 Sep 2006, at 19:16, Coles, J ((Jeremy)) wrote:
> > >>>>
> > >>>>> Dear All
> > >>>>>
> > >>>>> One or two of you may be interested in taking part in this
> > >> discussion.
> > >>>>> Graeme and Greig I believe you are already partly involved
with
> > >> the
> > >>>>> working group so perhaps one of you would like to attend?
Feedback
> > >>>>> from
> > >>>>> anyone else welcome as always!
> > >>>>>
> > >>>>> Jeremy
> > >>>>>
> > >>>>> -----Original Message-----
> > >>>>> From: Kors Bos [mailto:[log in to unmask]]
> > >>>>> Sent: 18 September 2006 15:03
> > >>>>> To: 'GDB'; [log in to unmask]
> > >>>>> Subject: pre-GDB meeting
> > >>>>>
> > >>>>> Dear colleagues,
> > >>>>>
> > >>>>> when we discussed the implementation of the SRMv2.2 storage
> > >> classes
> > >>>>> after Artem Trunov's presentation during the GDB at BNL it
became
> > >>>>> clear
> > >>>>> that we need more time for discussion. Artem and I therefor
> > >> propose a
> > >>>>> dedicated meeting on the afternoon of Tuesday October 3, the
day
> > >>>>> before
> > >>>>> the next GDB at CERN in the IT Aud. A more detailed agenda
will be
> > >> put
> > >>>>> up soon.
> > >>>>>
> > >>>>> I hope the experiments can be represented as well as the Tiers
but
> > >> of
> > >>>>> course anybody else is welcome. We need to arrive at very
> > >> practical
> > >>>>> solutions on how the storage classes are going to be used by
the
> > >>>>> experiments and how that is going to be implemented at the
Tiers.
> > >> The
> > >>>>> experiments foresee large scale Monte Carlo productions and
> > >>>>> reconstruction efforts very soon and it is at present not
clear
> > >> how
> > >>>>> the
> > >>>>> data will be managed.
> > >>>>>
> > >>>>> Your suggestions are much appreciated.
> > >>>>>
> > >>>>> Kors
> > >>>>>
> > >>>>>
> > >>>>>
> > >>>>>
> > >>>> --
> > >>>> Dr Graeme Stewart -
> > >> http://wiki.gridpp.ac.uk/wiki/User:Graeme_stewart
> > >>>> GridPP DM Wiki - http://wiki.gridpp.ac.uk/wiki/Data_Management
> > >>>> ScotGrid - http://www.scotgrid.ac.uk/
http://scotgrid.blogspot.com/
> > >>>>
> > >>>>
> > >>>>
> > >>> --
> > >>>
> > >>
>
========================================================================
> > >>> Dr Greig A Cowan
> > >> http://www.ph.ed.ac.uk/~gcowan1
> > >>> School of Physics, University of Edinburgh, James Clerk Maxwell
> > >> Building
> > >>> TIER-2 STORAGE SUPPORT PAGES:
> > >> http://wiki.gridpp.ac.uk/wiki/Grid_Storage
> > >>
>
========================================================================
> > >>
> > >
> >
> >
> >
>
> --
>
========================================================================
> Dr Greig A Cowan
http://www.ph.ed.ac.uk/~gcowan1
> School of Physics, University of Edinburgh, James Clerk Maxwell
Building
>
> TIER-2 STORAGE SUPPORT PAGES:
http://wiki.gridpp.ac.uk/wiki/Grid_Storage
>
========================================================================
|