From EGIWiki
Jump to: navigation, search
Main operations services Support Documentation Tools Activities Performance Technology Catch-all Services Resource Allocation Security

Detailed agenda: Grid Operations Meeting 18 April 2011

1. Middleware releases and staged rollout (Mario)

1.1. Update on the status of EMI-1 release (Cristina)

1.2. Staged Rollout

  1. gLite 3.1
    1. FTS/A/M under certification.
  2. gLite 3.2
    1. L&B under certification
    2. FTS/A/M under certification or verified.
    3. VOBOX in staged rollout state, no EA is doing the test.
  3. Operational tools
    1. SAM/Nagios update 10 under staged rollout.

No other component is foreseen in the near future in both gLite series before the EMI1.0 release.

1.3. Information on the upcoming EMI1.0 release (Mario)

Staged rollout managers: for each major MW stack of EMI (ARC, gLite and UNICORE) there are experienced people on each stack that will manage the process for the corresponding components:

Mail sent earlier this morning

in view of the upcoming EMI1 release, I would like to ask you which teams are going to change from glite 3.2 to the corresponding EMI components for the staged rollout.

there are currently a few components in glite 3.1 and 3.2 in certification or staged rollout, these components are the last ones in the "foreseeable future" in the glite series (and most 3.1 components have reached their end of life).

all effort is concentrated in EMI, as such I would like to receive your input until the end of the week (thursday) about your plans. please take the EA table as starting point, and also the EMI release tracker

I am in the process of updating this table for a few teams.

Furthermore, for EMI we will be using the EGI SW release process, that is tracked in the EGI RT queue "staged-rollout" the wiki:

Are going to be updated during this week with more details in particular for the EAs.

The components will be undergoing first through the verification process, and then trough the staged rollout. a list of components that will undergo the process will be given soon, after discussion on prioritization in the last OMB and after in the SA2 meeting.

It is foreseen that the first components will be going to staged rollout around the second week of May, this will be made more precise later.

We remind that the set of components that will make the UMD release, will depend on the test of staged rollout.

2. Operational Issues

2.1 TMPDIR and WORKDIR Update

New contribution from J. Templon. : Jobs wordir and tempdir

I will assume for the moment that a shared area will be used. This should NOT be the home directory, it should be some other directory. The associated environment variable should have some good name, standardized in EMI, which I think we are free to choose. Something like GMULTI_SHARED_DIR where G is for Grid, Multi means for jobs spanning multiple nodes, shared means of course shared across all these nodes. People may have even better ideas for the name. I would prefer not to include "EGI" or "EMI" or "UMD" or whatever in the name!!! This gives hope for other middleware projects to be able to adopt this as a standard.

The MPI grid tools would need to be modified to use this new directory (via the environment variable) for the shared communication. Putting the work here is correct since the "multiple node" type of jobs are the only type of jobs that need this directory.

2.2 Open Issues

WMSes (List here) and Top-BDII (List here) update.

3. AOB

3.1 Next meeting

Proposal: Monday 2nd of May 14:00

Personal tools