Difference between revisions of "CDWG Minutes 2013-09-11"

From OpenSFS
Jump to: navigation, search
Line 9: Line 9:
  
 
== Attendance ==
 
== Attendance ==
 +
 +
Aurelien Degremont (CEA)
 +
Peter Jones (Intel)
 +
John Forgan (Xyratex)
 +
Cory Spitz (Cray)
 +
Kit Westneat (DNN)
 +
James Simmons (ORNL)
  
 
== Minutes ==
 
== Minutes ==
Line 15: Line 22:
  
 
==== Xyratex LU-634 update ====
 
==== Xyratex LU-634 update ====
 +
 +
Nic: The patch attached to LU-634 was just experimental.  Xyratex is not interested in the work, no plans to push the patch to gerrit.
  
 
==== Organizations plans for RHEL7 adoption ====
 
==== Organizations plans for RHEL7 adoption ====
 +
 +
* LLNL - Maybe Mid-2014.  At the earliest.
 +
* Xyratex - not plans for now, sticking with RHEL6.X for a while
 +
* Cray - Only plan to move to RHEL7 when server Lustre support forces them to move
 +
* CEA - No plan before 2015
 +
 +
Cory mentioned that multiple kernel support only supported by ldiskfs, not kernel patching part of Lustre.  It would be nice to make that work (or perhaps finally go patchless to make the issue moot).
  
 
==== IU feedback for Intel work on LU-3288 and LU-3490 ====
 
==== IU feedback for Intel work on LU-3288 and LU-3490 ====
 +
 +
No "official" response from IU, but Peter reported that at least Stephen Simms seemed happy with the change.  Intel/OpenSFS believes the problem is addressed at this time.
  
 
==== Lustre patch submission procedures wiki page ====
 
==== Lustre patch submission procedures wiki page ====
 +
 +
No progress
  
 
=== Lustre 2.6.0 planning ===
 
=== Lustre 2.6.0 planning ===
  
=== Lustre 2.5.0 status update ===
+
* JamesORNL: Would like to add checksumming at the lnet layer
 +
* Interop with 2.5.x only; 2.4.x upgrade should be possible
 +
* Testing with Lustre client in 3.11 Linux kernel
 +
* Replace FC18 with FC19 client support (with an eye towards supporting what will become RHEL7)
 +
 
 +
==== Feature Highlights ====
 +
* UID Mapping and Shared Key (LU-3527)
 +
* IU Primary developers; sharing Lustre over a WAN between different institutions* Further LFSCK development (LU-1267)* Funded by OpenSFS; MDT-OST Consistency; MDT-MDT Consistency=== Lustre 2.5.0 status update ===
 +
 
 +
24 "blocking" issues.  Many are test script issues.  Newly created HSM tests are many of them.
 +
 
 +
Tests on one cluster went well with HSM tests, it was only later they realized that a configuration change on another cluster made HSM failures very common.
 +
 
 +
=== Developer Summit ===
 +
 
 +
Possible topics of discussion:
 +
 
 +
* Client performance
 +
* Patch landing process?
  
 
=== Patch landing process ===
 
=== Patch landing process ===
 +
 +
Some discussion.  Newer gerrit 2.6, with its new APIs perhaps enough to provide the desired features of the Xyratex folks.
 +
== LU-2779 ==
 +
 +
John suggested that LU-2779 is a candidate for closing.
  
 
== Action Items ==
 
== Action Items ==
  
* Xyratex to give update about patch for LU-634
 
* Investigate when you plan to go to RHEL7 (All organizations)
 
* IU to supply Intel feedback about LU-3288 and LU-3490 solutions
 
* Next time firm up message about 2.6.0 for LAD
 
 
* Make wiki.opensfs.org page describing Lustre patch submission procedures (Chris, everyone)
 
* Make wiki.opensfs.org page describing Lustre patch submission procedures (Chris, everyone)
 +
* Check on status of latest TWG contract.  If it has been signed, make sure it is publicized.
 +
* Check on LU-2779

Revision as of 15:36, 11 September 2013


Agenda

  • Review action items
  • Lustre 2.6.0 planning
  • Lustre 2.5.0 status update
  • Discuss patch landing process

Attendance

Aurelien Degremont (CEA) Peter Jones (Intel) John Forgan (Xyratex) Cory Spitz (Cray) Kit Westneat (DNN) James Simmons (ORNL)

Minutes

Actions items review

Xyratex LU-634 update

Nic: The patch attached to LU-634 was just experimental. Xyratex is not interested in the work, no plans to push the patch to gerrit.

Organizations plans for RHEL7 adoption

  • LLNL - Maybe Mid-2014. At the earliest.
  • Xyratex - not plans for now, sticking with RHEL6.X for a while
  • Cray - Only plan to move to RHEL7 when server Lustre support forces them to move
  • CEA - No plan before 2015

Cory mentioned that multiple kernel support only supported by ldiskfs, not kernel patching part of Lustre. It would be nice to make that work (or perhaps finally go patchless to make the issue moot).

IU feedback for Intel work on LU-3288 and LU-3490

No "official" response from IU, but Peter reported that at least Stephen Simms seemed happy with the change. Intel/OpenSFS believes the problem is addressed at this time.

Lustre patch submission procedures wiki page

No progress

Lustre 2.6.0 planning

  • JamesORNL: Would like to add checksumming at the lnet layer
  • Interop with 2.5.x only; 2.4.x upgrade should be possible
  • Testing with Lustre client in 3.11 Linux kernel
  • Replace FC18 with FC19 client support (with an eye towards supporting what will become RHEL7)

Feature Highlights

  • UID Mapping and Shared Key (LU-3527)
  • IU Primary developers; sharing Lustre over a WAN between different institutions* Further LFSCK development (LU-1267)* Funded by OpenSFS; MDT-OST Consistency; MDT-MDT Consistency=== Lustre 2.5.0 status update ===

24 "blocking" issues. Many are test script issues. Newly created HSM tests are many of them.

Tests on one cluster went well with HSM tests, it was only later they realized that a configuration change on another cluster made HSM failures very common.

Developer Summit

Possible topics of discussion:

  • Client performance
  • Patch landing process?

Patch landing process

Some discussion. Newer gerrit 2.6, with its new APIs perhaps enough to provide the desired features of the Xyratex folks.

LU-2779

John suggested that LU-2779 is a candidate for closing.

Action Items

  • Make wiki.opensfs.org page describing Lustre patch submission procedures (Chris, everyone)
  • Check on status of latest TWG contract. If it has been signed, make sure it is publicized.
  • Check on LU-2779