access_NewSun_Tasks_010 - ACCESS-NRI/accessdev-Trac-archive GitHub Wiki


#!html
<h1  style="text-align: center; color: green"> CAWCR-BoM ACCESS NWP Ngamai Migration Working Group</h1>

Issues and Task List table

  • Updated after Meeting 10

  • '''Following review discussions in Meeting 10, the following items are now considered CLOSED, have been removed from the table: 6, 7, 17i, 18, 19, 20, 21, 24, 35, 37.

  • Several new items have been added in this version.

  • Items marked (D) are development-only, not part of APS1 operational systems.'''

  • This table contains the main current items relevant to the working group.

  • Previous versions of this table are also available in notes for Meetings 1-4, and links on the main page.

  • Issues no longer active can be seen in earlier table versions.

No. ITEM STATUS/COMMENTS Contact Person

| 3 | Setup and rebuild of /apps | Complete, except for some Verify and Mars aspects. ACTION: Monitor Status. | /apps, rab| | --- | --- | --- | --- |

| 8/9/10 | Source Code for VAR,OPS,SURF | Migrate all SVN repositories from solar to ngamai early October. Migrate to accessdev & access-svn later. ACTION: Prepare for migration. Monitor reliability of access-svn server. |azs| | --- | --- | --- | --- |

| 11 | ~access directory | Goal of having interoperability with raijin is not straightforward, particularly with executable and libraries. Need to handle case by case. $HOST or $MACH subdirectory required in some instances. Also see Scott's tildeAccess notes. ACTION: Address case by case as ~access is being setup. |access.admin | | --- | --- | --- | --- |

| 12 | GCOM Libraries | Updated path/name: example: ~access/apps/gcom/GCOM3.5/ngamai/bld_12.1.8.273_1.6.5_new_optns-03. ACTION: Information on building gcom to be documented on the wiki. |azs,martin,ScottWales,ilia| | --- | --- | --- | --- |

| 13 | Migrate Trac databases | Preparing for cutover from solar to ngamai 1st weekend of Oct. ACTION: Prepare for migration. |azs| | --- | --- | --- | --- |

| 14 | UM Small execs | Do for vn7.3, 7.5, 7.6, 8.2 and 8.4. May be able to use copy from raijin. ACTION: No report. | martin | | --- | --- | --- | --- |

| 15 | Migrate UMUI, VARUI, OPSUI and SCSUI | * Preparing for cutover from solar to ngamai 1st weekend of Oct.

  • Prototypes working on ngamai, accessing databases on ngamai, solar, cherax, submitting jobs to ngamai, solar, raijin.
  • Databases to be moved at cutover point. ACTION: Prepare for migration. | azs, zhihong, ilia, xiao, say | | --- | --- | --- | --- |

| 16 | CAP program on ngamai | * vn8.1 now available and set up on Raijin.

  • Sufficient for time being; not urgent to port to ngamai, as we can create ancils on raijin and copy to ngamai.
  • Need to install also on ngamai for future. ACTION: Appoint someone | Group | | --- | --- | --- | --- |

| 17 | Re-compile/build UM 7.5/7.6 Executables for APS1 - Global, Regional, Access-C ...| * Executable builds basically all done.

  • Work in progress on documented of builds. NMOC to re-build all operational execs. ACTION: Detailed documentation for each build to be available on wiki. | ilia,xiao,azs,wenming,martin | | --- | --- | --- | --- |

| 26 | APS1 suites | AG1, AR1, AC1 all working and tested in research trials; operational trial versions in progress; see meeting notes for further details. ACTION: Continuing work. | xiao,joan | | --- | --- | --- | --- |

| 27 (D) | APS2 suite | APS2 porting needed before solar switch-off. ACTION: Xiao planning to cover this; then hand over to Sergei. | ciwt,xiao,sergei,joan | | --- | --- | --- | --- |

| 34 | Higher management's Porting plan. | Information from this WG feeding into porting project reporting. ACTION: Continue to provide info as required. | rab,mjn | | --- | --- | --- | --- |

| 36 | Verify | * NWP verification software to be ported to ngamai and raijin.

  • Chris Bridge to handle this, NMOC to manage.
  • ngamai version will be included in /apps; raijin version to follow. ACTION: NMOC to report progress on this item. | ChrisBridge | | --- | --- | --- | --- |

| 38 | Configuration Management of systems/suites that go into operations | * Suites covered in item 26 work.

  • Executables covered in item 17. ACTION: Work continuing. | Porting Group | | --- | --- | --- | --- |

| 39 (D) | Turboboost | * Turboboost is set on raijin.

  • Not critical to operational porting activity.
  • Will be investigated on ngamai after porting has been completed. ACTION: ??? | ilia,rab | | --- | --- | --- | --- |

| 40 (D) | Hyperthreading| * Not critical to operational porting activity.

  • Will be investigated on ngamai after porting has been completed. ACTION: ??? | ilia,rab | | --- | --- | --- | --- |

| 41 (D) | Level of thread support for OpenMPI library | * Not critical to operational porting activity.

  • Will be investigated on ngamai after porting has been completed. ACTION: ??? | ilia,rab | | --- | --- | --- | --- |

| 42 | Runtime variability | * Ilia and Xiao have found significant runtime variability in steps in the main NWP suites, especially in UM and RECON steps.

  • Joerg has investigated, discovered issue in MPI message-parsing (set_haloes), and kernel issue in memory handling, (fix identified with turn off of transparent huge pages).
  • Ilia's 2-run test job still has major slow-down in second run.
  • Joerg still setting up RECON test job to investigate. ACTION: Work continuing. | ilia,xiao,wenming,joerg | | --- | --- | --- | --- |

| 43 (D) | Rose-Cylc | * Rose-Cylc is needed on ngamai for development suites, starting with SREP 1.5km suites. Additional python packages are required. Xiao can install Rose-Cylc once these python packages are available.
ACTION: Robin to follow up /apps python aspects; Xiao to handle subsequent Rose-Cylc aspects. | rab,xiao | | --- | --- | --- | --- |

| 44 (D) | AGREPS | * AGREPS porting requited before soalr switch-off. ACTION: AGREPS team to handle this. | dhsmith,azs,mjn | | --- | --- | --- | --- |

⚠️ **GitHub.com Fallback** ⚠️