Changes between Version 20 and Version 21 of Public/User_Guide/News


Ignore:
Timestamp:
Aug 19, 2021, 10:33:12 AM (4 years ago)
Author:
Jochen Kreutz
Comment:

general update to reflect current system status and upcoming changes

Legend:

Unmodified
Added
Removed
Modified

  • Public/User_Guide/News

    v20 v21  
    55This is a summary of the latest news concerning the system. For a list of known problems related to the system, please refer to [wiki:Public/User_Guide/PaS this page].
    66
    7 ''Last update: 2021-02-18''
     7''Last update: 2021-08-19''
    88{{{#!comment
    99[[span(style=color: #FF0000, System will be in maintenance in CW37 (Monday, 2020-09-07 to Friday 2020-09-11))]]
    … …  
    1818=== ESB nodes ===
    1919
    20 - in CW51 the update of the first ESB rack started for using Extoll Fabri3 network (instead of IB)
    21   - work is still ongoing
     20- the first ESB rack (nodes `dp-esb[01-25]`) is planned to be revised to use IB again (instead of Extoll interconnect)
     21  - date for the HW intervention not yet fixed
    2222
    2323=== DAM nodes ===
    2424
    25 - first 8 DAM nodes (dp-dam[01-08]) are currently being integrated into Extoll Fabri3 network
    26  
    27 - Persistent memory for nodes dp-dam[03-16] has been extended to 3 TB with next maintenance (CW51)
     25- along with first ESB rack also the DAM nodes will move to IB (instead of using 40 GbE and Extoll)
    2826
    2927=== Network Federation Gateways ===
    3028
    31 - Gateway nodes have been completed in CW51 to the final layout:
     29- with aiming for an "all IB" solution the NFGWs will become obsolete
    3230
    33   * 2x NF-GW EDR/Extoll (1 x Fabri3, 1 x Tourmalet)
    34 
    35   * 2x NF-GW 40GbE/Extoll ( 1 x Fabri3, 1 x Tourmalet)
    36 
    37   * 2x NF-GW EDR/40GbE
    38 
    39 - **due to the ongoing Fabri3 installation two of the NF-GWs (the ones equipped with Fabri3 PCIe cards) are not in operation yet**
    40 
    41 - for an example on how to use the gateway nodes and for further information,
    42   please refer to the [wiki:/Public/User_Guide/Batch_system#HeterogeneousjobswithMPIcommunicationacrossmodules batchsystem] wiki page.
     31- current status is
     32  - 2x NF-GW EDR/Extoll (1 x Fabri3, 1 x Tourmalet)
     33  - 2x NF-GW 40GbE/Extoll ( 1 x Fabri3, 1 x Tourmalet)
     34  - 2x NF-GW EDR/40GbE
     35  - the NF-GWs equipped with Fabri3 PCIe cards are not in operation
     36  - for an example on how to use the gateway nodes and for further information,
     37    please refer to the [wiki:/Public/User_Guide/Batch_system#HeterogeneousjobswithMPIcommunicationacrossmodules batchsystem] wiki page.
    4338
    4439
    … …  
    4843
    4944- a NAM SW implementation has been done, a test environment on the DAM has been set up on dp-dam[09-16].
     45- for more information on NAM usage and an example, please refer to [wiki:Public/User_Guide/TAMPI_NAM NAM with TAMPI] page
    5046
    5147=== File Systems ===
    5248
    53 - **a new All Flash Storage Module (AFSM) is going to be added to the system on 24./25. February**
     49**please refer to the**  [wiki:Filesystems Filesystems] **overview**
    5450
    55 - DEEP-EST storage has been rebuilt for performance reasons
     51- recent changes:
     52  - a new All Flash Storage Module (AFSM) is in place and provides fast work file system mounted to `/work` on compute nodes and login node (`deepv`)
     53    - the older System Services and Storage Module (SSSM) still serves the /usr/local file system
     54    - SSSM storage has been rebuilt for performance reasons
    5655  - BeeGFS servers and clients have been updated
    57   - the SDV is de-coupled now meaning that the SDV nodes do not mount `/work` anymore and the DEEP-EST (CM,DAM,ESB) nodes only mount `/work` (not `/sdv-work`)
    58 
    59 - BeeGFS (`/work`) user quotas is in place now (see section "User management")
    60 
    61 - It is possible to access the `$ARCHIVE` file system from the `deepv` login node under `/arch`. For more information about `$ARCHIVE`, please refer to the [wiki:Filesystems Filesystems page] and see also
    62   the hint in the MOTD for efficient usage of the archive filesystem
    63 
    64 - DCPMM usage within BeeGFS has successfully been tested on `dp-dam03` using a 4.19 kernel
     56  - BeeGFS (`/work`) user quotas is in place now (see section "User management")
     57  - It is possible to access the `$ARCHIVE` file system from the `deepv` login node under `/arch`. 
     58    See hint in the MOTD for efficient usage of the archive filesystem
    6559 
    6660
    … …  
    6963=== SW updates ===
    7064
    71 - BeeOND integration into SLURM currently being prepared
     65- new SLURM version has been installed: 20.11.8.         
     66  - please use `--interactive` flag for interactive sessions now (see MOTD hint)
    7267
    73 - new SLURM features are being integrated and will be rolled out soon:
    74   - extended logging and improved resource management for jobs within a workflow
    75   - burst buffer plugin
    76 
    77 - 2020 Easybuild stage is being set up
     68- 2021 Easybuild stage is being set up
    7869
    7970- latest Intel oneAPI version is available in /usr/local/intel/oneapi