Changes between Version 3 and Version 4 of Public/User_Guide/System_overview


Ignore:
Timestamp:
May 17, 2019, 3:56:01 PM (6 years ago)
Author:
Jochen Kreutz
Comment:

—

Legend:

Unmodified
Added
Removed
Modified

  • Public/User_Guide/System_overview

    v3 v4  
    11= Overview of our systems =
    22
    3 This page is supposed to give a short overview on the available systems from a hardware point of view.
     3This page is supposed to give a short overview on the available systems from a hardware point of view. All hardware can be reached through a login node via SSH: '''!deep@fz-juelich.de'''.
     4The login node is implemented as virtual machine hosted by the master nodes (in a failover mode).
     5Please, see also information about [wiki:Public/User_Guide/Account getting an account] and using the [wiki:Public/User_Guide/Batch_system batch system].
    46
    57== Rack plan ==
    68
    7 This is a sketch of the available hardware.
     9This is a sketch of the available hardware and a short description of the hardware interesting for the system users (the nodes you can use for running your jobs on or that can be used for testing).
    810
    9 [[Image(Prototype_plus_SSSM_and_SDV_Rackplan_47U--2019-03.png)]]
    10 == Network overview ==
    11 
     11[[Image(Prototype_plus_SSSM_and_SDV_Rackplan_47U--2019-03.png, 50%)]]
    1212
    1313
    … …  
    3535}}}
    3636
    37 == SDV rack ==
     37=== SSSM rack ===
     38
     39This rack hosts the master nodes, files servers and the storage as well network components for the Gigabit Ethernet administration and service networks. Users can access the login node via '''!deep@fz-juelich.de''' (implemented as virtual machine running on the master nodes).
     40
     41=== CM rack ===
     42
     43Contains the hardware of the DEEP-EST Cluster Module including compute nodes, management nodes, network components and liquid cooling unit.
     44
     45* Cluster [50 nodes]: `dp-cn[01-50]`
     46 * 2 Intel Xeon 'Skylake' Gold 6146 (12 cores (24 threads), 3.2GHz)
     47 * 192 GB RAM
     48 * 1 x 400GB NVMe SSD (not exposed to users)
     49 * network: IB EDR (100 Gb/s)
     50
     51=== DAM rack ===
     52
     53This rack will host the nodes of the Data Analytics Module of the DEEP-EST prototype. Currently it contains for test servers:
     54
     55* Prototype DAM [4 nodes]: `protodam[01-04]`
     56 * 2 x Intel Xeon 'Skylake' (26 cores per socket)
     57 * 192 GB RAM
     58
     59=== SDV rack ===
     60
     61Along with the prototype systems serveral test nodes and so called software development vehicles have been installed in the scope of the DEEP(-ER,EST) projects. These are located in the SDV rack. The following components can be accessed by the users:
     62
    3863* Cluster [16 nodes]: `deeper-sdv[01-16]`
    3964 * 2 Intel Xeon 'Haswell' E5-v2680 v3 (2.5 GHz)
    4065 * 128 GB RAM
    41  * 1 NVMe with 400 GB per node
     66 * 1 NVMe with 400 GB per node( accessible through BeeGFS on demand)
    4267 * network: 100 Gb/s Extoll tourmalet
    4368
    44 {{{#!comment
    45 * KNLs:
    46  * 8 KNLs
    47  * 4 with EXTOLL
    48  * 2 with NVMe
    49  * 96 GB per KNL
    50 }}}
     69* KNLs [8 nodes]: `knl[01-08]`
     70 * 1 Intel Xeon Phi (64-68 cores)
     71 * 1 NVMe with 400 GB per node (accessible through BeeGFS on demand)
     72 * 16 GB MCDRAM plus 96 GB RAM per KNL
     73 * network: Gigabit Ethernet
     74
     75* KNMs [2 nodes]: `knm[01-02]`
     76 * 1 Intel Xeon Phi - Knight Mill (72 cores)
     77 * 16 GB MCDRAM plus 96 GB RAM per KNL
     78 * network: Gigabit Ethernet
    5179
    5280* GPU nodes for ML [3 nodes]: `ml-gpu[01-03]`
    … …  
    6290
    6391
     92 
     93== Network overview
    6494
    65 == DAM rack ==
    66 * Prototype DAM [4 nodes]: `protodam[01-04]`
    67  * 2 x Intel Xeon 'Skylake' (26 cores per socket)
    68  * 192 GB RAM
    69  
    70 
    71 
     95Different types of interconnects are in use along with the Gigabit Ethernet connectivity (used for administration and service network) that is available for all the nodes.
     96The following sketch should give a rough overview. Network details will be of particular interest for the storage access.
    7297
    7398