Computer Documentation Wiki

User Tools

Site Tools

Trace:
institute_lorentz:institutelorentz_maris

Differences

This shows you the differences between two versions of the page.

Link to this comparison view

Both sides previous revisionPrevious revision
Next revision		Previous revision
Last revisionBoth sides next revision
institute_lorentz:institutelorentz_maris [2018/09/18 07:03] – [About the cluster] lenocilinstitute_lorentz:institutelorentz_maris [2019/12/16 10:46] – [Maris Cluster] lenocil
Line 1: Line 1:
 ====== Maris Cluster ====== ====== Maris Cluster ======
 +
 +:!: **__As of December 2019__** the maris cluster is being refurbished in both hardware and software. All working nodes will be gradually moved from this cluster to a new one called **xmaris**. Old nodes not suitable for the new computational environment will be left unsupported and eventually trashed away.
 +
 +Access to xmaris has not been granted automatically to all existing maris users. Please contact //support// for any questions.
 +
 +The documentation of xmaris can be found [[institute_lorentz:xmaris|here]].
 +
 +----
 +
  
 ~~NOCACHE~~ ~~NOCACHE~~
Line 30: Line 39:
 ===== About the cluster ===== ===== About the cluster =====
  
-Maris' head node and nodes run the GNU/Linux OS Fedora 27. Currently there are seventy-two (73) nodes available for calculations. The latter are organized in groups according to their specs and configuration as the table below  shows+Maris' head node and nodes run the GNU/Linux OS Fedora 29. The number of nodes available for calculations is subject to change depending on maintenance works that need to be carried out on a regular basis. You are advised to run ''sinfo'' prior to any job submission. The nodes are organized in groups according to their specs and configuration
  
 ^ CPU node(s) ^ Server Type ^ CPU(s) ^ Clock Speed ^ Cores ^ Threads ^ RAM ^ CPU Family ^ ^ CPU node(s) ^ Server Type ^ CPU(s) ^ Clock Speed ^ Cores ^ Threads ^ RAM ^ CPU Family ^
Line 43: Line 52:
 | maris0[69-73] | Dell PowerEdge R815 | 4 x AMD 6376 | 3.2GHz | 64 | 64 | 512 GB | ::: | | maris0[69-73] | Dell PowerEdge R815 | 4 x AMD 6376 | 3.2GHz | 64 | 64 | 512 GB | ::: |
 | maris066 | Dell PowerEdge R815 | 4 x AMD 6376 | 3.2GHz | 64 | 64 | 192 GB | ::: | | maris066 | Dell PowerEdge R815 | 4 x AMD 6376 | 3.2GHz | 64 | 64 | 192 GB | ::: |
-| maris074  | Dell PowerEdge R815 | 4 x AMD 6276 | 3.2GHz | 64 | 64 | 192 GB | ::: |+| <del>maris074</del>  | Dell PowerEdge R815 | 4 x AMD 6276 | 3.2GHz | 64 | 64 | 192 GB | ::: |
 | maris076  | Dell PowerEdge R830 | 4 x Intel Xeon E5-4640 v4 | 2.1GHz | 96 | 96 | 512 GB | INTEL | | maris076  | Dell PowerEdge R830 | 4 x Intel Xeon E5-4640 v4 | 2.1GHz | 96 | 96 | 512 GB | INTEL |
 | maris077  | Dell PowerEdge R830 | 4 x Intel Xeon E5-4640 v4 | 2.1GHz | 96 | 96 | 512 GB | ::: | | maris077  | Dell PowerEdge R830 | 4 x Intel Xeon E5-4640 v4 | 2.1GHz | 96 | 96 | 512 GB | ::: |
Line 56: Line 65:
  
  
-:!: Note that the resources allocatable by slurm might be slightly lower to those in the table above because of the resources necessary to run a node's OS.+:!: The resources allocatable on each node might differ from those in the table above because of the resources necessary to run a node's OS.
  
 The nodes have been configured in a similar way to your workstation to maximize productivity although there are substantial differences worth noting. One of these is the home directory. In order to keep the network traffic at a low rate, the /home directory on the Maris cluster is different from the one of your Lorentz [[institute_lorentz:gnulinux_workstations|GNU/Linux Workstation]]. In order to access the latter from the head node you can use The nodes have been configured in a similar way to your workstation to maximize productivity although there are substantial differences worth noting. One of these is the home directory. In order to keep the network traffic at a low rate, the /home directory on the Maris cluster is different from the one of your Lorentz [[institute_lorentz:gnulinux_workstations|GNU/Linux Workstation]]. In order to access the latter from the head node you can use
Line 88: Line 97:
  
 Please remember that /marisdata is supposed to act as a __temporary__ storage device during your calculations. You are encouraged not to use it as an archive disk. Please remember that /marisdata is supposed to act as a __temporary__ storage device during your calculations. You are encouraged not to use it as an archive disk.
-==== Compilers and libraries ==== 
-We try to minimize the differences between your Lorentz workstation and Maris so you can be as productive as possible. A variety of compilers and libraries are available for you to use in a similar fashion to your workstation. Explore which modules are available by typing ''module avail''. For extra information take also a look at [[linux:compilers|this]] page and read the manual pages: ''man module''. 
  
-==== Running a calculation ====+==== The InfiniBand subcluster ====
  
-All calculations must be executed via slurm. A typical pseudo session would look like+maris078 has an EDR InfiniBand (IB) connector to and SSD storage server to achieve high I/O rates during calculations. The SSD storage server disks are mounted under ''/IBSSD'' and configured as a RAID0 (no redundancy for data!). The protocol used is //[[https://en.wikipedia.org/wiki/ISCSI_Extensions_for_RDMA|iSER]]//. 
 + 
 +<code bash> 
 + df -h /IBSSD/ 
 +Filesystem      Size  Used Avail Use% Mounted on 
 +/dev/sdc        5.1T   89M  4.8T   1% /IBSSD
  
-<code> 
-ssh into novamaris 
-write a slurm batch script in which you request all needed computation resources 
-submit the batch script to slurm for execution 
 </code> </code>
 +==== Compilers and libraries ====
 +We try to minimize the differences between your Lorentz workstation and Maris so you can be as productive as possible. A variety of compilers and libraries are available for you to use in a similar fashion to your workstation. Explore which modules are available by typing ''module avail''. For extra information take also a look at [[linux:compilers|this]] page and read the manual pages: ''man module''.
  
-An overview of maris' slurm configuration is given [[institute_lorentz:institutelorentz_maris_slurm|here]].+If you use MPI, do not forget to use  the ''openmpi-slurm/4.0.0'' module by which you can launch your MPI applications using slurm's ''srun''.
  
-A rough guide to slurm is [[:slurm_tutorial|here]].+==== Running a calculation ==== 
 + 
 +All calculations must be submitted and executed through ''slurm''. A typical pseudo-session would look like 
 + 
 +If this is the first time you use slurm, please have a look at this overview of  [[institute_lorentz:institutelorentz_maris_slurm|maris' slurm configuration]] and this [[:slurm_tutorial|short guide to slurm]] before submitting your calculations for execution.
  
  
Line 113: Line 127:
  
 Further readings: [[https://virtualenv.pypa.io/en/stable/|virtualenv]] and [[https://conda.io/docs/|conda]].  Further readings: [[https://virtualenv.pypa.io/en/stable/|virtualenv]] and [[https://conda.io/docs/|conda]]. 
 +
 +:!: The package manager ''conda'' seems not to perform efficiently on large anaconda environments.
 ===== Help ===== ===== Help =====
 Help with cluster issues can be requested through the [[https://helpdesk.lorentz.leidenuniv.nl|helpdesk]]. It is strongly advised  you discuss your problem also with other Maris users because they might have helpful tips. Here follows a list of Lorentz Institute members that could be consulted for tips Help with cluster issues can be requested through the [[https://helpdesk.lorentz.leidenuniv.nl|helpdesk]]. It is strongly advised  you discuss your problem also with other Maris users because they might have helpful tips. Here follows a list of Lorentz Institute members that could be consulted for tips

Page Tools

Except where otherwise noted, content on this wiki is licensed under the following license: CC Attribution-Share Alike 4.0 International
CC Attribution-Share Alike 4.0 International Donate Powered by PHP Valid HTML5 Valid CSS Driven by DokuWiki