DokuWiki

User Tools

Site Tools

Trace:
cluster:130

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
cluster:130 [2014/07/02 19:18] – [Costs] hmeijcluster:130 [2017/10/03 14:07] (current) – hmeij07
Line 3: Line 3:
 **[[cluster:0|Back]]** **[[cluster:0|Back]]**
  
-==== Total Jobs Submitted ====+==== Jobs Pending Historic ====
  
-Just because I keep track =), 2 millionth milestone reached in July 2013.+First some interesting progress graphs from our report to the provost.
  
-{{:cluster:totaljobs.png?800|}}+|  {{:cluster:2006-2014-pending.png|}}  | 
 +|  {{:cluster:cluster_citations_2014.jpg|}}  |
  
-<code> 
-06/01/2007,total,0,0, 
-06/01/2008,total,0,100000, 
-05/01/2009,total,0,200000, 
-03/01/2011,total,0,1000000, 
-11/01/2012,total,0,1500000, 
-07/01/2013,total,0,2000000, 
-06/01/2014,total,0,2320000, 
-</code> 
-==== 2014 Queue Usage ==== 
  
-For other years view: [[cluster:113|2013 Queue Usage]], [[cluster:105|2012 Queue Usage]], [[cluster:101|2011 Queue Usage]] ... +==== Report ====
  
  
-^  2014  ^ +{{:cluster:cluster-support-july2014.pdf|}}
-|    | +
-^  HPC Cluster  ^ +
-|    | +
-|  {{:cluster:grt_totals_2014.png|}}  | +
-|    |+
  
-^  2014  ^ 
-|    | 
-^  HPC Cluster  (Subset, less than 1,000 pending jobs)  ^ 
-|    | 
-|  {{:cluster:grt_totals_2014_subset.png|}}  | 
-|    | 
  
-^  2014  ^ 
-|    | 
-^  HPC Cluster  (mwgpu queue jobs)  ^ 
-|    | 
-|  {{:cluster:grt_totals_2014_mwgpu.png|}}  | 
-|    
  
 +==== Total Jobs Submitted ====
  
 +Just because I keep track =), 2 millionth milestone reached in July 2013.
 +
 +{{:cluster:totaljobs.png?800|}}
 +
 +A picture of our total number of job slots availability and cumulative total of jobs processed.
 +
 +<code>
 +"Date","Type","TSlots","TJobs","CPU Teraflops"
 +06/01/2007,total,240,0,0.7
 +06/01/2008,total,240,100000,0.7
 +05/01/2009,total,240,200000,0.7
 +03/01/2011,total,496,1000000,2.2
 +11/01/2012,total,598,1500000,2.5
 +07/01/2013,total,598,2000000,2.5
 +06/01/2014,total,790,2320000,7.1
 +</code>
 ==== Accounts ==== ==== Accounts ====
  
Line 122: Line 113:
 These options would require sufficiently sized hardware that than logically can be presented as virtual nodes (with virtual CPU, virtual disk and virtual network on board). These options would require sufficiently sized hardware that than logically can be presented as virtual nodes (with virtual CPU, virtual disk and virtual network on board).
  
 +<code>
 +[root@sharptail ~]# for i in `seq 33 45`; do  bhosts -w n$i| grep -v HOST; done
 +HOST_NAME          STATUS       JL/U    MAX  NJOBS    RUN  SSUSP  USUSP    RSV
 +n33                ok                 -     32     20     20      0      0      0
 +n34                ok                 -     32     21     21      0      0      0
 +n35                ok                 -     32     28     28      0      0      0
 +n36                ok                 -     32     28     28      0      0      0
 +n37                ok                 -     32     20     20      0      0      0
 +n38                closed_Adm         -     32     16     16      0      0      0
 +n39                closed_Adm         -     32     20     20      0      0      0
 +n40                ok                 -     32     23     23      0      0      0
 +n41                ok                 -     32     23     23      0      0      0
 +n42                ok                 -     32     28     28      0      0      0
 +n43                ok                 -     32     23     23      0      0      0
 +n44                ok                 -     32     25     25      0      0      0
 +n45                ok                 -     32     23     23      0      0      0
 +
 +[root@sharptail ~]# for i in `seq 33 45`; do  lsload n$i| grep -v HOST; done
 +HOST_NAME       status  r15s   r1m  r15m   ut    pg  ls    it   tmp   swp   mem
 +n33                 ok  23.0  22.3  21.9  50%   0.0   0 2e+08   72G   31G  247G
 +n34                 ok  22.8  22.2  22.1  43%   0.0   0 2e+08   72G   31G  247G
 +n35                 ok  29.8  29.7  29.7  67%   0.0   0 2e+08   72G   31G  246G
 +n36                 ok  29.2  29.1  28.9  74%   0.0   0 2e+08   72G   31G  247G
 +n37                -ok  20.9  20.7  20.6  56%   0.0   0 2e+08   72G   31G  248G
 +n38                -ok  16.0  10.9   4.9  50%   0.0   0 2e+08 9400M   32G  237G
 +n39                -ok  20.4  21.1  22.1  63%   0.0   0 2e+08 9296M   32G  211G
 +n40                 ok  23.0  23.0  22.8  76%   0.0   0 2e+08 9400M   32G  226G
 +n41                 ok  23.0  22.4  22.2  72%   0.0   0 2e+08 9408M   32G  226G
 +n42                 ok  23.3  23.5  23.1  70%   0.0   0 2e+08 9392M   32G  236G
 +n43                 ok  22.8  22.8  22.7  65%   0.0   0 2e+08 9360M   32G  173G
 +n44                 ok  25.1  25.1  25.0  78%   0.0   0 2e+08 9400M   32G  190G
 +n45                 ok  23.0  22.9  22.6  64%   0.0   0 2e+08 9400M   32G  226G
 +</code>
 ==== Costs ==== ==== Costs ====
  
 Here is a rough listing of what costs the HPCC generates and who pays the bill.  Acquisition costs have so far been covered by faculty grants and the Dell hardware/Energy savings project. Here is a rough listing of what costs the HPCC generates and who pays the bill.  Acquisition costs have so far been covered by faculty grants and the Dell hardware/Energy savings project.
 +
 +  * Grants
 +    * First $270K
 +    * Second $270K (first purchase $155K, second purchase $120K)
 +    * Dell replacement $62K
  
   * Recurring   * Recurring
cluster/130.1404328680.txt.gz · Last modified: by hmeij