DokuWiki

User Tools

Site Tools

Trace:
cluster:92

Differences

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

Link to this comparison view

Both sides previous revision Previous revision
Next revision 		Previous revision
Next revision Both sides next revision
cluster:92 [2010/12/09 16:10]
hmeij 		cluster:92 [2010/12/09 21:06]
hmeij
Line 6: Line 6:
 ===== HP Towards Deployment ===== ===== HP Towards Deployment =====
  
-  * +  * job 100,000 mile stone (and 1,000,000 on swallowtail) 
 + 
 +  * setup scripts to log usage, gather stats 
 + 
 +  * migrate commercial software to greentail?  matlab, stata 
 + 
 +  * buy new intel compilers and cmkl? 
 +   
 +  * set a users meeting 
 + 
 +  * set up rsnapshot 
 + 
 +  * run some test jobs via scheduler, some benchmarks 
 + 
 +  * install Lava (no SGE installed, so lets do this first) 
 + 
 +  * copy /share/apps across 
 +   
 +  * connect filer3's home directories, get a plan together
  
   * n21: missing dimms or bad dimms, open up the blade enclosure.   * n21: missing dimms or bad dimms, open up the blade enclosure.
  
-  * Clean up /root and archive the training session materials.+  * 12/09/10 CMU backup 
 +    * single file backup cmu.conf to /usr/local/backups/cmu
  
-  * Document training session materials.  Done, on itsdoku wiki.+  * 12/09/10 Backup databases (hpsmdb for SIM using postgresql, mysql not installed) 
 +    * not much success, not really needed, can do a rediscover
  
-  * Full backup of local hard disk (/ and /boot).  Done.+  * 12/09/10 Clean up /root and archive the training session materials.
  
   * 12/08/10 Linpack burn in.  Stressing the hardware. Done.  Results can be found here: [[cluster:91|Linpack]]   * 12/08/10 Linpack burn in.  Stressing the hardware. Done.  Results can be found here: [[cluster:91|Linpack]]
 +
 +  * 12/05/10 Document training session materials.  Done, on itsdoku wiki.
 +
 +  * 12/03/10 Full backup of local hard disk (/ and /boot).  Done.
  
   * 12/03/10 David Holton arrives for training.  Part of "resource for a week".  Replaced a disk that was already flagged as "predictive failure".  Biggest change in cluster configuration is how the MSA60 volumes were set up.  We destroyed all that and rearranged three volumes across the scsi cables (that is vertical versus horizontal) and applied LVM on top.   * 12/03/10 David Holton arrives for training.  Part of "resource for a week".  Replaced a disk that was already flagged as "predictive failure".  Biggest change in cluster configuration is how the MSA60 volumes were set up.  We destroyed all that and rearranged three volumes across the scsi cables (that is vertical versus horizontal) and applied LVM on top.
cluster/92.txt · Last modified: 2011/03/30 15:59 by hmeij

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