Difference between revisions of "Staff Priorities - Scott"

From SCECpedia
Jump to navigationJump to search
Line 1: Line 1:
 
== Yesterday ==
 
== Yesterday ==
*Replied to Nenad
+
*Monitored production runs
*Tagged code in SVN
+
*Fixed runs in error states
*Created monitord database
+
*Deleted and resubmitted held jobs on Titan
*Started Study 15.4
+
*Study 15.4 has 144/336 = 43% sites complete
*Found bad Titan proxy issue, regenerated
 
*Fixed issue with AutoSubmit tool trying to ID number of workflows on each system
 
*Changed size of DirectSynth jobs (wider, longer) to avoid OOM errors and ensure jobs finish in wallclock time
 
  
 
== Today ==
 
== Today ==
*Update technical slides with updated workflow hierarchy and walltime estimates
+
*Monitor production runs
*Check curves during downtime for errors
+
*Fix runs in error states
*Work on Titan batching of GPU jobs
+
*Begin calculations of ERF 36 hypocenters on Stampede
*Update list of sites which need fixing
+
*Respond to Nenad's question
 +
*Respond to Glenn's question
  
 
== Blocked ==
 
== Blocked ==

Revision as of 16:22, 11 May 2015

Yesterday

  • Monitored production runs
  • Fixed runs in error states
  • Deleted and resubmitted held jobs on Titan
  • Study 15.4 has 144/336 = 43% sites complete

Today

  • Monitor production runs
  • Fix runs in error states
  • Begin calculations of ERF 36 hypocenters on Stampede
  • Respond to Nenad's question
  • Respond to Glenn's question

Blocked

  • No

Follow-ups

  • No

Areas of Responsibilities

  • CyberShake
  • Broadband CyberShake
  • Code migration