| 
  • If you are citizen of an European Union member nation, you may not use this service unless you are at least 16 years old.

  • Stop wasting time looking for files and revisions. Connect your Gmail, DriveDropbox, and Slack accounts and in less than 2 minutes, Dokkio will automatically organize all your file attachments. Learn more and claim your free account.

View
 

FrontPage

This version was saved 14 years, 11 months ago View current version     Page history
Saved by PBworks
on August 21, 2005 at 11:43:08 am
 

The password is mpiblast

 

Feel free to edit this page by asking more questions, adding new insight, or restructuring what is here.

If you want to contact the admin, email cariaso at yahoo. Password change requests will be denied.

 

 

Tips for

RestrictiveFirewallsAndSourceForge

BuildMPIBlastFromSource

 

 

Currently I'm persuing a bug blasting variola. See the full discussion on this bug.

 

 

debug from

Master 61k .gz

Worker1 (Scheduler) 1k .gz

Worker2 1k .gz

Worker3 1k .gz

Worker4 1k .gz

Worker5 58k .gz

 

 

 

Typical 'top' from Master:

top - 11:46:03 up 2 days,  2:05,  1 user,  load average: 1.35, 1.33, 1.28
Tasks: 177 total,   1 running, 176 sleeping,   0 stopped,   0 zombie
Cpu(s):     0.0% user,    3.3% system,      0.0% nice,        96.7% idle
Mem:   1032988k total,  1018652k used,    14336k free,      504k buffers
Swap:  1967952k total,  1062416k used,   905536k free,     3856k cached

  PID USER      PR  NI  VIRT  RES  SHR S %CPU %MEM    TIME+  COMMAND                                                                                                  
    7 root      15   0     0    0    0 S  7.7  0.0  34:28.51 kswapd                                                                                          31120 figur     15   0  1140 1096  852 R  3.8  0.1   0:00.75 top                                                                                             30497 figur     11   0 1907m 924m  268 D  1.6 91.7   1569:36 mpiblast                                                                                            
    1 root       9   0   128   96   72 S  0.0  0.0   0:01.75 init

 

 

Unequal work Distribution

Lucas, I've run a command:

grep 'Giving' logfile cut d 'G' -f 2 sort uniq -c sort -n

On the debug from the scheduler for several variola runs.

T5_1 is 1x10k

T5_2 is 2x10k

T5_10 is 10x10k

The logs show that work is not being handed out equally.

Perhaps this relates to the other issue? perhaps its independednt?

 

T5_1
      1 iving 2 assignment 2 on frag 0
      1 iving 2 assignment 2 on frag 6
      1 iving 2 assignment 2 on frag 7
      1 iving 2 assignment 3 on frag 0
      1 iving 3 assignment 2 on frag 1
      1 iving 3 assignment 2 on frag 5
      1 iving 3 assignment 3 on frag 0
      1 iving 3 assignment 4 on frag 0
      1 iving 4 assignment 2 on frag 2
      1 iving 4 assignment 2 on frag 3
      1 iving 4 assignment 3 on frag 0
      1 iving 5 assignment 2 on frag 4
      1 iving 5 assignment 3 on frag 0
     17 iving 5 assignment 4 on frag 0                  

T5_2
      1 iving 2 assignment 3 on frag 0
      1 iving 3 assignment 3 on frag 0
      1 iving 4 assignment 3 on frag 0
      1 iving 5 assignment 3 on frag 0
      2 iving 2 assignment 2 on frag 0
      2 iving 2 assignment 2 on frag 6
      2 iving 2 assignment 2 on frag 7
      2 iving 3 assignment 2 on frag 1
      2 iving 3 assignment 2 on frag 5
      2 iving 4 assignment 2 on frag 2
      2 iving 4 assignment 2 on frag 3
      2 iving 5 assignment 2 on frag 4
    243 iving 3 assignment 4 on frag 0
    318 iving 5 assignment 4 on frag 0
   5220 iving 4 assignment 4 on frag 0       

T5_3
      1 iving 2 assignment 3 on frag 0
      1 iving 3 assignment 3 on frag 0
      1 iving 4 assignment 3 on frag 0
      1 iving 5 assignment 3 on frag 0
      3 iving 2 assignment 2 on frag 0
      3 iving 2 assignment 2 on frag 6
      3 iving 2 assignment 2 on frag 7
      3 iving 3 assignment 2 on frag 1
      3 iving 3 assignment 2 on frag 5
      3 iving 4 assignment 2 on frag 2
      3 iving 4 assignment 2 on frag 3
      3 iving 5 assignment 2 on frag 4
     20 iving 5 assignment 4 on frag 0
   4855 iving 4 assignment 4 on frag 0
   5701 iving 2 assignment 4 on frag 0       

T5_5
      1 iving 2 assignment 3 on frag 0
      1 iving 3 assignment 3 on frag 0
      1 iving 4 assignment 3 on frag 0
      1 iving 5 assignment 3 on frag 0
      5 iving 2 assignment 2 on frag 0
      5 iving 2 assignment 2 on frag 6
      5 iving 2 assignment 2 on frag 7
      5 iving 3 assignment 2 on frag 1
      5 iving 3 assignment 2 on frag 5
      5 iving 4 assignment 2 on frag 2
      5 iving 4 assignment 2 on frag 3
      5 iving 5 assignment 2 on frag 4
    399 iving 3 assignment 4 on frag 0
    489 iving 5 assignment 4 on frag 0
   5468 iving 4 assignment 4 on frag 0      

T5_10
      1 iving 2 assignment 3 on frag 0
      1 iving 3 assignment 3 on frag 0
      1 iving 4 assignment 3 on frag 0
      1 iving 5 assignment 3 on frag 0
     10 iving 2 assignment 2 on frag 0
     10 iving 2 assignment 2 on frag 6
     10 iving 2 assignment 2 on frag 7
     10 iving 3 assignment 2 on frag 1
     10 iving 3 assignment 2 on frag 5
     10 iving 4 assignment 2 on frag 2
     10 iving 4 assignment 2 on frag 3
     10 iving 5 assignment 2 on frag 4
    177 iving 5 assignment 4 on frag 0
   5066 iving 4 assignment 4 on frag 0
   5614 iving 2 assignment 4 on frag 0        

T5_15
      1 iving 2 assignment 3 on frag 0
      1 iving 3 assignment 3 on frag 0
      1 iving 4 assignment 3 on frag 0
      1 iving 5 assignment 3 on frag 0
     15 iving 2 assignment 2 on frag 0
     15 iving 2 assignment 2 on frag 6
     15 iving 2 assignment 2 on frag 7
     15 iving 3 assignment 2 on frag 1
     15 iving 3 assignment 2 on frag 5
     15 iving 4 assignment 2 on frag 2
     15 iving 4 assignment 2 on frag 3
     15 iving 5 assignment 2 on frag 4
    233 iving 5 assignment 4 on frag 0
   4960 iving 4 assignment 4 on frag 0
   5480 iving 2 assignment 4 on frag 0

Comments (0)

You don't have permission to comment on this page.