Showing posts with label XSEDE. Show all posts
Showing posts with label XSEDE. Show all posts

Saturday, January 2, 2016

Gordon, foreach doMC network aging run, 1.grid.network.2015Oct/net1


[hongqin@gordon-ln3 1.grid.network.2015Oct]$ cat grid_aging_gordon.pbs 
#!/bin/bash
#PBS -l nodes=1:ppn=8
#PBS -l walltime=12:30:00

module load R

echo hostname
cd /oasis/scratch/hongqin/temp_project/mactower-network-failure-simulation/1.grid.network.2015Oct
pwd

Rscript netwk_aging_sim.v0.1b.R -if1 net1/Degree4N1000_network.csv -if2 net1/Degree4N1000_EssenLookupTb.csv -l1 0.006 -l2 0.0002 -dt 0 -p 0.95 -n 50  -op net1 -od net1 -d 1 -iC 4 -h /oasis/scratch/hongqin/temp_project/mactower-network-failure-simulation/1.grid.network.2015Oct


Rscript netwk_aging_sim.v0.1b.R -if1 net1/Degree4N1000_network.csv -if2 net1/Degree4N1000_EssenLookupTb.csv -l1 0.006 -l2 0.0002 -dt 0 -p 0.89 -n 50  -op net1 -od net1 -d 1 -iC 4 -h /oasis/scratch/hongqin/temp_project/mactower-network-failure-simulation/1.grid.network.2015Oct



[hongqin@gordon-ln3 1.grid.network.2015Oct]$ cat grid_aging_gordon.pbs.e2390416
Loading required package: iterators
Loading required package: parallel
Error in library(GetoptLong) : there is no package called 'GetoptLong'
Execution halted
Loading required package: iterators
Loading required package: parallel
Error in library(GetoptLong) : there is no package called 'GetoptLong'
Execution halted

Try to install GetoptLong 
[hongqin@gordon-ln3 1.grid.network.2015Oct]$ module load R
[hongqin@gordon-ln3 1.grid.network.2015Oct]$ 


5:22pm. I can run the R-foreach-doMC code locally. 
$ Rscript netwk_aging_sim.v0.1b.R -if1 net1/Degree4N1000_network.csv -if2 net1/Degree4N1000_EssenLookupTb.csv -l1 0.006 -l2 0.0002 -dt 0 -p 0.95 -n 50  -op net1 -od net1 -d 1 -iC 4 -h /oasis/scratch/hongqin/temp_project/mactower-network-failure-simulation/1.grid.network.2015Oct

5:30pm qsub grid_aging_gordon.pbs 
Finally worked. 

Try  shell loop 
[hongqin@gordon-ln3 1.grid.network.2015Oct]$ cat grid_aging_loopgordon.pbs 
#!/bin/bash
#PBS -l nodes=1:ppn=8
#PBS -l walltime=12:30:00

module load R

echo hostname
cd /oasis/scratch/hongqin/temp_project/mactower-network-failure-simulation/1.grid.network.2015Oct
pwd

for p in 1.0 0.98 0.95 0.94 0.93 0.92 0.9 0.89 0.88 0.87 0.86 0.85 0.82 0.8 
do
   for LOne in 0.003 0.0035 0.004 0.0045 0.005 0.0055 0.006 0.0065 0.007 0.0075 0.008
   do
      echo "$p $LOne"
      #R --vanilla --slave -f 20151101-net-sim-ginppi.R --args $LOne 0.0002 5 $p 1000
      Rscript netwk_aging_sim.v0.1b.R -if1 net1/Degree4N1000_network.csv -if2 net1/Degree4N1000_EssenLookupTb.csv -l1 $LOne -l2 $LOne/10 -dt 0 -p $p -n 50  -op net1 -od net1 -d 1 -iC 4 -h /oasis/scratch/hongqin/temp_project/mactower-network-failure-simulation/1.grid.network.2015Oct
   done
done

Note: -l2 $LOne/10 DID NOT WORK!


5:57pm
[hongqin@gordon-ln3 1.grid.network.2015Oct]$ qsub grid_aging_loopgordon.pbs 
2390490.gordon-fe2.local
This job ran for 37 minutes much longer than I thought. 



=> modified netwk_aging_sim.v0.1b.R to take default lambda2.

=>by 6:57pm,  modified grid_aging_loopgordon.pbs  for a test run. 

[hongqin@gordon-ln3 1.grid.network.2015Oct]$ cat grid_aging_loopgordon.pbs
#!/bin/bash
#PBS -l nodes=1:ppn=16
#PBS -l walltime=07:00:00:00

module load R

echo hostname
cd /oasis/scratch/hongqin/temp_project/mactower-network-failure-simulation/1.grid.network.2015Oct
pwd

for p in 1.0 0.98 0.95 0.94 0.93 0.92 0.9 0.89 0.88 0.87 0.86 0.85 0.82 0.8 
do
   for LOne in 0.003 0.0035 0.004 0.0045 0.005 0.0055 0.006 0.0065 0.007 0.0075 0.008
   do
      echo "$p $LOne"
      #R --vanilla --slave -f 20151101-net-sim-ginppi.R --args $LOne 0.0002 5 $p 1000
      Rscript netwk_aging_sim.v0.1b.R -if1 net1/Degree4N1000_network.csv -if2 net1/Degree4N1000_EssenLookupTb.csv -l1 $LOne -l2 0 -dt 0 -p $p -n 5000  -op net1 -od net1 -d 1 -iC 16 -h /oasis/scratch/hongqin/temp_project/mactower-network-failure-simulation/1.grid.network.2015Oct
   done
done

7:01pm
[hongqin@gordon-ln3 1.grid.network.2015Oct]$ qsub grid_aging_loopgordon.pbs
2390576.gordon-fe2.local
This job could run for ~450 minutes. Each n.5000 simulation only take about 4 minutes. 


It turns out that this job from 16:05 to 05:43 PST, which is almost 14 hours (840 minutes)  for 157 runs. 






transfer file from byte to greenfield


A new directory
~/crucible/mc48o9p/hqin2/mactower-network-failure-simulation/


Thursday, November 5, 2015

*** bio386, Gordon exercise 20151105Thu

Gordon, file transfer

Procedure to transfer bio386.tar archives from QIN's directory to student directory: 
You can loginto Gordon using ssh or Putty directly
$ ssh username@gordon.sdsc.xsede.org
Then go to your file directory:  
$ cd /oasis/scratch/username/temp_project/
Then copy bio386.tar to your file directory
$  cp /oasis/scratch/hongqin/temp_project/bio386.tar . 
Then 
$ tar xvf bio386.tar 
Then
$ cd Slim-network-aging-bio386-fall-2015
Then 
$ nano -w  20151101-net-sim-ginppi.R
Inside of nano, you should change the username in the following line: 
mydir = '/oasis/scratch/username/temp_project/Slim-network-aging-bio386-fall-2015'
Then control-X save and exit nano
Now, we can need to change the working directory in PBS job script. 
$ nano -w netaging.pbs
Then change username in the following line
 cd /oasis/scratch/hongqin/temp_project/Slim-network-aging-bio386-fall-2015
Then exit and save. 
Then submit the job request
$ qsub netaging.pbs
If this runs, you are one of the first Spelman students to use a Federally funded super-computer. 
To check the status of your computing jobs
$ qstat -u username

Tuesday, October 27, 2015

bio386 20151027Tue

Research topic update.

Gordon login, and Unix shell practice.
Problems:
1. There is a delay for Gordon to update user profiles. Some students cannot log into Gordon after I add them to Gordon.
2. My login attempt to "login.xsdede.org" led to "access denied".



Wednesday, September 16, 2015

*** greenfield, netaging.pbs running results, each run is 6.5 SU

Conclusions: Each run is 8:30pm - 3am = 6.5 hours. 

20140914 8:30pm :: qsub netaging.pbs 

[hqin2@greenfield ms02GINPPI]$ cat netaging.pbs
#!/bin/bash
# Request 15 cores
#PBS -l nodes=1:ppn=15
#  Request 7days  of cpu time
#PBS -l walltime=7:00:00:00

module load R/3.2.1-mkl

echo hostname

pwd
cd /crucible/mc48o9p/hqin2/mactower-network-failure-simulation-master/ms02GINPPI
pwd

numactl -C +0 R --vanilla --slave -f net-aging-sim-20150915.R --args 92 92 0.02 1.0 2000  &
numactl -C +1 R --vanilla --slave -f net-aging-sim-20150915.R --args 93 93 0.02 1.0 2000  &
numactl -C +2 R --vanilla --slave -f net-aging-sim-20150915.R --args 94 94 0.02 1.0 2000  &
numactl -C +3 R --vanilla --slave -f net-aging-sim-20150915.R --args 95 95 0.02 1.0 2000  &
numactl -C +4 R --vanilla --slave -f net-aging-sim-20150915.R --args 96 96 0.02 1.0 2000  &
numactl -C +5 R --vanilla --slave -f net-aging-sim-20150915.R --args 97 97 0.02 1.0 2000  &
numactl -C +6 R --vanilla --slave -f net-aging-sim-20150915.R --args 98 98 0.02 1.0 2000  &
numactl -C +7 R --vanilla --slave -f net-aging-sim-20150915.R --args 99 99 0.02 1.0 2000  &
numactl -C +8 R --vanilla --slave -f net-aging-sim-20150915.R --args 100 100 0.02 1.0 2000  &
numactl -C +9 R --vanilla --slave -f net-aging-sim-20150915.R --args 101 101 0.02 1.0 2000  &
numactl -C +10 R --vanilla --slave -f net-aging-sim-20150915.R --args 102 102 0.02 1.0 2000  &
numactl -C +11 R --vanilla --slave -f net-aging-sim-20150915.R --args 103 103 0.02 1.0 2000  &
numactl -C +12 R --vanilla --slave -f net-aging-sim-20150915.R --args 92 92 0.01 1.0 2000  &


wait



[hqin2@greenfield ms02GINPPI]$ ll -th dipgin.ms02.output/9[2-9]/popages/*2000*
-rw-r--r-- 1 hqin2 mc48o9p 33K Sep 15 02:55 dipgin.ms02.output/96/popages/cutoff.4.p.1.lambda.0.02.popsize.2000.time.2015Sep15_025515.txt
-rw-r--r-- 1 hqin2 mc48o9p 33K Sep 15 02:55 dipgin.ms02.output/95/popages/cutoff.4.p.1.lambda.0.02.popsize.2000.time.2015Sep15_025509.txt
-rw-r--r-- 1 hqin2 mc48o9p 33K Sep 15 02:54 dipgin.ms02.output/98/popages/cutoff.4.p.1.lambda.0.02.popsize.2000.time.2015Sep15_025456.txt
-rw-r--r-- 1 hqin2 mc48o9p 34K Sep 15 02:54 dipgin.ms02.output/97/popages/cutoff.4.p.1.lambda.0.02.popsize.2000.time.2015Sep15_025451.txt
-rw-r--r-- 1 hqin2 mc48o9p 34K Sep 15 02:54 dipgin.ms02.output/94/popages/cutoff.4.p.1.lambda.0.02.popsize.2000.time.2015Sep15_025442.txt
-rw-r--r-- 1 hqin2 mc48o9p 33K Sep 15 02:54 dipgin.ms02.output/99/popages/cutoff.4.p.1.lambda.0.02.popsize.2000.time.2015Sep15_025409.txt
-rw-r--r-- 1 hqin2 mc48o9p 33K Sep 15 02:52 dipgin.ms02.output/92/popages/cutoff.4.p.1.lambda.0.01.popsize.2000.time.2015Sep15_025240.txt
-rw-r--r-- 1 hqin2 mc48o9p 33K Sep 15 02:52 dipgin.ms02.output/93/popages/cutoff.4.p.1.lambda.0.02.popsize.2000.time.2015Sep15_025211.txt
-rw-r--r-- 1 hqin2 mc48o9p 33K Sep 15 02:50 dipgin.ms02.output/92/popages/cutoff.4.p.1.lambda.0.02.popsize.2000.time.2015Sep15_025058.txt

[hqin2@greenfield ms02GINPPI]$ ll -th dipgin.ms02.output/10[234]/popages/*2000*
-rw-r--r-- 1 hqin2 mc48o9p 33K Sep 15 02:54 dipgin.ms02.output/102/popages/cutoff.4.p.1.lambda.0.02.popsize.2000.time.2015Sep15_025438.txt
-rw-r--r-- 1 hqin2 mc48o9p 33K Sep 15 02:53 dipgin.ms02.output/103/popages/cutoff.4.p.1.lambda.0.02.popsize.2000.time.2015Sep15_025353.txt



[hqin2@greenfield ms02GINPPI]$ cat netaging.pbs.o2350 | grep 2000 | grep "1.0"
[1] "101"  "101"  "0.02" "1.0"  "2000"
 "100"  "100"  "0.02" "1.0"  "2000"
[1] "94"   "94"   "0.02" "1.0"  "2000"
[1] "92"   "92"   "0.02" "1.0"  "2000"
 "103"  "0.02" "1.0"  "2000"
 "102"  "0.02" "1.0"  "2000"
 "1.0"  "2000"
[1] "97"   "97"   "0.02" "1.0"  "2000"
 "1.0"  "2000"
[1] "95"   "95"   "0.02" "1.0"  "2000"
[1] "96"   "96"   "0.02" "1.0"  "2000"
 "99"   "99"   "0.02" "1.0"  "2000"
 "92"   "92"   "0.01" "1.0"  "2000"


Monday, September 14, 2015

backup files from crucial to my data directory (in progress)



$ tar cf /arc/users/hqin2/ms02GINPPI.tar ms02GINPPI/ & 
[1] 17265
[hqin2@greenfield mactower-network-failure-simulation-master]$ ps
  PID TTY          TIME CMD
 1519 pts/10   00:00:00 bash
17265 pts/10   00:00:00 tar

17280 pts/10   00:00:00 ps

There some runtime errors during the tar operation. Maybe some simulation jobs were killed prematurely. 
$ tar: ms02GINPPI/dipgin.ms02.output/43/ms02_43.tab: Read error at byte 0, while reading 7680 bytes: Connection timed out
$ tar: ms02GINPPI/dipgin.ms02.output/49/popages/cutoff.4.p.1.lambda.0.02.popsize.2000.time.2014Oct22_043941.txt: Read error at byte 0, while reading 8192 bytes: Connection timed out
$ tar: ms02GINPPI/dipgin.ms02.output/133/ms02_133.tab: Read error at byte 0, while reading 1536 bytes: Connection timed out
$ tar: ms02GINPPI/dipgin.ms02.output/372/ms02_372.tab: Read error at byte 0, while reading 1536 bytes: Connection timed out
tar: ms02GINPPI/dipgin.ms02.output/71/popages/cutoff.4.p.1.lambda.0.02.popsize.2000.time.2015Feb17_113337.txt: Read error at byte 0, while reading 6656 bytes: Connection timed out
tar: ms02GINPPI/dipgin.ms02.output/71/ms02_71.tab: Read error at byte 0, while reading 8704 bytes: Connection timed out
tar: ms02GINPPI/dipgin.ms02.output/645/ms02_645.tab: Read error at byte 0, while reading 6656 bytes: Connection timed out
tar: ms02GINPPI/dipgin.ms02.output/324/ms02_324.tab: Read error at byte 0, while reading 9216 bytes: Connection timed out
tar: ms02GINPPI/dipgin.ms02.output/50/ms02_50.tab: Read error at byte 0, while reading 5632 bytes: Connection timed out
tar: ms02GINPPI/dipgin.ms02.output/68/popages/cutoff.4.p.1.lambda.0.02.popsize.2000.time.2015Feb05_212237.txt: Read error at byte 0, while reading 2048 bytes: Connection timed out
tar: ms02GINPPI/dipgin.ms02.output/86/popages/cutoff.4.p.0.6.lambda.0.02.popsize.2000.time.2015Feb01_021709.txt: Read error at byte 0, while reading 512 bytes: Connection timed out
tar: ms02GINPPI/dipgin.ms02.output/62/popages/cutoff.4.p.0.6.lambda.0.01.popsize.2000.time.2014Dec04_123712.txt: Read error at byte 0, while reading 7168 bytes: Connection timed out
tar: ms02GINPPI/dipgin.ms02.output/528/ms02_528.tab: Read error at byte 0, while reading 512 bytes: Connection timed out
tar: ms02GINPPI/dipgin.ms02.output/7/ms02_7.tab: Read error at byte 0, while reading 8704 bytes: Connection timed out
tar: ms02GINPPI/dipgin.ms02.output/428/ms02_428.tab: Read error at byte 0, while reading 1024 bytes: Connection timed out

tar: ms02GINPPI/dipgin.ms02.output/18/ms02_18.tab: Read error at byte 0, while reading 4096 bytes: Connection timed out








*** parallel runs of net-aging-sim-20150915.R -> net-aging-sim-2015Sep15.R



[hqin2@greenfield ms02GINPPI]$ cat netaging.pbs
#!/bin/bash
# Request 15 cores
#PBS -l nodes=1:ppn=15
#  Request 2:30 minutes of cpu time
#PBS -l walltime=7:00:00:00

module load R/3.2.1-mkl

echo hostname

pwd
cd /crucible/mc48o9p/hqin2/mactower-network-failure-simulation-master/ms02GINPPI
pwd

numactl -C +0 R --vanilla --slave -f net-aging-sim-20150915.R --args 95 95 0.02 1.0 50  &
numactl -C +1 R --vanilla --slave -f net-aging-sim-20150915.R --args 96 96 0.02 1.0 50  &
numactl -C +2 R --vanilla --slave -f net-aging-sim-20150915.R --args 97 97 0.02 1.0 50  &


wait



[hqin2@greenfield ms02GINPPI]$ qstat -u hqin2 -a

greenfield.psc.xsede.org: 
                                                                                  Req'd    Req'd       Elap
Job ID                  Username    Queue    Jobname          SessID  NDS   TSK   Memory   Time    S   Time
----------------------- ----------- -------- ---------------- ------ ----- ------ ------ --------- - ---------
2343.greenfield.psc.xs  hqin2       batch    netaging.pbs      44687     1     15    --  168:00:00 R  00:03:56



[hqin2@greenfield ms02GINPPI]$ ll -t dipgin.ms02.output/9[567]/popages/*0.02*
-rw-r--r-- 1 hqin2 mc48o9p 848 Sep 14 19:26 dipgin.ms02.output/97/popages/cutoff.4.p.1.lambda.0.02.popsize.50.time.2015Sep14_192617.txt
-rw-r--r-- 1 hqin2 mc48o9p 845 Sep 14 19:26 dipgin.ms02.output/95/popages/cutoff.4.p.1.lambda.0.02.popsize.50.time.2015Sep14_192616.txt

-rw-r--r-- 1 hqin2 mc48o9p 846 Sep 14 19:26 dipgin.ms02.output/96/popages/cutoff.4.p.1.lambda.0.02.popsize.50.time.2015Sep14_192613.txt



[hqin2@greenfield ms02GINPPI]$ cat netaging.pbs
#!/bin/bash
# Request 15 cores
#PBS -l nodes=1:ppn=15
#  Request 2:30 minutes of cpu time
#PBS -l walltime=7:00:00:00

module load R/3.2.1-mkl

echo hostname

pwd
cd /crucible/mc48o9p/hqin2/mactower-network-failure-simulation-master/ms02GINPPI
pwd

numactl -C +0 R --vanilla --slave -f net-aging-sim-20150915.R --args 95 95 0.02 1.0 150  &
numactl -C +1 R --vanilla --slave -f net-aging-sim-20150915.R --args 96 96 0.02 1.0 150  &
numactl -C +2 R --vanilla --slave -f net-aging-sim-20150915.R --args 97 97 0.02 1.0 150  &


wait



[hqin2@greenfield ms02GINPPI]$ qstat -u hqin2

greenfield.psc.xsede.org: 
                                                                                  Req'd    Req'd       Elap
Job ID                  Username    Queue    Jobname          SessID  NDS   TSK   Memory   Time    S   Time
----------------------- ----------- -------- ---------------- ------ ----- ------ ------ --------- - ---------

2344.greenfield.psc.xs  hqin2       batch    netaging.pbs      45653     1     15    --  168:00:00 R  00:21:47

[hqin2@greenfield ms02GINPPI]$ qstat
Job ID                    Name             User            Time Use S Queue
------------------------- ---------------- --------------- -------- - -----
2344.greenfield            netaging.pbs     hqin2           01:07:54 R batch 

/*Great. The Elapse time is 21 minutes but my CPU time is 3 times of it. So, I am running job in paralle. */

[hqin2@greenfield ms02GINPPI]$ ll -th dipgin.ms02.output/9[567]/popages/*txt
-rw-r--r-- 1 hqin2 mc48o9p 2.5K Sep 14 20:05 dipgin.ms02.output/95/popages/cutoff.4.p.1.lambda.0.02.popsize.150.time.2015Sep14_200529.txt
-rw-r--r-- 1 hqin2 mc48o9p 2.5K Sep 14 20:05 dipgin.ms02.output/96/popages/cutoff.4.p.1.lambda.0.02.popsize.150.time.2015Sep14_200528.txt
-rw-r--r-- 1 hqin2 mc48o9p 2.5K Sep 14 20:05 dipgin.ms02.output/97/popages/cutoff.4.p.1.lambda.0.02.popsize.150.time.2015Sep14_200527.txt
-rw-r--r-- 1 hqin2 mc48o9p  848 Sep 14 19:26 dipgin.ms02.output/97/popages/cutoff.4.p.1.lambda.0.02.popsize.50.time.2015Sep14_192617.txt
-rw-r--r-- 1 hqin2 mc48o9p  845 Sep 14 19:26 dipgin.ms02.output/95/popages/cutoff.4.p.1.lambda.0.02.popsize.50.time.2015Sep14_192616.txt


-rw-r--r-- 1 hqin2 mc48o9p  846 Sep 14 19:26 dipgin.ms02.output/96/popages/cutoff.4.p.1.lambda.0.02.popsize.50.time.2015Sep14_192613.txt
/*The three popsize.150 files are generated simultaneously. */



*** parallel runs on greenfield, example.R and example.pbs



helen:ms02GINPPI hqin$ cat example.R 
#20150914 testing parallel jobs on greenfield
# R CMD BATCH ./example.R --args 2 35 red
rm(list=ls())

source("lifespan.r")
source("network.r")

#R -f file --args start end
options(echo=TRUE) # if you want see commands in output file
args <- commandArgs(trailingOnly = TRUE)
print(args)
# trailingOnly=TRUE means that only your arguments are returned, check:
# print(commandsArgs(trailingOnly=FALSE))
start = as.integer(args[1]); start; 
end = as.integer(args[2]); end; 
tag = args[3]
  
myhost = 'greenfield'  # 'byte' 'blacklight' 'mactower'
myhost = 'byte'  # 'byte' 'blacklight' 'mactower'
myhost = 'helen'  # 'byte' 'blacklight' 'helen'

mydir = "/crucible/mc48o9p/hqin2/mactower-network-failure-simulation-master/ms02GINPPI"
if (myhost == 'byte') {  mydir = "/Users/hqin/github/mactower-network-failure-simulation/ms02GINPPI"
} else if (myhost == 'helen') { mydir = "/Users/hqin/github/mactower-network-failure-simulation/ms02GINPPI";  
}

print(paste("current dir is:", mydir))
list.files()
getwd()

print(paste("Now setwd"))
setwd(mydir)
list.files()

debug = 0; 
x = start:end 
outfile = paste( tag, start, end, "tab", sep='.')

write.csv( x, outfile, row.names=F)



[hqin2@greenfield ms02GINPPI]$ cat example.pbs
#!/bin/bash
# Request 15 cores
#PBS -l nodes=1:ppn=15
#  Request 1hr of cpu time
#PBS -l walltime=0:00:01:00

module load R/3.2.1-mkl
echo hostname

pwd
cd /crucible/mc48o9p/hqin2/mactower-network-failure-simulation-master/ms02GINPPI
pwd

numactl -C +0 R --vanilla --slave -f ./example.R --args 1 199999 '_zero' &
numactl -C +1 R --vanilla --slave -f ./example.R --args 2 299999 '_one' &
numactl -C +2 R --vanilla --slave -f ./example.R --args 3 399999 '_two' &
numactl -C +3 R --vanilla --slave -f ./example.R --args 4 499999 '_three' &
numactl -C +4 R --vanilla --slave -f ./example.R --args 4 499999 '_four' &
numactl -C +5 R --vanilla --slave -f ./example.R --args 4 499999 '_five' &
numactl -C +6 R --vanilla --slave -f ./example.R --args 4 499999 '_six' &
numactl -C +7 R --vanilla --slave -f ./example.R --args 4 499999 '_seven' &
numactl -C +8 R --vanilla --slave -f ./example.R --args 4 499999 '_eight' &
numactl -C +9 R --vanilla --slave -f ./example.R --args 4 499999 '_nine' &

wait

Monday, September 7, 2015

XSEDE SU Converter



https://www.xsede.org/su-converter

greenfield, netaging simulation test run, 8SU for each file generated with 2000 cells



[hqin2@greenfield ms02GINPPI]$ cat netagingd.pbs 
#!/bin/bash
# Request 15 cores
#PBS -l nodes=1:ppn=15
#  Request 6 days of cpu time
#PBS -l walltime=6:00:00:00

module load R/3.2.1-mkl

echo hostname

pwd
cd /crucible/mc48o9p/hqin2/mactower-network-failure-simulation-master/ms02GINPPI
pwd


R --vanilla --slave -f net-aging-sim-2014Sep7.R

[hqin2@greenfield ms02GINPPI]$ qstat
Job ID                    Name             User            Time Use S Queue
------------------------- ---------------- --------------- -------- - -----
1816.greenfield            newRunNew.job    ismini          132:07:5 R batch          
1985.greenfield            run_idba_ud.bash sczyrba         170:42:1 R batch          
1999.greenfield            netaging.pbs     hqin2           00:00:41 R batch    

1pm. problem. Local run of net-aging-sim-2014Sep7b.R works, but pbs does not.
[hqin2@greenfield ms02GINPPI]$ R -f net-aging-sim-2014Sep7b.R --args 105 106 
by 1:10pm, I removed old files and cleaned up the directory. Everything seems to work now. Perhaps I probably qsub a wrong file. 


[hqin2@greenfield ms02GINPPI]$ cat netagingd.pbs 
#!/bin/bash
# Request 15 cores
#PBS -l nodes=1:ppn=15
#  Request 7days of cpu time
#PBS -l walltime=7:00:00:00

module load R/3.2.1-mkl

echo hostname

pwd
cd /crucible/mc48o9p/hqin2/mactower-network-failure-simulation-master/ms02GINPPI
pwd

numactl -C +0 R --vanilla --slave -f net-aging-sim-2014Sep7b.R --args 90 90
numactl -C +1 R --vanilla --slave -f net-aging-sim-2014Sep7b.R --args 91 91
numactl -C +2 R --vanilla --slave -f net-aging-sim-2014Sep7b.R --args 92 92

[hqin2@greenfield ms02GINPPI]$ qstat 
Job ID                    Name             User            Time Use S Queue
------------------------- ---------------- --------------- -------- - -----
1816.greenfield            newRunNew.job    ismini          137:17:5 R batch          
1985.greenfield            run_idba_ud.bash sczyrba         245:35:3 R batch          
2007.greenfield            netagingc.pbs    hqin2           03:30:22 R batch          
2011.greenfield            netagingd.pbs    hqin2                  0 R batch 


20150915Monday, Note that the three jobs were run in sequential, not in parallel! 

[hqin2@greenfield ms02GINPPI]$ ll -t dipgin.ms02.output/90/popages/
total 142
-rw-r--r-- 1 hqin2 mc48o9p 33803 Sep 10 05:17 cutoff.4.p.1.lambda.0.02.popsize.2000.time.2015Sep10_051711.txt
-rw-r--r-- 1 hqin2 mc48o9p 33790 Sep  9 22:12 cutoff.4.p.0.9.lambda.0.02.popsize.2000.time.2015Sep09_221225.txt
-rw-r--r-- 1 hqin2 mc48o9p 33815 Sep  9 15:04 cutoff.4.p.0.8.lambda.0.02.popsize.2000.time.2015Sep09_150443.txt
-rw-r--r-- 1 hqin2 mc48o9p 33885 Sep  9 07:49 cutoff.4.p.0.7.lambda.0.02.popsize.2000.time.2015Sep09_074906.txt
-rw-r--r-- 1 hqin2 mc48o9p 33802 Sep  8 23:27 cutoff.4.p.1.lambda.0.01.popsize.2000.time.2015Sep08_232736.txt
-rw-r--r-- 1 hqin2 mc48o9p 33779 Sep  8 16:21 cutoff.4.p.0.9.lambda.0.01.popsize.2000.time.2015Sep08_162114.txt
-rw-r--r-- 1 hqin2 mc48o9p 33827 Sep  8 09:15 cutoff.4.p.0.8.lambda.0.01.popsize.2000.time.2015Sep08_091521.txt
-rw-r--r-- 1 hqin2 mc48o9p 33814 Sep  8 02:01 cutoff.4.p.0.7.lambda.0.01.popsize.2000.time.2015Sep08_020109.txt

[hqin2@greenfield ms02GINPPI]$ ll -t dipgin.ms02.output/91/popages/
total 142
-rw-r--r-- 1 hqin2 mc48o9p 33795 Sep 12 17:34 cutoff.4.p.1.lambda.0.02.popsize.2000.time.2015Sep12_173458.txt
-rw-r--r-- 1 hqin2 mc48o9p 33788 Sep 12 10:25 cutoff.4.p.0.9.lambda.0.02.popsize.2000.time.2015Sep12_102544.txt
-rw-r--r-- 1 hqin2 mc48o9p 33840 Sep 12 03:16 cutoff.4.p.0.8.lambda.0.02.popsize.2000.time.2015Sep12_031655.txt
-rw-r--r-- 1 hqin2 mc48o9p 33886 Sep 11 19:57 cutoff.4.p.0.7.lambda.0.02.popsize.2000.time.2015Sep11_195758.txt
-rw-r--r-- 1 hqin2 mc48o9p 33776 Sep 11 11:31 cutoff.4.p.1.lambda.0.01.popsize.2000.time.2015Sep11_113115.txt
-rw-r--r-- 1 hqin2 mc48o9p 33778 Sep 11 04:18 cutoff.4.p.0.9.lambda.0.01.popsize.2000.time.2015Sep11_041814.txt
-rw-r--r-- 1 hqin2 mc48o9p 33778 Sep 10 21:08 cutoff.4.p.0.8.lambda.0.01.popsize.2000.time.2015Sep10_210855.txt
-rw-r--r-- 1 hqin2 mc48o9p 33808 Sep 10 13:51 cutoff.4.p.0.7.lambda.0.01.popsize.2000.time.2015Sep10_135103.txt


[hqin2@greenfield ms02GINPPI]$ ll -t dipgin.ms02.output/92/popages/
total 107
-rw-r--r-- 1 hqin2 mc48o9p 33761 Sep 13 16:43 cutoff.4.p.0.9.lambda.0.01.popsize.2000.time.2015Sep13_164355.txt
-rw-r--r-- 1 hqin2 mc48o9p 33801 Sep 13 09:33 cutoff.4.p.0.8.lambda.0.01.popsize.2000.time.2015Sep13_093348.txt
-rw-r--r-- 1 hqin2 mc48o9p 33822 Sep 13 02:17 cutoff.4.p.0.7.lambda.0.01.popsize.2000.time.2015Sep13_021713.txt


Conclusions: Each run took 7-8 hours for popSize=2000. 




estimate greenfield SU for Gordon




[hqin2@greenfield ms02GINPPI]$ cat ms02.pbs
#!/bin/bash
# Request 15 cores
#PBS -l nodes=1:ppn=15
#  Request 2:30 minutes of cpu time
#PBS -l walltime=02:30:00

module load R/3.2.1-mkl

echo hostname

pwd
cd /crucible/mc48o9p/hqin2/mactower-network-failure-simulation-master/ms02GINPPI
pwd

R --vanilla --slave -f ms02-2015Aug27.R --args 900 999


10:10am






Using  "ls -l", find out that each ms02 network took 3 minutes on greenfield.
100 permutation means 300minutes = 5 SUs.


xsede startup allocation limit



https://portal.xsede.org/allocations-overview#sulimits

Thursday, August 27, 2015

greenfield job run (successful)

[hqin2@greenfield ~]$ cat foo.pbs 
#!/bin/bash
#PBS -l nodes=1:ppn=15
#PBS -l walltime=5:00
#PBS -o test1.out
#PBS -j oe
set echo
echo hostname
module load R/3.2.1-mkl
R --vanilla --slave CMD BATCH ./myR.R



[hqin2@greenfield ms02GINPPI]$ cat ms02.pbs
#!/bin/bash
# Request 15 cores
#PBS -l nodes=1:ppn=15
#  Request 30 minutes of cpu time
#PBS -l walltime=30:00

module load R/3.2.1-mkl

echo hostname

pwd
cd /crucible/mc48o9p/hqin2/mactower-network-failure-simulation-master/ms02GINPPI
pwd


R --vanilla --slave -f ms02-2015June24.R --args 1000 1001




I also updated the path in ms02-2015Aug27.R
Some input files were removed during the transfer and I put them back.












Greenfield, sample pbs job scripts



This  is an example to run a serial job on Greenfield using PBS: 

#!/bin/csh
#  Request 15 cores 
#  Note that this means the job will be allocated 750GB of memory 
#PBS -l nodes=1:ppn=15
#  Request 5 minutes of cpu time
#PBS -l walltime=30:00
#  Combine standard output and error into one file
#PBS -j oe 
set echo
cd $PBS_O_WORKDIR
module load R/3.2.1-mkl
# run my executable
R --vanilla --slave CMD BATCH ./example.R


And here is an example of “packing” several runs in one job,
so that they all run simultaneously. The output files should be all named different:


#!/bin/csh
#  Request 15 cores 
#  Note that this means the job will be allocated 750GB of memory 
#PBS -l nodes=1:ppn=15
#  Request 5 minutes of cpu time
#PBS -l walltime=30:00
#  Combine standard output and error into one file
#PBS -j oe 
set echo
cd $PBS_O_WORKDIR
# Define where /tmp files will be written
 setenv TMPDIR $PBS_O_WORKDIR
module load R/3.2.1-mkl
# run my executable
numactl -C +0 R --vanilla --slave CMD BATCH ./example0.R &
numactl -C +1 R --vanilla --slave CMD BATCH ./example1.R &
numactl -C +2 R --vanilla --slave CMD BATCH ./example2.R &
numactl -C +3 R --vanilla --slave CMD BATCH ./example3.R &
numactl -C +4 R --vanilla --slave CMD BATCH ./example4.R &
numactl -C +5 R --vanilla --slave CMD BATCH ./example5.R &
numactl -C +6 R --vanilla --slave CMD BATCH ./example6.R &
numactl -C +7 R --vanilla --slave CMD BATCH ./example7.R &
numactl -C +8 R --vanilla --slave CMD BATCH ./example8.R &
numactl -C +9 R --vanilla --slave CMD BATCH ./example9.R &
numactl -C +10 R --vanilla --slave CMD BATCH ./example10.R &
numactl -C +11 R --vanilla --slave CMD BATCH ./example11.R &
numactl -C +12 R --vanilla --slave CMD BATCH ./example12.R &
numactl -C +13 R --vanilla --slave CMD BATCH ./example13.R &
numactl -C +14 R --vanilla --slave CMD BATCH ./example14.R &
wait

Wednesday, August 26, 2015

greenfield job run (failed)



temporary storage place:  /crucible/mc48o9p/hqin2

emacs ms02.pbs













10:44am, $qsub ms02.pbs 

Error: 






Testing at $HOME, myR.R 
by 11:15am, I successfully submitted a job to greenfield. 

$ cat foo.pbs
#PBS -l nodes=1:ppn=1
#PBS -l walltime=5:00
#PBS -o test.out
#PBS -j oe
set echo
source /bin/bash
echo hostname
module load R

R -f myR.R















































greenfield, file transfer


xx@login.xsede.org


gsissh greenfield.psc.xsede.org





















Need to use /crucible for file storage
"Your /crucible home directory is  /crucible/group-name/user-name  wheregroup-name is the 7 character name for the PSC group associated with your grant."



$ ls /crucible/mc48o9p/hqin2



This works!















Monday, July 20, 2015

backup $SCRATCH from blacklight to byte

log into blacklight through xsede

hqin2@tg-login1:/brashear/hqin2> ls /arc/users/hqin2

0.ginppi.tar.gz  0.tar  mactower-network-failure-simulation-master.zip
/*I moved these files into a new folder /old */

qin2@tg-login1:/arc/users/hqin2> cd $SCRATCH
hqin2@tg-login1:/brashear/hqin2> pwd

/brashear/hqin
hqin2@tg-login1:/brashear/hqin2> tar cvf mactower-network-failure-simulation-master.20150720.tar mactower-network-failure-simulation-master/ &

cp mactower-network-failure-simulation-master.20150720.tar /arc/users/hqin2/.
/* this seems freezes my terminal. */

On byte:
Byte-2:blacklight hqin$ pwd

/Users/hqin/github/mactower-network-failure-simulation/blacklight
scp "hqin2@data.psc.xsede.org:mactower-network-failure-simulation-master.20150720.tar.gz" .







References:
http://hongqinlab.blogspot.com/2015/06/20150623tue-0624wed-0625thu-blacklight.html

blacklight --> greenfield --> bridges,

Notice email:

PSC is preparing to introduce its next-generation XSEDE-allocated system. Bridges is planned to enter production in January 2016 (see http://psc.edu/bridges). 

Blacklight will be decommissioned on August 15, 2015.

For the transition period, PSC will provide Greenfield, a new resource that, like Blacklight, features large shared memory. We are developing the user guide at http://www.psc.edu/index.php/resources-for-users/computing-resources/greenfield. Note that the content of this document is evolving.

While the computational capacity of Greenfield is less than that of Blacklight, we believe that your project can make good use of Greenfield and prepare you to continue on Bridges. Your accounts on Blacklight will remain active until 11pm EDT on August 15. Any files left on Blacklight’s $SCRATCH filesystem after August 15 will be lost. If you have an allocation on the Data Supercell (DSC), it will remain active for the remainder of your current XSEDE grant. DSC will be accessible from Greenfield and then from Bridges.

If you wish to discuss other options, or if you have any questions, please contact remarks@psc.edu
at your earliest convenience.