Condor tutorial for Condor Boot Camp
Submitting your first Condor job
First you need a job
Before you can submit a job to Condor, you need a job. We will quickly write a small program in C. If you aren't an expert C program, fear not. We will hold your hand throughout this process.
First, create a file called simple.c using your favorite editor. Put it anywhere you like in your home directory. In that file, put the following text. Copy and paste is a good choice:
% mkdir ~/condor-test
% cd ~/condor-test
% cat > simple.c
#include <stdio.h>
main(int argc, char **argv)
{
int sleep_time;
int input;
int failure;
if (argc != 3) {
printf("Usage: simple <sleep-time> <integer>\n");
failure = 1;
} else {
sleep_time = atoi(argv[1]);
input = atoi(argv[2]);
printf("Thinking really hard for %d seconds...\n", sleep_time);
sleep(sleep_time);
printf("We calculated: %d\n", input * 2);
failure = 0;
}
return failure;
}
type control-d here
Now compile that program:
% gcc -o simple simple.c % ls -lh simple -rwxr-x--- 1 train99 train99 4.9K Mar 15 16:24 simple*
Finally, run the program and tell it to sleep for four seconds and calculate 10 * 2:
% ./simple 4 10 Thinking really hard for 4 seconds... We calculated: 20
Great! You have a job you can tell Condor to run! Although it clearly isn't an interesting job, it models some of the aspects of a real scientific program. It takes a while to run and it does a calculation.
Submitting your job
Now that you have a job, you just have to tell Condor to run it. Put the following text into a file called submit:
Universe = vanilla Executable = simple Arguments = 4 10 Log = simple.log Output = simple.out Error = simple.error Queue
Let's examine each of these lines:
- Universe: The vanilla universe means a plain old job. Later on, we'll encounter some special universes.
- Executable: The name of your program
- Arguments: These are the arguments you want. They will be the same arguments we typed above.
- Log: This is the name of a file where Condor will record information about your job's execution. While it's not required, it is a really good idea to have a log.
- Output: Where Condor should put the standard output from your job.
- Error: Where Condor should put the standard error from your job. Our job isn't likely to have any, but we'll put it there to be safe.
Next, tell Condor to run your job:
% condor_submit submit Submitting job(s)con. Logging submit event(s). 1 job(s) submitted to cluster 6075.
Now, watch your job run:
% condor_q
-- Submitter: tg-login64.rcac.purdue.edu : <128.211.143.238:34353>
: tg-login64.rcac.purdue.edu
ID OWNER SUBMITTED RUN_TIME ST PRI SIZE CMD
2.0 train99 3/15 16:27 0+00:00:00 I 0 0.0 simple 4 10
1 jobs; 1 idle, 0 running, 0 held
% condor_q
-- Submitter: tg-login64.rcac.purdue.edu : <128.211.143.238:34353>
: tg-login64.rcac.purdue.edu
ID OWNER SUBMITTED RUN_TIME ST PRI SIZE CMD
2.0 train99 3/15 16:27 0+00:00:01 R 0 0.0 simple 4 10
1 jobs; 0 idle, 1 running, 0 held
% condor_q
-- Submitter: tg-login64.rcac.purdue.edu : <128.211.143.238:34353>
: tg-login64.rcac.purdue.edu
ID OWNER SUBMITTED RUN_TIME ST PRI SIZE CMD
0 jobs; 0 idle, 0 running, 0 held
Notice a few things here. In a real pool, when you do condor_q, you might get a long list of everyone's jobs. So you can tell condor_q to just list you jobs with the -sub option, which is short for submitter, as in:
% condor_q -sub royFor this tutorial, there is probably only one person per computer, so it probably isn't necessary. When my job was done, it was no longer listed. Because I told Condor to log information about my job, I can see what happened:
% cat simple.log
000 (002.000.000) 03/15 16:27:22 Job submitted from
host: <128.211.143.238:34353>
...
001 (002.000.000) 03/15 16:27:25 Job executing on
host: <128.211.143.238:33085>
...
005 (002.000.000) 03/15 16:27:29 Job terminated.
(1) Normal termination (return value 0)
Usr 0 00:00:00, Sys 0 00:00:00 - Run Remote Usage
Usr 0 00:00:00, Sys 0 00:00:00 - Run Local Usage
Usr 0 00:00:00, Sys 0 00:00:00 - Total Remote Usage
Usr 0 00:00:00, Sys 0 00:00:00 - Total Local Usage
0 - Run Bytes Sent By Job
0 - Run Bytes Received By Job
0 - Total Bytes Sent By Job
0 - Total Bytes Received By Job
...
That looks good: It took a few seconds for the job to start up, though you will often see slightly slower startups. Condor doesn't optimize for fast job startup, but for high throughput, The job ran for about four seconds. But did our job execute correctly? If this had been a real Condor pool, the execution computer would have been different than the submit computer, but otherwise it would have looked the same.
% cat simple.out Thinking really hard for 4 seconds... We calculated: 20
Excellent! We ran our sophisticated scientific job on a Condor pool!
Doing a parameter sweep
If you only ever had to run a single job, you probably wouldn't need Condor. But we would like to have our program calculate a whole set of values for different inputs. How can we do that? Let's change our submit file to look like this:
Universe = vanilla Executable = simple Arguments = 4 10 Log = simple.log Output = simple.$(Process).out Error = simple.$(Process).error Queue Arguments = 4 11 Queue Arguments = 4 12 Queue
There are two important differences to notice here. First, the Output and Error lines have the $(Process) macro in them. This means that the output and error files will be named according to the process number of the job. You'll see what this looks like in a moment. Second, we told Condor to run the same job an extra two times by adding extra Arguments and Queue statements. We are doing a parameter sweep on the values 10, 11, and 12. Let's see what happens:
% condor_submit submit
Submitting job(s)...
Logging submit event(s)...
3 job(s) submitted to cluster 2.
% condor_q
-- Submitter: roy@tg-login64.rcac.purdue.edu : <128.211.143.238:32787>
: tg-login64.rcac.purdue.edu
ID OWNER SUBMITTED RUN_TIME ST PRI SIZE CMD
2.0 roy 1/25 12:28 0+00:00:00 R 0 0.0 simple 4 10
2.1 roy 1/25 12:28 0+00:00:00 R 0 0.0 simple 4 11
2.2 roy 1/25 12:28 0+00:00:00 R 0 0.0 simple 4 12
3 jobs; 0 idle, 3 running, 0 held
% condor_q
-- Submitter: roy@tg-login64.rcac.purdue.edu : <128.211.143.238:32787>
: tg-login64.rcac.purdue.edu
ID OWNER SUBMITTED RUN_TIME ST PRI SIZE CMD
0 jobs; 0 idle, 0 running, 0 held
% ls simple*out
simple.0.out simple.1.out simple.2.out simple.out
% cat simple.0.out
Thinking really hard for 4 seconds...
We calculated: 20
% cat simple.1.out
Thinking really hard for 4 seconds...
We calculated: 22
% cat simple.2.out
Thinking really hard for 4 seconds...
We calculated: 24
Notice that we had three jobs with the same cluster number, but
different process numbers. They have the same cluster number because
they were all submitted from the same submit file. When the jobs ran,
they created three different output files, each with the desired
output.
You are now ready to submit lots of jobs! Although this example was simple, Condor has many, many options so you can get a wide variety of behaviors. You can find many of these if you look at the documentation for condor_submit.
- Copy the Windows version of simple.exe and cygwin1.dll to your submit machine, and adjust your Requirements such that the job will run on Windows. You'll need to use file transfer to send the executable and cygwin1.dll to the Windows machines, and bring back your output.
- How can you submit to either Windows or Linux using the same submit file?
- What if you want the cluster number to be part of the output filename?
- Condor sends you email when a job finishes. How can you control this?
- Make another scientific program that takes it input from a file. Now submit 3 copies of this program where each input file is in a separate directory. Use the initialdir option described in the lecture, or in the manual.
- Bonus points: You know that your job should never run for more than four hours. If it does, then the job should be killed because there is a problem. How can you tell Condor to do this for you?
