Example task list I copied, because I can't add images yet:
| ID | State | Output | E-Level | Times(r/u/s) | Command [run=1/1] |
|---|---|---|---|---|---|
| 0 | finished | /tmp/ts-out.2qvf6Q | 0 | 81453.46/585124.50/32.40 | [inc_mu01_eb02_1]python3 ./setup/run_calc0.py |
I am using task-spooler to queue my simulations and was wondering what the second and third time stand for. I figured that the "r" Time is how long the job ran, but what's curious is that the "u" time is several times longer than that, longer in fact than I have set up that task.
Can anyone tell me, what these stand for? I couldn't find anything about it on the man page. Thanks in advance!
CodePudding user response：
Probably "real", "user", and "system".
"real" is the observable time from the outside, comparable to using a stop watch to measure the time.
"user" and "system" is the actual CPU time spent executing the task. When your system has multiple CPUs or CPU cores, it perform CPU work in parallel, that's why "real" can be lower than "user".
Example: a program that fully utilizes two cores of your CPU, running for 10 seconds. real=10s, user system=20s