forked from BSC-RM/slurm_simulator
-
Notifications
You must be signed in to change notification settings - Fork 0
Commit
This commit does not belong to any branch on this repository, and may belong to a fork outside of the repository.
Validate that -D shows the correct state when jobs are requeued.
- Loading branch information
1 parent
1d3e2bc
commit e88e27c
Showing
4 changed files
with
366 additions
and
0 deletions.
There are no files selected for viewing
This file contains bidirectional Unicode text that may be interpreted or compiled differently than what appears below. To review, open the file in an editor that reveals hidden Unicode characters.
Learn more about bidirectional Unicode characters
This file contains bidirectional Unicode text that may be interpreted or compiled differently than what appears below. To review, open the file in an editor that reveals hidden Unicode characters.
Learn more about bidirectional Unicode characters
This file contains bidirectional Unicode text that may be interpreted or compiled differently than what appears below. To review, open the file in an editor that reveals hidden Unicode characters.
Learn more about bidirectional Unicode characters
This file contains bidirectional Unicode text that may be interpreted or compiled differently than what appears below. To review, open the file in an editor that reveals hidden Unicode characters.
Learn more about bidirectional Unicode characters
Original file line number | Diff line number | Diff line change |
---|---|---|
@@ -0,0 +1,363 @@ | ||
#!/usr/bin/expect | ||
############################################################################ | ||
# Purpose: Test of SLURM functionality | ||
# Validate that sacct -D shows correct job steps and states | ||
# when a job is requeued | ||
# | ||
# Output: "TEST: #.#" followed by "SUCCESS" if test was successful, OR | ||
# "FAILURE: ..." otherwise with an explanation of the failure, OR | ||
# anything else indicates a failure mode that must be investigated. | ||
############################################################################ | ||
# Copyright (C) 2014 SchedMD LLC | ||
# Written by Nathan Yee <nyee32@schedmd.com> | ||
# | ||
# This file is part of SLURM, a resource management program. | ||
# For details, see <http://slurm.schedmd.com/>. | ||
# Please also read the included file: DISCLAIMER. | ||
# | ||
# SLURM is free software; you can redistribute it and/or modify it under | ||
# the terms of the GNU General Public License as published by the Free | ||
# Software Foundation; either version 2 of the License, or (at your option) | ||
# any later version. | ||
# | ||
# SLURM is distributed in the hope that it will be useful, but WITHOUT ANY | ||
# WARRANTY; without even the implied warranty of MERCHANTABILITY or FITNESS | ||
# FOR A PARTICULAR PURPOSE. See the GNU General Public License for more | ||
# details. | ||
# | ||
# You should have received a copy of the GNU General Public License along | ||
# with SLURM; if not, write to the Free Software Foundation, Inc. | ||
# 51 Franklin Street, Fifth Floor, Boston, MA 02110-1301 USA. | ||
############################################################################ | ||
source ./globals | ||
|
||
set test_id 12.7 | ||
set exit_code 0 | ||
set job_id 0 | ||
set node "" | ||
set file_in "test$test_id\_sc" | ||
|
||
print_header $test_id | ||
|
||
proc mod_state { state } { | ||
|
||
global scontrol node exit_code | ||
|
||
spawn $scontrol update nodename=$node state=$state | ||
expect { | ||
timeout { | ||
send_user "\nFAILURE: scontrol is not responding\n" | ||
set exit_code 1 | ||
} | ||
eof { | ||
wait | ||
} | ||
} | ||
} | ||
|
||
proc check_step { num } { | ||
|
||
global sacct job_id exit_code | ||
|
||
set steps 0 | ||
spawn $sacct --job=$job_id\.batch -D --noheader --format=jobid%30 | ||
expect { | ||
-re "batch" { | ||
incr steps 1 | ||
exp_continue | ||
} | ||
timeout { | ||
send_user "\nFAILURE: sacct is not responding\n" | ||
set exit_code 1 | ||
} | ||
eof { | ||
wait | ||
} | ||
|
||
} | ||
if {$num != $steps} { | ||
send_user "\nFAILURE: found $steps step(s) when expecting " | ||
send_user "$num steps\n" | ||
set exit_code 1 | ||
} | ||
} | ||
|
||
make_bash_script $file_in "sleep 2" | ||
|
||
# Start a batch job to get a usable node | ||
spawn $sbatch -t1 --exclusive -o/dev/null $file_in | ||
expect { | ||
-re "Submitted batch job ($number)" { | ||
set job_id $expect_out(1,string) | ||
exp_continue | ||
} | ||
timeout { | ||
send_user "\nFAILURE: sbatch is not responding\n" | ||
set exit_code 1 | ||
} | ||
eof { | ||
wait | ||
} | ||
} | ||
|
||
if {$job_id == 0} { | ||
send_user "\nFAILURE: sbatch did not submit job\n" | ||
exit 1 | ||
} | ||
|
||
wait_for_job $job_id RUNNING | ||
|
||
set found 0 | ||
spawn $scontrol show job $job_id | ||
expect { | ||
-re "NodeList=($alpha_numeric_nodelist)" { | ||
set node $expect_out(1,string) | ||
set found 1 | ||
exp_continue | ||
} | ||
timeout { | ||
send_user "\nFAILURE: scontrol is not responding\n" | ||
set exit_code 1 | ||
} | ||
eof { | ||
wait | ||
} | ||
} | ||
|
||
if {$found != 1} { | ||
send_user "\nFAILURE: was not able to get usable node\n" | ||
exit 1 | ||
} | ||
|
||
cancel_job $job_id | ||
|
||
make_bash_script $file_in "sleep 20" | ||
|
||
# Submit job to be requeued | ||
set job_id 0 | ||
spawn $sbatch -N1 -w$node --exclusive -o/dev/null --requeue $file_in | ||
expect { | ||
-re "Submitted batch job ($number)" { | ||
set job_id $expect_out(1,string) | ||
exp_continue | ||
} | ||
timeout { | ||
send_user "\nFAILURE: sbatch is not responding\n" | ||
set exit_code 1 | ||
} | ||
eof { | ||
wait | ||
} | ||
} | ||
|
||
if {$job_id == 0} { | ||
send_user "\nFAILURE: sbatch did not submit job\n" | ||
exit 1 | ||
} | ||
|
||
wait_for_job $job_id RUNNING | ||
|
||
# Set the node that the job is running on to down | ||
mod_state "down" | ||
|
||
# Wait alittle bit for node state to change | ||
sleep 5 | ||
|
||
# Set the node back to resume | ||
mod_state "resume" | ||
|
||
# Check the number of steps | ||
check_step 0 | ||
|
||
# Check the job state | ||
set state_num 0 | ||
spawn $sacct --job=$job_id -D --noheader --format=state | ||
expect { | ||
-re "NODE_FAIL" { | ||
incr state_num 1 | ||
exp_continue | ||
} | ||
-re "PENDING" { | ||
incr state_num 1 | ||
exp_continue | ||
} | ||
timeout { | ||
send_user "\nFAILURE: sacct is not responding\n" | ||
set exit_code 1 | ||
} | ||
eof { | ||
wait | ||
} | ||
} | ||
|
||
if {$state_num != 2} { | ||
send_user "\nFAILURE: jobs state should be NODE_FAIL and PENDING\n" | ||
set exit_code 1 | ||
} | ||
|
||
wait_for_job $job_id RUNNING | ||
|
||
# Check the number of steps after job is running | ||
check_step 0 | ||
|
||
set state_num 0 | ||
spawn $sacct --job=$job_id -D --noheader --format=state | ||
expect { | ||
-re "NODE_FAIL" { | ||
incr state_num 1 | ||
exp_continue | ||
} | ||
-re "RUNNING" { | ||
incr state_num 1 | ||
exp_continue | ||
} | ||
timeout { | ||
send_user "\nFAILURE: sacct is not responding\n" | ||
set exit_code 1 | ||
} | ||
eof { | ||
wait | ||
} | ||
} | ||
|
||
if {$state_num != 2} { | ||
send_user "\nFAILURE: jobs state should be NODE_FAIL and RUNNING\n" | ||
set exit_code 1 | ||
} | ||
|
||
# Requeue the job | ||
spawn $scontrol requeue $job_id | ||
expect { | ||
timeout { | ||
send_user "\nFAILURE: scontrol is not responding\n" | ||
set exit_code 1 | ||
} | ||
eof { | ||
wait | ||
} | ||
} | ||
|
||
# Wait a bit for the job to be requeued then check its state | ||
sleep 5 | ||
|
||
set state_num 0 | ||
spawn $sacct --job=$job_id -D --noheader --format=state | ||
expect { | ||
-re "NODE_FAIL" { | ||
incr state_num 1 | ||
exp_continue | ||
} | ||
-re "REQUEUE" { | ||
incr state_num 1 | ||
exp_continue | ||
} | ||
-re "CANCELLED" { | ||
incr state_num 1 | ||
exp_continue | ||
} | ||
-re "PENDING" { | ||
incr state_num 1 | ||
exp_continue | ||
} | ||
timeout { | ||
send_user "\nFAILURE: sacct is not responding\n" | ||
set exit_code 1 | ||
} | ||
eof { | ||
wait | ||
} | ||
} | ||
|
||
if {$state_num != 4} { | ||
send_user "\nFAILURE: states are not as expected\n" | ||
set exit_code 1 | ||
} | ||
|
||
wait_for_job $job_id RUNNING | ||
|
||
# Check for steps after requeue | ||
check_step 1 | ||
|
||
set state_num 0 | ||
spawn $sacct --job=$job_id -D --noheader --format=state | ||
expect { | ||
-re "NODE_FAIL" { | ||
incr state_num 1 | ||
exp_continue | ||
} | ||
-re "REQUEUE" { | ||
incr state_num 1 | ||
exp_continue | ||
} | ||
-re "CANCELLED" { | ||
incr state_num 1 | ||
exp_continue | ||
} | ||
-re "RUNNING" { | ||
incr state_num 1 | ||
exp_continue | ||
} | ||
timeout { | ||
send_user "\nFAILURE: sacct is not responding\n" | ||
set exit_code 1 | ||
} | ||
eof { | ||
wait | ||
} | ||
} | ||
|
||
if {$state_num != 4} { | ||
send_user "\nFAILURE: states not as expected\n" | ||
set exit_code 1 | ||
} | ||
|
||
wait_for_job $job_id DONE | ||
|
||
# Check steps after job has completed | ||
check_step 2 | ||
|
||
# Check all job states and steps | ||
set state_num 0 | ||
spawn $sacct --job=$job_id -D --noheader --format=state | ||
expect { | ||
-re "NODE_FAIL" { | ||
incr state_num 1 | ||
exp_continue | ||
} | ||
-re "REQUEUE" { | ||
incr state_num 1 | ||
exp_continue | ||
} | ||
-re "CANCELLED" { | ||
incr state_num 1 | ||
exp_continue | ||
} | ||
-re "COMPLETED" { | ||
incr state_num 1 | ||
exp_continue | ||
} | ||
-re "COMPLETED" { | ||
incr state_num 1 | ||
exp_continue | ||
} | ||
timeout { | ||
send_user "\nFAILURE: sacct is not responding\n" | ||
set exit_code 1 | ||
} | ||
eof { | ||
wait | ||
} | ||
} | ||
|
||
if {$state_num != 5} { | ||
send_user "\nFAILURE: job states are not as expected\n" | ||
set exit_code 1 | ||
} | ||
|
||
cancel_job $job_id | ||
|
||
if {$exit_code == 0} { | ||
exec $bin_rm $file_in | ||
send_user "\nSUCCCESS\n" | ||
} | ||
exit $exit_code |