#!/usr/bin/env expect
############################################################################
# Purpose: Timing test for 5000 jobs.
#
# 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) 2012 SchedMD LLC
# Written by Danny Auble <da@schedmd.com>
#
# This file is part of Slurm, a resource management program.
# For details, see <https://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	"9.9"
set exit_code   0
set test_script "./test$test_id.bash"

#   job_blocks  Submit jobs in blocks of this size (job count)
set job_blocks  5000

#   job_cnt     Number of batch jobs to be submitted
set job_cnt     1000

print_header $test_id

if {[test_front_end] || $enable_memory_leak_debug != 0} {
	set job_cnt 2
}

#
# NOTE: test9.9.bash seems to have trouble running out of process IDs when
# more than about 5000 jobs are submitted at one time, so we can execute the
# script multiple times if necessary. A more reliable alternative would be
# to catch the fork() failures and retry.
#
# NOTE: The throughput rate is highly dependent upon configuration
#
proc _submit_jobs { job_name test_file } {
	global exit_code job_blocks job_cnt sbatch test_script

	log_user 0
	for {set jobs_rem $job_cnt} {$jobs_rem > 0} { } {
		if {$jobs_rem > $job_blocks} {
			set submit_cnt $job_blocks
		} else {
			set submit_cnt $jobs_rem
		}
		spawn -nottyinit -nottycopy $test_script $sbatch "/bin/hostname" $job_name $submit_cnt
		expect {
			eof {
				wait
			}
		}
		set jobs_rem [expr $jobs_rem - $job_blocks]
	}
	log_user 1
	if {[wait_for_all_jobs $job_name] != 0} {
		send_user "\nFAILURE: some submitted jobs failed to terminate\n"
		set exit_code 1
	}
}

set time_took [string trim [time {_submit_jobs "test$test_id" "/dev/null"}] " per iteration microseconds"]
set jobs_per_sec [expr $job_cnt * 1000000 / $time_took]
send_user "Ran $job_cnt jobs in $time_took microseconds or $jobs_per_sec jobs per second\n"

if { $exit_code != 0 } {
	exit $exit_code
}

send_user "\nSUCCESS\n"
exit $exit_code