Skip to content
Snippets Groups Projects
Commit 0e147eb8 authored by Moe Jette's avatar Moe Jette
Browse files

Add some more error checking.

parent ac864b8a
No related branches found
No related tags found
No related merge requests found
...@@ -41,12 +41,20 @@ if { [test_xcpu] } { ...@@ -41,12 +41,20 @@ if { [test_xcpu] } {
exit 0 exit 0
} }
# NOTE: One CPU per task emulation is not scalable to do via srun
# so we use "--share" as a no-op for this argument
if { [test_bluegene] } {
set srun_opts "--share"
} else {
set srun_opts "-c1"
}
# #
# Spawn a srun immediate jobs with ever larger node counts # Spawn a srun immediate jobs with ever larger node counts
# #
set timeout 60 set timeout $max_job_delay
for {set node_cnt 1} {$node_cnt > 0} {set node_cnt [expr $node_cnt * 2]} { for {set node_cnt 1} {$node_cnt > 0} {set node_cnt [expr $node_cnt * 2]} {
spawn $srun --immediate -N$node_cnt -c1 -t2 $bin_hostname spawn $srun --immediate -N$node_cnt $srun_opts -t2 $bin_hostname
expect { expect {
-re "Immediate execution impossible" { -re "Immediate execution impossible" {
send_user "This error is expected, no worries\n" send_user "This error is expected, no worries\n"
...@@ -63,6 +71,11 @@ for {set node_cnt 1} {$node_cnt > 0} {set node_cnt [expr $node_cnt * 2]} { ...@@ -63,6 +71,11 @@ for {set node_cnt 1} {$node_cnt > 0} {set node_cnt [expr $node_cnt * 2]} {
set node_cnt 0 set node_cnt 0
exp_continue exp_continue
} }
-re "error" {
send_user "\nFAILURE: some error happened\n"
set exit_code 1
exp_continue
}
timeout { timeout {
send_user "\nFAILURE: srun not responding\n" send_user "\nFAILURE: srun not responding\n"
set exit_code 1 set exit_code 1
......
0% Loading or .
You are about to add 0 people to the discussion. Proceed with caution.
Finish editing this message first!
Please register or to comment