Skip to content
New issue

Have a question about this project? Sign up for a free GitHub account to open an issue and contact its maintainers and the community.

By clicking “Sign up for GitHub”, you agree to our terms of service and privacy statement. We’ll occasionally send you account related emails.

Already on GitHub? Sign in to your account

HPC: pdsh over mrsh #18849

Merged
merged 2 commits into from
Mar 12, 2024
Merged
Show file tree
Hide file tree
Changes from all commits
Commits
File filter

Filter by extension

Filter by extension

Conversations
Failed to load comments.
Loading
Jump to
Jump to file
Failed to load files.
Loading
Diff view
Diff view
5 changes: 5 additions & 0 deletions tests/hpc/slurm_db.pm
Original file line number Diff line number Diff line change
Expand Up @@ -62,6 +62,11 @@ EOF
## munge must start before other slurm daemons
$self->enable_and_start('munge');
systemctl('is-active munge');

# Install mrsh and mrsh-server to allow t10 basic
zypper_call('in mrsh mrsh-server');
$self->enable_and_start('mrlogind.socket mrshd.socket');

$self->prepare_slurmdb_conf();
record_info("slurmdbd conf", script_output("cat /etc/slurm/slurmdbd.conf"));
$self->enable_and_start("slurmdbd");
Expand Down
29 changes: 28 additions & 1 deletion tests/hpc/slurm_master.pm
Original file line number Diff line number Diff line change
Expand Up @@ -82,6 +82,9 @@ sub run_basic_tests() {
my %test09 = t09_basic();
push(@all_results, \%test09);

my %test10 = t10_basic();
push(@all_results, \%test10);

return @all_results;
}

Expand Down Expand Up @@ -193,7 +196,7 @@ sub t07_basic() {
}

sub t08_basic() {
my $name = 'pdsh-slurm';
my $name = 'pdsh-slurm over ssh';
my $description = 'Basic check of pdsh-slurm over ssh';
my $result = 0;
# $slurm_pkg-munge is installed explicitly since slurm_23_02
Expand Down Expand Up @@ -225,6 +228,26 @@ sub t09_basic() {
return %results;
}

sub t10_basic() {
my $name = 'pdsh-slurm over mrsh';
my $description = 'Basic check of pdsh-slurm over mrsh';
my $result = 0;

my $sinfo_nodeaddr = script_output('sinfo -a --Format=nodeaddr -h');
my $pdsh_nodes = script_output("runuser -l nobody -c 'pdsh -R mrsh -P minor /usr/bin/hostname'");
my @sinfo_nodeaddr = (split ' ', $sinfo_nodeaddr);

foreach my $i (@sinfo_nodeaddr) {
if (index($pdsh_nodes, $i) == -1) {
$result = 1;
last;
}
}

my %results = generate_results($name, $description, $result);
return %results;
}

#############################################
## Accounting tests: for HPC/slurm cluster ##
#############################################
Expand Down Expand Up @@ -466,6 +489,10 @@ sub run ($self) {

$self->enable_and_start('munge');
systemctl('is-active munge');

zypper_call('in mrsh mrsh-server');
$self->enable_and_start('mrlogind.socket mrshd.socket');

barrier_wait('SLURM_SETUP_DBD');

$self->enable_and_start('slurmctld');
Expand Down
4 changes: 4 additions & 0 deletions tests/hpc/slurm_master_backup.pm
Original file line number Diff line number Diff line change
Expand Up @@ -31,6 +31,10 @@ sub run ($self) {
# enable and start munge
$self->enable_and_start('munge');

# Install mrsh and mrsh-server to allow t10 basic
zypper_call('in mrsh mrsh-server');
$self->enable_and_start('mrlogind.socket mrshd.socket');

# enable and start slurmctld
$self->enable_and_start('slurmctld');
systemctl 'status slurmctld';
Expand Down
5 changes: 5 additions & 0 deletions tests/hpc/slurm_master_backup_db.pm
Original file line number Diff line number Diff line change
Expand Up @@ -36,6 +36,11 @@ sub run ($self) {
barrier_wait("SLURM_MASTER_SERVICE_ENABLED");
record_info('slurm conf', script_output('cat /etc/slurm/slurm.conf'));
$self->enable_and_start('munge');

# Install mrsh and mrsh-server to allow t10 basic
zypper_call('in mrsh mrsh-server');
$self->enable_and_start('mrlogind.socket mrshd.socket');

$self->enable_and_start('slurmctld');
systemctl 'status slurmctld';
$self->enable_and_start('slurmd');
Expand Down
4 changes: 4 additions & 0 deletions tests/hpc/slurm_slave.pm
Original file line number Diff line number Diff line change
Expand Up @@ -47,6 +47,10 @@ sub run ($self) {
# enable and start munge
$self->enable_and_start('munge');

# Install mrsh and mrsh-server to allow t10 basic
zypper_call('in mrsh mrsh-server');
$self->enable_and_start('mrlogind.socket mrshd.socket');

# enable and start slurmd
$self->enable_and_start('slurmd');
systemctl 'status slurmd';
Expand Down
Loading