Skip to content

fix: nodes_alloc stats overcount #197

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.

Sign up for GitHub

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

Open
cgetzen wants to merge 1 commit into
base: master
Choose a base branch
from
+34 −2
Open

fix: nodes_alloc stats overcount #197

Show file tree
Hide file tree
Changes from all commits
Commits
Show all changes
1 commit
Select commit
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
33 changes: 31 additions & 2 deletions src/slurmctld/statistics.c
View file
Open in desktop
Original file line number Diff line number Diff line change
Expand Up @@ -244,6 +244,7 @@ extern void reset_stats(int level)

static void _free_job_stats(job_stats_t *j)
{
FREE_NULL_BITMAP(j->node_bitmap);
xfree(j->user_name);
xfree(j->partition);
xfree(j->account);
Expand Down Expand Up @@ -551,10 +552,17 @@ static int _fill_jobs_statistics(void *x, void *arg)
new->memory_alloc =
(j->tres_alloc_cnt ? j->tres_alloc_cnt[TRES_ARRAY_MEM] :
0);
if (j->node_bitmap)
new->node_bitmap = bit_copy(j->node_bitmap);

js->cpus_alloc += new->cpus_alloc;
js->nodes_alloc += new->nodes_alloc;
js->memory_alloc += new->memory_alloc;
if (j->node_bitmap) {
if (!js->node_bitmap)
js->node_bitmap = bit_copy(j->node_bitmap);
else
bit_or(js->node_bitmap, j->node_bitmap);
}
}

/*
Expand Down Expand Up @@ -636,12 +644,26 @@ static void _aggregate_job_to_jobs(jobs_stats_t *s, job_stats_t *j)
if (IS_JOB_RUNNING(j) || IS_JOB_SUSPENDED(j)) {
s->cpus_alloc += j->cpus_alloc;
s->memory_alloc += j->memory_alloc;
s->nodes_alloc += j->nodes_alloc;
if (j->node_bitmap) {
if (!s->node_bitmap)
s->node_bitmap = bit_copy(j->node_bitmap);
else
bit_or(s->node_bitmap, j->node_bitmap);
}
}

s->job_cnt++;
}

static int _finalize_ua_nodes_alloc(void *x, void *arg)
{
ua_stats_t *ua = x;

if (ua->s->node_bitmap)
ua->s->nodes_alloc = bit_set_count(ua->s->node_bitmap);
return SLURM_SUCCESS;
}

static int _get_users_accts(void *x, void *args)
{
users_accts_stats_t *s = args;
Expand Down Expand Up @@ -687,6 +709,9 @@ extern jobs_stats_t *statistics_get_jobs(bool lock)

list_for_each_ro(job_list, _fill_jobs_statistics, s);

if (s->node_bitmap)
s->nodes_alloc = bit_set_count(s->node_bitmap);

if (lock)
unlock_slurmctld(job_read_lock);

Expand Down Expand Up @@ -896,11 +921,15 @@ extern users_accts_stats_t *statistics_get_users_accounts(jobs_stats_t *js)

list_for_each(js->jobs, _get_users_accts, ua);

list_for_each(ua->users, _finalize_ua_nodes_alloc, NULL);
list_for_each(ua->accounts, _finalize_ua_nodes_alloc, NULL);

return ua;
}

extern void statistics_free_jobs(jobs_stats_t *s)
{
FREE_NULL_BITMAP(s->node_bitmap);
FREE_NULL_LIST(s->jobs);
xfree(s);
}
Expand Down
3 changes: 3 additions & 0 deletions src/slurmctld/statistics.h
View file
Open in desktop
Original file line number Diff line number Diff line change
Expand Up @@ -36,6 +36,7 @@
#ifndef _STATISTICS_H
#define _STATISTICS_H

#include "src/common/bitstring.h"
#include "src/slurmctld/slurmctld.h"

typedef struct node_stats {
Expand Down Expand Up @@ -191,6 +192,7 @@ typedef struct job_statistics {
uint16_t max_nodes;
uint64_t memory_alloc;
uint16_t min_nodes;
bitstr_t *node_bitmap;
uint16_t nodes_alloc;
char *partition;
uint32_t state_reason;
Expand All @@ -213,6 +215,7 @@ typedef struct jobs_statistics {
uint32_t job_cnt;
list_t *jobs;
uint64_t memory_alloc;
bitstr_t *node_bitmap;
uint16_t nodes_alloc;
uint32_t node_failed;
uint32_t oom;
Expand Down