Skip to content
GitLab
Explore
Sign in
Primary navigation
Search or go to…
Project
S
Slurm
Manage
Activity
Members
Labels
Plan
Issues
Issue boards
Milestones
Code
Merge requests
Repository
Branches
Commits
Tags
Repository graph
Compare revisions
Snippets
Build
Pipelines
Jobs
Pipeline schedules
Artifacts
Deploy
Releases
Package Registry
Model registry
Operate
Environments
Terraform modules
Monitor
Incidents
Service Desk
Analyze
Value stream analytics
Contributor analytics
CI/CD analytics
Repository analytics
Model experiments
Help
Help
Support
GitLab documentation
Compare GitLab plans
Community forum
Contribute to GitLab
Provide feedback
Terms and privacy
Keyboard shortcuts
?
Snippets
Groups
Projects
Show more breadcrumbs
tud-zih-energy
Slurm
Commits
0154fb34
Commit
0154fb34
authored
18 years ago
by
Moe Jette
Browse files
Options
Downloads
Patches
Plain Diff
Don't try to recover cons_res state data on slurmctld -c (cold start).
parent
a05519c2
No related branches found
No related tags found
No related merge requests found
Changes
3
Hide whitespace changes
Inline
Side-by-side
Showing
3 changed files
NEWS
+2
-0
2 additions, 0 deletions
NEWS
src/plugins/select/cons_res/select_cons_res.c
+4
-0
4 additions, 0 deletions
src/plugins/select/cons_res/select_cons_res.c
src/slurmctld/controller.c
+11
-4
11 additions, 4 deletions
src/slurmctld/controller.c
with
17 additions
and
4 deletions
NEWS
+
2
−
0
View file @
0154fb34
...
@@ -16,6 +16,8 @@ documents those changes that are of interest to users and admins.
...
@@ -16,6 +16,8 @@ documents those changes that are of interest to users and admins.
info for jobs changed.
info for jobs changed.
-- BLUEGENE - Changed logic for wiring bgl blocks to be more maintainable.
-- BLUEGENE - Changed logic for wiring bgl blocks to be more maintainable.
(Haven't tested on large system yet, works on 2 base partition system)
(Haven't tested on large system yet, works on 2 base partition system)
-- Do not read the select/cons_res state save file if slurmctld is
cold-started (with the "-c" option).
* Changes in SLURM 1.2.0-pre6
* Changes in SLURM 1.2.0-pre6
=============================
=============================
...
...
This diff is collapsed.
Click to expand it.
src/plugins/select/cons_res/select_cons_res.c
+
4
−
0
View file @
0154fb34
...
@@ -1139,6 +1139,10 @@ extern int select_p_state_restore(char *dir_name)
...
@@ -1139,6 +1139,10 @@ extern int select_p_state_restore(char *dir_name)
info
(
"cons_res: select_p_state_restore"
);
info
(
"cons_res: select_p_state_restore"
);
if
(
!
dir_name
)
{
error
(
"Starting cons_res with clean slate"
);
return
SLURM_SUCCESS
;
}
file_name
=
xstrdup
(
dir_name
);
file_name
=
xstrdup
(
dir_name
);
xstrcat
(
file_name
,
"/cons_res_state"
);
xstrcat
(
file_name
,
"/cons_res_state"
);
state_fd
=
open
(
file_name
,
O_RDONLY
);
state_fd
=
open
(
file_name
,
O_RDONLY
);
...
...
This diff is collapsed.
Click to expand it.
src/slurmctld/controller.c
+
11
−
4
View file @
0154fb34
...
@@ -255,8 +255,8 @@ int main(int argc, char *argv[])
...
@@ -255,8 +255,8 @@ int main(int argc, char *argv[])
if
(
checkpoint_init
(
slurmctld_conf
.
checkpoint_type
)
!=
if
(
checkpoint_init
(
slurmctld_conf
.
checkpoint_type
)
!=
SLURM_SUCCESS
)
SLURM_SUCCESS
)
fatal
(
"failed to initialize checkpoint plugin"
);
fatal
(
"failed to initialize checkpoint plugin"
);
if
(
s
elect_g_state_restore
(
slurmctld_conf
.
state_save_location
)
)
if
(
s
lurm_select_init
()
!=
SLURM_SUCCESS
)
fatal
(
"failed to
restor
e node selection plugin state"
);
fatal
(
"failed to
initializ
e node selection plugin state"
);
while
(
1
)
{
while
(
1
)
{
/* initialization for each primary<->backup switch */
/* initialization for each primary<->backup switch */
...
@@ -290,12 +290,18 @@ int main(int argc, char *argv[])
...
@@ -290,12 +290,18 @@ int main(int argc, char *argv[])
info
(
"Running as primary controller"
);
info
(
"Running as primary controller"
);
/* Recover node scheduler state info */
/* Recover node scheduler state info */
if
(
select_g_state_restore
(
slurmctld_conf
.
state_save_location
)
if
(
recover
)
{
!=
SLURM_SUCCESS
)
{
error_code
=
select_g_state_restore
(
slurmctld_conf
.
state_save_location
);
}
else
{
error_code
=
select_g_state_restore
(
NULL
);
}
if
(
error_code
!=
SLURM_SUCCESS
)
{
error
(
"failed to restore node selection state"
);
error
(
"failed to restore node selection state"
);
abort
();
abort
();
}
}
/*
/*
* create attached thread to process RPCs
* create attached thread to process RPCs
*/
*/
...
@@ -342,6 +348,7 @@ int main(int argc, char *argv[])
...
@@ -342,6 +348,7 @@ int main(int argc, char *argv[])
switch_save
(
slurmctld_conf
.
state_save_location
);
switch_save
(
slurmctld_conf
.
state_save_location
);
if
(
slurmctld_config
.
resume_backup
==
false
)
if
(
slurmctld_config
.
resume_backup
==
false
)
break
;
break
;
recover
=
2
;
}
}
/* Since pidfile is created as user root (its owner is
/* Since pidfile is created as user root (its owner is
...
...
This diff is collapsed.
Click to expand it.
Preview
0%
Loading
Try again
or
attach a new file
.
Cancel
You are about to add
0
people
to the discussion. Proceed with caution.
Finish editing this message first!
Save comment
Cancel
Please
register
or
sign in
to comment