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
0804e545
Commit
0804e545
authored
11 years ago
by
Morris Jette
Browse files
Options
Downloads
Patches
Plain Diff
cray mpmd - Add APID to data structure
parent
61269e2f
No related branches found
No related tags found
No related merge requests found
Changes
2
Hide whitespace changes
Inline
Side-by-side
Showing
2 changed files
src/slurmd/slurmstepd/multi_prog.c
+5
-6
5 additions, 6 deletions
src/slurmd/slurmstepd/multi_prog.c
src/slurmd/slurmstepd/slurmstepd_job.h
+1
-0
1 addition, 0 deletions
src/slurmd/slurmstepd/slurmstepd_job.h
with
6 additions
and
6 deletions
src/slurmd/slurmstepd/multi_prog.c
+
5
−
6
View file @
0804e545
...
@@ -316,6 +316,7 @@ extern void multi_prog_parse(stepd_step_rec_t *job, uint32_t **gtid)
...
@@ -316,6 +316,7 @@ extern void multi_prog_parse(stepd_step_rec_t *job, uint32_t **gtid)
hostlist_t
hl
;
hostlist_t
hl
;
tmp_cmd
=
xmalloc
(
sizeof
(
char
*
)
*
job
->
ntasks
);
tmp_cmd
=
xmalloc
(
sizeof
(
char
*
)
*
job
->
ntasks
);
node_id2nid
=
xmalloc
(
sizeof
(
uint32_t
)
*
job
->
nnodes
);
ranks_node_id
=
xmalloc
(
sizeof
(
uint32_t
)
*
job
->
ntasks
);
ranks_node_id
=
xmalloc
(
sizeof
(
uint32_t
)
*
job
->
ntasks
);
local_data
=
xstrdup
(
job
->
argv
[
1
]);
local_data
=
xstrdup
(
job
->
argv
[
1
]);
while
(
1
)
{
while
(
1
)
{
...
@@ -377,12 +378,6 @@ extern void multi_prog_parse(stepd_step_rec_t *job, uint32_t **gtid)
...
@@ -377,12 +378,6 @@ extern void multi_prog_parse(stepd_step_rec_t *job, uint32_t **gtid)
if
(
total_ranks
!=
job
->
ntasks
)
if
(
total_ranks
!=
job
->
ntasks
)
goto
fail
;
goto
fail
;
#if _DEBUG
info
(
"MPMD NumPEs:%u"
,
job
->
ntasks
);
/* Total rank count */
info
(
"MPMD NumPEsHere:%u"
,
job
->
node_tasks
);
/* Node's rank count */
#endif
node_id2nid
=
xmalloc
(
sizeof
(
uint32_t
)
*
job
->
nnodes
);
if
(
job
->
msg
->
complete_nodelist
&&
if
(
job
->
msg
->
complete_nodelist
&&
((
hl
=
hostlist_create
(
job
->
msg
->
complete_nodelist
))))
{
((
hl
=
hostlist_create
(
job
->
msg
->
complete_nodelist
))))
{
i
=
0
;
i
=
0
;
...
@@ -428,6 +423,7 @@ extern void multi_prog_parse(stepd_step_rec_t *job, uint32_t **gtid)
...
@@ -428,6 +423,7 @@ extern void multi_prog_parse(stepd_step_rec_t *job, uint32_t **gtid)
}
}
job
->
mpmd_set
=
xmalloc
(
sizeof
(
mpmd_set_t
));
job
->
mpmd_set
=
xmalloc
(
sizeof
(
mpmd_set_t
));
job
->
mpmd_set
->
apid
=
SLURM_ID_HASH
(
job
->
jobid
,
job
->
stepid
);
job
->
mpmd_set
->
command
=
xmalloc
(
sizeof
(
char
*
)
*
job
->
ntasks
);
job
->
mpmd_set
->
command
=
xmalloc
(
sizeof
(
char
*
)
*
job
->
ntasks
);
job
->
mpmd_set
->
first_pe
=
xmalloc
(
sizeof
(
int
)
*
job
->
ntasks
);
job
->
mpmd_set
->
first_pe
=
xmalloc
(
sizeof
(
int
)
*
job
->
ntasks
);
job
->
mpmd_set
->
start_pe
=
xmalloc
(
sizeof
(
int
)
*
job
->
ntasks
);
job
->
mpmd_set
->
start_pe
=
xmalloc
(
sizeof
(
int
)
*
job
->
ntasks
);
...
@@ -461,6 +457,9 @@ extern void multi_prog_parse(stepd_step_rec_t *job, uint32_t **gtid)
...
@@ -461,6 +457,9 @@ extern void multi_prog_parse(stepd_step_rec_t *job, uint32_t **gtid)
}
}
}
}
#if _DEBUG
#if _DEBUG
info
(
"MPMD Apid=%"
PRIu64
""
,
job
->
mpmd_set
->
apid
);
info
(
"MPMD NumPEs:%u"
,
job
->
ntasks
);
/* Total rank count */
info
(
"MPMD NumPEsHere:%u"
,
job
->
node_tasks
);
/* Node's rank count */
info
(
"MPMD NumCmds=%d"
,
job
->
mpmd_set
->
num_cmds
);
info
(
"MPMD NumCmds=%d"
,
job
->
mpmd_set
->
num_cmds
);
for
(
i
=
0
;
i
<
job
->
mpmd_set
->
num_cmds
;
i
++
)
{
for
(
i
=
0
;
i
<
job
->
mpmd_set
->
num_cmds
;
i
++
)
{
info
(
"MPMD Command:%s FirstPE: %d StartPE:%d TotalPEs:%d "
,
info
(
"MPMD Command:%s FirstPE: %d StartPE:%d TotalPEs:%d "
,
...
...
This diff is collapsed.
Click to expand it.
src/slurmd/slurmstepd/slurmstepd_job.h
+
1
−
0
View file @
0804e545
...
@@ -113,6 +113,7 @@ typedef struct {
...
@@ -113,6 +113,7 @@ typedef struct {
}
stepd_step_task_info_t
;
}
stepd_step_task_info_t
;
typedef
struct
{
/* MPMD specifications, needed for Cray */
typedef
struct
{
/* MPMD specifications, needed for Cray */
uint64_t
apid
;
/* Application ID */
int
num_cmds
;
/* Number of executables in MPMD set */
int
num_cmds
;
/* Number of executables in MPMD set */
char
**
command
;
/* Array of command name for each executable */
char
**
command
;
/* Array of command name for each executable */
int
*
first_pe
;
/* First rank on this node of each executable,
int
*
first_pe
;
/* First rank on this node of each executable,
...
...
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