From a9156dfd10b0b352e7cfb91bd42f885f813bbddf Mon Sep 17 00:00:00 2001
From: Morris Jette <jette@schedmd.com>
Date: Mon, 23 Apr 2012 14:50:57 -0700
Subject: [PATCH] Log duplicate node and partition names in slurm.conf
If a node or partition name is duplicated in slurm.conf, then log
it using error() and ignore the duplicate record. Update documentation
to be more clear
---
doc/man/man5/slurm.conf.5 | 4 ++++
src/common/node_conf.c | 2 +-
src/slurmctld/read_config.c | 12 +++++++-----
3 files changed, 12 insertions(+), 6 deletions(-)
diff --git a/doc/man/man5/slurm.conf.5 b/doc/man/man5/slurm.conf.5
index 03c05b879ae..d627e2d426b 100644
--- a/doc/man/man5/slurm.conf.5
+++ b/doc/man/man5/slurm.conf.5
@@ -2227,6 +2227,8 @@ configuration file and the default values can be reset multiple times
in the configuration file with multiple entries where "NodeName=DEFAULT".
The "NodeName=" specification must be placed on every line
describing the configuration of nodes.
+A single node name can not appear as a NodeName value in more than one line
+(duplicate node name records will be ignored).
In fact, it is generally possible and desirable to define the
configurations of all nodes in only a few lines.
This convention permits significant optimization in the scheduling
@@ -2618,6 +2620,8 @@ configuration file and the default values can be reset multiple times
in the configuration file with multiple entries where "PartitionName=DEFAULT".
The "PartitionName=" specification must be placed on every line
describing the configuration of partitions.
+A single partition name can not appear as a PartitionName value in more than
+one line (duplicate partition name records will be ignored).
If a partition that is in use is deleted from the configuration and slurm
is restarted or reconfigured (scontrol reconfigure), jobs using the partition
are canceled.
diff --git a/src/common/node_conf.c b/src/common/node_conf.c
index cbd4ea4e501..ca16593d1eb 100644
--- a/src/common/node_conf.c
+++ b/src/common/node_conf.c
@@ -236,7 +236,7 @@ static int _build_single_nodeline_info(slurm_conf_node_t *node_ptr,
node_rec->reason = xstrdup(node_ptr->reason);
} else {
/* FIXME - maybe should be fatal? */
- error("reconfiguration for node %s, ignoring!", alias);
+ error("Reconfiguration for node %s, ignoring!", alias);
}
free(alias);
}
diff --git a/src/slurmctld/read_config.c b/src/slurmctld/read_config.c
index c8bf8c91597..0365a593863 100644
--- a/src/slurmctld/read_config.c
+++ b/src/slurmctld/read_config.c
@@ -494,8 +494,10 @@ static int _build_single_partitionline_info(slurm_conf_partition_t *part)
xfree(part_ptr->name);
part_ptr->name = xstrdup(part->name);
} else {
- verbose("_parse_part_spec: duplicate entry for partition %s",
- part->name);
+ /* FIXME - maybe should be fatal? */
+ error("_parse_part_spec: duplicate entry for partition %s, "
+ "ignoring", part->name);
+ return EEXIST;
}
if (part->default_flag) {
@@ -514,7 +516,7 @@ static int _build_single_partitionline_info(slurm_conf_partition_t *part)
if (part->preempt_mode != (uint16_t) NO_VAL)
part_ptr->preempt_mode = part->preempt_mode;
- if(part->disable_root_jobs == (uint16_t)NO_VAL) {
+ if (part->disable_root_jobs == (uint16_t)NO_VAL) {
if (slurmctld_conf.disable_root_jobs)
part_ptr->flags |= PART_FLAG_NO_ROOT;
} else if (part->disable_root_jobs) {
@@ -523,7 +525,7 @@ static int _build_single_partitionline_info(slurm_conf_partition_t *part)
part_ptr->flags &= (~PART_FLAG_NO_ROOT);
}
- if(part_ptr->flags & PART_FLAG_NO_ROOT)
+ if (part_ptr->flags & PART_FLAG_NO_ROOT)
debug2("partition %s does not allow root jobs", part_ptr->name);
if ((part->default_time != NO_VAL) &&
@@ -593,7 +595,7 @@ static int _build_single_partitionline_info(slurm_conf_partition_t *part)
cnt_uniq = hostlist_count(hl);
if (cnt_tot != cnt_uniq) {
fatal("Duplicate Nodes for Partition %s",
- part->name);
+ part->name);
}
xfree(part_ptr->nodes);
part_ptr->nodes = hostlist_ranged_string_xmalloc(hl);
--
GitLab