diff --git a/META b/META
index fc8bcabd020a06166663c380c202b75714b26ab9..ea82c67c315987cb26bbc0fc6ff386b1a46f32dd 100644
--- a/META
+++ b/META
@@ -3,9 +3,9 @@
Api_revision: 0
Major: 2
Meta: 1
- Micro: 6
+ Micro: 7
Minor: 2
Name: slurm
Release: 1
Release_tags: dist
- Version: 2.2.6
+ Version: 2.2.7
diff --git a/NEWS b/NEWS
index 1dc00e02f1383c0605c1089b1523b04c9a009dfd..b7e40afd9927942aa264605b76a7b7b178b1fb48 100644
--- a/NEWS
+++ b/NEWS
@@ -1,6 +1,20 @@
This file describes changes in recent versions of SLURM. It primarily
documents those changes that are of interest to users and admins.
+
+* Changes in SLURM 2.2.7
+========================
+ -- Eliminate zombie process created if salloc exits with stopped child
+ process. Patch from Gerrit Renker, CSCS.
+ -- With default configuration on non-Cray systems, enable salloc to be
+ spawned as a background process. Based upon work by Don Albert (Bull) and
+ Gerrit Renker (CSCS).
+ -- Fixed Regression from 2.2.4 in accounting where an inherited limit
+ would not be set correctly in the added child association.
+ -- Fixed issue with accounting when asking for jobs with a hostlist.
+ -- Avoid clearing a node's Arch, OS, BootTime and SlurmdStartTime when
+ "scontrol reconfig" is run. Patch from Martin Perry, Bull.
+
* Changes in SLURM 2.2.6
========================
-- Fix displaying of account coordinators with sacctmgr. Possiblity to show
diff --git a/doc/html/accounting.shtml b/doc/html/accounting.shtml
index 32a425e7f1e02e55281a2caef572371ece112597..887f4c2d0edcc5b2eb9c6165235b5b1990a615b8 100644
--- a/doc/html/accounting.shtml
+++ b/doc/html/accounting.shtml
@@ -394,7 +394,7 @@ usage there is a line that starts with '->'. This a continuation
prompt since the previous mysql statement did not end with a ';'. It
assumes that you wish to input more info.)</p>
-live example:
+<p>live example:</p>
<pre>
mysql@snowflake:~$ mysql
@@ -406,24 +406,40 @@ Type 'help;' or '\h' for help. Type '\c' to clear the buffer.
mysql> grant all on slurm_acct_db.* TO 'slurm'@'localhost';
Query OK, 0 rows affected (0.00 sec)
+</pre>
-or with a password...
-
+<p>You may also need to do the same with the system name in order
+for mysql to work correctly:</p>
+<pre>
+mysql> grant all on slurm_acct_db.* TO 'slurm'@'system0';
+Query OK, 0 rows affected (0.00 sec)
+where 'system0' is the localhost or database storage host.
+</pre>
+<p>or with a password...</p>
+<pre>
mysql> grant all on slurm_acct_db.* TO 'slurm'@'localhost'
-> identified by 'some_pass' with grant option;
Query OK, 0 rows affected (0.00 sec)
</pre>
-<p>This will grant user 'slurm' access to do what it needs to do on
-the local host. This should be done before the SlurmDBD will work
-properly. After you grant permission to the Slurm user in mysql then
-you can start SlurmDBD and Slurm. You start SlurmDBD by typing
-'slurmdbd'. You can verify that SlurmDBD is running by typing 'ps aux
-| grep slurmdbd'. After SlurmDBD and the slurmctld start you can
-verify that the database was created by using the mysql command 'show
-databases;'. You can display the tables that slurm created in the
-database by using the mysql command 'use slurm_acct_db;' and then 'show
-tables;'.</p>
+<p>The same is true in the case, you made to do the same with the
+system name:</p>
+<pre>
+mysql> grant all on slurm_acct_db.* TO 'slurm'@'system0'
+ -> identified by 'some_pass' with grant option;
+where 'system0' is the localhost or database storage host.
+</pre>
+
+<p>This will grant user 'slurm' access to do what it needs to do on the local
+host or the storage host system. This must be done before the SlurmDBD will
+work properly. After you grant permission to the user 'slurm' in mysql then
+you can start SlurmDBD and the other SLURM daemons. You start SlurmDBD by
+typing its pathname '/usr/sbin/slurmdbd' or '/etc/init.d/slurmdbd start'. You
+can verify that SlurmDBD is running by typing 'ps aux | grep slurmdbd'. After
+the SlurmDBD and slurmctld daemons start, you can verify that the database
+was created by using the mysql command 'show databases;'. You can display the
+tables that slurm created in the database by using the mysql command
+'use slurm_acct_db;' and then 'show tables;'.</p>
<p>Use the mysql 'show databases;' command</p>
diff --git a/doc/man/man1/sacct.1 b/doc/man/man1/sacct.1
index 4c71cd68d7e21f6fb6b4d63b02d4eb11afad6bbc..890d064983bf65a590ec76a80ecbddd74f27c6bb 100644
--- a/doc/man/man1/sacct.1
+++ b/doc/man/man1/sacct.1
@@ -1138,7 +1138,7 @@ This example shows the same job accounting information with the
.nf
.ft 3
# sacct \-\-brief
-Jobid Status ExitCode
+ Jobid State ExitCode
\-\-\-\-\-\-\-\-\-\- \-\-\-\-\-\-\-\-\-\- \-\-\-\-\-\-\-\-
2 RUNNING 0
3 RUNNING 0
@@ -1175,8 +1175,8 @@ on the command line.
.PP
.nf
.ft 3
-# sacct \-\-format=jobid,ncpus,ntasks,nsignals,status
-Jobid Elapsed Ncpus Ntasks Status
+# sacct \-\-format=jobid,elapsed,ncpus,ntasks,state
+ Jobid Elapsed Ncpus Ntasks State
\-\-\-\-\-\-\-\-\-\- \-\-\-\-\-\-\-\-\-\- \-\-\-\-\-\-\-\-\-\- \-\-\-\-\-\-\-\- \-\-\-\-\-\-\-\-\-\-
3 00:01:30 2 1 COMPLETED
3.0 00:01:30 2 1 COMPLETED
diff --git a/doc/man/man1/salloc.1 b/doc/man/man1/salloc.1
index 658c18cb9c54245780580b03e62dc86ca19e3666..d10e5d96f0e894dc843a659de784d4f54ab898e1 100644
--- a/doc/man/man1/salloc.1
+++ b/doc/man/man1/salloc.1
@@ -313,7 +313,7 @@ in some failed state (non-zero exit code, node failure, timed out, etc).
.TP
\fBafterok:job_id[:jobid...]\fR
This job can begin execution after the specified jobs have successfully
-executed (ran to completion with non-zero exit code).
+executed (ran to completion with an exit code of zero).
.TP
\fBsingleton\fR
This job can begin execution after any previously launched jobs
diff --git a/doc/man/man1/sbatch.1 b/doc/man/man1/sbatch.1
index 0c0ed5ecd02be4c0b6ec178b97dc2e25b48f7623..0cdfa03e1e3cd47f580f8379821d362984e9d2d8 100644
--- a/doc/man/man1/sbatch.1
+++ b/doc/man/man1/sbatch.1
@@ -322,7 +322,7 @@ in some failed state (non-zero exit code, node failure, timed out, etc).
.TP
\fBafterok:job_id[:jobid...]\fR
This job can begin execution after the specified jobs have successfully
-executed (ran to completion with non-zero exit code).
+executed (ran to completion with an exit code of zero).
.TP
\fBsingleton\fR
This job can begin execution after any previously launched jobs
diff --git a/doc/man/man1/scontrol.1 b/doc/man/man1/scontrol.1
index 385c51449c41bc02a539a8c7338551e6d77f97e0..5999834c206ccbf5b4e3aa279bef15621cbf06bd 100644
--- a/doc/man/man1/scontrol.1
+++ b/doc/man/man1/scontrol.1
@@ -424,7 +424,7 @@ in some failed state (non-zero exit code, node failure, timed out, etc).
.TP
\fBafterok:job_id[:jobid...]\fR
This job can begin execution after the specified jobs have successfully
-executed (ran to completion with non-zero exit code).
+executed (ran to completion with an exit code of zero).
.TP
\fBsingleton\fR
This job can begin execution after any previously launched jobs
diff --git a/doc/man/man1/srun.1 b/doc/man/man1/srun.1
index b17e144e0a2ebaabe42a96a09b29b4c2036f7ff9..8187ac65df8b344ef8281126d67bbcc4e5b5c2e2 100644
--- a/doc/man/man1/srun.1
+++ b/doc/man/man1/srun.1
@@ -336,7 +336,7 @@ in some failed state (non-zero exit code, node failure, timed out, etc).
.TP
\fBafterok:job_id[:jobid...]\fR
This job can begin execution after the specified jobs have successfully
-executed (ran to completion with non-zero exit code).
+executed (ran to completion with an exit code of zero).
.TP
\fBsingleton\fR
This job can begin execution after any previously launched jobs
diff --git a/slurm.spec b/slurm.spec
index 10263924b66259429f86f85e0d8fed63412d555c..37a89df7e2bfd4e303aef7b10e534013de8adb05 100644
--- a/slurm.spec
+++ b/slurm.spec
@@ -86,14 +86,14 @@
%endif
Name: slurm
-Version: 2.2.6
+Version: 2.2.7
Release: 1%{?dist}
Summary: Simple Linux Utility for Resource Management
License: GPL
Group: System Environment/Base
-Source: slurm-2.2.6.tar.bz2
+Source: slurm-2.2.7.tar.bz2
BuildRoot: %{_tmppath}/%{name}-%{version}-%{release}
URL: https://computing.llnl.gov/linux/slurm/
@@ -368,7 +368,7 @@ Gives the ability for SLURM to use Berkeley Lab Checkpoint/Restart
#############################################################################
%prep
-%setup -n slurm-2.2.6
+%setup -n slurm-2.2.7
%build
%configure --program-prefix=%{?_program_prefix:%{_program_prefix}} \
diff --git a/src/plugins/accounting_storage/mysql/as_mysql_assoc.c b/src/plugins/accounting_storage/mysql/as_mysql_assoc.c
index 15d97df59d4c7d1b772107ff1175b468dc274914..3b696b704b6ce0a871f33dc51fa50560b8e37b88 100644
--- a/src/plugins/accounting_storage/mysql/as_mysql_assoc.c
+++ b/src/plugins/accounting_storage/mysql/as_mysql_assoc.c
@@ -643,24 +643,26 @@ static int _set_assoc_limits_for_add(
if (!(row = mysql_fetch_row(result)))
goto end_it;
- if (row[ASSOC2_REQ_DEF_QOS] && assoc->def_qos_id == NO_VAL)
+ if (row[ASSOC2_REQ_DEF_QOS] && assoc->def_qos_id == INFINITE)
assoc->def_qos_id = slurm_atoul(row[ASSOC2_REQ_DEF_QOS]);
- else if (assoc->def_qos_id == NO_VAL)
+ else if (assoc->def_qos_id == INFINITE)
assoc->def_qos_id = 0;
- if (row[ASSOC2_REQ_MCMPJ] && assoc->max_cpu_mins_pj == (uint64_t)NO_VAL)
+ if (row[ASSOC2_REQ_MCMPJ]
+ && assoc->max_cpu_mins_pj == (uint64_t)INFINITE)
assoc->max_cpu_mins_pj = slurm_atoull(row[ASSOC2_REQ_MCMPJ]);
- if (row[ASSOC2_REQ_MCRM] && assoc->max_cpu_run_mins == (uint64_t)NO_VAL)
+ if (row[ASSOC2_REQ_MCRM]
+ && assoc->max_cpu_run_mins == (uint64_t)INFINITE)
assoc->max_cpu_run_mins = slurm_atoull(row[ASSOC2_REQ_MCRM]);
- if (row[ASSOC2_REQ_MCPJ] && assoc->max_cpus_pj == NO_VAL)
+ if (row[ASSOC2_REQ_MCPJ] && assoc->max_cpus_pj == INFINITE)
assoc->max_cpus_pj = slurm_atoul(row[ASSOC2_REQ_MCPJ]);
- if (row[ASSOC2_REQ_MJ] && assoc->max_jobs == NO_VAL)
+ if (row[ASSOC2_REQ_MJ] && assoc->max_jobs == INFINITE)
assoc->max_jobs = slurm_atoul(row[ASSOC2_REQ_MJ]);
- if (row[ASSOC2_REQ_MNPJ] && assoc->max_nodes_pj == NO_VAL)
+ if (row[ASSOC2_REQ_MNPJ] && assoc->max_nodes_pj == INFINITE)
assoc->max_nodes_pj = slurm_atoul(row[ASSOC2_REQ_MNPJ]);
- if (row[ASSOC2_REQ_MSJ] && assoc->max_submit_jobs == NO_VAL)
+ if (row[ASSOC2_REQ_MSJ] && assoc->max_submit_jobs == INFINITE)
assoc->max_submit_jobs = slurm_atoul(row[ASSOC2_REQ_MSJ]);
- if (row[ASSOC2_REQ_MWPJ] && assoc->max_wall_pj == NO_VAL)
+ if (row[ASSOC2_REQ_MWPJ] && assoc->max_wall_pj == INFINITE)
assoc->max_wall_pj = slurm_atoul(row[ASSOC2_REQ_MWPJ]);
if (assoc->qos_list) {
diff --git a/src/plugins/accounting_storage/mysql/as_mysql_jobacct_process.c b/src/plugins/accounting_storage/mysql/as_mysql_jobacct_process.c
index 05345ecadfdb30dba6e8ba48f56ac9ee4f7ccabe..6befc441696f126c725e2a6d2d536c65d40ab79f 100644
--- a/src/plugins/accounting_storage/mysql/as_mysql_jobacct_process.c
+++ b/src/plugins/accounting_storage/mysql/as_mysql_jobacct_process.c
@@ -843,7 +843,7 @@ extern List setup_cluster_list_with_inx(mysql_conn_t *mysql_conn,
}
temp_hl = hostlist_create(job_cond->used_nodes);
- if (!hostlist_count(temp_hl)) {
+ if (hostlist_count(temp_hl) <= 0) {
error("we didn't get any real hosts to look for.");
goto no_hosts;
}
@@ -869,8 +869,7 @@ extern List setup_cluster_list_with_inx(mysql_conn_t *mysql_conn,
mysql_conn->conn, THIS_FILE, __LINE__, query);
if (!(result = mysql_db_query_ret(mysql_conn, query, 0))) {
xfree(query);
- hostlist_destroy(temp_hl);
- return NULL;
+ goto no_hosts;
}
xfree(query);
@@ -902,14 +901,16 @@ extern List setup_cluster_list_with_inx(mysql_conn_t *mysql_conn,
_destroy_local_cluster(local_cluster);
}
mysql_free_result(result);
- hostlist_iterator_destroy(h_itr);
+
if (!list_count(local_cluster_list)) {
- hostlist_destroy(temp_hl);
list_destroy(local_cluster_list);
- return NULL;
+ local_cluster_list = NULL;
+ goto no_hosts;
}
+
no_hosts:
+ hostlist_iterator_destroy(h_itr);
hostlist_destroy(temp_hl);
return local_cluster_list;
diff --git a/src/salloc/salloc.c b/src/salloc/salloc.c
index a36ef2fc98bb7e6f4e95dd862ea69c25ecc6074a..1112ed6d54e2fab0b45a52c86761e28edd2ae7b1 100644
--- a/src/salloc/salloc.c
+++ b/src/salloc/salloc.c
@@ -222,6 +222,7 @@ int main(int argc, char *argv[])
* a) input is from a terminal (stdin has valid termios attributes),
* b) controlling terminal exists (non-negative tpgid),
* c) salloc is not run in allocation-only (--no-shell) mode,
+ * NOTE: d and e below are configuration dependent
* d) salloc runs in its own process group (true in interactive
* shells that support job control),
* e) salloc has been configured at compile-time to support background
@@ -237,10 +238,10 @@ int main(int argc, char *argv[])
error("no controlling terminal: please set --no-shell");
exit(error_exit);
}
+#ifdef SALLOC_RUN_FOREGROUND
} else if ((!opt.no_shell) && (pid == getpgrp())) {
if (tpgid == pid)
is_interactive = true;
-#ifdef SALLOC_RUN_FOREGROUND
while (tcgetpgrp(STDIN_FILENO) != pid) {
if (!is_interactive) {
error("Waiting for program to be placed in "
@@ -249,8 +250,12 @@ int main(int argc, char *argv[])
}
killpg(pid, SIGTTIN);
}
-#endif
}
+#else
+ } else if (!opt.no_shell) {
+ is_interactive = true;
+ }
+#endif
/*
* Reset saved tty attributes at exit, in case a child
* process died before properly resetting terminal.
@@ -487,6 +492,9 @@ relinquish:
if (WIFEXITED(status)) {
rc = WEXITSTATUS(status);
+ } else if (WIFSTOPPED(status)) {
+ /* Terminate stopped child process */
+ _forward_signal(SIGKILL);
} else if (WIFSIGNALED(status)) {
verbose("Command \"%s\" was terminated by signal %d",
command_argv[0], WTERMSIG(status));
diff --git a/src/slurmctld/read_config.c b/src/slurmctld/read_config.c
index 132039efc8b062fdf5eafb23680029b11a5bb079..7c388adf005ce74bd116acc0dc4a50773ec3c755 100644
--- a/src/slurmctld/read_config.c
+++ b/src/slurmctld/read_config.c
@@ -658,9 +658,7 @@ int read_slurm_conf(int recover, bool reconfig)
old_node_table_ptr = node_record_table_ptr;
for (i=0, node_ptr=old_node_table_ptr; i<node_record_count;
i++, node_ptr++) {
- xfree(node_ptr->arch);
xfree(node_ptr->features);
- xfree(node_ptr->os);
node_ptr->features = xstrdup(
node_ptr->config_ptr->feature);
/* Store the original configured CPU count somewhere
@@ -919,11 +917,13 @@ static int _restore_node_state(int recover,
node_ptr->name, old_node_ptr->port,
node_ptr->config_ptr->cpus);
}
+ node_ptr->boot_time = old_node_ptr->boot_time;
node_ptr->cpus = old_node_ptr->cpus;
node_ptr->cores = old_node_ptr->cores;
node_ptr->sockets = old_node_ptr->sockets;
node_ptr->threads = old_node_ptr->threads;
node_ptr->real_memory = old_node_ptr->real_memory;
+ node_ptr->slurmd_start_time = old_node_ptr->slurmd_start_time;
node_ptr->tmp_disk = old_node_ptr->tmp_disk;
node_ptr->weight = old_node_ptr->weight;