From 4f14cf7e8cd2ff10a7887f03fd5878fb9f46938c Mon Sep 17 00:00:00 2001
From: Danny Auble <da@llnl.gov>
Date: Fri, 27 Jun 2008 20:14:53 +0000
Subject: [PATCH] added a better rc from step_launch and finished accounting
---
doc/html/accounting.shtml | 36 +++++++++++++++++++-----------------
src/api/step_launch.c | 5 +++++
2 files changed, 24 insertions(+), 17 deletions(-)
diff --git a/doc/html/accounting.shtml b/doc/html/accounting.shtml
index c17008cc9cd..3551bc0c61a 100644
--- a/doc/html/accounting.shtml
+++ b/doc/html/accounting.shtml
@@ -233,7 +233,8 @@ components. A value of "auth/munge" is recommended.</li>
<li><b>DbdHost</b>:
The name of the machine where the Slurm Database Daemon is executed.
This should be a node name without the full domain name (e.g. "lx0001").
-This defaults to <i>localhost</i>.</li>
+This defaults to <i>localhost</i> but should be supplied to avoid a
+ warning message.</li>
<li><b>DbdPort</b>:
The port number that the Slurm Database Daemon (slurmdbd) listens
@@ -251,19 +252,21 @@ The default value is none (performs logging via syslog).</li>
Identifies the places in which to look for SLURM plugins.
This is a colon-separated list of directories, like the PATH
environment variable.
-The default value is "/usr/local/lib/slurm".</li>
+The default value is the prefix given at configure time + "/lib/slurm".</li>
<li><b>SlurmUser</b>:
The name of the user that the <i>slurmctld</i> daemon executes as.
This user must exist on the machine executing the Slurm Database Daemon
and have the same user ID as the hosts on which <i>slurmctld</i> execute.
For security purposes, a user other than "root" is recommended.
-The default value is "root". </li>
+The default value is "root". This name should also be the same slurm
+user on all clusters reporting to the DBD.</li>
<li><b>StorageHost</b>:
Define the name of the host the database is running where we are going
to store the data.
-Ideally this should be the host on which slurmdbd executes.</li>
+Ideally this should be the host on which slurmdbd executes. But could
+be a different machine.</li>
<li><b>StorageLoc</b>:
Specifies the name of the database where accounting
@@ -302,13 +305,15 @@ with to store the job accounting data.</li>
<h2>Tools</h2>
-<p>There are two tools available to work with accounting data,
-<b>sacct</b> and <b>sacctmgr</b>.
-Both of these tools will get or set data through the SlurmDBD daemon.
+<p>There are a few tools available to work with accounting data,
+<b>sacct</b>, <b>sacctmgr</b>, and <b>sreport</b>.
+These tools all get or set data through the SlurmDBD daemon.<br>
Sacct is used to generate accounting report for both running and
-completed jobs.
+completed jobs.<br>
Sacctmgr is used to manage associations in the database:
-add or remove clusters, add or remove users, etc.
+add or remove clusters, add or remove users, etc.<br>
+Sreport is used to generate various reports on usage collected over a
+given time period.<br>
See the man pages for each command for more information.</p>
<p>Web interfaces with graphical output is currently under
@@ -511,14 +516,11 @@ execute line:</p>
<pre>
sacctmgr remove user where default=test
</pre>
+Note: In most cases when removing entities the record of their
+existance is still kept around only marked deleted. If an entity has
+existed for less than 1 day the entity will be removed completely.
+This is for the case of typos and such.
-<h2>Node State Information</h2>
-
-<p>Node state information is also recorded in the database.
-Whenever a node goes DOWN or becomes DRAINED that event is
-logged along with the node's <i>Reason</i> field.
-This can be used to generate various reports.
-
-<p style="text-align: center;">Last modified 25 March 2008</p>
+<p style="text-align: center;">Last modified 27 June 2008</p>
</ul></body></html>
diff --git a/src/api/step_launch.c b/src/api/step_launch.c
index c74952d1737..39e4fff15ab 100644
--- a/src/api/step_launch.c
+++ b/src/api/step_launch.c
@@ -1011,6 +1011,7 @@ static int _launch_tasks(slurm_step_ctx_t *ctx,
ListIterator ret_itr;
ret_data_info_t *ret_data = NULL;
int rc = SLURM_SUCCESS;
+ int tot_rc = SLURM_SUCCESS;
debug("Entering _launch_tasks");
if (ctx->verbose_level) {
@@ -1048,6 +1049,7 @@ static int _launch_tasks(slurm_step_ctx_t *ctx,
error("Task launch failed on node %s: %m",
ret_data->node_name);
rc = SLURM_ERROR;
+ tot_rc = rc;
} else {
#if 0 /* only for debugging, might want to make this a callback */
errno = ret_data->err;
@@ -1058,6 +1060,9 @@ static int _launch_tasks(slurm_step_ctx_t *ctx,
}
list_iterator_destroy(ret_itr);
list_destroy(ret_list);
+
+ if(tot_rc != SLURM_SUCESS)
+ return tot_rc;
return rc;
}
--
GitLab