Hi all,
This patch is a thing to let crm_mon display the attribute value of the node.
The details argued in the following threads.
http://www.gossamer-threads.com/lists/linuxha/pacemaker/59168
This function applies a patch to crm_mon.c to use it, and please install
crm_mon.
This patch is a change set of stable-1.0: I can apply to 15377.
And I attach a "-A" option, and please carry out crm_mon.
The main function is as follows.
* I added a function to display the attribute value of the node.
- When abnormality occurred in an attribute value of pingd; of the function
to display a warning message added it.
- Of the function that a list shows a warning message for indication of
"fail-count" added it.
* Originally I deleted it because the function to display an attribute value
of implemented pingd was redundant.
The attribute to show below excludes you from indication.
* probe_complete
* shutdown
* terminate
* fail-count*
* last-failure*
I want you to merge it into a source tree if you do not have any problem.
Best Regards,
IIDA Yuusuke
I show below indication example.
# crm_mon -fA1
============
Last updated: 26 Fri Feb 13:49:05 2010
Stack: openais
Current DC: node1 - partition with quorum
Version: 1.0.7-049006f17277+ stable-1.0 tip
Two two Nodes configured, expected votes
Two Resources configured.
============
Online: [node1 node2]
Resource Group: grpDummy
prmDummy1 (ocf::heartbeat:Dummy): Started node2
prmDummy2 (ocf::heartbeat:Dummy): Started node2
prmDummy3 (ocf::heartbeat:Dummy): Started node2
Clone Set: clnPingd
Started: [node2 node1]
Node Attributes:
* Node node2:
+ default_ping_set : 0 : Link is failure!!
(Expected=100)
* Node node1:
+ default_ping_set : 100
Migration summary:
* Node node2:
* Node node1:
prmDummy3: migration-threshold=1 fail-count=1: Resource is failure!!
Failed actions:
prmDummy3_monitor_10000 (node=node1, call=13, rc=7, status=complete): not
running
#
--- stable-1.0/tools/crm_mon.c 2010-02-26 15:05:25.000000000 +0900
+++ hb_monitor/pacemaker106/tools/crm_mon.c 2010-02-26 15:02:04.000000000 +0900
@@ -82,6 +82,8 @@
gboolean print_failcount = FALSE;
gboolean print_operations = FALSE;
gboolean print_timing = FALSE;
+gboolean print_nodes_attr = FALSE;
+#define FILTER_STR {"shutdown", "terminate", "fail-count", "last-failure", "probe_complete", NULL}
gboolean log_diffs = FALSE;
gboolean log_updates = FALSE;
@@ -247,11 +249,12 @@
{"mail-to", 1, 0, 'T', "Send Mail alerts to this user. See also --mail-from, --mail-host, --mail-prefix", !ENABLE_ESMTP},
{"-spacer-", 1, 0, '-', "\nDisplay Options:"},
- {"group-by-node", 0, 0, 'n', "Group resources by node" },
- {"inactive", 0, 0, 'r', "Display inactive resources" },
- {"failcounts", 0, 0, 'f', "Display resource fail counts"},
- {"operations", 0, 0, 'o', "Display resource operation history" },
- {"timing-details", 0, 0, 't', "Display resource operation history with timing details\n" },
+ {"group-by-node", 0, 0, 'n', "\tGroup resources by node" },
+ {"inactive", 0, 0, 'r', "\tDisplay inactive resources" },
+ {"failcounts", 0, 0, 'f', "\tDisplay resource fail counts"},
+ {"operations", 0, 0, 'o', "\tDisplay resource operation history" },
+ {"timing-details", 0, 0, 't', "\tDisplay resource operation history with timing details" },
+ {"show-node-attributes", 0, 0, 'A', "Display node attributes\n" },
{"-spacer-", 1, 0, '-', "\nAdditional Options:"},
{"interval", 1, 0, 'i', "\tUpdate frequency in seconds" },
@@ -297,7 +300,7 @@
pid_file = crm_strdup("/tmp/ClusterMon.pid");
crm_log_init(basename(argv[0]), LOG_CRIT, FALSE, FALSE, 0, NULL);
- crm_set_options("V?$i:nrh:dp:s1wx:oftNS:T:F:H:P:E:e:", "mode [options]", long_options,
+ crm_set_options("V?$i:nrh:dp:s1wx:oftANS:T:F:H:P:E:e:", "mode [options]", long_options,
"Provides a summary of cluster's current state."
"\n\nOutputs varying levels of detail in a number of different formats.\n");
@@ -343,6 +346,9 @@
case 'f':
print_failcount = TRUE;
break;
+ case 'A':
+ print_nodes_attr = TRUE;
+ break;
case 'p':
crm_free(pid_file);
pid_file = crm_strdup(optarg);
@@ -570,17 +576,6 @@
extern int get_failcount(node_t *node, resource_t *rsc, int *last_failure, pe_working_set_t *data_set);
-static void get_ping_score(node_t *node, pe_working_set_t *data_set)
-{
- const char *attr = "pingd";
- const char *value = NULL;
- value = g_hash_table_lookup(node->details->attrs, attr);
-
- if(value != NULL) {
- print_as(" %s=%s", attr, value);
- }
-}
-
static void print_date(time_t time)
{
int lpc = 0;
@@ -622,6 +617,11 @@
print_date(last_failure);
}
+ if(failcount > 0) {
+ printed = TRUE;
+ print_as(": Resource is failure!!");
+ }
+
if(printed) {
print_as("\n");
}
@@ -718,6 +718,84 @@
g_list_free(sorted_op_list);
}
+static void print_attr_msg(node_t *node, GListPtr rsc_list, const char *attrname, const char *attrvalue)
+{
+ slist_iter(rsc, resource_t, rsc_list, lpc2,
+
+ if(rsc->children != NULL) {
+ print_attr_msg(node, rsc->children, attrname, attrvalue);
+ }
+
+ if(safe_str_eq("pingd", g_hash_table_lookup(rsc->meta, "type"))) {
+ const char *name = "pingd";
+ const char *multiplier = NULL;
+ char **host_list = NULL;
+ int host_list_num = 0;
+ int expected_score = 0;
+
+ if(g_hash_table_lookup(rsc->meta, "name") != NULL) {
+ name = g_hash_table_lookup(rsc->meta, "name");
+ }
+
+ /* To identify the resource with the attribute name. */
+ if(safe_str_eq(name, attrname)) {
+ multiplier = g_hash_table_lookup(rsc->meta, "multiplier");
+ host_list = g_strsplit(g_hash_table_lookup(rsc->meta, "host_list"), " ", 0);
+ host_list_num = g_strv_length(host_list);
+ g_strfreev(host_list);
+ /* pingd multiplier is the same as the default value. */
+ expected_score = host_list_num * crm_parse_int(multiplier, "1");
+
+ /* pingd is abnormal score. */
+ if(crm_parse_int(attrvalue, "0") < expected_score) {
+ print_as("\t: Link is failure!! (Expected=%d)", expected_score);
+ }
+ }
+ }
+ );
+}
+
+static void print_nodes_attribute(pe_working_set_t *data_set)
+{
+ xmlNode *cib_status = get_object_root(XML_CIB_TAG_STATUS, data_set->input);
+ xmlNode *trns_attr = NULL;
+ int i;
+ const char *filt_str[] = FILTER_STR;
+
+ print_as("\nNode Attributes:\n");
+
+ xml_child_iter_filter(
+ cib_status, node_state, XML_CIB_TAG_STATE,
+ node_t *node = pe_find_node_id(data_set->nodes, ID(node_state));
+ if(node == NULL || node->details->online == FALSE){
+ continue;
+ }
+
+ print_as("* Node %s:\n", crm_element_value(node_state, XML_ATTR_UNAME));
+
+ trns_attr = find_xml_node(node_state, XML_TAG_TRANSIENT_NODEATTRS, FALSE);
+ trns_attr = find_xml_node(trns_attr, XML_TAG_ATTR_SETS, FALSE);
+
+ xml_child_iter(trns_attr, nvpair,
+ const char *node_attr_name = crm_element_value(nvpair, XML_NVPAIR_ATTR_NAME);
+ const char *node_attr_value = crm_element_value(nvpair, XML_NVPAIR_ATTR_VALUE);
+
+ /* filtering automatic attributes */
+ for(i=0;filt_str[i]!=NULL;i++) {
+ if(g_str_has_prefix(node_attr_name, filt_str[i])) {
+ goto filtering;
+ }
+ }
+
+ print_as(" + %-32s\t: %-10s", node_attr_name, node_attr_value);
+ print_attr_msg(node, node->details->running_rsc, node_attr_name, node_attr_value);
+ print_as("\n");
+filtering:
+ continue;
+ );
+ );
+}
+
static void print_node_summary(pe_working_set_t *data_set, gboolean operations)
{
xmlNode *lrm_rsc = NULL;
@@ -737,7 +815,6 @@
}
print_as("* Node %s: ", crm_element_value(node_state, XML_ATTR_UNAME));
- get_ping_score(node, data_set);
print_as("\n");
lrm_rsc = find_xml_node(node_state, XML_CIB_TAG_LRM, FALSE);
@@ -953,6 +1030,10 @@
);
}
+ if(print_nodes_attr) {
+ print_nodes_attribute(data_set);
+ }
+
if(print_operations || print_failcount) {
print_node_summary(data_set, print_operations);
}
_______________________________________________
Pacemaker mailing list
Pacemaker@oss.clusterlabs.org
http://oss.clusterlabs.org/mailman/listinfo/pacemaker
