From d4dd67e6ba4aaa8e45e4572272d6b9c762506bea Mon Sep 17 00:00:00 2001
From: Fulvio Galeazzi <fulvio.galeazzi@garr.it>
Date: Wed, 21 Oct 2020 12:38:32 +0200
Subject: [PATCH] 2020-10-21: FG; Added some PG states, updated for Nautilus
misplaced/degraded objects.
---
Ceph/Config/userparameter_ceph.conf | 3 +
Ceph/Script/cephHealth.pl | 16 ++
Ceph/Script/cephPg.pl | 10 +-
Ceph/Template/zbx_tmpl_ceph-adm.xml | 260 +++++++++++++++++++++++++++-
4 files changed, 279 insertions(+), 10 deletions(-)
diff --git a/Ceph/Config/userparameter_ceph.conf b/Ceph/Config/userparameter_ceph.conf
index 94e1801..1fda748 100644
--- a/Ceph/Config/userparameter_ceph.conf
+++ b/Ceph/Config/userparameter_ceph.conf
@@ -45,6 +45,7 @@ UserParameter=ceph.pgstat.cln[*],/etc/zabbix/scripts/cephPg.pl $1 -f cln
UserParameter=ceph.pgstat.dee[*],/etc/zabbix/scripts/cephPg.pl $1 -f dee
UserParameter=ceph.pgstat.deg[*],/etc/zabbix/scripts/cephPg.pl $1 -f deg
UserParameter=ceph.pgstat.dow[*],/etc/zabbix/scripts/cephPg.pl $1 -f dow
+UserParameter=ceph.pgstat.ful[*],/etc/zabbix/scripts/cephPg.pl $1 -f ful
UserParameter=ceph.pgstat.ncm[*],/etc/zabbix/scripts/cephPg.pl $1 -f ncm
UserParameter=ceph.pgstat.ncs[*],/etc/zabbix/scripts/cephPg.pl $1 -f ncs
UserParameter=ceph.pgstat.oth[*],/etc/zabbix/scripts/cephPg.pl $1 -f oth
@@ -53,8 +54,10 @@ UserParameter=ceph.pgstat.rec[*],/etc/zabbix/scripts/cephPg.pl $1 -f rec
UserParameter=ceph.pgstat.rem[*],/etc/zabbix/scripts/cephPg.pl $1 -f rem
UserParameter=ceph.pgstat.rep[*],/etc/zabbix/scripts/cephPg.pl $1 -f rep
UserParameter=ceph.pgstat.scr[*],/etc/zabbix/scripts/cephPg.pl $1 -f scr
+UserParameter=ceph.pgstat.sna[*],/etc/zabbix/scripts/cephPg.pl $1 -f sna
UserParameter=ceph.pgstat.sta[*],/etc/zabbix/scripts/cephPg.pl $1 -f sta
UserParameter=ceph.pgstat.und[*],/etc/zabbix/scripts/cephPg.pl $1 -f und
+UserParameter=ceph.pgstat.unf[*],/etc/zabbix/scripts/cephPg.pl $1 -f unf
# Disks
UserParameter=ceph.osdsize.all.discovery[*],/etc/zabbix/scripts/queryCephDisks.pl $1 $2 -j
UserParameter=ceph.osdsize.all.count[*],/etc/zabbix/scripts/queryCephDisks.pl $1 $2 -s $3
diff --git a/Ceph/Script/cephHealth.pl b/Ceph/Script/cephHealth.pl
index 3e3fc9b..036083e 100755
--- a/Ceph/Script/cephHealth.pl
+++ b/Ceph/Script/cephHealth.pl
@@ -281,6 +281,22 @@ foreach my $_line (@_data)
}
}
+# Fetch the data and put it in an array
+# Nautilus fix: misplaced no longer in health detail
+my @_data2 = `$cephCmd pg stat`;
+chomp @_data2;
+foreach my $_line2 (@_data2)
+{
+ if ($_line2 =~ m/ (\d+)\/(\d+) objects misplaced \(([-+]?[0-9]*\.?[0-9]+)\%\)/) {
+ $objMisplaced = $1;
+ $objMisplacedFrac = $3;
+ }
+ if ($_line2 =~ m/ (\d+)\/(\d+) objects degraded \(([-+]?[0-9]*\.?[0-9]+)\%\)/) {
+ $objDegraded = $1;
+ $objDegradedFrac = $3;
+ }
+}
+
if (defined $opt_status) {
print $status."\n";
} elsif (defined $opt_object_degraded) {
diff --git a/Ceph/Script/cephPg.pl b/Ceph/Script/cephPg.pl
index 13ca5c2..fca7d0e 100755
--- a/Ceph/Script/cephPg.pl
+++ b/Ceph/Script/cephPg.pl
@@ -95,26 +95,34 @@ my %statesHash = (
'activeclean' => 'acc',
'active' => 'act',
'backfilling' => 'bck',
+ 'forced_backfill' => 'bck',
'wait_backfill' => 'bck',
- 'backfill_toofull' => 'bck',
'clean' => 'cln',
'deep' => 'dee',
'degraded' => 'deg',
'down' => 'dow',
+ 'backfill_toofull' => 'ful',
+ 'recovery_toofull' => 'ful',
'incomplete' => 'ncm',
'inconsistent' => 'ncs',
+ 'activating' => 'oth',
'creating' => 'oth',
'replay' => 'oth',
'splitting' => 'oth',
'peered' => 'pee',
'peering' => 'pee',
+ 'forced_recovery' => 'rec',
'recovering' => 'rec',
'recovery_wait' => 'rec',
'remapped' => 'rem',
'repair' => 'rep',
'scrubbing' => 'scr',
+ 'snaptrim' => 'sna',
+ 'snaptrim_wait' => 'sna',
'stale' => 'sta',
'undersized' => 'und',
+ 'backfill_unfound' => 'unf',
+ 'recovery_unfound' => 'unf',
);
my %pgHash = (
'tot' => 0,
diff --git a/Ceph/Template/zbx_tmpl_ceph-adm.xml b/Ceph/Template/zbx_tmpl_ceph-adm.xml
index df94ce4..c4b6329 100644
--- a/Ceph/Template/zbx_tmpl_ceph-adm.xml
+++ b/Ceph/Template/zbx_tmpl_ceph-adm.xml
@@ -1,7 +1,7 @@
<?xml version="1.0" encoding="UTF-8"?>
<zabbix_export>
<version>3.0</version>
- <date>2018-05-08T06:28:09Z</date>
+ <date>2020-10-21T10:36:49Z</date>
<groups>
<group>
<name>Templates</name>
@@ -1276,6 +1276,49 @@
<valuemap/>
<logtimefmt/>
</item>
+ <item>
+ <name>Ceph PG full - toofull</name>
+ <type>0</type>
+ <snmp_community/>
+ <multiplier>0</multiplier>
+ <snmp_oid/>
+ <key>ceph.pgstat.ful[{$CEPH_CONNPAR}]</key>
+ <delay>60</delay>
+ <history>15</history>
+ <trends>365</trends>
+ <status>0</status>
+ <value_type>3</value_type>
+ <allowed_hosts/>
+ <units/>
+ <delta>0</delta>
+ <snmpv3_contextname/>
+ <snmpv3_securityname/>
+ <snmpv3_securitylevel>0</snmpv3_securitylevel>
+ <snmpv3_authprotocol>0</snmpv3_authprotocol>
+ <snmpv3_authpassphrase/>
+ <snmpv3_privprotocol>0</snmpv3_privprotocol>
+ <snmpv3_privpassphrase/>
+ <formula>1</formula>
+ <delay_flex/>
+ <params/>
+ <ipmi_sensor/>
+ <data_type>0</data_type>
+ <authtype>0</authtype>
+ <username/>
+ <password/>
+ <publickey/>
+ <privatekey/>
+ <port/>
+ <description>Ceph PG: backfill_toofull and recovery_toofull</description>
+ <inventory_link>0</inventory_link>
+ <applications>
+ <application>
+ <name>Ceph ADM</name>
+ </application>
+ </applications>
+ <valuemap/>
+ <logtimefmt/>
+ </item>
<item>
<name>Ceph PG incomplete</name>
<type>0</type>
@@ -1620,6 +1663,49 @@
<valuemap/>
<logtimefmt/>
</item>
+ <item>
+ <name>Ceph PG snaptrim</name>
+ <type>0</type>
+ <snmp_community/>
+ <multiplier>0</multiplier>
+ <snmp_oid/>
+ <key>ceph.pgstat.sna[{$CEPH_CONNPAR}]</key>
+ <delay>60</delay>
+ <history>15</history>
+ <trends>365</trends>
+ <status>0</status>
+ <value_type>3</value_type>
+ <allowed_hosts/>
+ <units/>
+ <delta>0</delta>
+ <snmpv3_contextname/>
+ <snmpv3_securityname/>
+ <snmpv3_securitylevel>0</snmpv3_securitylevel>
+ <snmpv3_authprotocol>0</snmpv3_authprotocol>
+ <snmpv3_authpassphrase/>
+ <snmpv3_privprotocol>0</snmpv3_privprotocol>
+ <snmpv3_privpassphrase/>
+ <formula>1</formula>
+ <delay_flex/>
+ <params/>
+ <ipmi_sensor/>
+ <data_type>0</data_type>
+ <authtype>0</authtype>
+ <username/>
+ <password/>
+ <publickey/>
+ <privatekey/>
+ <port/>
+ <description>Ceph PG: snaptrim</description>
+ <inventory_link>0</inventory_link>
+ <applications>
+ <application>
+ <name>Ceph ADM</name>
+ </application>
+ </applications>
+ <valuemap/>
+ <logtimefmt/>
+ </item>
<item>
<name>Ceph PG stale</name>
<type>0</type>
@@ -1749,6 +1835,49 @@
<valuemap/>
<logtimefmt/>
</item>
+ <item>
+ <name>Ceph PG unfound</name>
+ <type>0</type>
+ <snmp_community/>
+ <multiplier>0</multiplier>
+ <snmp_oid/>
+ <key>ceph.pgstat.unf[{$CEPH_CONNPAR}]</key>
+ <delay>60</delay>
+ <history>15</history>
+ <trends>365</trends>
+ <status>0</status>
+ <value_type>3</value_type>
+ <allowed_hosts/>
+ <units/>
+ <delta>0</delta>
+ <snmpv3_contextname/>
+ <snmpv3_securityname/>
+ <snmpv3_securitylevel>0</snmpv3_securitylevel>
+ <snmpv3_authprotocol>0</snmpv3_authprotocol>
+ <snmpv3_authpassphrase/>
+ <snmpv3_privprotocol>0</snmpv3_privprotocol>
+ <snmpv3_privpassphrase/>
+ <formula>1</formula>
+ <delay_flex/>
+ <params/>
+ <ipmi_sensor/>
+ <data_type>0</data_type>
+ <authtype>0</authtype>
+ <username/>
+ <password/>
+ <publickey/>
+ <privatekey/>
+ <port/>
+ <description>Ceph PG: backfill_unfound, recovery_unfound</description>
+ <inventory_link>0</inventory_link>
+ <applications>
+ <application>
+ <name>Ceph ADM</name>
+ </application>
+ </applications>
+ <valuemap/>
+ <logtimefmt/>
+ </item>
<item>
<name>Ceph Pool number</name>
<type>0</type>
@@ -2327,7 +2456,7 @@
<snmp_oid/>
<key>ceph.pool.discovery[{$CEPH_CONNPAR}]</key>
<delay>3600</delay>
- <status>1</status>
+ <status>0</status>
<allowed_hosts/>
<snmpv3_contextname/>
<snmpv3_securityname/>
@@ -2360,7 +2489,7 @@
<multiplier>0</multiplier>
<snmp_oid/>
<key>ceph.pool.frac[{$CEPH_CONNPAR},{#POOL}]</key>
- <delay>120</delay>
+ <delay>300</delay>
<history>15</history>
<trends>365</trends>
<status>0</status>
@@ -2404,7 +2533,7 @@
<multiplier>0</multiplier>
<snmp_oid/>
<key>ceph.pool.objs[{$CEPH_CONNPAR},{#POOL}]</key>
- <delay>120</delay>
+ <delay>300</delay>
<history>15</history>
<trends>365</trends>
<status>0</status>
@@ -2448,7 +2577,7 @@
<multiplier>0</multiplier>
<snmp_oid/>
<key>ceph.pool.size[{$CEPH_CONNPAR},{#POOL}]</key>
- <delay>120</delay>
+ <delay>300</delay>
<history>15</history>
<trends>365</trends>
<status>0</status>
@@ -2487,7 +2616,84 @@
</item_prototype>
</item_prototypes>
<trigger_prototypes/>
- <graph_prototypes/>
+ <graph_prototypes>
+ <graph_prototype>
+ <name>Pool {#POOL}: object number</name>
+ <width>900</width>
+ <height>200</height>
+ <yaxismin>0.0000</yaxismin>
+ <yaxismax>100.0000</yaxismax>
+ <show_work_period>1</show_work_period>
+ <show_triggers>1</show_triggers>
+ <type>0</type>
+ <show_legend>1</show_legend>
+ <show_3d>0</show_3d>
+ <percent_left>0.0000</percent_left>
+ <percent_right>0.0000</percent_right>
+ <ymin_type_1>0</ymin_type_1>
+ <ymax_type_1>0</ymax_type_1>
+ <ymin_item_1>0</ymin_item_1>
+ <ymax_item_1>0</ymax_item_1>
+ <graph_items>
+ <graph_item>
+ <sortorder>0</sortorder>
+ <drawtype>0</drawtype>
+ <color>009900</color>
+ <yaxisside>0</yaxisside>
+ <calc_fnc>2</calc_fnc>
+ <type>0</type>
+ <item>
+ <host>Template App Ceph</host>
+ <key>ceph.pool.objs[{$CEPH_CONNPAR},{#POOL}]</key>
+ </item>
+ </graph_item>
+ </graph_items>
+ </graph_prototype>
+ <graph_prototype>
+ <name>Pool {#POOL}: size and used fraction</name>
+ <width>900</width>
+ <height>200</height>
+ <yaxismin>0.0000</yaxismin>
+ <yaxismax>100.0000</yaxismax>
+ <show_work_period>1</show_work_period>
+ <show_triggers>1</show_triggers>
+ <type>0</type>
+ <show_legend>1</show_legend>
+ <show_3d>0</show_3d>
+ <percent_left>0.0000</percent_left>
+ <percent_right>0.0000</percent_right>
+ <ymin_type_1>1</ymin_type_1>
+ <ymax_type_1>0</ymax_type_1>
+ <ymin_item_1>0</ymin_item_1>
+ <ymax_item_1>0</ymax_item_1>
+ <graph_items>
+ <graph_item>
+ <sortorder>0</sortorder>
+ <drawtype>0</drawtype>
+ <color>990000</color>
+ <yaxisside>1</yaxisside>
+ <calc_fnc>2</calc_fnc>
+ <type>0</type>
+ <item>
+ <host>Template App Ceph</host>
+ <key>ceph.pool.frac[{$CEPH_CONNPAR},{#POOL}]</key>
+ </item>
+ </graph_item>
+ <graph_item>
+ <sortorder>1</sortorder>
+ <drawtype>0</drawtype>
+ <color>000099</color>
+ <yaxisside>0</yaxisside>
+ <calc_fnc>2</calc_fnc>
+ <type>0</type>
+ <item>
+ <host>Template App Ceph</host>
+ <key>ceph.pool.size[{$CEPH_CONNPAR},{#POOL}]</key>
+ </item>
+ </graph_item>
+ </graph_items>
+ </graph_prototype>
+ </graph_prototypes>
<host_prototypes/>
</discovery_rule>
<discovery_rule>
@@ -2530,7 +2736,7 @@
<multiplier>0</multiplier>
<snmp_oid/>
<key>ceph.poolgrp.frac[{$CEPH_CONNPAR},{#POOLGRP}]</key>
- <delay>120</delay>
+ <delay>300</delay>
<history>15</history>
<trends>365</trends>
<status>0</status>
@@ -2574,7 +2780,7 @@
<multiplier>0</multiplier>
<snmp_oid/>
<key>ceph.poolgrp.objs[{$CEPH_CONNPAR},{#POOLGRP}]</key>
- <delay>120</delay>
+ <delay>300</delay>
<history>15</history>
<trends>365</trends>
<status>0</status>
@@ -2618,7 +2824,7 @@
<multiplier>0</multiplier>
<snmp_oid/>
<key>ceph.poolgrp.size[{$CEPH_CONNPAR},{#POOLGRP}]</key>
- <delay>120</delay>
+ <delay>300</delay>
<history>15</history>
<trends>365</trends>
<status>0</status>
@@ -3490,6 +3696,42 @@
<key>ceph.pgstat.rep[{$CEPH_CONNPAR}]</key>
</item>
</graph_item>
+ <graph_item>
+ <sortorder>14</sortorder>
+ <drawtype>0</drawtype>
+ <color>274482</color>
+ <yaxisside>0</yaxisside>
+ <calc_fnc>2</calc_fnc>
+ <type>0</type>
+ <item>
+ <host>Template App Ceph</host>
+ <key>ceph.pgstat.ful[{$CEPH_CONNPAR}]</key>
+ </item>
+ </graph_item>
+ <graph_item>
+ <sortorder>15</sortorder>
+ <drawtype>0</drawtype>
+ <color>2B5429</color>
+ <yaxisside>0</yaxisside>
+ <calc_fnc>2</calc_fnc>
+ <type>0</type>
+ <item>
+ <host>Template App Ceph</host>
+ <key>ceph.pgstat.sna[{$CEPH_CONNPAR}]</key>
+ </item>
+ </graph_item>
+ <graph_item>
+ <sortorder>16</sortorder>
+ <drawtype>0</drawtype>
+ <color>8048B4</color>
+ <yaxisside>0</yaxisside>
+ <calc_fnc>2</calc_fnc>
+ <type>0</type>
+ <item>
+ <host>Template App Ceph</host>
+ <key>ceph.pgstat.unf[{$CEPH_CONNPAR}]</key>
+ </item>
+ </graph_item>
</graph_items>
</graph>
<graph>
--
GitLab