From c9a9132d107d99a2f303fa766dae87397ac18274 Mon Sep 17 00:00:00 2001
From: elijah <elijah@riseup.net>
Date: Wed, 4 Mar 2015 10:58:24 -0800
Subject: temporarily increase the delay between soledad / web api tests to 60
 minutes, until we are able to fix the issue with the test users creating db
 bloat.

---
 puppet/modules/site_check_mk/files/extra_service_conf.mk | 15 ++++++++++-----
 1 file changed, 10 insertions(+), 5 deletions(-)

(limited to 'puppet/modules/site_check_mk/files')

diff --git a/puppet/modules/site_check_mk/files/extra_service_conf.mk b/puppet/modules/site_check_mk/files/extra_service_conf.mk
index 03d1ea76..61b0dd39 100644
--- a/puppet/modules/site_check_mk/files/extra_service_conf.mk
+++ b/puppet/modules/site_check_mk/files/extra_service_conf.mk
@@ -1,13 +1,18 @@
 # retry 3 times before setting a service into a hard state
 # and send out notification
-extra_service_conf["max_check_attempts"] = [ 
-  ("4", ALL_HOSTS , ALL_SERVICES ) 
+extra_service_conf["max_check_attempts"] = [
+  ("4", ALL_HOSTS , ALL_SERVICES )
 ]
 
-# run check_mk_agent every 2 minutes if it terminates
-# successfully.
+#
+# run check_mk_agent every 2 minutes if it terminates successfully.
 # see https://leap.se/code/issues/6539 for the rationale
+#
+# update: temporarily set interval to 60 minutes until we solve the
+#         issue with the users db getting bloated with deleted
+#         test users.
+#
 extra_service_conf["normal_check_interval"] = [
-  ("2", ALL_HOSTS , "Check_MK" )
+  ("60", ALL_HOSTS , "Check_MK" )
 ]
 
-- 
cgit v1.2.3


From eeb5fd763d7f78d6dcff252981cc9e38dd446fa6 Mon Sep 17 00:00:00 2001
From: elijah <elijah@riseup.net>
Date: Wed, 1 Apr 2015 22:26:56 -0700
Subject: run check_mk tests every 10 minutes

---
 puppet/modules/site_check_mk/files/extra_service_conf.mk | 8 ++------
 1 file changed, 2 insertions(+), 6 deletions(-)

(limited to 'puppet/modules/site_check_mk/files')

diff --git a/puppet/modules/site_check_mk/files/extra_service_conf.mk b/puppet/modules/site_check_mk/files/extra_service_conf.mk
index 61b0dd39..a4c6e769 100644
--- a/puppet/modules/site_check_mk/files/extra_service_conf.mk
+++ b/puppet/modules/site_check_mk/files/extra_service_conf.mk
@@ -5,14 +5,10 @@ extra_service_conf["max_check_attempts"] = [
 ]
 
 #
-# run check_mk_agent every 2 minutes if it terminates successfully.
+# run check_mk_agent every 10 minutes if it terminates successfully.
 # see https://leap.se/code/issues/6539 for the rationale
 #
-# update: temporarily set interval to 60 minutes until we solve the
-#         issue with the users db getting bloated with deleted
-#         test users.
-#
 extra_service_conf["normal_check_interval"] = [
-  ("60", ALL_HOSTS , "Check_MK" )
+  ("10", ALL_HOSTS , "Check_MK" )
 ]
 
-- 
cgit v1.2.3


From 6019eff30ef839e5c6a603fde7fe3fc98d4d4f47 Mon Sep 17 00:00:00 2001
From: varac <varacanero@zeromail.org>
Date: Sun, 1 Mar 2015 10:16:44 +0100
Subject: added local check_mk couchdb script (#6749)

leap_couch_stats.sh is a local check_mk agent script
which provides per-db stats as well as global stats.

Change-Id: I1eba19a3a0210d3127acbad119dfd2918414ff4a
---
 .../agent/local_checks/couchdb/leap_couch_stats.sh | 106 +++++++++++++++++++++
 1 file changed, 106 insertions(+)
 create mode 100755 puppet/modules/site_check_mk/files/agent/local_checks/couchdb/leap_couch_stats.sh

(limited to 'puppet/modules/site_check_mk/files')

diff --git a/puppet/modules/site_check_mk/files/agent/local_checks/couchdb/leap_couch_stats.sh b/puppet/modules/site_check_mk/files/agent/local_checks/couchdb/leap_couch_stats.sh
new file mode 100755
index 00000000..51a8ac52
--- /dev/null
+++ b/puppet/modules/site_check_mk/files/agent/local_checks/couchdb/leap_couch_stats.sh
@@ -0,0 +1,106 @@
+#!/bin/bash
+#
+# todo:
+#  - thresholds
+#  - couch response time
+#  - make CURL/URL/DBLIST_EXCLUDE vars configurable
+#  - move load_nagios_utils() to helper library so we can use it from multiple scripts
+
+start_time=$(date +%s.%N)
+
+CURL='curl -s --netrc-file /etc/couchdb/couchdb.netrc'
+URL='http://127.0.0.1:5984'
+TMPFILE=$(mktemp)
+DBLIST_EXCLUDE='user-'
+PREFIX='Couchdb_'
+
+
+load_nagios_utils () {
+  # load the nagios utils
+  # in debian, the package nagios-plugins-common installs utils.sh to /usr/lib/nagios/plugins/utils.sh
+  utilsfn=
+  for d in $PROGPATH /usr/lib/nagios/plugins /usr/lib64/nagios/plugins /usr/local/nagios/libexec /opt/nagios-plugins/libexec . ; do
+    if [ -f "$d/utils.sh" ]; then
+      utilsfn=$d/utils.sh;
+    fi
+  done
+  if [ "$utilsfn" = "" ]; then
+    echo "UNKNOWN - cannot find utils.sh (part of nagios plugins)";
+    exit 3;
+  fi
+  . "$utilsfn";
+  STATE[$STATE_OK]='OK'
+  STATE[$STATE_WARNING]='Warning'
+  STATE[$STATE_CRITICAL]='Critical'
+  STATE[$STATE_UNKNOWN]='Unknown'
+  STATE[$STATE_DEPENDENT]='Dependend'
+}
+
+get_global_stats_perf () {
+  trap "localexit=3" ERR
+  local localexit db_count
+  localexit=0
+
+  # get a list of all dbs
+  $CURL -X GET $URL/_all_dbs | json_pp | egrep -v '(\[|\])' > $TMPFILE
+
+  db_count=$( wc -l < $TMPFILE)
+  excluded_db_count=$( grep -c "$DBLIST_EXCLUDE" $TMPFILE )
+
+  echo "db_count=$db_count|excluded_db_count=$excluded_db_count"
+  return ${localexit}
+}
+
+db_stats () {
+  trap "localexit=3" ERR
+  local db db_stats doc_count del_doc_count localexit
+  localexit=0
+
+  db=$1
+  perf="$perf|${db}_docs=$( $CURL -s -X GET ${URL}/$db | json_pp |grep 'doc_count' | sed 's/[^0-9]//g' )"
+  db_stats=$( $CURL -s -X GET ${URL}/$db | json_pp )
+
+  doc_count=$( echo "$db_stats" | grep 'doc_count' | grep -v 'deleted_doc_count' | sed 's/[^0-9]//g' )
+  del_doc_count=$( echo "$db_stats" | grep 'doc_del_count' | sed 's/[^0-9]//g' )
+
+  # don't divide by zero
+  if [ $del_doc_count -eq 0 ]
+  then
+    del_doc_perc=0
+  else
+    del_doc_perc=$(( del_doc_count * 100 / doc_count ))
+  fi
+
+  bytes=$( echo "$db_stats" | grep disk_size | sed 's/[^0-9]//g' )
+  disk_size=$( echo "scale = 2; $bytes / 1024 / 1024" | bc -l )
+
+  echo -n "${localexit} ${PREFIX}${db}_database ${db}_docs=$doc_count|${db}_deleted_docs=$del_doc_count|${db}_deleted_docs_percentage=${del_doc_perc}%"
+  printf "|${db}_disksize_mb=%02.2fmb ${STATE[localexit]}: database $db\n" "$disk_size"
+
+  return ${localexit}
+}
+
+# main
+
+load_nagios_utils
+
+# per-db stats
+# get a list of all dbs
+$CURL -X GET $URL/_all_dbs | json_pp | egrep -v '(\[|\])' > $TMPFILE
+
+# get list of dbs to check
+dbs=$( grep -v "${DBLIST_EXCLUDE}" $TMPFILE | tr -d '\n"' | sed 's/,/ /g' )
+
+for db in $dbs
+do
+  db_stats "$db"
+done
+
+# show global couchdb stats
+global_stats_perf=$(get_global_stats_perf)
+exitcode=$?
+
+end_time=$(date +%s.%N)
+duration=$( echo "scale = 2; $end_time - $start_time" | bc -l )
+
+printf "${exitcode} ${PREFIX}global_stats ${global_stats_perf}|script_duration=%02.2fs ${STATE[exitcode]}: global couchdb status\n" "$duration"
-- 
cgit v1.2.3


From 7f069dc47c318e9047a3ae7a29a90f3471610e34 Mon Sep 17 00:00:00 2001
From: elijah <elijah@riseup.net>
Date: Wed, 15 Apr 2015 09:36:30 -0700
Subject: fix tapicero & webapp logs: remove heartbeat log check, move to
 /var/log/tapicero, fix webapp logwatch location.

---
 .../site_check_mk/files/agent/logwatch/syslog/tapicero.cfg    | 10 ----------
 .../site_check_mk/files/agent/logwatch/syslog/webapp.cfg      |  5 -----
 .../modules/site_check_mk/files/agent/logwatch/tapicero.cfg   | 11 +++++++++++
 puppet/modules/site_check_mk/files/agent/logwatch/webapp.cfg  |  6 ++++++
 4 files changed, 17 insertions(+), 15 deletions(-)
 delete mode 100644 puppet/modules/site_check_mk/files/agent/logwatch/syslog/tapicero.cfg
 delete mode 100644 puppet/modules/site_check_mk/files/agent/logwatch/syslog/webapp.cfg
 create mode 100644 puppet/modules/site_check_mk/files/agent/logwatch/tapicero.cfg
 create mode 100644 puppet/modules/site_check_mk/files/agent/logwatch/webapp.cfg

(limited to 'puppet/modules/site_check_mk/files')

diff --git a/puppet/modules/site_check_mk/files/agent/logwatch/syslog/tapicero.cfg b/puppet/modules/site_check_mk/files/agent/logwatch/syslog/tapicero.cfg
deleted file mode 100644
index e5721eea..00000000
--- a/puppet/modules/site_check_mk/files/agent/logwatch/syslog/tapicero.cfg
+++ /dev/null
@@ -1,10 +0,0 @@
-# Ignore transient Tapicero errors when creating a db (#6511)
- I tapicero.*(Creating database|Checking security of|Writing security to|Uploading design doc to) user-.* failed (\(trying again soon\)|(twice )?due to): (RestClient::Resource Not Found|RestClient::InternalServerError): (404 Resource Not Found|500 Internal Server Error)
- C tapicero.*RestClient::InternalServerError:
-# possible race condition between multiple tapicero
-# instances, so we ignore it
-# see https://leap.se/code/issues/5168
- I tapicero.*RestClient::PreconditionFailed:
- C tapicero.*Creating database.*failed due to:
- C tapicero.*failed
- W tapicero.*Couch stream ended unexpectedly.
diff --git a/puppet/modules/site_check_mk/files/agent/logwatch/syslog/webapp.cfg b/puppet/modules/site_check_mk/files/agent/logwatch/syslog/webapp.cfg
deleted file mode 100644
index 00f9c7fd..00000000
--- a/puppet/modules/site_check_mk/files/agent/logwatch/syslog/webapp.cfg
+++ /dev/null
@@ -1,5 +0,0 @@
-# check for webapp errors
- C webapp.*Could not connect to couch database messages due to 401 Unauthorized: {"error":"unauthorized","reason":"You are not a server admin."}
-# ignore RoutingErrors that rails throw when it can't handle a url
-# see https://leap.se/code/issues/5173
- I webapp.*ActionController::RoutingError
diff --git a/puppet/modules/site_check_mk/files/agent/logwatch/tapicero.cfg b/puppet/modules/site_check_mk/files/agent/logwatch/tapicero.cfg
new file mode 100644
index 00000000..f527f120
--- /dev/null
+++ b/puppet/modules/site_check_mk/files/agent/logwatch/tapicero.cfg
@@ -0,0 +1,11 @@
+/var/log/leap/tapicero.log
+# Ignore transient Tapicero errors when creating a db (#6511)
+ I tapicero.*(Creating database|Checking security of|Writing security to|Uploading design doc to) user-.* failed (\(trying again soon\)|(twice )?due to): (RestClient::Resource Not Found|RestClient::InternalServerError): (404 Resource Not Found|500 Internal Server Error)
+ C tapicero.*RestClient::InternalServerError:
+# possible race condition between multiple tapicero
+# instances, so we ignore it
+# see https://leap.se/code/issues/5168
+ I tapicero.*RestClient::PreconditionFailed:
+ C tapicero.*Creating database.*failed due to:
+ C tapicero.*failed
+ W tapicero.*Couch stream ended unexpectedly.
diff --git a/puppet/modules/site_check_mk/files/agent/logwatch/webapp.cfg b/puppet/modules/site_check_mk/files/agent/logwatch/webapp.cfg
new file mode 100644
index 00000000..008e9e09
--- /dev/null
+++ b/puppet/modules/site_check_mk/files/agent/logwatch/webapp.cfg
@@ -0,0 +1,6 @@
+/var/log/leap/webapp.log
+# check for webapp errors
+ C webapp.*Could not connect to couch database messages due to 401 Unauthorized: {"error":"unauthorized","reason":"You are not a server admin."}
+# ignore RoutingErrors that rails throw when it can't handle a url
+# see https://leap.se/code/issues/5173
+ I webapp.*ActionController::RoutingError
-- 
cgit v1.2.3


From bb07407485ed1626221a1190cc2fb2789f95ed22 Mon Sep 17 00:00:00 2001
From: elijah <elijah@riseup.net>
Date: Wed, 15 Apr 2015 16:12:11 -0700
Subject: clean up logging mess: add 'logfile' define, mv openvpn and stunnel
 logs to their own files, fix mx logwatch path.

---
 .../modules/site_check_mk/files/agent/logwatch/leap_mx.cfg |  2 +-
 .../modules/site_check_mk/files/agent/logwatch/openvpn.cfg | 14 ++++++++++++++
 .../modules/site_check_mk/files/agent/logwatch/stunnel.cfg | 10 ++++++++++
 .../site_check_mk/files/agent/logwatch/syslog/openvpn.cfg  | 13 -------------
 .../site_check_mk/files/agent/logwatch/syslog/stunnel.cfg  |  9 ---------
 5 files changed, 25 insertions(+), 23 deletions(-)
 create mode 100644 puppet/modules/site_check_mk/files/agent/logwatch/openvpn.cfg
 create mode 100644 puppet/modules/site_check_mk/files/agent/logwatch/stunnel.cfg
 delete mode 100644 puppet/modules/site_check_mk/files/agent/logwatch/syslog/openvpn.cfg
 delete mode 100644 puppet/modules/site_check_mk/files/agent/logwatch/syslog/stunnel.cfg

(limited to 'puppet/modules/site_check_mk/files')

diff --git a/puppet/modules/site_check_mk/files/agent/logwatch/leap_mx.cfg b/puppet/modules/site_check_mk/files/agent/logwatch/leap_mx.cfg
index c71c5392..166d0230 100644
--- a/puppet/modules/site_check_mk/files/agent/logwatch/leap_mx.cfg
+++ b/puppet/modules/site_check_mk/files/agent/logwatch/leap_mx.cfg
@@ -1,4 +1,4 @@
-/var/log/leap_mx.log
+/var/log/leap/mx.log
  W Don't know how to deliver mail
  W No public key, stopping the processing chain
 
diff --git a/puppet/modules/site_check_mk/files/agent/logwatch/openvpn.cfg b/puppet/modules/site_check_mk/files/agent/logwatch/openvpn.cfg
new file mode 100644
index 00000000..ed50f420
--- /dev/null
+++ b/puppet/modules/site_check_mk/files/agent/logwatch/openvpn.cfg
@@ -0,0 +1,14 @@
+/var/log/leap/openvpn.log
+# ignore openvpn TLS initialization errors when clients
+# suddenly hangup before properly establishing
+# a tls connection
+ I ovpn-.*TLS Error: Unroutable control packet received from
+ I ovpn-.*TLS Error: TLS key negotiation failed to occur within 60 seconds \(check your network connectivity\)
+ I ovpn-.*TLS Error: TLS handshake failed
+ I ovpn-.*TLS Error: TLS object -> incoming plaintext read error
+ I ovpn-.*Fatal TLS error \(check_tls_errors_co\), restarting
+ I ovpn-.*TLS_ERROR: BIO read tls_read_plaintext error: error:140890B2:SSL routines:SSL3_GET_CLIENT_CERTIFICATE:no certificate
+
+ I ovpn-.*SIGUSR1\[soft,tls-error\] received, client-instance restarting
+ I ovpn-.*VERIFY ERROR: depth=0, error=certificate has expired
+
diff --git a/puppet/modules/site_check_mk/files/agent/logwatch/stunnel.cfg b/puppet/modules/site_check_mk/files/agent/logwatch/stunnel.cfg
new file mode 100644
index 00000000..b1e6cf2f
--- /dev/null
+++ b/puppet/modules/site_check_mk/files/agent/logwatch/stunnel.cfg
@@ -0,0 +1,10 @@
+/var/log/leap/stunnel.log
+# check for stunnel failures
+#
+# these are temporary failures and happen very often, so we
+# ignore them until we tuned stunnel timeouts/logging,
+# see https://leap.se/code/issues/5218
+ I stunnel:.*Connection reset by peer
+ I stunnel:.*Peer suddenly disconnected
+ I stunnel:.*Connection refused
+
diff --git a/puppet/modules/site_check_mk/files/agent/logwatch/syslog/openvpn.cfg b/puppet/modules/site_check_mk/files/agent/logwatch/syslog/openvpn.cfg
deleted file mode 100644
index ac17c0ca..00000000
--- a/puppet/modules/site_check_mk/files/agent/logwatch/syslog/openvpn.cfg
+++ /dev/null
@@ -1,13 +0,0 @@
-# ignore openvpn TLS initialization errors when clients
-# suddenly hangup before properly establishing
-# a tls connection
- I ovpn-.*TLS Error: Unroutable control packet received from
- I ovpn-.*TLS Error: TLS key negotiation failed to occur within 60 seconds \(check your network connectivity\)
- I ovpn-.*TLS Error: TLS handshake failed
- I ovpn-.*TLS Error: TLS object -> incoming plaintext read error
- I ovpn-.*Fatal TLS error \(check_tls_errors_co\), restarting
- I ovpn-.*TLS_ERROR: BIO read tls_read_plaintext error: error:140890B2:SSL routines:SSL3_GET_CLIENT_CERTIFICATE:no certificate
-
- I ovpn-.*SIGUSR1\[soft,tls-error\] received, client-instance restarting
- I ovpn-.*VERIFY ERROR: depth=0, error=certificate has expired
-
diff --git a/puppet/modules/site_check_mk/files/agent/logwatch/syslog/stunnel.cfg b/puppet/modules/site_check_mk/files/agent/logwatch/syslog/stunnel.cfg
deleted file mode 100644
index eb3131f2..00000000
--- a/puppet/modules/site_check_mk/files/agent/logwatch/syslog/stunnel.cfg
+++ /dev/null
@@ -1,9 +0,0 @@
-# check for stunnel failures
-#
-# these are temporary failures and happen very often, so we
-# ignore them until we tuned stunnel timeouts/logging,
-# see https://leap.se/code/issues/5218
- I stunnel:.*Connection reset by peer
- I stunnel:.*Peer suddenly disconnected
- I stunnel:.*Connection refused
-
-- 
cgit v1.2.3


From e65460dcefda6660431d937e9a66d17a1d80e104 Mon Sep 17 00:00:00 2001
From: varac <varacanero@zeromail.org>
Date: Sun, 26 Apr 2015 21:19:33 +0200
Subject: Tapicero changed it's error message when uploading design doc fails
 in race condition with another tapicero instance #6534

Change-Id: Ie194a2983210601bd24aef5e74f8b7fa2b7c433f
---
 puppet/modules/site_check_mk/files/agent/logwatch/tapicero.cfg | 2 +-
 1 file changed, 1 insertion(+), 1 deletion(-)

(limited to 'puppet/modules/site_check_mk/files')

diff --git a/puppet/modules/site_check_mk/files/agent/logwatch/tapicero.cfg b/puppet/modules/site_check_mk/files/agent/logwatch/tapicero.cfg
index f527f120..d98f5094 100644
--- a/puppet/modules/site_check_mk/files/agent/logwatch/tapicero.cfg
+++ b/puppet/modules/site_check_mk/files/agent/logwatch/tapicero.cfg
@@ -1,6 +1,6 @@
 /var/log/leap/tapicero.log
 # Ignore transient Tapicero errors when creating a db (#6511)
- I tapicero.*(Creating database|Checking security of|Writing security to|Uploading design doc to) user-.* failed (\(trying again soon\)|(twice )?due to): (RestClient::Resource Not Found|RestClient::InternalServerError): (404 Resource Not Found|500 Internal Server Error)
+ I tapicero.*(Creating database|Checking security of|Writing security to|Uploading design doc to) user-.* failed (\(trying again soon\)|(twice )?due to): (RestClient::ResourceNotFound|RestClient::InternalServerError): (404 Resource Not Found|500 Internal Server Error)
  C tapicero.*RestClient::InternalServerError:
 # possible race condition between multiple tapicero
 # instances, so we ignore it
-- 
cgit v1.2.3


From eaddcfca6761bac329a57a65453958b6741f2420 Mon Sep 17 00:00:00 2001
From: varac <varacanero@zeromail.org>
Date: Sun, 26 Apr 2015 22:41:29 +0200
Subject: run check_mk_agent every 4 instead of 10 minutes, useful for better
 graphs

Change-Id: Ibefc6ce08cf714cf79a460a8b6eb32e2851ce22c
---
 puppet/modules/site_check_mk/files/extra_service_conf.mk | 4 ++--
 1 file changed, 2 insertions(+), 2 deletions(-)

(limited to 'puppet/modules/site_check_mk/files')

diff --git a/puppet/modules/site_check_mk/files/extra_service_conf.mk b/puppet/modules/site_check_mk/files/extra_service_conf.mk
index a4c6e769..c7120a96 100644
--- a/puppet/modules/site_check_mk/files/extra_service_conf.mk
+++ b/puppet/modules/site_check_mk/files/extra_service_conf.mk
@@ -5,10 +5,10 @@ extra_service_conf["max_check_attempts"] = [
 ]
 
 #
-# run check_mk_agent every 10 minutes if it terminates successfully.
+# run check_mk_agent every 4 minutes if it terminates successfully.
 # see https://leap.se/code/issues/6539 for the rationale
 #
 extra_service_conf["normal_check_interval"] = [
-  ("10", ALL_HOSTS , "Check_MK" )
+  ("4", ALL_HOSTS , "Check_MK" )
 ]
 
-- 
cgit v1.2.3


From ccf63cf34fedbcff2923b11f2e49c3a58b6c1180 Mon Sep 17 00:00:00 2001
From: varac <varacanero@zeromail.org>
Date: Wed, 27 May 2015 11:17:06 +0200
Subject: leap_couch_stats.sh handles rotated dbs (#6987)

Change-Id: I115ebdefd7365bf15a30c4a3ce7a4543ad757cec
---
 .../agent/local_checks/couchdb/leap_couch_stats.sh | 25 ++++++++++++++++------
 1 file changed, 19 insertions(+), 6 deletions(-)

(limited to 'puppet/modules/site_check_mk/files')

diff --git a/puppet/modules/site_check_mk/files/agent/local_checks/couchdb/leap_couch_stats.sh b/puppet/modules/site_check_mk/files/agent/local_checks/couchdb/leap_couch_stats.sh
index 51a8ac52..95474ccb 100755
--- a/puppet/modules/site_check_mk/files/agent/local_checks/couchdb/leap_couch_stats.sh
+++ b/puppet/modules/site_check_mk/files/agent/local_checks/couchdb/leap_couch_stats.sh
@@ -11,7 +11,7 @@ start_time=$(date +%s.%N)
 CURL='curl -s --netrc-file /etc/couchdb/couchdb.netrc'
 URL='http://127.0.0.1:5984'
 TMPFILE=$(mktemp)
-DBLIST_EXCLUDE='user-'
+DBLIST_EXCLUDE='(user-|sessions_|tokens_)'
 PREFIX='Couchdb_'
 
 
@@ -45,7 +45,7 @@ get_global_stats_perf () {
   $CURL -X GET $URL/_all_dbs | json_pp | egrep -v '(\[|\])' > $TMPFILE
 
   db_count=$( wc -l < $TMPFILE)
-  excluded_db_count=$( grep -c "$DBLIST_EXCLUDE" $TMPFILE )
+  excluded_db_count=$( egrep -c "$DBLIST_EXCLUDE" $TMPFILE )
 
   echo "db_count=$db_count|excluded_db_count=$excluded_db_count"
   return ${localexit}
@@ -56,7 +56,14 @@ db_stats () {
   local db db_stats doc_count del_doc_count localexit
   localexit=0
 
-  db=$1
+  db="$1"
+  name="$2"
+
+  if [ -z "$name" ]
+  then
+    name="$db"
+  fi
+
   perf="$perf|${db}_docs=$( $CURL -s -X GET ${URL}/$db | json_pp |grep 'doc_count' | sed 's/[^0-9]//g' )"
   db_stats=$( $CURL -s -X GET ${URL}/$db | json_pp )
 
@@ -74,8 +81,8 @@ db_stats () {
   bytes=$( echo "$db_stats" | grep disk_size | sed 's/[^0-9]//g' )
   disk_size=$( echo "scale = 2; $bytes / 1024 / 1024" | bc -l )
 
-  echo -n "${localexit} ${PREFIX}${db}_database ${db}_docs=$doc_count|${db}_deleted_docs=$del_doc_count|${db}_deleted_docs_percentage=${del_doc_perc}%"
-  printf "|${db}_disksize_mb=%02.2fmb ${STATE[localexit]}: database $db\n" "$disk_size"
+  echo -n "${localexit} ${PREFIX}${name}_database ${name}_docs=$doc_count|${name}_deleted_docs=$del_doc_count|${name}_deleted_docs_percentage=${del_doc_perc}%"
+  printf "|${name}_disksize_mb=%02.2fmb ${STATE[localexit]}: database $name\n" "$disk_size"
 
   return ${localexit}
 }
@@ -89,13 +96,19 @@ load_nagios_utils
 $CURL -X GET $URL/_all_dbs | json_pp | egrep -v '(\[|\])' > $TMPFILE
 
 # get list of dbs to check
-dbs=$( grep -v "${DBLIST_EXCLUDE}" $TMPFILE | tr -d '\n"' | sed 's/,/ /g' )
+dbs=$( egrep -v "${DBLIST_EXCLUDE}" $TMPFILE | tr -d '\n"' | sed 's/,/ /g' )
 
 for db in $dbs
 do
   db_stats "$db"
 done
 
+# special handling for rotated dbs
+suffix=$(($(date +'%s') / (60*60*24*30) + 1))
+db_stats "sessions_${suffix}" "sessions"
+db_stats "tokens_${suffix}" "tokens"
+
+
 # show global couchdb stats
 global_stats_perf=$(get_global_stats_perf)
 exitcode=$?
-- 
cgit v1.2.3