[SCM] CTDB repository - branch master updated - ctdb-1.0.114-24-g83446b2

[Ronnie Sahlberg]

The branch, master has been updated
       via  83446b2e7e28e3ed6627c1950053018b8799984a (commit)
       via  234b86fb19aae7a43f1dd2c0f69b03164fe5aaca (commit)
      from  1cdaaa0a3f53d1b075340a33dfdc42b534e99187 (commit)

http://gitweb.samba.org/?p=sahlberg/ctdb.git;a=shortlog;h=master


- Log -----------------------------------------------------------------
commit 83446b2e7e28e3ed6627c1950053018b8799984a
Author: Ronnie Sahlberg <ronniesahlberg at gmail.com>
Date:   Fri Apr 23 08:52:09 2010 +1000

    Add a setting where CTDB will monitor and warn for low memory conditions.
    
        CTDB_MONITOR_FREE_MEMORY_WARN
    
    BZ 59747

commit 234b86fb19aae7a43f1dd2c0f69b03164fe5aaca
Author: Ronnie Sahlberg <ronniesahlberg at gmail.com>
Date:   Fri Apr 23 08:35:01 2010 +1000

    In the example script to remove all ip addresses after a ctdb crash,
    add the NATGW address as one to be removed in addition to the
    public addresses.

-----------------------------------------------------------------------

Summary of changes:
 config/ctdb-crash-cleanup.sh |    2 +-
 config/ctdb.sysconfig        |   15 ++++++++++-----
 config/events.d/00.ctdb      |    8 ++++++++
 3 files changed, 19 insertions(+), 6 deletions(-)


Changeset truncated at 500 lines:

diff --git a/config/ctdb-crash-cleanup.sh b/config/ctdb-crash-cleanup.sh
index ca6a838..420db76 100755
--- a/config/ctdb-crash-cleanup.sh
+++ b/config/ctdb-crash-cleanup.sh
@@ -22,7 +22,7 @@ ctdb status 2>/dev/null && {
     exit 0
 }
 
-cat "$CTDB_PUBLIC_ADDRESSES" | cut -d/ -f1 | while read _IP; do
+(cat /etc/sysconfig/ctdb | egrep "^CTDB_NATGW_PUBLIC_IP" | sed -e "s/.*=//" -e "s/\/.*//";cat "$CTDB_PUBLIC_ADDRESSES" | cut -d/ -f1) | while read _IP; do
 	_IP_HELD=`/sbin/ip addr show | grep "inet $_IP/"`
 	[ -z "$_IP_HELD" ] || {
 		_IFACE=`echo $_IP_HELD | sed -e "s/.*\s//"`
diff --git a/config/ctdb.sysconfig b/config/ctdb.sysconfig
index a19dd0e..c94ce68 100644
--- a/config/ctdb.sysconfig
+++ b/config/ctdb.sysconfig
@@ -112,14 +112,19 @@ CTDB_RECOVERY_LOCK="/some/place/on/shared/storage"
 # defaults to tcp
 # CTDB_TRANSPORT="tcp"
 
-# When set, this variable makes ctdb monitor the amount of free memory
-# in the system (the second number in the buffers/cache output from free -m).
-# If the amount of free memory drops below this treshold the node will become
-# unhealthy and ctdb and all managed services will be shutdown.
+# These setting allow monitoring for low/out-out of memory conditions.
+#
+# If set, once available memory drops below CTDB_MONITOR_FREE_MEMORY_WARN
+# ctdb will start logging messages that memory is low, but will not
+# take any further action.
+#
+# If the amount of free memory drops below CTDB_MONITOR_FREE_MEMORY 
+# ctdb will fail all service over to a different node and finally shutdown.
 # Once this occurs, the administrator needs to find the reason for the OOM
 # situation, rectify it and restart ctdb with "service ctdb start"
 # The unit is MByte
-# CTDB_MONITOR_FREE_MEMORY=100
+# CTDB_MONITOR_FREE_MEMORY_WARN=100
+# CTDB_MONITOR_FREE_MEMORY=10
 
 # When set to yes, the CTDB node will start in DISABLED mode and not host
 # any public ip addresses. The administrator needs to explicitely enable
diff --git a/config/events.d/00.ctdb b/config/events.d/00.ctdb
index 5255617..bfebcd2 100755
--- a/config/events.d/00.ctdb
+++ b/config/events.d/00.ctdb
@@ -44,6 +44,14 @@ case "$1" in
 	    fi
 	}
 
+	# warn when we get low on memory
+	[ -z "$CTDB_MONITOR_FREE_MEMORY_WARN" ] || {
+		FREE_MEM=`free -m | grep "buffers/cache" | while read A B C D ;do /bin/echo -n $D ; done`
+		[ `expr "$FREE_MEM" "<" "$CTDB_MONITOR_FREE_MEMORY_WARN"` != "0" ] && {
+			echo "Running low on memory. Free:$FREE_MEM while CTDB treshold is $CTDB_MONITOR_FREE_MEMORY_WARN"
+		}
+	}
+
 	# monitor that we are not running out of memory
 	[ -z "$CTDB_MONITOR_FREE_MEMORY" ] || {
 		FREE_MEM=`free -m | grep "buffers/cache" | while read A B C D ;do /bin/echo -n $D ; done`


-- 
CTDB repository