ctdb-scripts: Change statd-callout to be more scalable

Updating ctdb.tdb on each add-client, del-client and each delete
during notify was too ambitious.  Persistent transactions do not
perform well enough to do this.

Revert to having add-client and del-client create touch files.  Each
monitor event calls "statd-callout update" to convert touch files into
ctdb.tdb records.

Update testcases to do the "update" and add an extra test.

Signed-off-by: Martin Schwenke <martin@meltin.net>
Pair-programmed-with: Amitay Isaacs <amitay@gmail.com>
Reviewed-by: Amitay Isaacs <amitay@gmail.com>

11 files changed, 123 insertions, 59 deletions

diff --git a/ctdb/config/events.d/60.ganesha b/ctdb/config/events.d/60.ganesha
index 150be1f159..fc170983dc 100755
--- a/ctdb/config/events.d/60.ganesha
+++ b/ctdb/config/events.d/60.ganesha
@@ -221,6 +221,7 @@ case "$1" in
 	} || exit $?
 
 	update_tickles 2049
+	nfs_update_lock_info
 
 	# check that statd responds to rpc requests
 	# if statd is not running we try to restart it
diff --git a/ctdb/config/events.d/60.nfs b/ctdb/config/events.d/60.nfs
index c4e798e2ca..d570cd784b 100755
--- a/ctdb/config/events.d/60.nfs
+++ b/ctdb/config/events.d/60.nfs
@@ -91,6 +91,7 @@ case "$1" in
 	} || exit $?
 
 	update_tickles 2049
+	nfs_update_lock_info
 
 	nfs_check_rpc_services
 
diff --git a/ctdb/config/functions b/ctdb/config/functions
index 8c5e472f1a..da726222cb 100755
--- a/ctdb/config/functions
+++ b/ctdb/config/functions
@@ -690,6 +690,16 @@ get_tcp_connections_for_ip ()
 	 {print $4" "$5}'
 }
 
+##################################################################
+# use statd-callout to update NFS lock info
+##################################################################
+nfs_update_lock_info ()
+{
+    if [ -x "$CTDB_BASE/statd-callout" ] ; then
+	"$CTDB_BASE/statd-callout" update
+    fi
+}
+
 ########################################################
 # start/stop the Ganesha nfs service
 ########################################################
diff --git a/ctdb/config/statd-callout b/ctdb/config/statd-callout
index b92942557f..4a331aca2c 100755
--- a/ctdb/config/statd-callout
+++ b/ctdb/config/statd-callout
@@ -30,7 +30,19 @@ loadconfig nfs
 nl="
 "
 
+ctdb_setup_service_state_dir "statd-callout"
+
+cd "$service_state_dir" || \
+    die "Failed to change directory to \"${service_state_dir}\""
+
 case "$1" in
+    # Keep a single file to keep track of the last "add-client" or
+    # "del-client'.  These get pushed to ctdb.tdb during "update",
+    # which will generally be run once each "monitor" cycle.  In this
+    # way we avoid scalability problems with flood of persistent
+    # transactions after a "notify" when all the clients re-take their
+    # locks.
+
     add-client)
 	# statd does not tell us to which IP the client connected so
 	# we must add it to all the IPs that we serve
@@ -38,42 +50,47 @@ case "$1" in
 	pnn=$(ctdb xpnn | sed -e 's/.*://')
 	date=$(date '+%s')
 	ctdb ip -X |
-	tail -n +2 | {
-	    # This all needs to be in the end of the pipe so it
-	    # doesn't get lost
-	    items=""
-	    while IFS="|" read x sip node x ; do
-		[ "$node" = "$pnn" ] || continue # not us
-		key="statd-state@${sip}@${cip}"
-		item="\"${key}\" \"${date}\""
-		items="${items}${items:+${nl}}${item}"
-	    done
-	    if ! echo "$items" | ctdb ptrans "ctdb.tdb" ; then
-		die "Failed to add clients"
-	    fi
-	}
+	tail -n +2 |
+	while IFS="|" read x sip node x ; do
+	    [ "$node" = "$pnn" ] || continue # not us
+	    key="statd-state@${sip}@${cip}"
+	    echo "\"${key}\" \"${date}\"" >"$key"
+	done
 	;;
-  del-client)
+
+    del-client)
 	# statd does not tell us from which IP the client disconnected
 	# so we must add it to all the IPs that we serve
 	cip="$2"
 	pnn=$(ctdb xpnn | sed -e 's/.*://')
 	ctdb ip -X |
-	tail -n +2 | {
-	    # This all needs to be in the end of the pipe so it
-	    # doesn't get lost
-	    items=""
-	    while IFS="|" read x sip node x ; do
-		[ "$node" = "$pnn" ] || continue # not us
-		key="statd-state@${sip}@${cip}"
-		item="\"${key}\" \"\""
-		items="${items}${items:+${nl}}${item}"
-	    done
-	    if ! echo "$items" | ctdb ptrans "ctdb.tdb" ; then
-		die "Failed to delete clients"
-	    fi
-	}
+	tail -n +2 |
+	while IFS="|" read x sip node x ; do
+	    [ "$node" = "$pnn" ] || continue # not us
+	    key="statd-state@${sip}@${cip}"
+	    echo "\"${key}\" \"\"" >"$key"
+	done
 	;;
+
+    update)
+        files=$(echo statd-state@*)
+	if [ "$files" = "statd-state@*" ] ; then
+	    # No files!
+	    exit 0
+	fi
+	# Filter out lines for any IP addresses that are not currently
+	# hosted public IP addresses.
+	pnn=$(ctdb xpnn | sed -e 's/.*://')
+	ctdb_ips=$(ctdb ip | tail -n +2)
+	sed_expr=$(echo "$ctdb_ips" |
+	    awk -v pnn=$pnn 'pnn == $2 { \
+                ip = $1; gsub(/\./, "\\.", ip); \
+                printf "/statd-state@%s@/p\n", ip }')
+        if cat $files | sed -n "$sed_expr" | ctdb ptrans "ctdb.tdb" ; then
+            rm $files
+	fi
+        ;;
+
     notify)
 	# we must restart the lockmanager (on all nodes) so that we get
 	# a clusterwide grace period (so other clients dont take out
@@ -144,7 +161,8 @@ case "$1" in
 	# Construct a sed expression to take catdb output and produce pairs of:
 	#   server-IP client-IP
 	# but only for the server-IPs that are hosted on this node.
-	sed_expr=$(ctdb ip | tail -n +2 |
+	ctdb_all_ips=$(ctdb ip -n all | tail -n +2)
+	sed_expr=$(echo "$ctdb_all_ips" |
 	    awk -v pnn=$pnn 'pnn == $2 { \
                 ip = $1; gsub(/\./, "\\.", ip); \
                 printf "s/^key.*=.*statd-state@\\(%s\\)@\\([^\"]*\\).*/\\1 \\2/p\n", ip }')
@@ -152,34 +170,42 @@ case "$1" in
 	statd_state=$(ctdb catdb ctdb.tdb | sed -n "$sed_expr" | sort)
 	[ -n "$statd_state" ] || exit 0
 
-	# The following is dangerous if this script times out before
-	# all of the smnotify commands are run.  Revert to individual
-	# pdelete commands for now and consider optimising smnotify to
-	# read all the data from stdin and then run it in the
-	# background.
-	#
-	# Delete all the items from the TDB
-	#if ! echo "$statd_state" | \
-	#    awk '{ printf "\"statd-state@%s@%s\" \"\"\n", $1, $2 }') | \
-	#    ctdb ptrans ctdb.tdb ; then
+	prev=""
+	echo "$statd_state" | {
+	    # This all needs to be in the same command group at the
+	    # end of the pipe so it doesn't get lost when the loop
+	    # completes.
+	    items=""
+	    while read sip cip ; do
+		# Collect item to delete from the DB
+		key="statd-state@${sip}@${cip}"
+		item="\"${key}\" \"\""
+		items="${items}${items:+${nl}}${item}"
 
-	#    die "Yikes!"
-	#fi
+		# NOTE: Consider optimising smnotify to read all the
+		# data from stdin and then run it in the background.
+
+		# Reset stateval for each serverip
+		[ "$sip" = "$prev" ] || stateval="$state_even"
+		# Send notifies for server shutdown
+		smnotify --client=$cip --ip=$sip --server=$sip --stateval=$stateval
+		smnotify --client=$cip --ip=$sip --server=$NFS_HOSTNAME --stateval=$stateval
+		# Send notifies for server startup
+		stateval=$(($stateval + 1))
+		smnotify --client=$cip --ip=$sip --server=$sip --stateval=$stateval
+		smnotify --client=$cip --ip=$sip --server=$NFS_HOSTNAME --stateval=$stateval
+	    done
 
-	prev=""
-	echo "$statd_state" |
-	while read sip cip ; do
-	    # Delete the entry from the DB
-	    ctdb pdelete ctdb.tdb "statd-state@${sip}@${cip}"
-	    # Reset stateval for each serverip
-	    [ "$sip" = "$prev" ] || stateval="$state_even"
-	    # Send notifies for server shutdown
-	    smnotify --client=$cip --ip=$sip --server=$sip --stateval=$stateval
-	    smnotify --client=$cip --ip=$sip --server=$NFS_HOSTNAME --stateval=$stateval
-	    # Send notifies for server startup
-	    stateval=$(($stateval + 1))
-	    smnotify --client=$cip --ip=$sip --server=$sip --stateval=$stateval
-	    smnotify --client=$cip --ip=$sip --server=$NFS_HOSTNAME --stateval=$stateval
-	done
+	    echo "$items" | ctdb ptrans "ctdb.tdb"
+	}
+
+	# Remove any stale touch files (i.e. for IPs not currently
+	# hosted on this node and created since the last "update").
+	# There's nothing else we can do with them at this stage.
+	echo "$ctdb_all_ips" |
+	    awk -v pnn=$pnn 'pnn != $2 { print $1 }' |
+	    while read sip ; do
+		rm -f "statd-state@${sip}@"*
+	    done
 	;;
 esac
diff --git a/ctdb/tests/eventscripts/statd-callout.001.sh b/ctdb/tests/eventscripts/statd-callout.001.sh
index 5f7b7e281b..29b9fbc8bf 100755
--- a/ctdb/tests/eventscripts/statd-callout.001.sh
+++ b/ctdb/tests/eventscripts/statd-callout.001.sh
@@ -10,5 +10,6 @@ FAKE_DATE_OUTPUT="1234565789"
 
 ok_null
 simple_test_event "add-client" "192.168.123.45"
+simple_test_event "update"
 
 check_ctdb_tdb_statd_state "192.168.123.45"
diff --git a/ctdb/tests/eventscripts/statd-callout.002.sh b/ctdb/tests/eventscripts/statd-callout.002.sh
index f8778f7e98..009da1b0d9 100755
--- a/ctdb/tests/eventscripts/statd-callout.002.sh
+++ b/ctdb/tests/eventscripts/statd-callout.002.sh
@@ -2,7 +2,7 @@
 
 . "${TEST_SCRIPTS_DIR}/unit.sh"
 
-define_test "2 x add-client"
+define_test "2 x add-client, update"
 
 setup_ctdb
 
@@ -11,5 +11,6 @@ FAKE_DATE_OUTPUT="1234565789"
 ok_null
 simple_test_event "add-client" "192.168.123.45"
 simple_test_event "add-client" "192.168.123.46"
+simple_test_event "update"
 
 check_ctdb_tdb_statd_state "192.168.123.45" "192.168.123.46"
diff --git a/ctdb/tests/eventscripts/statd-callout.003.sh b/ctdb/tests/eventscripts/statd-callout.003.sh
index 1319ee4099..ed28de683e 100755
--- a/ctdb/tests/eventscripts/statd-callout.003.sh
+++ b/ctdb/tests/eventscripts/statd-callout.003.sh
@@ -2,7 +2,7 @@
 
 . "${TEST_SCRIPTS_DIR}/unit.sh"
 
-define_test "add-client, del-client"
+define_test "add-client, update, del-client, update"
 
 setup_ctdb
 
@@ -10,6 +10,9 @@ FAKE_DATE_OUTPUT="1234565789"
 
 ok_null
 simple_test_event "add-client" "192.168.123.45"
+simple_test_event "update"
+
 simple_test_event "del-client" "192.168.123.45"
+simple_test_event "update"
 
 check_ctdb_tdb_statd_state
diff --git a/ctdb/tests/eventscripts/statd-callout.004.sh b/ctdb/tests/eventscripts/statd-callout.004.sh
index 5702b85290..011ced9578 100755
--- a/ctdb/tests/eventscripts/statd-callout.004.sh
+++ b/ctdb/tests/eventscripts/statd-callout.004.sh
@@ -10,6 +10,7 @@ FAKE_DATE_OUTPUT="1234565789"
 
 ok_null
 simple_test_event "add-client" "192.168.123.45"
+simple_test_event "update"
 
 check_ctdb_tdb_statd_state "192.168.123.45"
 
diff --git a/ctdb/tests/eventscripts/statd-callout.005.sh b/ctdb/tests/eventscripts/statd-callout.005.sh
index 65e291d088..ceb4445fb7 100755
--- a/ctdb/tests/eventscripts/statd-callout.005.sh
+++ b/ctdb/tests/eventscripts/statd-callout.005.sh
@@ -10,11 +10,13 @@ FAKE_DATE_OUTPUT="1234565789"
 
 ok_null
 simple_test_event "add-client" "192.168.123.45"
+simple_test_event "update"
 
 FAKE_CTDB_PNN=1
 
 ok_null
 simple_test_event "add-client" "192.168.123.46"
+simple_test_event "update"
 
 FAKE_CTDB_PNN=0
 
diff --git a/ctdb/tests/eventscripts/statd-callout.006.sh b/ctdb/tests/eventscripts/statd-callout.006.sh
index df8af8876b..0db86fee0f 100755
--- a/ctdb/tests/eventscripts/statd-callout.006.sh
+++ b/ctdb/tests/eventscripts/statd-callout.006.sh
@@ -10,11 +10,13 @@ FAKE_DATE_OUTPUT="1234565789"
 
 ok_null
 simple_test_event "add-client" "192.168.123.45"
+simple_test_event "update"
 
 FAKE_CTDB_PNN=1
 
 ok_null
 simple_test_event "add-client" "192.168.123.46"
+simple_test_event "update"
 
 FAKE_CTDB_PNN=0
 
diff --git a/ctdb/tests/eventscripts/statd-callout.007.sh b/ctdb/tests/eventscripts/statd-callout.007.sh
new file mode 100755
index 0000000000..32339cd3b7
--- /dev/null
+++ b/ctdb/tests/eventscripts/statd-callout.007.sh
@@ -0,0 +1,16 @@
+#!/bin/sh
+
+. "${TEST_SCRIPTS_DIR}/unit.sh"
+
+define_test "add-client, del-client, update"
+
+setup_ctdb
+
+FAKE_DATE_OUTPUT="1234565789"
+
+ok_null
+simple_test_event "add-client" "192.168.123.45"
+simple_test_event "del-client" "192.168.123.45"
+simple_test_event "update"
+
+check_ctdb_tdb_statd_state