Add fence-and-reclaim test

Add a test which exercises the various reasons for fencing mounts and
checks that we reclaim the resources that they had.

Signed-off-by: Zach Brown <zab@versity.com>

tests/funcs/fs.sh

@@ -17,6 +17,17 @@ t_sync_seq_index()
 	t_quiet sync
 }
 
+t_mount_rid()
+{
+	local nr="${1:-0}"
+	local mnt="$(eval echo \$T_M$nr)"
+	local rid
+
+	rid=$(scoutfs statfs -s rid -p "$mnt")
+
+	echo "$rid"
+}
+
 #
 # Output the "f.$fsid.r.$rid" identifier string for the given mount
 # number, 0 is used by default if none is specified. 
@@ -132,6 +143,16 @@ t_umount()
 	eval t_quiet umount \$T_M$nr
 }
 
+t_force_umount()
+{
+	local nr="$1"
+
+	test "$nr" -lt "$T_NR_MOUNTS" || \
+		t_fail "fs nr $nr invalid"
+
+	eval t_quiet umount -f \$T_M$nr
+}
+
 #
 # Attempt to mount all the configured mounts, assuming that they're
 # not already mounted.
@@ -277,3 +298,67 @@ t_counter_diff_changed() {
 		echo "counter $which didn't change" ||
 		echo "counter $which changed"
 }
+
+#
+# See if we can find a local mount with the caller's rid.
+#
+t_rid_is_mounted() {
+	local rid="$1"
+	local fr="$1"
+
+	for fr in /sys/fs/scoutfs/*; do
+		if [ "$(cat $fr/rid)" == "$rid" ]; then
+			return 0
+		fi
+	done
+
+	return 1
+}
+
+#
+# A given mount is being fenced if any mount has a fence request pending
+# for it which hasn't finished and been removed.
+#
+t_rid_is_fencing() {
+	local rid="$1"
+	local fr
+
+	for fr in /sys/fs/scoutfs/*; do
+		if [ -d "$fr/fence/$rid" ]; then
+			return 0
+		fi
+	done
+
+	return 1
+}
+
+#
+# Wait until the mount identified by the first rid arg is not in any
+# states specified by the remaining state description word args.
+#
+t_wait_if_rid_is() {
+	local rid="$1"
+
+	while ( [[ $* =~ mounted ]] && t_rid_is_mounted $rid ) ||
+	      ( [[ $* =~ fencing ]] && t_rid_is_fencing $rid ) ; do
+		sleep .5
+	done
+}
+
+#
+# Wait until any mount identifies itself as the elected leader.  We can
+# be waiting while tests mount and unmount so mounts may not be mounted
+# at the test's expected mount points.
+#
+t_wait_for_leader() {
+	local i
+
+	while sleep .25; do
+		for i in $(t_fs_nrs); do
+			local ldr="$(t_sysfs_path $i 2>/dev/null)/quorum/is_leader"
+			if [ "$(cat $ldr 2>/dev/null)" == "1" ]; then
+				return
+			fi
+		done
+	done
+}

tests/golden/fence-and-reclaim

@@ -0,0 +1,5 @@
+== make sure all mounts can see each other
+== force unmount one client, connection timeout, fence nop, mount
+== force unmount all non-server, connection timeout, fence nop, mount
+== force unmount server, quorum elects new leader, fence nop, mount
+== force unmount everything, new server fences all previous

tests/sequence

@@ -28,6 +28,7 @@ lock-conflicting-batch-commit.sh
 cross-mount-data-free.sh
 persistent-item-vers.sh
 setup-error-teardown.sh
+fence-and-reclaim.sh
 mount-unmount-race.sh
 createmany-parallel-mounts.sh
 archive-light-cycle.sh

tests/tests/fence-and-reclaim.sh

@@ -0,0 +1,127 @@
+#
+# Fence nodes and reclaim their resources.
+#
+
+t_require_commands sleep touch grep sync scoutfs
+t_require_mounts 2
+
+#
+# Make sure that all mounts can read the results of a write from each
+# mount.  And make sure that the greatest of all the written seqs is
+# visible after the writes were commited by remote reads.
+#
+check_read_write()
+{
+	local expected
+	local greatest=0
+	local seq
+	local path
+	local saw
+	local w
+	local r
+
+	for w in $(t_fs_nrs); do
+		expected="$w wrote at $(date --rfc-3339=ns)"
+		eval path="\$T_D${w}/written"
+		echo "$expected" > "$path"
+
+		seq=$(scoutfs stat -s meta_seq $path)
+		if [ "$seq" -gt "$greatest" ]; then
+			greatest=$seq
+		fi
+
+		for r in $(t_fs_nrs); do
+			eval path="\$T_D${r}/written"
+			saw=$(cat "$path")
+			if [ "$saw" != "$expected" ]; then
+				echo "mount $r read '$saw' after mount $w wrote '$expected'"
+			fi
+		done
+	done
+
+	seq=$(scoutfs statfs -s committed_seq -p $T_D0)
+	if [ "$seq" -lt "$greatest" ]; then
+		echo "committed_seq $seq less than greatest $greatest"
+	fi
+}
+
+echo "== make sure all mounts can see each other"
+check_read_write
+
+echo "== force unmount one client, connection timeout, fence nop, mount"
+cl=$(t_first_client_nr)
+sv=$(t_server_nr)
+rid=$(t_mount_rid $cl)
+echo "cl $cl sv $sv rid $rid" >> "$T_TMP.log"
+sync
+t_force_umount $cl
+# wait for client reconnection to timeout
+while grep -q $rid $(t_debugfs_path $sv)/connections; do
+	sleep .5
+done
+while t_rid_is_fencing $rid; do
+	sleep .5
+done
+t_mount $cl
+check_read_write
+
+echo "== force unmount all non-server, connection timeout, fence nop, mount"
+sv=$(t_server_nr)
+pattern="nonsense"
+sync
+for cl in $(t_fs_nrs); do
+	if [ $cl == $sv ]; then
+		continue;
+	fi
+
+	rid=$(t_mount_rid $cl)
+	pattern="$pattern|$rid"
+	echo "cl $cl sv $sv rid $rid" >> "$T_TMP.log"
+
+	t_force_umount $cl
+done
+
+# wait for all client reconnections to timeout
+while egrep -q "($pattern)" $(t_debugfs_path $sv)/connections; do
+	sleep .5
+done
+# wait for all fence requests to complete
+while test -d $(echo /sys/fs/scoutfs/*/fence/* | cut -d " " -f 1); do
+	sleep .5
+done
+# remount all the clients
+for cl in $(t_fs_nrs); do
+	if [ $cl == $sv ]; then
+		continue;
+	fi
+	t_mount $cl
+done
+check_read_write
+
+echo "== force unmount server, quorum elects new leader, fence nop, mount"
+sv=$(t_server_nr)
+rid=$(t_mount_rid $sv)
+echo "sv $sv rid $rid" >> "$T_TMP.log"
+sync
+t_force_umount $sv
+t_wait_for_leader
+# wait until new server is done fencing unmounted leader rid
+while t_rid_is_fencing $rid; do
+	sleep .5
+done
+t_mount $sv
+check_read_write
+
+echo "== force unmount everything, new server fences all previous"
+sync
+for nr in $(t_fs_nrs); do
+	t_force_umount $nr
+done
+t_mount_all
+# wait for all fence requests to complete
+while test -d $(echo /sys/fs/scoutfs/*/fence/* | cut -d " " -f 1); do
+	sleep .5
+done
+check_read_write
+
+t_pass