raft.c: Set candidate_retrying if no leader elected since last election.

[mirror_ovs.git] / tests / ovsdb-cluster.at

diff --git a/tests/ovsdb-cluster.at b/tests/ovsdb-cluster.at
index 0fbb2681f9fa0ad942ad727361b0efe5a5699d1f..c8532fa2747e2687d8b422c7b56c076bb77423d0 100644 (file)
--- a/tests/ovsdb-cluster.at
+++ b/tests/ovsdb-cluster.at
@@ -66,23 +66,30 @@ EXECUTION_EXAMPLES
 AT_BANNER([OVSDB - disconnect from cluster])
 
 OVS_START_SHELL_HELPERS
-# ovsdb_test_cluster_disconnect LEADER_OR_FOLLOWER
+# ovsdb_test_cluster_disconnect N_SERVERS LEADER_OR_FOLLOWER [CHECK_FLAPPING]
+# Test server disconnected from the cluster.
+# N_SERVERS: Number of servers in the cluster.
+# LEADER_OR_FOLLOWER: The role of the server that is disconnected from the
+#                     cluster: "leader" or "follower".
+# CHECK_FLAPPING: Whether to check if is_disconnected flapped. "yes", "no".
 ovsdb_test_cluster_disconnect () {
-    leader_or_follower=$1
+    n=$1
+    leader_or_follower=$2
+    check_flapping=$3
     schema_name=`ovsdb-tool schema-name $abs_srcdir/idltest.ovsschema`
     ordinal_schema > schema
     AT_CHECK([ovsdb-tool '-vPATTERN:console:%c|%p|%m' create-cluster s1.db $abs_srcdir/idltest.ovsschema unix:s1.raft], [0], [], [stderr])
     cid=`ovsdb-tool db-cid s1.db`
     schema_name=`ovsdb-tool schema-name $abs_srcdir/idltest.ovsschema`
-    for i in `seq 2 3`; do
+    for i in `seq 2 $n`; do
         AT_CHECK([ovsdb-tool join-cluster s$i.db $schema_name unix:s$i.raft unix:s1.raft])
     done
 
     on_exit 'kill `cat *.pid`'
-    for i in `seq 3`; do
+    for i in `seq $n`; do
         AT_CHECK([ovsdb-server -v -vconsole:off -vsyslog:off --detach --no-chdir --log-file=s$i.log --pidfile=s$i.pid --unixctl=s$i --remote=punix:s$i.ovsdb s$i.db])
     done
-    for i in `seq 3`; do
+    for i in `seq $n`; do
         AT_CHECK([ovsdb_client_wait unix:s$i.ovsdb $schema_name connected])
     done
 
@@ -96,14 +103,18 @@ ovsdb_test_cluster_disconnect () {
     # a VIP on a load-balance. So we use single remote to test here.
     if test $leader_or_follower == "leader"; then
         target=1
-        shutdown="2 3"
+        shutdown=`seq $(($n/2 + 1)) $n`
+        cleanup=`seq $(($n/2))`
     else
-        target=3
+        target=$n
 
-        # shutdown follower before the leader so that there is no chance for s3
-        # become leader during the process.
-        shutdown="2 1"
+        # shutdown followers before the leader (s1) so that there is no chance for
+        # s$n to become leader during the process.
+        shutdown="`seq 2 $(($n/2 + 1))` 1"
+        cleanup=`seq $(($n/2 + 2)) $n`
     fi
+    echo shutdown=$shutdown
+    echo cleanup=$cleanup
 
     # Connect to $target.  Use "wait" to trigger a non-op transaction so
     # that test-ovsdb will not quit.
@@ -119,6 +130,11 @@ ovsdb_test_cluster_disconnect () {
 
     OVS_WAIT_UNTIL([grep "000: i=1" test-ovsdb.log])
 
+    # Start collecting raft_is_connected logs for $target before shutting down
+    # any servers.
+    tail -f s$target.log > raft_is_connected.log &
+    echo $! > tail.pid
+
     # Shutdown the other servers so that $target is disconnected from the cluster.
     for i in $shutdown; do
         OVS_APP_EXIT_AND_WAIT_BY_TARGET([`pwd`/s$i], [s$i.pid])
@@ -127,18 +143,40 @@ ovsdb_test_cluster_disconnect () {
     # The test-ovsdb should detect the disconnect and retry.
     OVS_WAIT_UNTIL([grep disconnect test-ovsdb.log])
 
-    OVS_APP_EXIT_AND_WAIT_BY_TARGET([`pwd`/s$target], [s$target.pid])
+    # The $target debug log should show raft_is_connected: false.
+    OVS_WAIT_UNTIL([grep "raft_is_connected: false" raft_is_connected.log])
+
+    # Save the current count of "raft_is_connected: true"
+    count_old=`grep "raft_is_connected: true" raft_is_connected.log | wc -l`
+    echo count_old $count_old
+
+    if test X$check_flapping == X"yes"; then
+        sleep 10
+    fi
+    # Make sure raft_is_connected didn't flap from false to true.
+    count_new=`grep "raft_is_connected: true" raft_is_connected.log | wc -l`
+    echo count_new $count_new
+    AT_CHECK([test $count_new == $count_old])
+
+    for i in $cleanup; do
+        OVS_APP_EXIT_AND_WAIT_BY_TARGET([`pwd`/s$i], [s$i.pid])
+    done
 }
 OVS_END_SHELL_HELPERS
 
 AT_SETUP([OVSDB cluster - follower disconnect from cluster, single remote])
 AT_KEYWORDS([ovsdb server negative unix cluster disconnect])
-ovsdb_test_cluster_disconnect follower
+ovsdb_test_cluster_disconnect 3 follower
 AT_CLEANUP
 
 AT_SETUP([OVSDB cluster - leader disconnect from cluster, single remote])
 AT_KEYWORDS([ovsdb server negative unix cluster disconnect])
-ovsdb_test_cluster_disconnect leader
+ovsdb_test_cluster_disconnect 3 leader
+AT_CLEANUP
+
+AT_SETUP([OVSDB cluster - leader disconnect from cluster, check flapping])
+AT_KEYWORDS([ovsdb server negative unix cluster disconnect])
+ovsdb_test_cluster_disconnect 5 leader yes
 AT_CLEANUP
 
 \f