func TestStandbyJoinMiss(t *testing.T) {
clusterSize := 2
_, etcds, err := CreateCluster(clusterSize, &os.ProcAttr{Files: []*os.File{nil, os.Stdout, os.Stderr}}, false)
if err != nil {
t.Fatal("cannot create cluster")
}
defer DestroyCluster(etcds)
c := etcd.NewClient(nil)
c.SyncCluster()
time.Sleep(1 * time.Second)
// Verify that we have two machines.
result, err := c.Get("_etcd/machines", false, true)
assert.NoError(t, err)
assert.Equal(t, len(result.Node.Nodes), clusterSize)
resp, _ := tests.Put("http://localhost:7001/v2/admin/config", "application/json", bytes.NewBufferString(`{"removeDelay":4, "syncInterval":4}`))
if !assert.Equal(t, resp.StatusCode, 200) {
t.FailNow()
}
time.Sleep(time.Second)
resp, _ = tests.Delete("http://localhost:7001/v2/admin/machines/node2", "application/json", nil)
if !assert.Equal(t, resp.StatusCode, 200) {
t.FailNow()
}
// Wait for a monitor cycle before checking for removal.
time.Sleep(server.ActiveMonitorTimeout + (1 * time.Second))
// Verify that we now have one peer.
result, err = c.Get("_etcd/machines", false, true)
assert.NoError(t, err)
assert.Equal(t, len(result.Node.Nodes), 1)
// Simulate the join failure
_, err = server.NewClient(nil).AddMachine("http://localhost:7001",
&server.JoinCommand{
MinVersion: store.MinVersion(),
MaxVersion: store.MaxVersion(),
Name: "node2",
RaftURL: "http://127.0.0.1:7002",
EtcdURL: "http://127.0.0.1:4002",
})
assert.NoError(t, err)
time.Sleep(6 * time.Second)
go tests.Delete("http://localhost:7001/v2/admin/machines/node2", "application/json", nil)
time.Sleep(time.Second)
result, err = c.Get("_etcd/machines", false, true)
assert.NoError(t, err)
assert.Equal(t, len(result.Node.Nodes), 1)
}
// Create a five nodes
// Kill all the nodes and restart, then remove the leader
func TestMultiNodeKillAllAndRecoveryAndRemoveLeader(t *testing.T) {
procAttr := new(os.ProcAttr)
procAttr.Files = []*os.File{nil, os.Stdout, os.Stderr}
stop := make(chan bool)
leaderChan := make(chan string, 1)
all := make(chan bool, 1)
clusterSize := 5
argGroup, etcds, err := CreateCluster(clusterSize, procAttr, false)
defer DestroyCluster(etcds)
if err != nil {
t.Fatal("cannot create cluster")
}
c := etcd.NewClient(nil)
go Monitor(clusterSize, clusterSize, leaderChan, all, stop)
<-all
<-leaderChan
stop <- true
// It needs some time to sync current commits and write it to disk.
// Or some instance may be restarted as a new peer, and we don't support
// to connect back the old cluster that doesn't have majority alive
// without log now.
time.Sleep(time.Second)
c.SyncCluster()
// kill all
DestroyCluster(etcds)
time.Sleep(time.Second)
stop = make(chan bool)
leaderChan = make(chan string, 1)
all = make(chan bool, 1)
time.Sleep(time.Second)
for i := 0; i < clusterSize; i++ {
etcds[i], err = os.StartProcess(EtcdBinPath, argGroup[i], procAttr)
}
go Monitor(clusterSize, 1, leaderChan, all, stop)
<-all
leader := <-leaderChan
_, err = c.Set("foo", "bar", 0)
if err != nil {
t.Fatalf("Recovery error: %s", err)
}
port, _ := strconv.Atoi(strings.Split(leader, ":")[2])
num := port - 7000
resp, _ := tests.Delete(leader+"/v2/admin/machines/node"+strconv.Itoa(num), "application/json", nil)
if !assert.Equal(t, resp.StatusCode, 200) {
t.FailNow()
}
// check the old leader is in standby mode now
time.Sleep(time.Second)
resp, _ = tests.Get(leader + "/name")
assert.Equal(t, resp.StatusCode, 404)
}