6158 lines
166 KiB
Go
6158 lines
166 KiB
Go
package agent
|
|
|
|
import (
|
|
"bytes"
|
|
"context"
|
|
"crypto/md5"
|
|
"crypto/tls"
|
|
"crypto/x509"
|
|
"encoding/base64"
|
|
"encoding/json"
|
|
"fmt"
|
|
"io/ioutil"
|
|
"math/rand"
|
|
"net"
|
|
"net/http"
|
|
"net/http/httptest"
|
|
"net/url"
|
|
"os"
|
|
"path"
|
|
"path/filepath"
|
|
"strconv"
|
|
"strings"
|
|
"sync"
|
|
"testing"
|
|
"time"
|
|
|
|
"github.com/golang/protobuf/jsonpb"
|
|
"github.com/google/go-cmp/cmp"
|
|
"github.com/google/go-cmp/cmp/cmpopts"
|
|
"github.com/google/tcpproxy"
|
|
"github.com/hashicorp/consul/agent/hcp"
|
|
"github.com/hashicorp/consul/agent/hcp/scada"
|
|
"github.com/hashicorp/go-hclog"
|
|
"github.com/hashicorp/hcp-scada-provider/capability"
|
|
"github.com/hashicorp/serf/coordinate"
|
|
"github.com/hashicorp/serf/serf"
|
|
"github.com/stretchr/testify/assert"
|
|
"github.com/stretchr/testify/mock"
|
|
"github.com/stretchr/testify/require"
|
|
"golang.org/x/sync/errgroup"
|
|
"google.golang.org/grpc"
|
|
"gopkg.in/square/go-jose.v2/jwt"
|
|
|
|
"github.com/hashicorp/consul/agent/cache"
|
|
cachetype "github.com/hashicorp/consul/agent/cache-types"
|
|
"github.com/hashicorp/consul/agent/checks"
|
|
"github.com/hashicorp/consul/agent/config"
|
|
"github.com/hashicorp/consul/agent/connect"
|
|
"github.com/hashicorp/consul/agent/consul"
|
|
"github.com/hashicorp/consul/agent/structs"
|
|
"github.com/hashicorp/consul/agent/token"
|
|
"github.com/hashicorp/consul/api"
|
|
"github.com/hashicorp/consul/internal/go-sso/oidcauth/oidcauthtest"
|
|
"github.com/hashicorp/consul/ipaddr"
|
|
"github.com/hashicorp/consul/lib"
|
|
"github.com/hashicorp/consul/proto/pbautoconf"
|
|
"github.com/hashicorp/consul/sdk/freeport"
|
|
"github.com/hashicorp/consul/sdk/testutil"
|
|
"github.com/hashicorp/consul/sdk/testutil/retry"
|
|
"github.com/hashicorp/consul/testrpc"
|
|
"github.com/hashicorp/consul/tlsutil"
|
|
"github.com/hashicorp/consul/types"
|
|
)
|
|
|
|
func getService(a *TestAgent, id string) *structs.NodeService {
|
|
return a.State.Service(structs.NewServiceID(id, nil))
|
|
}
|
|
|
|
func getCheck(a *TestAgent, id types.CheckID) *structs.HealthCheck {
|
|
return a.State.Check(structs.NewCheckID(id, nil))
|
|
}
|
|
|
|
func requireServiceExists(t *testing.T, a *TestAgent, id string) *structs.NodeService {
|
|
t.Helper()
|
|
svc := getService(a, id)
|
|
require.NotNil(t, svc, "missing service %q", id)
|
|
return svc
|
|
}
|
|
|
|
func requireServiceMissing(t *testing.T, a *TestAgent, id string) {
|
|
t.Helper()
|
|
require.Nil(t, getService(a, id), "have service %q (expected missing)", id)
|
|
}
|
|
|
|
func requireCheckExists(t *testing.T, a *TestAgent, id types.CheckID) *structs.HealthCheck {
|
|
t.Helper()
|
|
chk := getCheck(a, id)
|
|
require.NotNil(t, chk, "missing check %q", id)
|
|
return chk
|
|
}
|
|
|
|
func requireCheckMissing(t *testing.T, a *TestAgent, id types.CheckID) {
|
|
t.Helper()
|
|
require.Nil(t, getCheck(a, id), "have check %q (expected missing)", id)
|
|
}
|
|
|
|
func requireCheckExistsMap(t *testing.T, m interface{}, id types.CheckID) {
|
|
t.Helper()
|
|
require.Contains(t, m, structs.NewCheckID(id, nil), "missing check %q", id)
|
|
}
|
|
|
|
func requireCheckMissingMap(t *testing.T, m interface{}, id types.CheckID) {
|
|
t.Helper()
|
|
require.NotContains(t, m, structs.NewCheckID(id, nil), "have check %q (expected missing)", id)
|
|
}
|
|
|
|
func TestAgent_MultiStartStop(t *testing.T) {
|
|
if testing.Short() {
|
|
t.Skip("too slow for testing.Short")
|
|
}
|
|
|
|
for i := 0; i < 10; i++ {
|
|
t.Run("", func(t *testing.T) {
|
|
t.Parallel()
|
|
a := NewTestAgent(t, "")
|
|
time.Sleep(250 * time.Millisecond)
|
|
a.Shutdown()
|
|
})
|
|
}
|
|
}
|
|
|
|
func TestAgent_ConnectClusterIDConfig(t *testing.T) {
|
|
if testing.Short() {
|
|
t.Skip("too slow for testing.Short")
|
|
}
|
|
|
|
tests := []struct {
|
|
name string
|
|
hcl string
|
|
wantClusterID string
|
|
wantErr bool
|
|
}{
|
|
{
|
|
name: "default TestAgent has fixed cluster id",
|
|
hcl: "",
|
|
wantClusterID: connect.TestClusterID,
|
|
},
|
|
{
|
|
name: "no cluster ID specified sets to test ID",
|
|
hcl: "connect { enabled = true }",
|
|
wantClusterID: connect.TestClusterID,
|
|
},
|
|
{
|
|
name: "non-UUID cluster_id is fatal",
|
|
hcl: `connect {
|
|
enabled = true
|
|
ca_config {
|
|
cluster_id = "fake-id"
|
|
}
|
|
}`,
|
|
wantClusterID: "",
|
|
wantErr: true,
|
|
},
|
|
}
|
|
|
|
for _, tt := range tests {
|
|
t.Run(tt.name, func(t *testing.T) {
|
|
a := TestAgent{HCL: tt.hcl}
|
|
err := a.Start(t)
|
|
if tt.wantErr {
|
|
if err == nil {
|
|
t.Fatal("expected error, got nil")
|
|
}
|
|
return // don't run the rest of the test
|
|
}
|
|
if !tt.wantErr && err != nil {
|
|
t.Fatal(err)
|
|
}
|
|
defer a.Shutdown()
|
|
|
|
cfg := a.consulConfig()
|
|
assert.Equal(t, tt.wantClusterID, cfg.CAConfig.ClusterID)
|
|
})
|
|
}
|
|
}
|
|
|
|
func TestAgent_StartStop(t *testing.T) {
|
|
if testing.Short() {
|
|
t.Skip("too slow for testing.Short")
|
|
}
|
|
|
|
t.Parallel()
|
|
a := NewTestAgent(t, "")
|
|
defer a.Shutdown()
|
|
|
|
if err := a.Leave(); err != nil {
|
|
t.Fatalf("err: %v", err)
|
|
}
|
|
if err := a.Shutdown(); err != nil {
|
|
t.Fatalf("err: %v", err)
|
|
}
|
|
|
|
select {
|
|
case <-a.ShutdownCh():
|
|
default:
|
|
t.Fatalf("should be closed")
|
|
}
|
|
}
|
|
|
|
func TestAgent_RPCPing(t *testing.T) {
|
|
if testing.Short() {
|
|
t.Skip("too slow for testing.Short")
|
|
}
|
|
|
|
t.Parallel()
|
|
a := NewTestAgent(t, "")
|
|
defer a.Shutdown()
|
|
testrpc.WaitForTestAgent(t, a.RPC, "dc1")
|
|
|
|
var out struct{}
|
|
if err := a.RPC("Status.Ping", struct{}{}, &out); err != nil {
|
|
t.Fatalf("err: %v", err)
|
|
}
|
|
}
|
|
|
|
func TestAgent_TokenStore(t *testing.T) {
|
|
if testing.Short() {
|
|
t.Skip("too slow for testing.Short")
|
|
}
|
|
|
|
t.Parallel()
|
|
|
|
a := NewTestAgent(t, `
|
|
acl {
|
|
tokens {
|
|
default = "user"
|
|
agent = "agent"
|
|
agent_recovery = "recovery"
|
|
}
|
|
}
|
|
`)
|
|
defer a.Shutdown()
|
|
|
|
if got, want := a.tokens.UserToken(), "user"; got != want {
|
|
t.Fatalf("got %q want %q", got, want)
|
|
}
|
|
if got, want := a.tokens.AgentToken(), "agent"; got != want {
|
|
t.Fatalf("got %q want %q", got, want)
|
|
}
|
|
if got, want := a.tokens.IsAgentRecoveryToken("recovery"), true; got != want {
|
|
t.Fatalf("got %v want %v", got, want)
|
|
}
|
|
}
|
|
|
|
func TestAgent_ReconnectConfigSettings(t *testing.T) {
|
|
if testing.Short() {
|
|
t.Skip("too slow for testing.Short")
|
|
}
|
|
|
|
t.Parallel()
|
|
func() {
|
|
a := NewTestAgent(t, "")
|
|
defer a.Shutdown()
|
|
|
|
lan := a.consulConfig().SerfLANConfig.ReconnectTimeout
|
|
if lan != 3*24*time.Hour {
|
|
t.Fatalf("bad: %s", lan.String())
|
|
}
|
|
|
|
wan := a.consulConfig().SerfWANConfig.ReconnectTimeout
|
|
if wan != 3*24*time.Hour {
|
|
t.Fatalf("bad: %s", wan.String())
|
|
}
|
|
}()
|
|
|
|
func() {
|
|
a := NewTestAgent(t, `
|
|
reconnect_timeout = "24h"
|
|
reconnect_timeout_wan = "36h"
|
|
`)
|
|
defer a.Shutdown()
|
|
|
|
lan := a.consulConfig().SerfLANConfig.ReconnectTimeout
|
|
if lan != 24*time.Hour {
|
|
t.Fatalf("bad: %s", lan.String())
|
|
}
|
|
|
|
wan := a.consulConfig().SerfWANConfig.ReconnectTimeout
|
|
if wan != 36*time.Hour {
|
|
t.Fatalf("bad: %s", wan.String())
|
|
}
|
|
}()
|
|
}
|
|
|
|
func TestAgent_HTTPMaxHeaderBytes(t *testing.T) {
|
|
tests := []struct {
|
|
name string
|
|
maxHeaderBytes int
|
|
expectedHTTPResponse int
|
|
}{
|
|
{
|
|
"max header bytes 1 returns 431 http response when too large headers are sent",
|
|
1,
|
|
431,
|
|
},
|
|
{
|
|
"max header bytes 0 returns 200 http response, as the http.DefaultMaxHeaderBytes size of 1MB is used",
|
|
0,
|
|
200,
|
|
},
|
|
{
|
|
"negative maxHeaderBytes returns 200 http response, as the http.DefaultMaxHeaderBytes size of 1MB is used",
|
|
-10,
|
|
200,
|
|
},
|
|
}
|
|
for _, tt := range tests {
|
|
t.Run(tt.name, func(t *testing.T) {
|
|
caConfig := tlsutil.Config{}
|
|
tlsConf, err := tlsutil.NewConfigurator(caConfig, hclog.New(nil))
|
|
require.NoError(t, err)
|
|
|
|
bd := BaseDeps{
|
|
Deps: consul.Deps{
|
|
Logger: hclog.NewInterceptLogger(nil),
|
|
Tokens: new(token.Store),
|
|
TLSConfigurator: tlsConf,
|
|
GRPCConnPool: &fakeGRPCConnPool{},
|
|
},
|
|
RuntimeConfig: &config.RuntimeConfig{
|
|
HTTPAddrs: []net.Addr{
|
|
&net.TCPAddr{IP: net.ParseIP("127.0.0.1"), Port: freeport.GetOne(t)},
|
|
},
|
|
HTTPMaxHeaderBytes: tt.maxHeaderBytes,
|
|
},
|
|
Cache: cache.New(cache.Options{}),
|
|
}
|
|
bd, err = initEnterpriseBaseDeps(bd, nil)
|
|
require.NoError(t, err)
|
|
|
|
a, err := New(bd)
|
|
require.NoError(t, err)
|
|
|
|
a.startLicenseManager(testutil.TestContext(t))
|
|
|
|
srvs, err := a.listenHTTP()
|
|
require.NoError(t, err)
|
|
|
|
require.Equal(t, tt.maxHeaderBytes, a.config.HTTPMaxHeaderBytes)
|
|
|
|
ctx, cancel := context.WithTimeout(context.Background(), 2*time.Second)
|
|
t.Cleanup(cancel)
|
|
|
|
g := new(errgroup.Group)
|
|
for _, s := range srvs {
|
|
g.Go(s.Run)
|
|
}
|
|
|
|
require.Len(t, srvs, 1)
|
|
|
|
client := &http.Client{}
|
|
for _, s := range srvs {
|
|
u := url.URL{Scheme: s.Protocol, Host: s.Addr.String()}
|
|
req, err := http.NewRequest(http.MethodGet, u.String(), nil)
|
|
require.NoError(t, err)
|
|
|
|
// This is directly pulled from the testing of request limits in the net/http source
|
|
// https://github.com/golang/go/blob/go1.15.3/src/net/http/serve_test.go#L2897-L2900
|
|
var bytesPerHeader = len("header12345: val12345\r\n")
|
|
for i := 0; i < ((tt.maxHeaderBytes+4096)/bytesPerHeader)+1; i++ {
|
|
req.Header.Set(fmt.Sprintf("header%05d", i), fmt.Sprintf("val%05d", i))
|
|
}
|
|
|
|
resp, err := client.Do(req.WithContext(ctx))
|
|
require.NoError(t, err)
|
|
require.Equal(t, tt.expectedHTTPResponse, resp.StatusCode, "expected a '%d' http response, got '%d'", tt.expectedHTTPResponse, resp.StatusCode)
|
|
}
|
|
})
|
|
}
|
|
}
|
|
|
|
type fakeGRPCConnPool struct{}
|
|
|
|
func (f fakeGRPCConnPool) ClientConn(_ string) (*grpc.ClientConn, error) {
|
|
return nil, nil
|
|
}
|
|
|
|
func (f fakeGRPCConnPool) ClientConnLeader() (*grpc.ClientConn, error) {
|
|
return nil, nil
|
|
}
|
|
|
|
func (f fakeGRPCConnPool) SetGatewayResolver(_ func(string) string) {
|
|
}
|
|
|
|
func TestAgent_ReconnectConfigWanDisabled(t *testing.T) {
|
|
if testing.Short() {
|
|
t.Skip("too slow for testing.Short")
|
|
}
|
|
|
|
t.Parallel()
|
|
|
|
a := NewTestAgent(t, `
|
|
ports { serf_wan = -1 }
|
|
reconnect_timeout_wan = "36h"
|
|
`)
|
|
defer a.Shutdown()
|
|
|
|
// This is also testing that we dont panic like before #4515
|
|
require.Nil(t, a.consulConfig().SerfWANConfig)
|
|
}
|
|
|
|
func TestAgent_AddService(t *testing.T) {
|
|
if testing.Short() {
|
|
t.Skip("too slow for testing.Short")
|
|
}
|
|
|
|
t.Run("normal", func(t *testing.T) {
|
|
t.Parallel()
|
|
testAgent_AddService(t, "enable_central_service_config = false")
|
|
})
|
|
t.Run("service manager", func(t *testing.T) {
|
|
t.Parallel()
|
|
testAgent_AddService(t, "enable_central_service_config = true")
|
|
})
|
|
}
|
|
|
|
func testAgent_AddService(t *testing.T, extraHCL string) {
|
|
t.Helper()
|
|
|
|
a := NewTestAgent(t, `
|
|
node_name = "node1"
|
|
`+extraHCL)
|
|
defer a.Shutdown()
|
|
|
|
duration3s, _ := time.ParseDuration("3s")
|
|
duration10s, _ := time.ParseDuration("10s")
|
|
|
|
tests := []struct {
|
|
desc string
|
|
srv *structs.NodeService
|
|
wantSrv func(ns *structs.NodeService)
|
|
chkTypes []*structs.CheckType
|
|
healthChks map[string]*structs.HealthCheck
|
|
}{
|
|
{
|
|
"one check",
|
|
&structs.NodeService{
|
|
ID: "svcid1",
|
|
Service: "svcname1",
|
|
Tags: []string{"tag1"},
|
|
Weights: nil, // nil weights...
|
|
Port: 8100,
|
|
EnterpriseMeta: *structs.DefaultEnterpriseMetaInDefaultPartition(),
|
|
},
|
|
// ... should be populated to avoid "IsSame" returning true during AE.
|
|
func(ns *structs.NodeService) {
|
|
ns.Weights = &structs.Weights{
|
|
Passing: 1,
|
|
Warning: 1,
|
|
}
|
|
},
|
|
[]*structs.CheckType{
|
|
{
|
|
CheckID: "check1",
|
|
Name: "name1",
|
|
TTL: time.Minute,
|
|
Notes: "note1",
|
|
},
|
|
},
|
|
map[string]*structs.HealthCheck{
|
|
"check1": {
|
|
Node: "node1",
|
|
CheckID: "check1",
|
|
Name: "name1",
|
|
Interval: "",
|
|
Timeout: "", // these are empty because a TTL was provided
|
|
Status: "critical",
|
|
Notes: "note1",
|
|
ServiceID: "svcid1",
|
|
ServiceName: "svcname1",
|
|
ServiceTags: []string{"tag1"},
|
|
Type: "ttl",
|
|
EnterpriseMeta: *structs.DefaultEnterpriseMetaInDefaultPartition(),
|
|
},
|
|
},
|
|
},
|
|
{
|
|
"one http check with interval and duration",
|
|
&structs.NodeService{
|
|
ID: "svcid1",
|
|
Service: "svcname1",
|
|
Tags: []string{"tag1"},
|
|
Weights: nil, // nil weights...
|
|
Port: 8100,
|
|
EnterpriseMeta: *structs.DefaultEnterpriseMetaInDefaultPartition(),
|
|
},
|
|
// ... should be populated to avoid "IsSame" returning true during AE.
|
|
func(ns *structs.NodeService) {
|
|
ns.Weights = &structs.Weights{
|
|
Passing: 1,
|
|
Warning: 1,
|
|
}
|
|
},
|
|
[]*structs.CheckType{
|
|
{
|
|
CheckID: "check1",
|
|
Name: "name1",
|
|
HTTP: "http://localhost:8100/",
|
|
Interval: duration10s,
|
|
Timeout: duration3s,
|
|
Notes: "note1",
|
|
},
|
|
},
|
|
map[string]*structs.HealthCheck{
|
|
"check1": {
|
|
Node: "node1",
|
|
CheckID: "check1",
|
|
Name: "name1",
|
|
Interval: "10s",
|
|
Timeout: "3s",
|
|
Status: "critical",
|
|
Notes: "note1",
|
|
ServiceID: "svcid1",
|
|
ServiceName: "svcname1",
|
|
ServiceTags: []string{"tag1"},
|
|
Type: "http",
|
|
EnterpriseMeta: *structs.DefaultEnterpriseMetaInDefaultPartition(),
|
|
},
|
|
},
|
|
},
|
|
{
|
|
"multiple checks",
|
|
&structs.NodeService{
|
|
ID: "svcid2",
|
|
Service: "svcname2",
|
|
Weights: &structs.Weights{
|
|
Passing: 2,
|
|
Warning: 1,
|
|
},
|
|
Tags: []string{"tag2"},
|
|
Port: 8200,
|
|
EnterpriseMeta: *structs.DefaultEnterpriseMetaInDefaultPartition(),
|
|
},
|
|
nil, // No change expected
|
|
[]*structs.CheckType{
|
|
{
|
|
CheckID: "check1",
|
|
Name: "name1",
|
|
TTL: time.Minute,
|
|
Notes: "note1",
|
|
},
|
|
{
|
|
CheckID: "check-noname",
|
|
TTL: time.Minute,
|
|
},
|
|
{
|
|
Name: "check-noid",
|
|
TTL: time.Minute,
|
|
},
|
|
{
|
|
TTL: time.Minute,
|
|
},
|
|
},
|
|
map[string]*structs.HealthCheck{
|
|
"check1": {
|
|
Node: "node1",
|
|
CheckID: "check1",
|
|
Name: "name1",
|
|
Interval: "",
|
|
Timeout: "", // these are empty bcause a TTL was provided
|
|
Status: "critical",
|
|
Notes: "note1",
|
|
ServiceID: "svcid2",
|
|
ServiceName: "svcname2",
|
|
ServiceTags: []string{"tag2"},
|
|
Type: "ttl",
|
|
EnterpriseMeta: *structs.DefaultEnterpriseMetaInDefaultPartition(),
|
|
},
|
|
"check-noname": {
|
|
Node: "node1",
|
|
CheckID: "check-noname",
|
|
Name: "Service 'svcname2' check",
|
|
Interval: "",
|
|
Timeout: "", // these are empty because a TTL was provided
|
|
Status: "critical",
|
|
ServiceID: "svcid2",
|
|
ServiceName: "svcname2",
|
|
ServiceTags: []string{"tag2"},
|
|
Type: "ttl",
|
|
EnterpriseMeta: *structs.DefaultEnterpriseMetaInDefaultPartition(),
|
|
},
|
|
"service:svcid2:3": {
|
|
Node: "node1",
|
|
CheckID: "service:svcid2:3",
|
|
Name: "check-noid",
|
|
Interval: "",
|
|
Timeout: "", // these are empty becuase a TTL was provided
|
|
Status: "critical",
|
|
ServiceID: "svcid2",
|
|
ServiceName: "svcname2",
|
|
ServiceTags: []string{"tag2"},
|
|
Type: "ttl",
|
|
EnterpriseMeta: *structs.DefaultEnterpriseMetaInDefaultPartition(),
|
|
},
|
|
"service:svcid2:4": {
|
|
Node: "node1",
|
|
CheckID: "service:svcid2:4",
|
|
Name: "Service 'svcname2' check",
|
|
Interval: "",
|
|
Timeout: "", // these are empty because a TTL was provided
|
|
Status: "critical",
|
|
ServiceID: "svcid2",
|
|
ServiceName: "svcname2",
|
|
ServiceTags: []string{"tag2"},
|
|
Type: "ttl",
|
|
EnterpriseMeta: *structs.DefaultEnterpriseMetaInDefaultPartition(),
|
|
},
|
|
},
|
|
},
|
|
}
|
|
|
|
for _, tt := range tests {
|
|
t.Run(tt.desc, func(t *testing.T) {
|
|
// check the service registration
|
|
t.Run(tt.srv.ID, func(t *testing.T) {
|
|
err := a.addServiceFromSource(tt.srv, tt.chkTypes, false, "", ConfigSourceLocal)
|
|
if err != nil {
|
|
t.Fatalf("err: %v", err)
|
|
}
|
|
|
|
got := getService(a, tt.srv.ID)
|
|
// Make a copy since the tt.srv points to the one in memory in the local
|
|
// state still so changing it is a tautology!
|
|
want := *tt.srv
|
|
if tt.wantSrv != nil {
|
|
tt.wantSrv(&want)
|
|
}
|
|
require.Equal(t, &want, got)
|
|
require.True(t, got.IsSame(&want))
|
|
})
|
|
|
|
// check the health checks
|
|
for k, v := range tt.healthChks {
|
|
t.Run(k, func(t *testing.T) {
|
|
got := getCheck(a, types.CheckID(k))
|
|
require.Equal(t, v, got)
|
|
})
|
|
}
|
|
|
|
// check the ttl checks
|
|
for k := range tt.healthChks {
|
|
t.Run(k+" ttl", func(t *testing.T) {
|
|
chk := a.checkTTLs[structs.NewCheckID(types.CheckID(k), nil)]
|
|
if chk == nil {
|
|
t.Fatal("got nil want TTL check")
|
|
}
|
|
if got, want := string(chk.CheckID.ID), k; got != want {
|
|
t.Fatalf("got CheckID %v want %v", got, want)
|
|
}
|
|
if got, want := chk.TTL, time.Minute; got != want {
|
|
t.Fatalf("got TTL %v want %v", got, want)
|
|
}
|
|
})
|
|
}
|
|
})
|
|
}
|
|
}
|
|
|
|
// addServiceFromSource is a test helper that exists to maintain an old function
|
|
// signature that was used in many tests.
|
|
// Deprecated: use AddService
|
|
func (a *Agent) addServiceFromSource(service *structs.NodeService, chkTypes []*structs.CheckType, persist bool, token string, source configSource) error {
|
|
return a.AddService(AddServiceRequest{
|
|
Service: service,
|
|
chkTypes: chkTypes,
|
|
persist: persist,
|
|
token: token,
|
|
replaceExistingChecks: false,
|
|
Source: source,
|
|
})
|
|
}
|
|
|
|
func TestAgent_AddServices_AliasUpdateCheckNotReverted(t *testing.T) {
|
|
if testing.Short() {
|
|
t.Skip("too slow for testing.Short")
|
|
}
|
|
|
|
t.Run("normal", func(t *testing.T) {
|
|
t.Parallel()
|
|
testAgent_AddServices_AliasUpdateCheckNotReverted(t, "enable_central_service_config = false")
|
|
})
|
|
t.Run("service manager", func(t *testing.T) {
|
|
t.Parallel()
|
|
testAgent_AddServices_AliasUpdateCheckNotReverted(t, "enable_central_service_config = true")
|
|
})
|
|
}
|
|
|
|
func testAgent_AddServices_AliasUpdateCheckNotReverted(t *testing.T, extraHCL string) {
|
|
t.Helper()
|
|
|
|
a := NewTestAgent(t, `
|
|
node_name = "node1"
|
|
`+extraHCL)
|
|
defer a.Shutdown()
|
|
|
|
// It's tricky to get an UpdateCheck call to be timed properly so it lands
|
|
// right in the middle of an addServiceInternal call so we cheat a bit and
|
|
// rely upon alias checks to do that work for us. We add enough services
|
|
// that probabilistically one of them is going to end up properly in the
|
|
// critical section.
|
|
//
|
|
// The first number I picked here (10) surprisingly failed every time prior
|
|
// to PR #6144 solving the underlying problem.
|
|
const numServices = 10
|
|
|
|
services := make([]*structs.ServiceDefinition, numServices)
|
|
checkIDs := make([]types.CheckID, numServices)
|
|
services[0] = &structs.ServiceDefinition{
|
|
ID: "fake",
|
|
Name: "fake",
|
|
Port: 8080,
|
|
Checks: []*structs.CheckType{},
|
|
}
|
|
for i := 1; i < numServices; i++ {
|
|
name := fmt.Sprintf("web-%d", i)
|
|
|
|
services[i] = &structs.ServiceDefinition{
|
|
ID: name,
|
|
Name: name,
|
|
Port: 8080 + i,
|
|
Checks: []*structs.CheckType{
|
|
{
|
|
Name: "alias-for-fake-service",
|
|
AliasService: "fake",
|
|
},
|
|
},
|
|
}
|
|
|
|
checkIDs[i] = types.CheckID("service:" + name)
|
|
}
|
|
|
|
// Add all of the services quickly as you might do from config file snippets.
|
|
for _, service := range services {
|
|
ns := service.NodeService()
|
|
|
|
chkTypes, err := service.CheckTypes()
|
|
require.NoError(t, err)
|
|
|
|
require.NoError(t, a.addServiceFromSource(ns, chkTypes, false, service.Token, ConfigSourceLocal))
|
|
}
|
|
|
|
retry.Run(t, func(r *retry.R) {
|
|
gotChecks := a.State.Checks(nil)
|
|
for id, check := range gotChecks {
|
|
require.Equal(r, "passing", check.Status, "check %q is wrong", id)
|
|
require.Equal(r, "No checks found.", check.Output, "check %q is wrong", id)
|
|
}
|
|
})
|
|
}
|
|
|
|
func test_createAlias(t *testing.T, agent *TestAgent, chk *structs.CheckType, expectedResult string) func(r *retry.R) {
|
|
t.Helper()
|
|
serviceNum := rand.Int()
|
|
srv := &structs.NodeService{
|
|
Service: fmt.Sprintf("serviceAlias-%d", serviceNum),
|
|
Tags: []string{"tag1"},
|
|
Port: 8900 + serviceNum,
|
|
}
|
|
if srv.ID == "" {
|
|
srv.ID = fmt.Sprintf("serviceAlias-%d", serviceNum)
|
|
}
|
|
chk.Status = api.HealthWarning
|
|
if chk.CheckID == "" {
|
|
chk.CheckID = types.CheckID(fmt.Sprintf("check-%d", serviceNum))
|
|
}
|
|
err := agent.addServiceFromSource(srv, []*structs.CheckType{chk}, false, "", ConfigSourceLocal)
|
|
assert.NoError(t, err)
|
|
return func(r *retry.R) {
|
|
t.Helper()
|
|
found := false
|
|
for _, c := range agent.State.CheckStates(structs.WildcardEnterpriseMetaInDefaultPartition()) {
|
|
if c.Check.CheckID == chk.CheckID {
|
|
found = true
|
|
assert.Equal(t, expectedResult, c.Check.Status, "Check state should be %s, was %s in %#v", expectedResult, c.Check.Status, c.Check)
|
|
srvID := structs.NewServiceID(srv.ID, structs.WildcardEnterpriseMetaInDefaultPartition())
|
|
if err := agent.Agent.State.RemoveService(srvID); err != nil {
|
|
fmt.Println("[DEBUG] Fail to remove service", srvID, ", err:=", err)
|
|
}
|
|
fmt.Println("[DEBUG] Service Removed", srvID, ", err:=", err)
|
|
break
|
|
}
|
|
}
|
|
assert.True(t, found)
|
|
}
|
|
}
|
|
|
|
// TestAgent_CheckAliasRPC test the Alias Check to be properly sync remotely
|
|
// and locally.
|
|
// It contains a few hacks such as unlockIndexOnNode because watch performed
|
|
// in CheckAlias.runQuery() waits for 1 min, so Shutdoww the agent might take time
|
|
// So, we ensure the agent will update regularilly the index
|
|
func TestAgent_CheckAliasRPC(t *testing.T) {
|
|
if testing.Short() {
|
|
t.Skip("too slow for testing.Short")
|
|
}
|
|
|
|
t.Helper()
|
|
|
|
a := NewTestAgent(t, `
|
|
node_name = "node1"
|
|
`)
|
|
|
|
srv := &structs.NodeService{
|
|
ID: "svcid1",
|
|
Service: "svcname1",
|
|
Tags: []string{"tag1"},
|
|
Port: 8100,
|
|
}
|
|
unlockIndexOnNode := func() {
|
|
// We ensure to not block and update Agent's index
|
|
srv.Tags = []string{fmt.Sprintf("tag-%s", time.Now())}
|
|
assert.NoError(t, a.waitForUp())
|
|
err := a.addServiceFromSource(srv, []*structs.CheckType{}, false, "", ConfigSourceLocal)
|
|
assert.NoError(t, err)
|
|
}
|
|
shutdownAgent := func() {
|
|
// This is to be sure Alias Checks on remote won't be blocked during 1 min
|
|
unlockIndexOnNode()
|
|
fmt.Println("[DEBUG] STARTING shutdown for TestAgent_CheckAliasRPC", time.Now())
|
|
go a.Shutdown()
|
|
unlockIndexOnNode()
|
|
fmt.Println("[DEBUG] DONE shutdown for TestAgent_CheckAliasRPC", time.Now())
|
|
}
|
|
defer shutdownAgent()
|
|
testrpc.WaitForTestAgent(t, a.RPC, "dc1")
|
|
|
|
assert.NoError(t, a.waitForUp())
|
|
err := a.addServiceFromSource(srv, []*structs.CheckType{}, false, "", ConfigSourceLocal)
|
|
assert.NoError(t, err)
|
|
|
|
retry.Run(t, func(r *retry.R) {
|
|
t.Helper()
|
|
var args structs.NodeSpecificRequest
|
|
args.Datacenter = "dc1"
|
|
args.Node = "node1"
|
|
args.AllowStale = true
|
|
var out structs.IndexedNodeServices
|
|
err := a.RPC("Catalog.NodeServices", &args, &out)
|
|
assert.NoError(r, err)
|
|
foundService := false
|
|
lookup := structs.NewServiceID("svcid1", structs.WildcardEnterpriseMetaInDefaultPartition())
|
|
for _, srv := range out.NodeServices.Services {
|
|
if lookup.Matches(srv.CompoundServiceID()) {
|
|
foundService = true
|
|
}
|
|
}
|
|
assert.True(r, foundService, "could not find svcid1 in %#v", out.NodeServices.Services)
|
|
})
|
|
|
|
checks := make([](func(*retry.R)), 0)
|
|
|
|
checks = append(checks, test_createAlias(t, a, &structs.CheckType{
|
|
Name: "Check_Local_Ok",
|
|
AliasService: "svcid1",
|
|
}, api.HealthPassing))
|
|
|
|
checks = append(checks, test_createAlias(t, a, &structs.CheckType{
|
|
Name: "Check_Local_Fail",
|
|
AliasService: "svcidNoExistingID",
|
|
}, api.HealthCritical))
|
|
|
|
checks = append(checks, test_createAlias(t, a, &structs.CheckType{
|
|
Name: "Check_Remote_Host_Ok",
|
|
AliasNode: "node1",
|
|
AliasService: "svcid1",
|
|
}, api.HealthPassing))
|
|
|
|
checks = append(checks, test_createAlias(t, a, &structs.CheckType{
|
|
Name: "Check_Remote_Host_Non_Existing_Service",
|
|
AliasNode: "node1",
|
|
AliasService: "svcidNoExistingID",
|
|
}, api.HealthCritical))
|
|
|
|
// We wait for max 5s for all checks to be in sync
|
|
{
|
|
for i := 0; i < 50; i++ {
|
|
unlockIndexOnNode()
|
|
allNonWarning := true
|
|
for _, chk := range a.State.Checks(structs.WildcardEnterpriseMetaInDefaultPartition()) {
|
|
if chk.Status == api.HealthWarning {
|
|
allNonWarning = false
|
|
}
|
|
}
|
|
if allNonWarning {
|
|
break
|
|
} else {
|
|
time.Sleep(100 * time.Millisecond)
|
|
}
|
|
}
|
|
}
|
|
|
|
for _, toRun := range checks {
|
|
unlockIndexOnNode()
|
|
retry.Run(t, toRun)
|
|
}
|
|
}
|
|
|
|
func TestAgent_AddServiceWithH2PINGCheck(t *testing.T) {
|
|
t.Parallel()
|
|
a := NewTestAgent(t, "")
|
|
defer a.Shutdown()
|
|
check := []*structs.CheckType{
|
|
{
|
|
CheckID: "test-h2ping-check",
|
|
Name: "test-h2ping-check",
|
|
H2PING: "localhost:12345",
|
|
TLSSkipVerify: true,
|
|
Interval: 10 * time.Second,
|
|
},
|
|
}
|
|
|
|
nodeService := &structs.NodeService{
|
|
ID: "test-h2ping-check-service",
|
|
Service: "test-h2ping-check-service",
|
|
}
|
|
err := a.addServiceFromSource(nodeService, check, false, "", ConfigSourceLocal)
|
|
if err != nil {
|
|
t.Fatalf("Error registering service: %v", err)
|
|
}
|
|
requireCheckExists(t, a, "test-h2ping-check")
|
|
}
|
|
|
|
func TestAgent_AddServiceWithH2CPINGCheck(t *testing.T) {
|
|
t.Parallel()
|
|
a := NewTestAgent(t, "")
|
|
defer a.Shutdown()
|
|
check := []*structs.CheckType{
|
|
{
|
|
CheckID: "test-h2cping-check",
|
|
Name: "test-h2cping-check",
|
|
H2PING: "localhost:12345",
|
|
TLSSkipVerify: true,
|
|
Interval: 10 * time.Second,
|
|
H2PingUseTLS: false,
|
|
},
|
|
}
|
|
|
|
nodeService := &structs.NodeService{
|
|
ID: "test-h2cping-check-service",
|
|
Service: "test-h2cping-check-service",
|
|
}
|
|
err := a.addServiceFromSource(nodeService, check, false, "", ConfigSourceLocal)
|
|
if err != nil {
|
|
t.Fatalf("Error registering service: %v", err)
|
|
}
|
|
requireCheckExists(t, a, "test-h2cping-check")
|
|
}
|
|
|
|
func TestAgent_AddServiceNoExec(t *testing.T) {
|
|
if testing.Short() {
|
|
t.Skip("too slow for testing.Short")
|
|
}
|
|
|
|
t.Run("normal", func(t *testing.T) {
|
|
t.Parallel()
|
|
testAgent_AddServiceNoExec(t, "enable_central_service_config = false")
|
|
})
|
|
t.Run("service manager", func(t *testing.T) {
|
|
t.Parallel()
|
|
testAgent_AddServiceNoExec(t, "enable_central_service_config = true")
|
|
})
|
|
}
|
|
|
|
func testAgent_AddServiceNoExec(t *testing.T, extraHCL string) {
|
|
t.Helper()
|
|
|
|
a := NewTestAgent(t, `
|
|
node_name = "node1"
|
|
`+extraHCL)
|
|
defer a.Shutdown()
|
|
testrpc.WaitForTestAgent(t, a.RPC, "dc1")
|
|
|
|
srv := &structs.NodeService{
|
|
ID: "svcid1",
|
|
Service: "svcname1",
|
|
Tags: []string{"tag1"},
|
|
Port: 8100,
|
|
}
|
|
chk := &structs.CheckType{
|
|
ScriptArgs: []string{"exit", "0"},
|
|
Interval: 15 * time.Second,
|
|
}
|
|
|
|
err := a.addServiceFromSource(srv, []*structs.CheckType{chk}, false, "", ConfigSourceLocal)
|
|
if err == nil || !strings.Contains(err.Error(), "Scripts are disabled on this agent") {
|
|
t.Fatalf("err: %v", err)
|
|
}
|
|
|
|
err = a.addServiceFromSource(srv, []*structs.CheckType{chk}, false, "", ConfigSourceRemote)
|
|
if err == nil || !strings.Contains(err.Error(), "Scripts are disabled on this agent") {
|
|
t.Fatalf("err: %v", err)
|
|
}
|
|
}
|
|
|
|
func TestAgent_AddServiceNoRemoteExec(t *testing.T) {
|
|
if testing.Short() {
|
|
t.Skip("too slow for testing.Short")
|
|
}
|
|
|
|
t.Run("normal", func(t *testing.T) {
|
|
t.Parallel()
|
|
testAgent_AddServiceNoRemoteExec(t, "enable_central_service_config = false")
|
|
})
|
|
t.Run("service manager", func(t *testing.T) {
|
|
t.Parallel()
|
|
testAgent_AddServiceNoRemoteExec(t, "enable_central_service_config = true")
|
|
})
|
|
}
|
|
|
|
func testAgent_AddServiceNoRemoteExec(t *testing.T, extraHCL string) {
|
|
t.Helper()
|
|
|
|
a := NewTestAgent(t, `
|
|
node_name = "node1"
|
|
enable_local_script_checks = true
|
|
`+extraHCL)
|
|
defer a.Shutdown()
|
|
testrpc.WaitForTestAgent(t, a.RPC, "dc1")
|
|
|
|
srv := &structs.NodeService{
|
|
ID: "svcid1",
|
|
Service: "svcname1",
|
|
Tags: []string{"tag1"},
|
|
Port: 8100,
|
|
}
|
|
chk := &structs.CheckType{
|
|
ScriptArgs: []string{"exit", "0"},
|
|
Interval: 15 * time.Second,
|
|
}
|
|
|
|
err := a.addServiceFromSource(srv, []*structs.CheckType{chk}, false, "", ConfigSourceRemote)
|
|
if err == nil || !strings.Contains(err.Error(), "Scripts are disabled on this agent") {
|
|
t.Fatalf("err: %v", err)
|
|
}
|
|
}
|
|
|
|
func TestAddServiceIPv4TaggedDefault(t *testing.T) {
|
|
if testing.Short() {
|
|
t.Skip("too slow for testing.Short")
|
|
}
|
|
|
|
t.Helper()
|
|
|
|
a := NewTestAgent(t, "")
|
|
defer a.Shutdown()
|
|
testrpc.WaitForTestAgent(t, a.RPC, "dc1")
|
|
|
|
srv := &structs.NodeService{
|
|
Service: "my_service",
|
|
ID: "my_service_id",
|
|
Port: 8100,
|
|
Address: "10.0.1.2",
|
|
}
|
|
|
|
err := a.addServiceFromSource(srv, []*structs.CheckType{}, false, "", ConfigSourceRemote)
|
|
require.Nil(t, err)
|
|
|
|
ns := a.State.Service(structs.NewServiceID("my_service_id", nil))
|
|
require.NotNil(t, ns)
|
|
|
|
svcAddr := structs.ServiceAddress{Address: srv.Address, Port: srv.Port}
|
|
require.Equal(t, svcAddr, ns.TaggedAddresses[structs.TaggedAddressLANIPv4])
|
|
require.Equal(t, svcAddr, ns.TaggedAddresses[structs.TaggedAddressWANIPv4])
|
|
_, ok := ns.TaggedAddresses[structs.TaggedAddressLANIPv6]
|
|
require.False(t, ok)
|
|
_, ok = ns.TaggedAddresses[structs.TaggedAddressWANIPv6]
|
|
require.False(t, ok)
|
|
}
|
|
|
|
func TestAddServiceIPv6TaggedDefault(t *testing.T) {
|
|
if testing.Short() {
|
|
t.Skip("too slow for testing.Short")
|
|
}
|
|
|
|
t.Helper()
|
|
|
|
a := NewTestAgent(t, "")
|
|
defer a.Shutdown()
|
|
testrpc.WaitForTestAgent(t, a.RPC, "dc1")
|
|
|
|
srv := &structs.NodeService{
|
|
Service: "my_service",
|
|
ID: "my_service_id",
|
|
Port: 8100,
|
|
Address: "::5",
|
|
}
|
|
|
|
err := a.addServiceFromSource(srv, []*structs.CheckType{}, false, "", ConfigSourceRemote)
|
|
require.Nil(t, err)
|
|
|
|
ns := a.State.Service(structs.NewServiceID("my_service_id", nil))
|
|
require.NotNil(t, ns)
|
|
|
|
svcAddr := structs.ServiceAddress{Address: srv.Address, Port: srv.Port}
|
|
require.Equal(t, svcAddr, ns.TaggedAddresses[structs.TaggedAddressLANIPv6])
|
|
require.Equal(t, svcAddr, ns.TaggedAddresses[structs.TaggedAddressWANIPv6])
|
|
_, ok := ns.TaggedAddresses[structs.TaggedAddressLANIPv4]
|
|
require.False(t, ok)
|
|
_, ok = ns.TaggedAddresses[structs.TaggedAddressWANIPv4]
|
|
require.False(t, ok)
|
|
}
|
|
|
|
func TestAddServiceIPv4TaggedSet(t *testing.T) {
|
|
if testing.Short() {
|
|
t.Skip("too slow for testing.Short")
|
|
}
|
|
|
|
t.Helper()
|
|
|
|
a := NewTestAgent(t, "")
|
|
defer a.Shutdown()
|
|
testrpc.WaitForTestAgent(t, a.RPC, "dc1")
|
|
|
|
srv := &structs.NodeService{
|
|
Service: "my_service",
|
|
ID: "my_service_id",
|
|
Port: 8100,
|
|
Address: "10.0.1.2",
|
|
TaggedAddresses: map[string]structs.ServiceAddress{
|
|
structs.TaggedAddressWANIPv4: {
|
|
Address: "10.100.200.5",
|
|
Port: 8100,
|
|
},
|
|
},
|
|
}
|
|
|
|
err := a.addServiceFromSource(srv, []*structs.CheckType{}, false, "", ConfigSourceRemote)
|
|
require.Nil(t, err)
|
|
|
|
ns := a.State.Service(structs.NewServiceID("my_service_id", nil))
|
|
require.NotNil(t, ns)
|
|
|
|
svcAddr := structs.ServiceAddress{Address: srv.Address, Port: srv.Port}
|
|
require.Equal(t, svcAddr, ns.TaggedAddresses[structs.TaggedAddressLANIPv4])
|
|
require.Equal(t, structs.ServiceAddress{Address: "10.100.200.5", Port: 8100}, ns.TaggedAddresses[structs.TaggedAddressWANIPv4])
|
|
_, ok := ns.TaggedAddresses[structs.TaggedAddressLANIPv6]
|
|
require.False(t, ok)
|
|
_, ok = ns.TaggedAddresses[structs.TaggedAddressWANIPv6]
|
|
require.False(t, ok)
|
|
}
|
|
|
|
func TestAddServiceIPv6TaggedSet(t *testing.T) {
|
|
if testing.Short() {
|
|
t.Skip("too slow for testing.Short")
|
|
}
|
|
|
|
t.Helper()
|
|
|
|
a := NewTestAgent(t, "")
|
|
defer a.Shutdown()
|
|
testrpc.WaitForTestAgent(t, a.RPC, "dc1")
|
|
|
|
srv := &structs.NodeService{
|
|
Service: "my_service",
|
|
ID: "my_service_id",
|
|
Port: 8100,
|
|
Address: "::5",
|
|
TaggedAddresses: map[string]structs.ServiceAddress{
|
|
structs.TaggedAddressWANIPv6: {
|
|
Address: "::6",
|
|
Port: 8100,
|
|
},
|
|
},
|
|
}
|
|
|
|
err := a.addServiceFromSource(srv, []*structs.CheckType{}, false, "", ConfigSourceRemote)
|
|
require.Nil(t, err)
|
|
|
|
ns := a.State.Service(structs.NewServiceID("my_service_id", nil))
|
|
require.NotNil(t, ns)
|
|
|
|
svcAddr := structs.ServiceAddress{Address: srv.Address, Port: srv.Port}
|
|
require.Equal(t, svcAddr, ns.TaggedAddresses[structs.TaggedAddressLANIPv6])
|
|
require.Equal(t, structs.ServiceAddress{Address: "::6", Port: 8100}, ns.TaggedAddresses[structs.TaggedAddressWANIPv6])
|
|
_, ok := ns.TaggedAddresses[structs.TaggedAddressLANIPv4]
|
|
require.False(t, ok)
|
|
_, ok = ns.TaggedAddresses[structs.TaggedAddressWANIPv4]
|
|
require.False(t, ok)
|
|
}
|
|
|
|
func TestAgent_RemoveService(t *testing.T) {
|
|
if testing.Short() {
|
|
t.Skip("too slow for testing.Short")
|
|
}
|
|
|
|
t.Run("normal", func(t *testing.T) {
|
|
t.Parallel()
|
|
testAgent_RemoveService(t, "enable_central_service_config = false")
|
|
})
|
|
t.Run("service manager", func(t *testing.T) {
|
|
t.Parallel()
|
|
testAgent_RemoveService(t, "enable_central_service_config = true")
|
|
})
|
|
}
|
|
|
|
func testAgent_RemoveService(t *testing.T, extraHCL string) {
|
|
t.Helper()
|
|
|
|
a := NewTestAgent(t, extraHCL)
|
|
defer a.Shutdown()
|
|
|
|
// Remove a service that doesn't exist
|
|
if err := a.RemoveService(structs.NewServiceID("redis", nil)); err != nil {
|
|
t.Fatalf("err: %v", err)
|
|
}
|
|
|
|
// Remove without an ID
|
|
if err := a.RemoveService(structs.NewServiceID("", nil)); err == nil {
|
|
t.Fatalf("should have errored")
|
|
}
|
|
|
|
// Removing a service with a single check works
|
|
{
|
|
srv := &structs.NodeService{
|
|
ID: "memcache",
|
|
Service: "memcache",
|
|
Port: 8000,
|
|
}
|
|
chkTypes := []*structs.CheckType{{TTL: time.Minute}}
|
|
|
|
if err := a.addServiceFromSource(srv, chkTypes, false, "", ConfigSourceLocal); err != nil {
|
|
t.Fatalf("err: %v", err)
|
|
}
|
|
|
|
// Add a check after the fact with a specific check ID
|
|
check := &structs.CheckDefinition{
|
|
ID: "check2",
|
|
Name: "check2",
|
|
ServiceID: "memcache",
|
|
TTL: time.Minute,
|
|
}
|
|
hc := check.HealthCheck("node1")
|
|
if err := a.AddCheck(hc, check.CheckType(), false, "", ConfigSourceLocal); err != nil {
|
|
t.Fatalf("err: %s", err)
|
|
}
|
|
|
|
if err := a.RemoveService(structs.NewServiceID("memcache", nil)); err != nil {
|
|
t.Fatalf("err: %s", err)
|
|
}
|
|
require.Nil(t, a.State.Check(structs.NewCheckID("service:memcache", nil)), "have memcache check")
|
|
require.Nil(t, a.State.Check(structs.NewCheckID("check2", nil)), "have check2 check")
|
|
}
|
|
|
|
// Removing a service with multiple checks works
|
|
{
|
|
// add a service to remove
|
|
srv := &structs.NodeService{
|
|
ID: "redis",
|
|
Service: "redis",
|
|
Port: 8000,
|
|
}
|
|
chkTypes := []*structs.CheckType{
|
|
{TTL: time.Minute},
|
|
{TTL: 30 * time.Second},
|
|
}
|
|
if err := a.addServiceFromSource(srv, chkTypes, false, "", ConfigSourceLocal); err != nil {
|
|
t.Fatalf("err: %v", err)
|
|
}
|
|
|
|
// add another service that wont be affected
|
|
srv = &structs.NodeService{
|
|
ID: "mysql",
|
|
Service: "mysql",
|
|
Port: 3306,
|
|
}
|
|
chkTypes = []*structs.CheckType{
|
|
{TTL: time.Minute},
|
|
{TTL: 30 * time.Second},
|
|
}
|
|
if err := a.addServiceFromSource(srv, chkTypes, false, "", ConfigSourceLocal); err != nil {
|
|
t.Fatalf("err: %v", err)
|
|
}
|
|
|
|
// Remove the service
|
|
if err := a.RemoveService(structs.NewServiceID("redis", nil)); err != nil {
|
|
t.Fatalf("err: %v", err)
|
|
}
|
|
|
|
// Ensure we have a state mapping
|
|
requireServiceMissing(t, a, "redis")
|
|
|
|
// Ensure checks were removed
|
|
requireCheckMissing(t, a, "service:redis:1")
|
|
requireCheckMissing(t, a, "service:redis:2")
|
|
requireCheckMissingMap(t, a.checkTTLs, "service:redis:1")
|
|
requireCheckMissingMap(t, a.checkTTLs, "service:redis:2")
|
|
|
|
// check the mysql service is unnafected
|
|
requireCheckExistsMap(t, a.checkTTLs, "service:mysql:1")
|
|
requireCheckExists(t, a, "service:mysql:1")
|
|
requireCheckExistsMap(t, a.checkTTLs, "service:mysql:2")
|
|
requireCheckExists(t, a, "service:mysql:2")
|
|
}
|
|
}
|
|
|
|
func TestAgent_RemoveServiceRemovesAllChecks(t *testing.T) {
|
|
if testing.Short() {
|
|
t.Skip("too slow for testing.Short")
|
|
}
|
|
|
|
t.Run("normal", func(t *testing.T) {
|
|
t.Parallel()
|
|
testAgent_RemoveServiceRemovesAllChecks(t, "enable_central_service_config = false")
|
|
})
|
|
t.Run("service manager", func(t *testing.T) {
|
|
t.Parallel()
|
|
testAgent_RemoveServiceRemovesAllChecks(t, "enable_central_service_config = true")
|
|
})
|
|
}
|
|
|
|
func testAgent_RemoveServiceRemovesAllChecks(t *testing.T, extraHCL string) {
|
|
t.Helper()
|
|
|
|
a := NewTestAgent(t, `
|
|
node_name = "node1"
|
|
`+extraHCL)
|
|
defer a.Shutdown()
|
|
svc := &structs.NodeService{ID: "redis", Service: "redis", Port: 8000, EnterpriseMeta: *structs.DefaultEnterpriseMetaInDefaultPartition()}
|
|
chk1 := &structs.CheckType{CheckID: "chk1", Name: "chk1", TTL: time.Minute}
|
|
chk2 := &structs.CheckType{CheckID: "chk2", Name: "chk2", TTL: 2 * time.Minute}
|
|
hchk1 := &structs.HealthCheck{
|
|
Node: "node1",
|
|
CheckID: "chk1",
|
|
Name: "chk1",
|
|
Status: "critical",
|
|
ServiceID: "redis",
|
|
ServiceName: "redis",
|
|
Type: "ttl",
|
|
EnterpriseMeta: *structs.DefaultEnterpriseMetaInDefaultPartition(),
|
|
}
|
|
hchk2 := &structs.HealthCheck{Node: "node1",
|
|
CheckID: "chk2",
|
|
Name: "chk2",
|
|
Status: "critical",
|
|
ServiceID: "redis",
|
|
ServiceName: "redis",
|
|
Type: "ttl",
|
|
EnterpriseMeta: *structs.DefaultEnterpriseMetaInDefaultPartition(),
|
|
}
|
|
|
|
// register service with chk1
|
|
if err := a.addServiceFromSource(svc, []*structs.CheckType{chk1}, false, "", ConfigSourceLocal); err != nil {
|
|
t.Fatal("Failed to register service", err)
|
|
}
|
|
|
|
// verify chk1 exists
|
|
requireCheckExists(t, a, "chk1")
|
|
|
|
// update the service with chk2
|
|
if err := a.addServiceFromSource(svc, []*structs.CheckType{chk2}, false, "", ConfigSourceLocal); err != nil {
|
|
t.Fatal("Failed to update service", err)
|
|
}
|
|
|
|
// check that both checks are there
|
|
require.Equal(t, hchk1, getCheck(a, "chk1"))
|
|
require.Equal(t, hchk2, getCheck(a, "chk2"))
|
|
|
|
// Remove service
|
|
if err := a.RemoveService(structs.NewServiceID("redis", nil)); err != nil {
|
|
t.Fatal("Failed to remove service", err)
|
|
}
|
|
|
|
// Check that both checks are gone
|
|
requireCheckMissing(t, a, "chk1")
|
|
requireCheckMissing(t, a, "chk2")
|
|
}
|
|
|
|
// TestAgent_IndexChurn is designed to detect a class of issues where
|
|
// we would have unnecessary catalog churn from anti-entropy. See issues
|
|
// #3259, #3642, #3845, and #3866.
|
|
func TestAgent_IndexChurn(t *testing.T) {
|
|
if testing.Short() {
|
|
t.Skip("too slow for testing.Short")
|
|
}
|
|
|
|
t.Parallel()
|
|
|
|
t.Run("no tags", func(t *testing.T) {
|
|
verifyIndexChurn(t, nil)
|
|
})
|
|
|
|
t.Run("with tags", func(t *testing.T) {
|
|
verifyIndexChurn(t, []string{"foo", "bar"})
|
|
})
|
|
}
|
|
|
|
// verifyIndexChurn registers some things and runs anti-entropy a bunch of times
|
|
// in a row to make sure there are no index bumps.
|
|
func verifyIndexChurn(t *testing.T, tags []string) {
|
|
t.Helper()
|
|
a := NewTestAgent(t, "")
|
|
defer a.Shutdown()
|
|
|
|
weights := &structs.Weights{
|
|
Passing: 1,
|
|
Warning: 1,
|
|
}
|
|
// Ensure we have a leader before we start adding the services
|
|
testrpc.WaitForLeader(t, a.RPC, "dc1")
|
|
|
|
svc := &structs.NodeService{
|
|
ID: "redis",
|
|
Service: "redis",
|
|
Port: 8000,
|
|
Tags: tags,
|
|
Weights: weights,
|
|
}
|
|
if err := a.addServiceFromSource(svc, nil, true, "", ConfigSourceLocal); err != nil {
|
|
t.Fatalf("err: %v", err)
|
|
}
|
|
|
|
chk := &structs.HealthCheck{
|
|
CheckID: "redis-check",
|
|
Name: "Service-level check",
|
|
ServiceID: "redis",
|
|
Status: api.HealthCritical,
|
|
}
|
|
chkt := &structs.CheckType{
|
|
TTL: time.Hour,
|
|
}
|
|
if err := a.AddCheck(chk, chkt, true, "", ConfigSourceLocal); err != nil {
|
|
t.Fatalf("err: %v", err)
|
|
}
|
|
|
|
chk = &structs.HealthCheck{
|
|
CheckID: "node-check",
|
|
Name: "Node-level check",
|
|
Status: api.HealthCritical,
|
|
}
|
|
chkt = &structs.CheckType{
|
|
TTL: time.Hour,
|
|
}
|
|
if err := a.AddCheck(chk, chkt, true, "", ConfigSourceLocal); err != nil {
|
|
t.Fatalf("err: %v", err)
|
|
}
|
|
|
|
if err := a.sync.State.SyncFull(); err != nil {
|
|
t.Fatalf("err: %v", err)
|
|
}
|
|
|
|
args := &structs.ServiceSpecificRequest{
|
|
Datacenter: "dc1",
|
|
ServiceName: "redis",
|
|
}
|
|
var before structs.IndexedCheckServiceNodes
|
|
|
|
// This sleep is so that the serfHealth check is added to the agent
|
|
// A value of 375ms is sufficient enough time to ensure the serfHealth
|
|
// check is added to an agent. 500ms so that we don't see flakiness ever.
|
|
time.Sleep(500 * time.Millisecond)
|
|
|
|
if err := a.RPC("Health.ServiceNodes", args, &before); err != nil {
|
|
t.Fatalf("err: %v", err)
|
|
}
|
|
for _, name := range before.Nodes[0].Checks {
|
|
a.logger.Debug("Registered node", "node", name.Name)
|
|
}
|
|
if got, want := len(before.Nodes), 1; got != want {
|
|
t.Fatalf("got %d want %d", got, want)
|
|
}
|
|
if got, want := len(before.Nodes[0].Checks), 3; /* incl. serfHealth */ got != want {
|
|
t.Fatalf("got %d want %d", got, want)
|
|
}
|
|
|
|
for i := 0; i < 10; i++ {
|
|
a.logger.Info("Sync in progress", "iteration", i+1)
|
|
if err := a.sync.State.SyncFull(); err != nil {
|
|
t.Fatalf("err: %v", err)
|
|
}
|
|
}
|
|
// If this test fails here this means that the Consul-X-Index
|
|
// has changed for the RPC, which means that idempotent ops
|
|
// are not working as intended.
|
|
var after structs.IndexedCheckServiceNodes
|
|
if err := a.RPC("Health.ServiceNodes", args, &after); err != nil {
|
|
t.Fatalf("err: %v", err)
|
|
}
|
|
require.Equal(t, before, after)
|
|
}
|
|
|
|
func TestAgent_AddCheck(t *testing.T) {
|
|
if testing.Short() {
|
|
t.Skip("too slow for testing.Short")
|
|
}
|
|
|
|
t.Parallel()
|
|
a := NewTestAgent(t, `
|
|
enable_script_checks = true
|
|
`)
|
|
defer a.Shutdown()
|
|
|
|
health := &structs.HealthCheck{
|
|
Node: "foo",
|
|
CheckID: "mem",
|
|
Name: "memory util",
|
|
Status: api.HealthCritical,
|
|
}
|
|
chk := &structs.CheckType{
|
|
ScriptArgs: []string{"exit", "0"},
|
|
Interval: 15 * time.Second,
|
|
}
|
|
err := a.AddCheck(health, chk, false, "", ConfigSourceLocal)
|
|
if err != nil {
|
|
t.Fatalf("err: %v", err)
|
|
}
|
|
|
|
// Ensure we have a check mapping
|
|
sChk := requireCheckExists(t, a, "mem")
|
|
|
|
// Ensure our check is in the right state
|
|
if sChk.Status != api.HealthCritical {
|
|
t.Fatalf("check not critical")
|
|
}
|
|
|
|
// Ensure a TTL is setup
|
|
requireCheckExistsMap(t, a.checkMonitors, "mem")
|
|
}
|
|
|
|
func TestAgent_AddCheck_StartPassing(t *testing.T) {
|
|
if testing.Short() {
|
|
t.Skip("too slow for testing.Short")
|
|
}
|
|
|
|
t.Parallel()
|
|
a := NewTestAgent(t, `
|
|
enable_script_checks = true
|
|
`)
|
|
defer a.Shutdown()
|
|
|
|
health := &structs.HealthCheck{
|
|
Node: "foo",
|
|
CheckID: "mem",
|
|
Name: "memory util",
|
|
Status: api.HealthPassing,
|
|
}
|
|
chk := &structs.CheckType{
|
|
ScriptArgs: []string{"exit", "0"},
|
|
Interval: 15 * time.Second,
|
|
}
|
|
err := a.AddCheck(health, chk, false, "", ConfigSourceLocal)
|
|
if err != nil {
|
|
t.Fatalf("err: %v", err)
|
|
}
|
|
|
|
// Ensure we have a check mapping
|
|
sChk := requireCheckExists(t, a, "mem")
|
|
|
|
// Ensure our check is in the right state
|
|
if sChk.Status != api.HealthPassing {
|
|
t.Fatalf("check not passing")
|
|
}
|
|
|
|
// Ensure a TTL is setup
|
|
requireCheckExistsMap(t, a.checkMonitors, "mem")
|
|
}
|
|
|
|
func TestAgent_AddCheck_MinInterval(t *testing.T) {
|
|
if testing.Short() {
|
|
t.Skip("too slow for testing.Short")
|
|
}
|
|
|
|
t.Parallel()
|
|
a := NewTestAgent(t, `
|
|
enable_script_checks = true
|
|
`)
|
|
defer a.Shutdown()
|
|
|
|
health := &structs.HealthCheck{
|
|
Node: "foo",
|
|
CheckID: "mem",
|
|
Name: "memory util",
|
|
Status: api.HealthCritical,
|
|
}
|
|
chk := &structs.CheckType{
|
|
ScriptArgs: []string{"exit", "0"},
|
|
Interval: time.Microsecond,
|
|
}
|
|
err := a.AddCheck(health, chk, false, "", ConfigSourceLocal)
|
|
if err != nil {
|
|
t.Fatalf("err: %v", err)
|
|
}
|
|
|
|
// Ensure we have a check mapping
|
|
requireCheckExists(t, a, "mem")
|
|
|
|
// Ensure a TTL is setup
|
|
if mon, ok := a.checkMonitors[structs.NewCheckID("mem", nil)]; !ok {
|
|
t.Fatalf("missing mem monitor")
|
|
} else if mon.Interval != checks.MinInterval {
|
|
t.Fatalf("bad mem monitor interval")
|
|
}
|
|
}
|
|
|
|
func TestAgent_AddCheck_MissingService(t *testing.T) {
|
|
if testing.Short() {
|
|
t.Skip("too slow for testing.Short")
|
|
}
|
|
|
|
t.Parallel()
|
|
a := NewTestAgent(t, `
|
|
enable_script_checks = true
|
|
`)
|
|
defer a.Shutdown()
|
|
|
|
health := &structs.HealthCheck{
|
|
Node: "foo",
|
|
CheckID: "baz",
|
|
Name: "baz check 1",
|
|
ServiceID: "baz",
|
|
}
|
|
chk := &structs.CheckType{
|
|
ScriptArgs: []string{"exit", "0"},
|
|
Interval: time.Microsecond,
|
|
}
|
|
err := a.AddCheck(health, chk, false, "", ConfigSourceLocal)
|
|
if err == nil || err.Error() != fmt.Sprintf("ServiceID %q does not exist", structs.ServiceIDString("baz", nil)) {
|
|
t.Fatalf("expected service id error, got: %v", err)
|
|
}
|
|
}
|
|
|
|
func TestAgent_AddCheck_RestoreState(t *testing.T) {
|
|
if testing.Short() {
|
|
t.Skip("too slow for testing.Short")
|
|
}
|
|
|
|
t.Parallel()
|
|
a := NewTestAgent(t, "")
|
|
defer a.Shutdown()
|
|
|
|
// Create some state and persist it
|
|
ttl := &checks.CheckTTL{
|
|
CheckID: structs.NewCheckID("baz", nil),
|
|
TTL: time.Minute,
|
|
}
|
|
err := a.persistCheckState(ttl, api.HealthPassing, "yup")
|
|
if err != nil {
|
|
t.Fatalf("err: %s", err)
|
|
}
|
|
|
|
// Build and register the check definition and initial state
|
|
health := &structs.HealthCheck{
|
|
Node: "foo",
|
|
CheckID: "baz",
|
|
Name: "baz check 1",
|
|
}
|
|
chk := &structs.CheckType{
|
|
TTL: time.Minute,
|
|
}
|
|
err = a.AddCheck(health, chk, false, "", ConfigSourceLocal)
|
|
if err != nil {
|
|
t.Fatalf("err: %s", err)
|
|
}
|
|
|
|
// Ensure the check status was restored during registration
|
|
check := requireCheckExists(t, a, "baz")
|
|
if check.Status != api.HealthPassing {
|
|
t.Fatalf("bad: %#v", check)
|
|
}
|
|
if check.Output != "yup" {
|
|
t.Fatalf("bad: %#v", check)
|
|
}
|
|
}
|
|
|
|
func TestAgent_AddCheck_ExecDisable(t *testing.T) {
|
|
if testing.Short() {
|
|
t.Skip("too slow for testing.Short")
|
|
}
|
|
|
|
t.Parallel()
|
|
|
|
a := NewTestAgent(t, "")
|
|
defer a.Shutdown()
|
|
|
|
health := &structs.HealthCheck{
|
|
Node: "foo",
|
|
CheckID: "mem",
|
|
Name: "memory util",
|
|
Status: api.HealthCritical,
|
|
}
|
|
chk := &structs.CheckType{
|
|
ScriptArgs: []string{"exit", "0"},
|
|
Interval: 15 * time.Second,
|
|
}
|
|
err := a.AddCheck(health, chk, false, "", ConfigSourceLocal)
|
|
if err == nil || !strings.Contains(err.Error(), "Scripts are disabled on this agent") {
|
|
t.Fatalf("err: %v", err)
|
|
}
|
|
|
|
// Ensure we don't have a check mapping
|
|
requireCheckMissing(t, a, "mem")
|
|
|
|
err = a.AddCheck(health, chk, false, "", ConfigSourceRemote)
|
|
if err == nil || !strings.Contains(err.Error(), "Scripts are disabled on this agent") {
|
|
t.Fatalf("err: %v", err)
|
|
}
|
|
|
|
// Ensure we don't have a check mapping
|
|
requireCheckMissing(t, a, "mem")
|
|
}
|
|
|
|
func TestAgent_AddCheck_ExecRemoteDisable(t *testing.T) {
|
|
if testing.Short() {
|
|
t.Skip("too slow for testing.Short")
|
|
}
|
|
|
|
t.Parallel()
|
|
|
|
a := NewTestAgent(t, `
|
|
enable_local_script_checks = true
|
|
`)
|
|
defer a.Shutdown()
|
|
testrpc.WaitForTestAgent(t, a.RPC, "dc1")
|
|
|
|
health := &structs.HealthCheck{
|
|
Node: "foo",
|
|
CheckID: "mem",
|
|
Name: "memory util",
|
|
Status: api.HealthCritical,
|
|
}
|
|
chk := &structs.CheckType{
|
|
ScriptArgs: []string{"exit", "0"},
|
|
Interval: 15 * time.Second,
|
|
}
|
|
err := a.AddCheck(health, chk, false, "", ConfigSourceRemote)
|
|
if err == nil || !strings.Contains(err.Error(), "Scripts are disabled on this agent from remote calls") {
|
|
t.Fatalf("err: %v", err)
|
|
}
|
|
|
|
// Ensure we don't have a check mapping
|
|
requireCheckMissing(t, a, "mem")
|
|
}
|
|
|
|
func TestAgent_AddCheck_GRPC(t *testing.T) {
|
|
if testing.Short() {
|
|
t.Skip("too slow for testing.Short")
|
|
}
|
|
|
|
t.Parallel()
|
|
a := NewTestAgent(t, "")
|
|
defer a.Shutdown()
|
|
|
|
health := &structs.HealthCheck{
|
|
Node: "foo",
|
|
CheckID: "grpchealth",
|
|
Name: "grpc health checking protocol",
|
|
Status: api.HealthCritical,
|
|
}
|
|
chk := &structs.CheckType{
|
|
GRPC: "localhost:12345/package.Service",
|
|
Interval: 15 * time.Second,
|
|
}
|
|
err := a.AddCheck(health, chk, false, "", ConfigSourceLocal)
|
|
if err != nil {
|
|
t.Fatalf("err: %v", err)
|
|
}
|
|
|
|
// Ensure we have a check mapping
|
|
sChk := requireCheckExists(t, a, "grpchealth")
|
|
|
|
// Ensure our check is in the right state
|
|
if sChk.Status != api.HealthCritical {
|
|
t.Fatalf("check not critical")
|
|
}
|
|
|
|
// Ensure a check is setup
|
|
requireCheckExistsMap(t, a.checkGRPCs, "grpchealth")
|
|
}
|
|
|
|
func TestAgent_RestoreServiceWithAliasCheck(t *testing.T) {
|
|
// t.Parallel() don't even think about making this parallel
|
|
|
|
// This test is very contrived and tests for the absence of race conditions
|
|
// related to the implementation of alias checks. As such it is slow,
|
|
// serial, full of sleeps and retries, and not generally a great test to
|
|
// run all of the time.
|
|
//
|
|
// That said it made it incredibly easy to root out various race conditions
|
|
// quite successfully.
|
|
//
|
|
// The original set of races was between:
|
|
//
|
|
// - agent startup reloading Services and Checks from disk
|
|
// - API requests to also re-register those same Services and Checks
|
|
// - the goroutines for the as-yet-to-be-stopped CheckAlias goroutines
|
|
|
|
if os.Getenv("SLOWTEST") != "1" {
|
|
t.Skip("skipping slow test; set SLOWTEST=1 to run")
|
|
return
|
|
}
|
|
|
|
// We do this so that the agent logs and the informational messages from
|
|
// the test itself are interwoven properly.
|
|
logf := func(t *testing.T, a *TestAgent, format string, args ...interface{}) {
|
|
a.logger.Info("testharness: " + fmt.Sprintf(format, args...))
|
|
}
|
|
|
|
cfg := `
|
|
server = false
|
|
bootstrap = false
|
|
enable_central_service_config = false
|
|
`
|
|
a := StartTestAgent(t, TestAgent{HCL: cfg})
|
|
defer a.Shutdown()
|
|
|
|
handler := http.HandlerFunc(func(w http.ResponseWriter, req *http.Request) {
|
|
w.WriteHeader(http.StatusOK)
|
|
_, _ = w.Write([]byte("OK\n"))
|
|
})
|
|
testHTTPServer := httptest.NewServer(handler)
|
|
t.Cleanup(testHTTPServer.Close)
|
|
|
|
registerServicesAndChecks := func(t *testing.T, a *TestAgent) {
|
|
// add one persistent service with a simple check
|
|
require.NoError(t, a.addServiceFromSource(
|
|
&structs.NodeService{
|
|
ID: "ping",
|
|
Service: "ping",
|
|
Port: 8000,
|
|
},
|
|
[]*structs.CheckType{
|
|
{
|
|
HTTP: testHTTPServer.URL,
|
|
Method: "GET",
|
|
Interval: 5 * time.Second,
|
|
Timeout: 1 * time.Second,
|
|
},
|
|
},
|
|
true, "", ConfigSourceLocal,
|
|
))
|
|
|
|
// add one persistent sidecar service with an alias check in the manner
|
|
// of how sidecar_service would add it
|
|
require.NoError(t, a.addServiceFromSource(
|
|
&structs.NodeService{
|
|
ID: "ping-sidecar-proxy",
|
|
Service: "ping-sidecar-proxy",
|
|
Port: 9000,
|
|
},
|
|
[]*structs.CheckType{
|
|
{
|
|
Name: "Connect Sidecar Aliasing ping",
|
|
AliasService: "ping",
|
|
},
|
|
},
|
|
true, "", ConfigSourceLocal,
|
|
))
|
|
}
|
|
|
|
retryUntilCheckState := func(t *testing.T, a *TestAgent, checkID string, expectedStatus string) {
|
|
t.Helper()
|
|
retry.Run(t, func(r *retry.R) {
|
|
chk := requireCheckExists(t, a, types.CheckID(checkID))
|
|
if chk.Status != expectedStatus {
|
|
logf(t, a, "check=%q expected status %q but got %q", checkID, expectedStatus, chk.Status)
|
|
r.Fatalf("check=%q expected status %q but got %q", checkID, expectedStatus, chk.Status)
|
|
}
|
|
logf(t, a, "check %q has reached desired status %q", checkID, expectedStatus)
|
|
})
|
|
}
|
|
|
|
registerServicesAndChecks(t, a)
|
|
|
|
time.Sleep(1 * time.Second)
|
|
|
|
retryUntilCheckState(t, a, "service:ping", api.HealthPassing)
|
|
retryUntilCheckState(t, a, "service:ping-sidecar-proxy", api.HealthPassing)
|
|
|
|
logf(t, a, "==== POWERING DOWN ORIGINAL ====")
|
|
|
|
require.NoError(t, a.Shutdown())
|
|
|
|
time.Sleep(1 * time.Second)
|
|
|
|
futureHCL := cfg + `
|
|
node_id = "` + string(a.Config.NodeID) + `"
|
|
node_name = "` + a.Config.NodeName + `"
|
|
`
|
|
|
|
restartOnce := func(idx int, t *testing.T) {
|
|
t.Helper()
|
|
|
|
// Reload and retain former NodeID and data directory.
|
|
a2 := StartTestAgent(t, TestAgent{HCL: futureHCL, DataDir: a.DataDir})
|
|
defer a2.Shutdown()
|
|
a = nil
|
|
|
|
// reregister during standup; we use an adjustable timing to try and force a race
|
|
sleepDur := time.Duration(idx+1) * 500 * time.Millisecond
|
|
time.Sleep(sleepDur)
|
|
logf(t, a2, "re-registering checks and services after a delay of %v", sleepDur)
|
|
for i := 0; i < 20; i++ { // RACE RACE RACE!
|
|
registerServicesAndChecks(t, a2)
|
|
time.Sleep(50 * time.Millisecond)
|
|
}
|
|
|
|
time.Sleep(1 * time.Second)
|
|
|
|
retryUntilCheckState(t, a2, "service:ping", api.HealthPassing)
|
|
|
|
logf(t, a2, "giving the alias check a chance to notice...")
|
|
time.Sleep(5 * time.Second)
|
|
|
|
retryUntilCheckState(t, a2, "service:ping-sidecar-proxy", api.HealthPassing)
|
|
}
|
|
|
|
for i := 0; i < 20; i++ {
|
|
name := "restart-" + strconv.Itoa(i)
|
|
ok := t.Run(name, func(t *testing.T) {
|
|
restartOnce(i, t)
|
|
})
|
|
require.True(t, ok, name+" failed")
|
|
}
|
|
}
|
|
|
|
func TestAgent_AddCheck_Alias(t *testing.T) {
|
|
if testing.Short() {
|
|
t.Skip("too slow for testing.Short")
|
|
}
|
|
|
|
t.Parallel()
|
|
|
|
a := NewTestAgent(t, "")
|
|
defer a.Shutdown()
|
|
|
|
health := &structs.HealthCheck{
|
|
Node: "foo",
|
|
CheckID: "aliashealth",
|
|
Name: "Alias health check",
|
|
Status: api.HealthCritical,
|
|
}
|
|
chk := &structs.CheckType{
|
|
AliasService: "foo",
|
|
}
|
|
err := a.AddCheck(health, chk, false, "", ConfigSourceLocal)
|
|
require.NoError(t, err)
|
|
|
|
// Ensure we have a check mapping
|
|
sChk := requireCheckExists(t, a, "aliashealth")
|
|
require.Equal(t, api.HealthCritical, sChk.Status)
|
|
|
|
chkImpl, ok := a.checkAliases[structs.NewCheckID("aliashealth", nil)]
|
|
require.True(t, ok, "missing aliashealth check")
|
|
require.Equal(t, "", chkImpl.RPCReq.Token)
|
|
|
|
cs := a.State.CheckState(structs.NewCheckID("aliashealth", nil))
|
|
require.NotNil(t, cs)
|
|
require.Equal(t, "", cs.Token)
|
|
}
|
|
|
|
func TestAgent_AddCheck_Alias_setToken(t *testing.T) {
|
|
if testing.Short() {
|
|
t.Skip("too slow for testing.Short")
|
|
}
|
|
|
|
t.Parallel()
|
|
|
|
a := NewTestAgent(t, "")
|
|
defer a.Shutdown()
|
|
|
|
health := &structs.HealthCheck{
|
|
Node: "foo",
|
|
CheckID: "aliashealth",
|
|
Name: "Alias health check",
|
|
Status: api.HealthCritical,
|
|
}
|
|
chk := &structs.CheckType{
|
|
AliasService: "foo",
|
|
}
|
|
err := a.AddCheck(health, chk, false, "foo", ConfigSourceLocal)
|
|
require.NoError(t, err)
|
|
|
|
cs := a.State.CheckState(structs.NewCheckID("aliashealth", nil))
|
|
require.NotNil(t, cs)
|
|
require.Equal(t, "foo", cs.Token)
|
|
|
|
chkImpl, ok := a.checkAliases[structs.NewCheckID("aliashealth", nil)]
|
|
require.True(t, ok, "missing aliashealth check")
|
|
require.Equal(t, "foo", chkImpl.RPCReq.Token)
|
|
}
|
|
|
|
func TestAgent_AddCheck_Alias_userToken(t *testing.T) {
|
|
if testing.Short() {
|
|
t.Skip("too slow for testing.Short")
|
|
}
|
|
|
|
t.Parallel()
|
|
|
|
a := NewTestAgent(t, `
|
|
acl_token = "hello"
|
|
`)
|
|
defer a.Shutdown()
|
|
|
|
health := &structs.HealthCheck{
|
|
Node: "foo",
|
|
CheckID: "aliashealth",
|
|
Name: "Alias health check",
|
|
Status: api.HealthCritical,
|
|
}
|
|
chk := &structs.CheckType{
|
|
AliasService: "foo",
|
|
}
|
|
err := a.AddCheck(health, chk, false, "", ConfigSourceLocal)
|
|
require.NoError(t, err)
|
|
|
|
cs := a.State.CheckState(structs.NewCheckID("aliashealth", nil))
|
|
require.NotNil(t, cs)
|
|
require.Equal(t, "", cs.Token) // State token should still be empty
|
|
|
|
chkImpl, ok := a.checkAliases[structs.NewCheckID("aliashealth", nil)]
|
|
require.True(t, ok, "missing aliashealth check")
|
|
require.Equal(t, "hello", chkImpl.RPCReq.Token) // Check should use the token
|
|
}
|
|
|
|
func TestAgent_AddCheck_Alias_userAndSetToken(t *testing.T) {
|
|
if testing.Short() {
|
|
t.Skip("too slow for testing.Short")
|
|
}
|
|
|
|
t.Parallel()
|
|
|
|
a := NewTestAgent(t, `
|
|
acl_token = "hello"
|
|
`)
|
|
defer a.Shutdown()
|
|
|
|
health := &structs.HealthCheck{
|
|
Node: "foo",
|
|
CheckID: "aliashealth",
|
|
Name: "Alias health check",
|
|
Status: api.HealthCritical,
|
|
}
|
|
chk := &structs.CheckType{
|
|
AliasService: "foo",
|
|
}
|
|
err := a.AddCheck(health, chk, false, "goodbye", ConfigSourceLocal)
|
|
require.NoError(t, err)
|
|
|
|
cs := a.State.CheckState(structs.NewCheckID("aliashealth", nil))
|
|
require.NotNil(t, cs)
|
|
require.Equal(t, "goodbye", cs.Token)
|
|
|
|
chkImpl, ok := a.checkAliases[structs.NewCheckID("aliashealth", nil)]
|
|
require.True(t, ok, "missing aliashealth check")
|
|
require.Equal(t, "goodbye", chkImpl.RPCReq.Token)
|
|
}
|
|
|
|
func TestAgent_RemoveCheck(t *testing.T) {
|
|
if testing.Short() {
|
|
t.Skip("too slow for testing.Short")
|
|
}
|
|
|
|
t.Parallel()
|
|
a := NewTestAgent(t, `
|
|
enable_script_checks = true
|
|
`)
|
|
defer a.Shutdown()
|
|
|
|
// Remove check that doesn't exist
|
|
if err := a.RemoveCheck(structs.NewCheckID("mem", nil), false); err != nil {
|
|
t.Fatalf("err: %v", err)
|
|
}
|
|
|
|
// Remove without an ID
|
|
if err := a.RemoveCheck(structs.NewCheckID("", nil), false); err == nil {
|
|
t.Fatalf("should have errored")
|
|
}
|
|
|
|
health := &structs.HealthCheck{
|
|
Node: "foo",
|
|
CheckID: "mem",
|
|
Name: "memory util",
|
|
Status: api.HealthCritical,
|
|
}
|
|
chk := &structs.CheckType{
|
|
ScriptArgs: []string{"exit", "0"},
|
|
Interval: 15 * time.Second,
|
|
}
|
|
err := a.AddCheck(health, chk, false, "", ConfigSourceLocal)
|
|
if err != nil {
|
|
t.Fatalf("err: %v", err)
|
|
}
|
|
|
|
// Remove check
|
|
if err := a.RemoveCheck(structs.NewCheckID("mem", nil), false); err != nil {
|
|
t.Fatalf("err: %v", err)
|
|
}
|
|
|
|
// Ensure we have a check mapping
|
|
requireCheckMissing(t, a, "mem")
|
|
|
|
// Ensure a TTL is setup
|
|
requireCheckMissingMap(t, a.checkMonitors, "mem")
|
|
}
|
|
|
|
func TestAgent_HTTPCheck_TLSSkipVerify(t *testing.T) {
|
|
if testing.Short() {
|
|
t.Skip("too slow for testing.Short")
|
|
}
|
|
|
|
t.Parallel()
|
|
|
|
handler := http.HandlerFunc(func(w http.ResponseWriter, r *http.Request) {
|
|
fmt.Fprintln(w, "GOOD")
|
|
})
|
|
server := httptest.NewTLSServer(handler)
|
|
defer server.Close()
|
|
|
|
a := NewTestAgent(t, "")
|
|
defer a.Shutdown()
|
|
|
|
health := &structs.HealthCheck{
|
|
Node: "foo",
|
|
CheckID: "tls",
|
|
Name: "tls check",
|
|
Status: api.HealthCritical,
|
|
}
|
|
chk := &structs.CheckType{
|
|
HTTP: server.URL,
|
|
Interval: 20 * time.Millisecond,
|
|
TLSSkipVerify: true,
|
|
}
|
|
|
|
err := a.AddCheck(health, chk, false, "", ConfigSourceLocal)
|
|
if err != nil {
|
|
t.Fatalf("err: %v", err)
|
|
}
|
|
|
|
retry.Run(t, func(r *retry.R) {
|
|
status := getCheck(a, "tls")
|
|
if status.Status != api.HealthPassing {
|
|
r.Fatalf("bad: %v", status.Status)
|
|
}
|
|
if !strings.Contains(status.Output, "GOOD") {
|
|
r.Fatalf("bad: %v", status.Output)
|
|
}
|
|
})
|
|
|
|
}
|
|
|
|
func TestAgent_HTTPCheck_EnableAgentTLSForChecks(t *testing.T) {
|
|
if testing.Short() {
|
|
t.Skip("too slow for testing.Short")
|
|
}
|
|
|
|
t.Parallel()
|
|
|
|
run := func(t *testing.T, ca string) {
|
|
a := StartTestAgent(t, TestAgent{
|
|
UseHTTPS: true,
|
|
HCL: `
|
|
enable_agent_tls_for_checks = true
|
|
|
|
verify_incoming = true
|
|
server_name = "consul.test"
|
|
key_file = "../test/client_certs/server.key"
|
|
cert_file = "../test/client_certs/server.crt"
|
|
` + ca,
|
|
})
|
|
defer a.Shutdown()
|
|
|
|
health := &structs.HealthCheck{
|
|
Node: "foo",
|
|
CheckID: "tls",
|
|
Name: "tls check",
|
|
Status: api.HealthCritical,
|
|
}
|
|
|
|
addr, err := firstAddr(a.Agent.apiServers, "https")
|
|
require.NoError(t, err)
|
|
url := fmt.Sprintf("https://%s/v1/agent/self", addr.String())
|
|
chk := &structs.CheckType{
|
|
HTTP: url,
|
|
Interval: 20 * time.Millisecond,
|
|
}
|
|
|
|
err = a.AddCheck(health, chk, false, "", ConfigSourceLocal)
|
|
if err != nil {
|
|
t.Fatalf("err: %v", err)
|
|
}
|
|
|
|
retry.Run(t, func(r *retry.R) {
|
|
status := getCheck(a, "tls")
|
|
if status.Status != api.HealthPassing {
|
|
r.Fatalf("bad: %v", status.Status)
|
|
}
|
|
if !strings.Contains(status.Output, "200 OK") {
|
|
r.Fatalf("bad: %v", status.Output)
|
|
}
|
|
})
|
|
}
|
|
|
|
// We need to test both methods of passing the CA info to ensure that
|
|
// we propagate all the fields correctly. All the other fields are
|
|
// covered by the HCL in the test run function.
|
|
tests := []struct {
|
|
desc string
|
|
config string
|
|
}{
|
|
{"ca_file", `ca_file = "../test/client_certs/rootca.crt"`},
|
|
{"ca_path", `ca_path = "../test/client_certs/path"`},
|
|
}
|
|
for _, tt := range tests {
|
|
t.Run(tt.desc, func(t *testing.T) {
|
|
run(t, tt.config)
|
|
})
|
|
}
|
|
}
|
|
|
|
func TestAgent_updateTTLCheck(t *testing.T) {
|
|
if testing.Short() {
|
|
t.Skip("too slow for testing.Short")
|
|
}
|
|
|
|
t.Parallel()
|
|
a := NewTestAgent(t, "")
|
|
defer a.Shutdown()
|
|
checkBufSize := 100
|
|
health := &structs.HealthCheck{
|
|
Node: "foo",
|
|
CheckID: "mem",
|
|
Name: "memory util",
|
|
Status: api.HealthCritical,
|
|
}
|
|
chk := &structs.CheckType{
|
|
TTL: 15 * time.Second,
|
|
OutputMaxSize: checkBufSize,
|
|
}
|
|
|
|
// Add check and update it.
|
|
err := a.AddCheck(health, chk, false, "", ConfigSourceLocal)
|
|
if err != nil {
|
|
t.Fatalf("err: %v", err)
|
|
}
|
|
if err := a.updateTTLCheck(structs.NewCheckID("mem", nil), api.HealthPassing, "foo"); err != nil {
|
|
t.Fatalf("err: %v", err)
|
|
}
|
|
|
|
// Ensure we have a check mapping.
|
|
status := getCheck(a, "mem")
|
|
if status.Status != api.HealthPassing {
|
|
t.Fatalf("bad: %v", status)
|
|
}
|
|
if status.Output != "foo" {
|
|
t.Fatalf("bad: %v", status)
|
|
}
|
|
|
|
if err := a.updateTTLCheck(structs.NewCheckID("mem", nil), api.HealthCritical, strings.Repeat("--bad-- ", 5*checkBufSize)); err != nil {
|
|
t.Fatalf("err: %v", err)
|
|
}
|
|
|
|
// Ensure we have a check mapping.
|
|
status = getCheck(a, "mem")
|
|
if status.Status != api.HealthCritical {
|
|
t.Fatalf("bad: %v", status)
|
|
}
|
|
if len(status.Output) > checkBufSize*2 {
|
|
t.Fatalf("bad: %v", len(status.Output))
|
|
}
|
|
}
|
|
|
|
func TestAgent_PersistService(t *testing.T) {
|
|
if testing.Short() {
|
|
t.Skip("too slow for testing.Short")
|
|
}
|
|
|
|
t.Run("normal", func(t *testing.T) {
|
|
t.Parallel()
|
|
testAgent_PersistService(t, "enable_central_service_config = false")
|
|
})
|
|
t.Run("service manager", func(t *testing.T) {
|
|
t.Parallel()
|
|
testAgent_PersistService(t, "enable_central_service_config = true")
|
|
})
|
|
}
|
|
|
|
func testAgent_PersistService(t *testing.T, extraHCL string) {
|
|
t.Helper()
|
|
|
|
cfg := `
|
|
server = false
|
|
bootstrap = false
|
|
` + extraHCL
|
|
a := StartTestAgent(t, TestAgent{HCL: cfg})
|
|
defer a.Shutdown()
|
|
|
|
svc := &structs.NodeService{
|
|
ID: "redis",
|
|
Service: "redis",
|
|
Tags: []string{"foo"},
|
|
Port: 8000,
|
|
}
|
|
|
|
file := filepath.Join(a.Config.DataDir, servicesDir, structs.NewServiceID(svc.ID, nil).StringHashSHA256())
|
|
|
|
// Check is not persisted unless requested
|
|
if err := a.addServiceFromSource(svc, nil, false, "", ConfigSourceLocal); err != nil {
|
|
t.Fatalf("err: %v", err)
|
|
}
|
|
if _, err := os.Stat(file); err == nil {
|
|
t.Fatalf("should not persist")
|
|
}
|
|
|
|
// Persists to file if requested
|
|
if err := a.addServiceFromSource(svc, nil, true, "mytoken", ConfigSourceLocal); err != nil {
|
|
t.Fatalf("err: %v", err)
|
|
}
|
|
if _, err := os.Stat(file); err != nil {
|
|
t.Fatalf("err: %s", err)
|
|
}
|
|
expected, err := json.Marshal(persistedService{
|
|
Token: "mytoken",
|
|
Service: svc,
|
|
Source: "local",
|
|
})
|
|
if err != nil {
|
|
t.Fatalf("err: %s", err)
|
|
}
|
|
content, err := ioutil.ReadFile(file)
|
|
if err != nil {
|
|
t.Fatalf("err: %s", err)
|
|
}
|
|
if !bytes.Equal(expected, content) {
|
|
t.Fatalf("bad: %s", string(content))
|
|
}
|
|
|
|
// Updates service definition on disk
|
|
svc.Port = 8001
|
|
if err := a.addServiceFromSource(svc, nil, true, "mytoken", ConfigSourceLocal); err != nil {
|
|
t.Fatalf("err: %v", err)
|
|
}
|
|
expected, err = json.Marshal(persistedService{
|
|
Token: "mytoken",
|
|
Service: svc,
|
|
Source: "local",
|
|
})
|
|
if err != nil {
|
|
t.Fatalf("err: %s", err)
|
|
}
|
|
content, err = ioutil.ReadFile(file)
|
|
if err != nil {
|
|
t.Fatalf("err: %s", err)
|
|
}
|
|
if !bytes.Equal(expected, content) {
|
|
t.Fatalf("bad: %s", string(content))
|
|
}
|
|
a.Shutdown()
|
|
|
|
// Should load it back during later start
|
|
a2 := StartTestAgent(t, TestAgent{HCL: cfg, DataDir: a.DataDir})
|
|
defer a2.Shutdown()
|
|
|
|
restored := a2.State.ServiceState(structs.NewServiceID(svc.ID, nil))
|
|
if restored == nil {
|
|
t.Fatalf("service %q missing", svc.ID)
|
|
}
|
|
if got, want := restored.Token, "mytoken"; got != want {
|
|
t.Fatalf("got token %q want %q", got, want)
|
|
}
|
|
if got, want := restored.Service.Port, 8001; got != want {
|
|
t.Fatalf("got port %d want %d", got, want)
|
|
}
|
|
}
|
|
|
|
func TestAgent_persistedService_compat(t *testing.T) {
|
|
if testing.Short() {
|
|
t.Skip("too slow for testing.Short")
|
|
}
|
|
|
|
t.Run("normal", func(t *testing.T) {
|
|
t.Parallel()
|
|
testAgent_persistedService_compat(t, "enable_central_service_config = false")
|
|
})
|
|
t.Run("service manager", func(t *testing.T) {
|
|
t.Parallel()
|
|
testAgent_persistedService_compat(t, "enable_central_service_config = true")
|
|
})
|
|
}
|
|
|
|
func testAgent_persistedService_compat(t *testing.T, extraHCL string) {
|
|
t.Helper()
|
|
|
|
// Tests backwards compatibility of persisted services from pre-0.5.1
|
|
a := NewTestAgent(t, extraHCL)
|
|
defer a.Shutdown()
|
|
|
|
svc := &structs.NodeService{
|
|
ID: "redis",
|
|
Service: "redis",
|
|
Tags: []string{"foo"},
|
|
Port: 8000,
|
|
TaggedAddresses: map[string]structs.ServiceAddress{},
|
|
Weights: &structs.Weights{Passing: 1, Warning: 1},
|
|
EnterpriseMeta: *structs.DefaultEnterpriseMetaInDefaultPartition(),
|
|
}
|
|
|
|
// Encode the NodeService directly. This is what previous versions
|
|
// would serialize to the file (without the wrapper)
|
|
encoded, err := json.Marshal(svc)
|
|
if err != nil {
|
|
t.Fatalf("err: %s", err)
|
|
}
|
|
|
|
// Write the content to the file
|
|
file := filepath.Join(a.Config.DataDir, servicesDir, structs.NewServiceID(svc.ID, nil).StringHashSHA256())
|
|
if err := os.MkdirAll(filepath.Dir(file), 0700); err != nil {
|
|
t.Fatalf("err: %s", err)
|
|
}
|
|
if err := ioutil.WriteFile(file, encoded, 0600); err != nil {
|
|
t.Fatalf("err: %s", err)
|
|
}
|
|
|
|
// Load the services
|
|
if err := a.loadServices(a.Config, nil); err != nil {
|
|
t.Fatalf("err: %s", err)
|
|
}
|
|
|
|
// Ensure the service was restored
|
|
result := requireServiceExists(t, a, "redis")
|
|
require.Equal(t, svc, result)
|
|
}
|
|
|
|
func TestAgent_persistedService_compat_hash(t *testing.T) {
|
|
t.Run("normal", func(t *testing.T) {
|
|
t.Parallel()
|
|
testAgent_persistedService_compat_hash(t, "enable_central_service_config = false")
|
|
})
|
|
t.Run("service manager", func(t *testing.T) {
|
|
t.Parallel()
|
|
testAgent_persistedService_compat_hash(t, "enable_central_service_config = true")
|
|
})
|
|
|
|
}
|
|
|
|
func testAgent_persistedService_compat_hash(t *testing.T, extraHCL string) {
|
|
t.Helper()
|
|
|
|
// Tests backwards compatibility of persisted services from pre-0.5.1
|
|
a := NewTestAgent(t, extraHCL)
|
|
defer a.Shutdown()
|
|
|
|
svc := &structs.NodeService{
|
|
ID: "redis",
|
|
Service: "redis",
|
|
Tags: []string{"foo"},
|
|
Port: 8000,
|
|
TaggedAddresses: map[string]structs.ServiceAddress{},
|
|
Weights: &structs.Weights{Passing: 1, Warning: 1},
|
|
EnterpriseMeta: *structs.DefaultEnterpriseMetaInDefaultPartition(),
|
|
}
|
|
|
|
// Encode the NodeService directly. This is what previous versions
|
|
// would serialize to the file (without the wrapper)
|
|
encoded, err := json.Marshal(svc)
|
|
if err != nil {
|
|
t.Fatalf("err: %s", err)
|
|
}
|
|
|
|
// Write the content to the file using the old md5 based path
|
|
file := filepath.Join(a.Config.DataDir, servicesDir, stringHashMD5(svc.ID))
|
|
if err := os.MkdirAll(filepath.Dir(file), 0700); err != nil {
|
|
t.Fatalf("err: %s", err)
|
|
}
|
|
if err := ioutil.WriteFile(file, encoded, 0600); err != nil {
|
|
t.Fatalf("err: %s", err)
|
|
}
|
|
|
|
wrapped := persistedServiceConfig{
|
|
ServiceID: "redis",
|
|
Defaults: &structs.ServiceConfigResponse{},
|
|
EnterpriseMeta: *structs.DefaultEnterpriseMetaInDefaultPartition(),
|
|
}
|
|
|
|
encodedConfig, err := json.Marshal(wrapped)
|
|
if err != nil {
|
|
t.Fatalf("err: %s", err)
|
|
}
|
|
|
|
configFile := filepath.Join(a.Config.DataDir, serviceConfigDir, stringHashMD5(svc.ID))
|
|
if err := os.MkdirAll(filepath.Dir(configFile), 0700); err != nil {
|
|
t.Fatalf("err: %s", err)
|
|
}
|
|
if err := ioutil.WriteFile(configFile, encodedConfig, 0600); err != nil {
|
|
t.Fatalf("err: %s", err)
|
|
}
|
|
|
|
// Load the services
|
|
if err := a.loadServices(a.Config, nil); err != nil {
|
|
t.Fatalf("err: %s", err)
|
|
}
|
|
|
|
// Ensure the service was restored
|
|
result := requireServiceExists(t, a, "redis")
|
|
require.Equal(t, svc, result)
|
|
}
|
|
|
|
// Exists for backwards compatibility testing
|
|
func stringHashMD5(s string) string {
|
|
return fmt.Sprintf("%x", md5.Sum([]byte(s)))
|
|
}
|
|
|
|
func TestAgent_PurgeService(t *testing.T) {
|
|
if testing.Short() {
|
|
t.Skip("too slow for testing.Short")
|
|
}
|
|
|
|
t.Run("normal", func(t *testing.T) {
|
|
t.Parallel()
|
|
testAgent_PurgeService(t, "enable_central_service_config = false")
|
|
})
|
|
t.Run("service manager", func(t *testing.T) {
|
|
t.Parallel()
|
|
testAgent_PurgeService(t, "enable_central_service_config = true")
|
|
})
|
|
}
|
|
|
|
func testAgent_PurgeService(t *testing.T, extraHCL string) {
|
|
t.Helper()
|
|
|
|
a := NewTestAgent(t, extraHCL)
|
|
defer a.Shutdown()
|
|
|
|
svc := &structs.NodeService{
|
|
ID: "redis",
|
|
Service: "redis",
|
|
Tags: []string{"foo"},
|
|
Port: 8000,
|
|
}
|
|
|
|
file := filepath.Join(a.Config.DataDir, servicesDir, structs.NewServiceID(svc.ID, nil).StringHashSHA256())
|
|
if err := a.addServiceFromSource(svc, nil, true, "", ConfigSourceLocal); err != nil {
|
|
t.Fatalf("err: %v", err)
|
|
}
|
|
// Exists
|
|
if _, err := os.Stat(file); err != nil {
|
|
t.Fatalf("err: %s", err)
|
|
}
|
|
|
|
// Not removed
|
|
if err := a.removeService(structs.NewServiceID(svc.ID, nil), false); err != nil {
|
|
t.Fatalf("err: %s", err)
|
|
}
|
|
if _, err := os.Stat(file); err != nil {
|
|
t.Fatalf("err: %s", err)
|
|
}
|
|
|
|
// Re-add the service
|
|
if err := a.addServiceFromSource(svc, nil, true, "", ConfigSourceLocal); err != nil {
|
|
t.Fatalf("err: %v", err)
|
|
}
|
|
|
|
// Removed
|
|
if err := a.removeService(structs.NewServiceID(svc.ID, nil), true); err != nil {
|
|
t.Fatalf("err: %s", err)
|
|
}
|
|
if _, err := os.Stat(file); !os.IsNotExist(err) {
|
|
t.Fatalf("bad: %#v", err)
|
|
}
|
|
}
|
|
|
|
func TestAgent_PurgeServiceOnDuplicate(t *testing.T) {
|
|
if testing.Short() {
|
|
t.Skip("too slow for testing.Short")
|
|
}
|
|
|
|
t.Run("normal", func(t *testing.T) {
|
|
t.Parallel()
|
|
testAgent_PurgeServiceOnDuplicate(t, "enable_central_service_config = false")
|
|
})
|
|
t.Run("service manager", func(t *testing.T) {
|
|
t.Parallel()
|
|
testAgent_PurgeServiceOnDuplicate(t, "enable_central_service_config = true")
|
|
})
|
|
}
|
|
|
|
func testAgent_PurgeServiceOnDuplicate(t *testing.T, extraHCL string) {
|
|
t.Helper()
|
|
|
|
cfg := `
|
|
server = false
|
|
bootstrap = false
|
|
` + extraHCL
|
|
a := StartTestAgent(t, TestAgent{HCL: cfg})
|
|
defer a.Shutdown()
|
|
|
|
svc1 := &structs.NodeService{
|
|
ID: "redis",
|
|
Service: "redis",
|
|
Tags: []string{"foo"},
|
|
Port: 8000,
|
|
}
|
|
|
|
// First persist the service
|
|
require.NoError(t, a.addServiceFromSource(svc1, nil, true, "", ConfigSourceLocal))
|
|
a.Shutdown()
|
|
|
|
// Try bringing the agent back up with the service already
|
|
// existing in the config
|
|
a2 := StartTestAgent(t, TestAgent{Name: "Agent2", HCL: cfg + `
|
|
service = {
|
|
id = "redis"
|
|
name = "redis"
|
|
tags = ["bar"]
|
|
port = 9000
|
|
}
|
|
`, DataDir: a.DataDir})
|
|
defer a2.Shutdown()
|
|
|
|
sid := svc1.CompoundServiceID()
|
|
file := filepath.Join(a.Config.DataDir, servicesDir, sid.StringHashSHA256())
|
|
_, err := os.Stat(file)
|
|
require.Error(t, err, "should have removed persisted service")
|
|
result := requireServiceExists(t, a, "redis")
|
|
require.NotEqual(t, []string{"bar"}, result.Tags)
|
|
require.NotEqual(t, 9000, result.Port)
|
|
}
|
|
|
|
func TestAgent_PersistCheck(t *testing.T) {
|
|
if testing.Short() {
|
|
t.Skip("too slow for testing.Short")
|
|
}
|
|
|
|
t.Parallel()
|
|
cfg := `
|
|
server = false
|
|
bootstrap = false
|
|
enable_script_checks = true
|
|
`
|
|
a := StartTestAgent(t, TestAgent{HCL: cfg})
|
|
defer a.Shutdown()
|
|
|
|
check := &structs.HealthCheck{
|
|
Node: a.config.NodeName,
|
|
CheckID: "mem",
|
|
Name: "memory check",
|
|
Status: api.HealthPassing,
|
|
}
|
|
chkType := &structs.CheckType{
|
|
ScriptArgs: []string{"/bin/true"},
|
|
Interval: 10 * time.Second,
|
|
}
|
|
|
|
cid := check.CompoundCheckID()
|
|
file := filepath.Join(a.Config.DataDir, checksDir, cid.StringHashSHA256())
|
|
|
|
// Not persisted if not requested
|
|
require.NoError(t, a.AddCheck(check, chkType, false, "", ConfigSourceLocal))
|
|
_, err := os.Stat(file)
|
|
require.Error(t, err, "should not persist")
|
|
|
|
// Should persist if requested
|
|
require.NoError(t, a.AddCheck(check, chkType, true, "mytoken", ConfigSourceLocal))
|
|
_, err = os.Stat(file)
|
|
require.NoError(t, err)
|
|
|
|
expected, err := json.Marshal(persistedCheck{
|
|
Check: check,
|
|
ChkType: chkType,
|
|
Token: "mytoken",
|
|
Source: "local",
|
|
})
|
|
require.NoError(t, err)
|
|
|
|
content, err := ioutil.ReadFile(file)
|
|
require.NoError(t, err)
|
|
|
|
require.Equal(t, expected, content)
|
|
|
|
// Updates the check definition on disk
|
|
check.Name = "mem1"
|
|
require.NoError(t, a.AddCheck(check, chkType, true, "mytoken", ConfigSourceLocal))
|
|
expected, err = json.Marshal(persistedCheck{
|
|
Check: check,
|
|
ChkType: chkType,
|
|
Token: "mytoken",
|
|
Source: "local",
|
|
})
|
|
require.NoError(t, err)
|
|
content, err = ioutil.ReadFile(file)
|
|
require.NoError(t, err)
|
|
require.Equal(t, expected, content)
|
|
a.Shutdown()
|
|
|
|
// Should load it back during later start
|
|
a2 := StartTestAgent(t, TestAgent{Name: "Agent2", HCL: cfg, DataDir: a.DataDir})
|
|
defer a2.Shutdown()
|
|
|
|
result := requireCheckExists(t, a2, check.CheckID)
|
|
require.Equal(t, api.HealthCritical, result.Status)
|
|
require.Equal(t, "mem1", result.Name)
|
|
|
|
// Should have restored the monitor
|
|
requireCheckExistsMap(t, a2.checkMonitors, check.CheckID)
|
|
chkState := a2.State.CheckState(structs.NewCheckID(check.CheckID, nil))
|
|
require.NotNil(t, chkState)
|
|
require.Equal(t, "mytoken", chkState.Token)
|
|
}
|
|
|
|
func TestAgent_PurgeCheck(t *testing.T) {
|
|
if testing.Short() {
|
|
t.Skip("too slow for testing.Short")
|
|
}
|
|
|
|
t.Parallel()
|
|
a := NewTestAgent(t, "")
|
|
defer a.Shutdown()
|
|
|
|
check := &structs.HealthCheck{
|
|
Node: a.Config.NodeName,
|
|
CheckID: "mem",
|
|
Name: "memory check",
|
|
Status: api.HealthPassing,
|
|
}
|
|
|
|
file := filepath.Join(a.Config.DataDir, checksDir, checkIDHash(check.CheckID))
|
|
if err := a.AddCheck(check, nil, true, "", ConfigSourceLocal); err != nil {
|
|
t.Fatalf("err: %v", err)
|
|
}
|
|
|
|
// Not removed
|
|
if err := a.RemoveCheck(structs.NewCheckID(check.CheckID, nil), false); err != nil {
|
|
t.Fatalf("err: %s", err)
|
|
}
|
|
if _, err := os.Stat(file); err != nil {
|
|
t.Fatalf("err: %s", err)
|
|
}
|
|
|
|
// Removed
|
|
if err := a.RemoveCheck(structs.NewCheckID(check.CheckID, nil), true); err != nil {
|
|
t.Fatalf("err: %s", err)
|
|
}
|
|
if _, err := os.Stat(file); !os.IsNotExist(err) {
|
|
t.Fatalf("bad: %#v", err)
|
|
}
|
|
}
|
|
|
|
func TestAgent_PurgeCheckOnDuplicate(t *testing.T) {
|
|
if testing.Short() {
|
|
t.Skip("too slow for testing.Short")
|
|
}
|
|
|
|
t.Parallel()
|
|
nodeID := NodeID()
|
|
a := StartTestAgent(t, TestAgent{
|
|
HCL: `
|
|
node_id = "` + nodeID + `"
|
|
node_name = "Node ` + nodeID + `"
|
|
server = false
|
|
bootstrap = false
|
|
enable_script_checks = true
|
|
`})
|
|
defer a.Shutdown()
|
|
|
|
check1 := &structs.HealthCheck{
|
|
Node: a.Config.NodeName,
|
|
CheckID: "mem",
|
|
Name: "memory check",
|
|
Status: api.HealthPassing,
|
|
EnterpriseMeta: *structs.DefaultEnterpriseMetaInDefaultPartition(),
|
|
}
|
|
|
|
// First persist the check
|
|
if err := a.AddCheck(check1, nil, true, "", ConfigSourceLocal); err != nil {
|
|
t.Fatalf("err: %v", err)
|
|
}
|
|
a.Shutdown()
|
|
|
|
// Start again with the check registered in config
|
|
a2 := StartTestAgent(t, TestAgent{
|
|
Name: "Agent2",
|
|
DataDir: a.DataDir,
|
|
HCL: `
|
|
node_id = "` + nodeID + `"
|
|
node_name = "Node ` + nodeID + `"
|
|
server = false
|
|
bootstrap = false
|
|
enable_script_checks = true
|
|
check = {
|
|
id = "mem"
|
|
name = "memory check"
|
|
notes = "my cool notes"
|
|
args = ["/bin/check-redis.py"]
|
|
interval = "30s"
|
|
timeout = "5s"
|
|
}
|
|
`})
|
|
defer a2.Shutdown()
|
|
|
|
cid := check1.CompoundCheckID()
|
|
file := filepath.Join(a.DataDir, checksDir, cid.StringHashSHA256())
|
|
if _, err := os.Stat(file); err == nil {
|
|
t.Fatalf("should have removed persisted check")
|
|
}
|
|
result := requireCheckExists(t, a2, "mem")
|
|
expected := &structs.HealthCheck{
|
|
Node: a2.Config.NodeName,
|
|
CheckID: "mem",
|
|
Name: "memory check",
|
|
Status: api.HealthCritical,
|
|
Notes: "my cool notes",
|
|
Interval: "30s",
|
|
Timeout: "5s",
|
|
EnterpriseMeta: *structs.DefaultEnterpriseMetaInDefaultPartition(),
|
|
}
|
|
require.Equal(t, expected, result)
|
|
}
|
|
|
|
func TestAgent_DeregisterPersistedSidecarAfterRestart(t *testing.T) {
|
|
if testing.Short() {
|
|
t.Skip("too slow for testing.Short")
|
|
}
|
|
|
|
t.Parallel()
|
|
nodeID := NodeID()
|
|
a := StartTestAgent(t, TestAgent{
|
|
HCL: `
|
|
node_id = "` + nodeID + `"
|
|
node_name = "Node ` + nodeID + `"
|
|
server = false
|
|
bootstrap = false
|
|
enable_central_service_config = false
|
|
`})
|
|
defer a.Shutdown()
|
|
|
|
srv := &structs.NodeService{
|
|
ID: "svc",
|
|
Service: "svc",
|
|
Weights: &structs.Weights{
|
|
Passing: 2,
|
|
Warning: 1,
|
|
},
|
|
Tags: []string{"tag2"},
|
|
Port: 8200,
|
|
EnterpriseMeta: *structs.DefaultEnterpriseMetaInDefaultPartition(),
|
|
|
|
Connect: structs.ServiceConnect{
|
|
SidecarService: &structs.ServiceDefinition{},
|
|
},
|
|
}
|
|
|
|
connectSrv, _, _, err := sidecarServiceFromNodeService(srv, "")
|
|
require.NoError(t, err)
|
|
|
|
// First persist the check
|
|
err = a.addServiceFromSource(srv, nil, true, "", ConfigSourceLocal)
|
|
require.NoError(t, err)
|
|
err = a.addServiceFromSource(connectSrv, nil, true, "", ConfigSourceLocal)
|
|
require.NoError(t, err)
|
|
|
|
// check both services were registered
|
|
require.NotNil(t, a.State.Service(srv.CompoundServiceID()))
|
|
require.NotNil(t, a.State.Service(connectSrv.CompoundServiceID()))
|
|
|
|
a.Shutdown()
|
|
|
|
// Start again with the check registered in config
|
|
a2 := StartTestAgent(t, TestAgent{
|
|
Name: "Agent2",
|
|
DataDir: a.DataDir,
|
|
HCL: `
|
|
node_id = "` + nodeID + `"
|
|
node_name = "Node ` + nodeID + `"
|
|
server = false
|
|
bootstrap = false
|
|
enable_central_service_config = false
|
|
`})
|
|
defer a2.Shutdown()
|
|
|
|
// check both services were restored
|
|
require.NotNil(t, a2.State.Service(srv.CompoundServiceID()))
|
|
require.NotNil(t, a2.State.Service(connectSrv.CompoundServiceID()))
|
|
|
|
err = a2.RemoveService(srv.CompoundServiceID())
|
|
require.NoError(t, err)
|
|
|
|
// check both services were deregistered
|
|
require.Nil(t, a2.State.Service(srv.CompoundServiceID()))
|
|
require.Nil(t, a2.State.Service(connectSrv.CompoundServiceID()))
|
|
}
|
|
|
|
func TestAgent_loadChecks_token(t *testing.T) {
|
|
if testing.Short() {
|
|
t.Skip("too slow for testing.Short")
|
|
}
|
|
|
|
t.Parallel()
|
|
a := NewTestAgent(t, `
|
|
check = {
|
|
id = "rabbitmq"
|
|
name = "rabbitmq"
|
|
token = "abc123"
|
|
ttl = "10s"
|
|
}
|
|
`)
|
|
defer a.Shutdown()
|
|
|
|
requireCheckExists(t, a, "rabbitmq")
|
|
require.Equal(t, "abc123", a.State.CheckToken(structs.NewCheckID("rabbitmq", nil)))
|
|
}
|
|
|
|
func TestAgent_unloadChecks(t *testing.T) {
|
|
if testing.Short() {
|
|
t.Skip("too slow for testing.Short")
|
|
}
|
|
|
|
t.Parallel()
|
|
a := NewTestAgent(t, "")
|
|
defer a.Shutdown()
|
|
|
|
// First register a service
|
|
svc := &structs.NodeService{
|
|
ID: "redis",
|
|
Service: "redis",
|
|
Tags: []string{"foo"},
|
|
Port: 8000,
|
|
}
|
|
if err := a.addServiceFromSource(svc, nil, false, "", ConfigSourceLocal); err != nil {
|
|
t.Fatalf("err: %v", err)
|
|
}
|
|
|
|
// Register a check
|
|
check1 := &structs.HealthCheck{
|
|
Node: a.Config.NodeName,
|
|
CheckID: "service:redis",
|
|
Name: "redischeck",
|
|
Status: api.HealthPassing,
|
|
ServiceID: "redis",
|
|
ServiceName: "redis",
|
|
}
|
|
if err := a.AddCheck(check1, nil, false, "", ConfigSourceLocal); err != nil {
|
|
t.Fatalf("err: %s", err)
|
|
}
|
|
|
|
requireCheckExists(t, a, check1.CheckID)
|
|
|
|
// Unload all of the checks
|
|
if err := a.unloadChecks(); err != nil {
|
|
t.Fatalf("err: %s", err)
|
|
}
|
|
|
|
// Make sure it was unloaded
|
|
requireCheckMissing(t, a, check1.CheckID)
|
|
}
|
|
|
|
func TestAgent_loadServices_token(t *testing.T) {
|
|
if testing.Short() {
|
|
t.Skip("too slow for testing.Short")
|
|
}
|
|
|
|
t.Run("normal", func(t *testing.T) {
|
|
t.Parallel()
|
|
testAgent_loadServices_token(t, "enable_central_service_config = false")
|
|
})
|
|
t.Run("service manager", func(t *testing.T) {
|
|
t.Parallel()
|
|
testAgent_loadServices_token(t, "enable_central_service_config = true")
|
|
})
|
|
}
|
|
|
|
func testAgent_loadServices_token(t *testing.T, extraHCL string) {
|
|
t.Helper()
|
|
|
|
a := NewTestAgent(t, `
|
|
service = {
|
|
id = "rabbitmq"
|
|
name = "rabbitmq"
|
|
port = 5672
|
|
token = "abc123"
|
|
}
|
|
`+extraHCL)
|
|
defer a.Shutdown()
|
|
|
|
requireServiceExists(t, a, "rabbitmq")
|
|
if token := a.State.ServiceToken(structs.NewServiceID("rabbitmq", nil)); token != "abc123" {
|
|
t.Fatalf("bad: %s", token)
|
|
}
|
|
}
|
|
|
|
func TestAgent_loadServices_sidecar(t *testing.T) {
|
|
if testing.Short() {
|
|
t.Skip("too slow for testing.Short")
|
|
}
|
|
|
|
t.Run("normal", func(t *testing.T) {
|
|
t.Parallel()
|
|
testAgent_loadServices_sidecar(t, "enable_central_service_config = false")
|
|
})
|
|
t.Run("service manager", func(t *testing.T) {
|
|
t.Parallel()
|
|
testAgent_loadServices_sidecar(t, "enable_central_service_config = true")
|
|
})
|
|
}
|
|
|
|
func testAgent_loadServices_sidecar(t *testing.T, extraHCL string) {
|
|
t.Helper()
|
|
|
|
a := NewTestAgent(t, `
|
|
service = {
|
|
id = "rabbitmq"
|
|
name = "rabbitmq"
|
|
port = 5672
|
|
token = "abc123"
|
|
connect = {
|
|
sidecar_service {}
|
|
}
|
|
}
|
|
`+extraHCL)
|
|
defer a.Shutdown()
|
|
|
|
svc := requireServiceExists(t, a, "rabbitmq")
|
|
if token := a.State.ServiceToken(structs.NewServiceID("rabbitmq", nil)); token != "abc123" {
|
|
t.Fatalf("bad: %s", token)
|
|
}
|
|
sidecarSvc := requireServiceExists(t, a, "rabbitmq-sidecar-proxy")
|
|
if token := a.State.ServiceToken(structs.NewServiceID("rabbitmq-sidecar-proxy", nil)); token != "abc123" {
|
|
t.Fatalf("bad: %s", token)
|
|
}
|
|
|
|
// Verify default checks have been added
|
|
wantChecks := sidecarDefaultChecks(sidecarSvc.ID, sidecarSvc.Address, sidecarSvc.Proxy.LocalServiceAddress, sidecarSvc.Port)
|
|
gotChecks := a.State.ChecksForService(sidecarSvc.CompoundServiceID(), true)
|
|
gotChkNames := make(map[string]types.CheckID)
|
|
for _, check := range gotChecks {
|
|
requireCheckExists(t, a, check.CheckID)
|
|
gotChkNames[check.Name] = check.CheckID
|
|
}
|
|
for _, check := range wantChecks {
|
|
chkName := check.Name
|
|
require.NotNil(t, gotChkNames[chkName])
|
|
}
|
|
|
|
// Sanity check rabbitmq service should NOT have sidecar info in state since
|
|
// it's done it's job and should be a registration syntax sugar only.
|
|
assert.Nil(t, svc.Connect.SidecarService)
|
|
}
|
|
|
|
func TestAgent_loadServices_sidecarSeparateToken(t *testing.T) {
|
|
if testing.Short() {
|
|
t.Skip("too slow for testing.Short")
|
|
}
|
|
|
|
t.Run("normal", func(t *testing.T) {
|
|
t.Parallel()
|
|
testAgent_loadServices_sidecarSeparateToken(t, "enable_central_service_config = false")
|
|
})
|
|
t.Run("service manager", func(t *testing.T) {
|
|
t.Parallel()
|
|
testAgent_loadServices_sidecarSeparateToken(t, "enable_central_service_config = true")
|
|
})
|
|
}
|
|
|
|
func testAgent_loadServices_sidecarSeparateToken(t *testing.T, extraHCL string) {
|
|
t.Helper()
|
|
|
|
a := NewTestAgent(t, `
|
|
service = {
|
|
id = "rabbitmq"
|
|
name = "rabbitmq"
|
|
port = 5672
|
|
token = "abc123"
|
|
connect = {
|
|
sidecar_service {
|
|
token = "789xyz"
|
|
}
|
|
}
|
|
}
|
|
`+extraHCL)
|
|
defer a.Shutdown()
|
|
|
|
requireServiceExists(t, a, "rabbitmq")
|
|
if token := a.State.ServiceToken(structs.NewServiceID("rabbitmq", nil)); token != "abc123" {
|
|
t.Fatalf("bad: %s", token)
|
|
}
|
|
requireServiceExists(t, a, "rabbitmq-sidecar-proxy")
|
|
if token := a.State.ServiceToken(structs.NewServiceID("rabbitmq-sidecar-proxy", nil)); token != "789xyz" {
|
|
t.Fatalf("bad: %s", token)
|
|
}
|
|
}
|
|
|
|
func TestAgent_loadServices_sidecarInheritMeta(t *testing.T) {
|
|
if testing.Short() {
|
|
t.Skip("too slow for testing.Short")
|
|
}
|
|
|
|
t.Run("normal", func(t *testing.T) {
|
|
t.Parallel()
|
|
testAgent_loadServices_sidecarInheritMeta(t, "enable_central_service_config = false")
|
|
})
|
|
t.Run("service manager", func(t *testing.T) {
|
|
t.Parallel()
|
|
testAgent_loadServices_sidecarInheritMeta(t, "enable_central_service_config = true")
|
|
})
|
|
}
|
|
|
|
func testAgent_loadServices_sidecarInheritMeta(t *testing.T, extraHCL string) {
|
|
t.Helper()
|
|
|
|
a := NewTestAgent(t, `
|
|
service = {
|
|
id = "rabbitmq"
|
|
name = "rabbitmq"
|
|
port = 5672
|
|
tags = ["a", "b"],
|
|
meta = {
|
|
environment = "prod"
|
|
}
|
|
connect = {
|
|
sidecar_service {
|
|
|
|
}
|
|
}
|
|
}
|
|
`+extraHCL)
|
|
defer a.Shutdown()
|
|
|
|
svc := requireServiceExists(t, a, "rabbitmq")
|
|
require.Len(t, svc.Tags, 2)
|
|
require.Len(t, svc.Meta, 1)
|
|
|
|
sidecar := requireServiceExists(t, a, "rabbitmq-sidecar-proxy")
|
|
require.ElementsMatch(t, svc.Tags, sidecar.Tags)
|
|
require.Len(t, sidecar.Meta, 1)
|
|
meta, ok := sidecar.Meta["environment"]
|
|
require.True(t, ok, "missing sidecar service meta")
|
|
require.Equal(t, "prod", meta)
|
|
}
|
|
|
|
func TestAgent_loadServices_sidecarOverrideMeta(t *testing.T) {
|
|
if testing.Short() {
|
|
t.Skip("too slow for testing.Short")
|
|
}
|
|
|
|
t.Run("normal", func(t *testing.T) {
|
|
t.Parallel()
|
|
testAgent_loadServices_sidecarOverrideMeta(t, "enable_central_service_config = false")
|
|
})
|
|
t.Run("service manager", func(t *testing.T) {
|
|
t.Parallel()
|
|
testAgent_loadServices_sidecarOverrideMeta(t, "enable_central_service_config = true")
|
|
})
|
|
}
|
|
|
|
func testAgent_loadServices_sidecarOverrideMeta(t *testing.T, extraHCL string) {
|
|
t.Helper()
|
|
|
|
a := NewTestAgent(t, `
|
|
service = {
|
|
id = "rabbitmq"
|
|
name = "rabbitmq"
|
|
port = 5672
|
|
tags = ["a", "b"],
|
|
meta = {
|
|
environment = "prod"
|
|
}
|
|
connect = {
|
|
sidecar_service {
|
|
tags = ["foo"],
|
|
meta = {
|
|
environment = "qa"
|
|
}
|
|
}
|
|
}
|
|
}
|
|
`+extraHCL)
|
|
defer a.Shutdown()
|
|
|
|
svc := requireServiceExists(t, a, "rabbitmq")
|
|
require.Len(t, svc.Tags, 2)
|
|
require.Len(t, svc.Meta, 1)
|
|
|
|
sidecar := requireServiceExists(t, a, "rabbitmq-sidecar-proxy")
|
|
require.Len(t, sidecar.Tags, 1)
|
|
require.Equal(t, "foo", sidecar.Tags[0])
|
|
require.Len(t, sidecar.Meta, 1)
|
|
meta, ok := sidecar.Meta["environment"]
|
|
require.True(t, ok, "missing sidecar service meta")
|
|
require.Equal(t, "qa", meta)
|
|
}
|
|
|
|
func TestAgent_unloadServices(t *testing.T) {
|
|
if testing.Short() {
|
|
t.Skip("too slow for testing.Short")
|
|
}
|
|
|
|
t.Run("normal", func(t *testing.T) {
|
|
t.Parallel()
|
|
testAgent_unloadServices(t, "enable_central_service_config = false")
|
|
})
|
|
t.Run("service manager", func(t *testing.T) {
|
|
t.Parallel()
|
|
testAgent_unloadServices(t, "enable_central_service_config = true")
|
|
})
|
|
}
|
|
|
|
func testAgent_unloadServices(t *testing.T, extraHCL string) {
|
|
t.Helper()
|
|
|
|
a := NewTestAgent(t, extraHCL)
|
|
defer a.Shutdown()
|
|
|
|
svc := &structs.NodeService{
|
|
ID: "redis",
|
|
Service: "redis",
|
|
Tags: []string{"foo"},
|
|
Port: 8000,
|
|
}
|
|
|
|
// Register the service
|
|
if err := a.addServiceFromSource(svc, nil, false, "", ConfigSourceLocal); err != nil {
|
|
t.Fatalf("err: %v", err)
|
|
}
|
|
|
|
requireServiceExists(t, a, svc.ID)
|
|
|
|
// Unload all services
|
|
if err := a.unloadServices(); err != nil {
|
|
t.Fatalf("err: %s", err)
|
|
}
|
|
if len(a.State.Services(structs.WildcardEnterpriseMetaInDefaultPartition())) != 0 {
|
|
t.Fatalf("should have unloaded services")
|
|
}
|
|
}
|
|
|
|
func TestAgent_Service_MaintenanceMode(t *testing.T) {
|
|
if testing.Short() {
|
|
t.Skip("too slow for testing.Short")
|
|
}
|
|
|
|
t.Parallel()
|
|
a := NewTestAgent(t, "")
|
|
defer a.Shutdown()
|
|
|
|
svc := &structs.NodeService{
|
|
ID: "redis",
|
|
Service: "redis",
|
|
Tags: []string{"foo"},
|
|
Port: 8000,
|
|
}
|
|
|
|
// Register the service
|
|
if err := a.addServiceFromSource(svc, nil, false, "", ConfigSourceLocal); err != nil {
|
|
t.Fatalf("err: %v", err)
|
|
}
|
|
|
|
sid := structs.NewServiceID("redis", nil)
|
|
// Enter maintenance mode for the service
|
|
if err := a.EnableServiceMaintenance(sid, "broken", "mytoken"); err != nil {
|
|
t.Fatalf("err: %s", err)
|
|
}
|
|
|
|
// Make sure the critical health check was added
|
|
checkID := serviceMaintCheckID(sid)
|
|
check := a.State.Check(checkID)
|
|
if check == nil {
|
|
t.Fatalf("should have registered critical maintenance check")
|
|
}
|
|
|
|
// Check that the token was used to register the check
|
|
if token := a.State.CheckToken(checkID); token != "mytoken" {
|
|
t.Fatalf("expected 'mytoken', got: '%s'", token)
|
|
}
|
|
|
|
// Ensure the reason was set in notes
|
|
if check.Notes != "broken" {
|
|
t.Fatalf("bad: %#v", check)
|
|
}
|
|
|
|
// Leave maintenance mode
|
|
if err := a.DisableServiceMaintenance(sid); err != nil {
|
|
t.Fatalf("err: %s", err)
|
|
}
|
|
|
|
// Ensure the check was deregistered
|
|
|
|
if found := a.State.Check(checkID); found != nil {
|
|
t.Fatalf("should have deregistered maintenance check")
|
|
}
|
|
|
|
// Enter service maintenance mode without providing a reason
|
|
if err := a.EnableServiceMaintenance(sid, "", ""); err != nil {
|
|
t.Fatalf("err: %s", err)
|
|
}
|
|
|
|
// Ensure the check was registered with the default notes
|
|
check = a.State.Check(checkID)
|
|
if check == nil {
|
|
t.Fatalf("should have registered critical check")
|
|
}
|
|
if check.Notes != defaultServiceMaintReason {
|
|
t.Fatalf("bad: %#v", check)
|
|
}
|
|
}
|
|
|
|
func TestAgent_Service_Reap(t *testing.T) {
|
|
if testing.Short() {
|
|
t.Skip("too slow for testing.Short")
|
|
}
|
|
|
|
// t.Parallel() // timing test. no parallel
|
|
a := StartTestAgent(t, TestAgent{Overrides: `
|
|
check_reap_interval = "50ms"
|
|
check_deregister_interval_min = "0s"
|
|
`})
|
|
defer a.Shutdown()
|
|
testrpc.WaitForTestAgent(t, a.RPC, "dc1")
|
|
|
|
svc := &structs.NodeService{
|
|
ID: "redis",
|
|
Service: "redis",
|
|
Tags: []string{"foo"},
|
|
Port: 8000,
|
|
}
|
|
chkTypes := []*structs.CheckType{
|
|
{
|
|
Status: api.HealthPassing,
|
|
TTL: 25 * time.Millisecond,
|
|
DeregisterCriticalServiceAfter: 200 * time.Millisecond,
|
|
},
|
|
}
|
|
|
|
// Register the service.
|
|
if err := a.addServiceFromSource(svc, chkTypes, false, "", ConfigSourceLocal); err != nil {
|
|
t.Fatalf("err: %v", err)
|
|
}
|
|
|
|
// Make sure it's there and there's no critical check yet.
|
|
requireServiceExists(t, a, "redis")
|
|
require.Len(t, a.State.CriticalCheckStates(structs.WildcardEnterpriseMetaInDefaultPartition()), 0, "should not have critical checks")
|
|
|
|
// Wait for the check TTL to fail but before the check is reaped.
|
|
time.Sleep(100 * time.Millisecond)
|
|
requireServiceExists(t, a, "redis")
|
|
require.Len(t, a.State.CriticalCheckStates(nil), 1, "should have 1 critical check")
|
|
|
|
// Pass the TTL.
|
|
if err := a.updateTTLCheck(structs.NewCheckID("service:redis", nil), api.HealthPassing, "foo"); err != nil {
|
|
t.Fatalf("err: %v", err)
|
|
}
|
|
requireServiceExists(t, a, "redis")
|
|
require.Len(t, a.State.CriticalCheckStates(structs.WildcardEnterpriseMetaInDefaultPartition()), 0, "should not have critical checks")
|
|
|
|
// Wait for the check TTL to fail again.
|
|
time.Sleep(100 * time.Millisecond)
|
|
requireServiceExists(t, a, "redis")
|
|
require.Len(t, a.State.CriticalCheckStates(structs.WildcardEnterpriseMetaInDefaultPartition()), 1, "should have 1 critical check")
|
|
|
|
// Wait for the reap.
|
|
time.Sleep(400 * time.Millisecond)
|
|
requireServiceMissing(t, a, "redis")
|
|
require.Len(t, a.State.CriticalCheckStates(structs.WildcardEnterpriseMetaInDefaultPartition()), 0, "should not have critical checks")
|
|
}
|
|
|
|
func TestAgent_Service_NoReap(t *testing.T) {
|
|
if testing.Short() {
|
|
t.Skip("too slow for testing.Short")
|
|
}
|
|
|
|
// t.Parallel() // timing test. no parallel
|
|
a := StartTestAgent(t, TestAgent{Overrides: `
|
|
check_reap_interval = "50ms"
|
|
check_deregister_interval_min = "0s"
|
|
`})
|
|
defer a.Shutdown()
|
|
|
|
svc := &structs.NodeService{
|
|
ID: "redis",
|
|
Service: "redis",
|
|
Tags: []string{"foo"},
|
|
Port: 8000,
|
|
}
|
|
chkTypes := []*structs.CheckType{
|
|
{
|
|
Status: api.HealthPassing,
|
|
TTL: 25 * time.Millisecond,
|
|
},
|
|
}
|
|
|
|
// Register the service.
|
|
if err := a.addServiceFromSource(svc, chkTypes, false, "", ConfigSourceLocal); err != nil {
|
|
t.Fatalf("err: %v", err)
|
|
}
|
|
|
|
// Make sure it's there and there's no critical check yet.
|
|
requireServiceExists(t, a, "redis")
|
|
require.Len(t, a.State.CriticalCheckStates(structs.WildcardEnterpriseMetaInDefaultPartition()), 0)
|
|
|
|
// Wait for the check TTL to fail.
|
|
time.Sleep(200 * time.Millisecond)
|
|
requireServiceExists(t, a, "redis")
|
|
require.Len(t, a.State.CriticalCheckStates(structs.WildcardEnterpriseMetaInDefaultPartition()), 1)
|
|
|
|
// Wait a while and make sure it doesn't reap.
|
|
time.Sleep(200 * time.Millisecond)
|
|
requireServiceExists(t, a, "redis")
|
|
require.Len(t, a.State.CriticalCheckStates(structs.WildcardEnterpriseMetaInDefaultPartition()), 1)
|
|
}
|
|