Test Shamir-to-Transit and Transit-to-Shamir Seal Migration for post-…

…1.4 Vault. (#9214) * move adjustForSealMigration to vault package * fix adjustForSealMigration * begin working on new seal migration test * create shamir seal migration test * refactor testhelpers * add VerifyRaftConfiguration to testhelpers * stub out TestTransit * Revert "refactor testhelpers" This reverts commit 39593defd0d4c6fd79aedfd37df6298391abb9db. * get shamir test working again * stub out transit join * work on transit join * remove debug code * initTransit now works with raft join * runTransit works with inmem * work on runTransit with raft * runTransit works with raft * cleanup tests * TestSealMigration_TransitToShamir_Pre14 * TestSealMigration_ShamirToTransit_Pre14 * split for pre-1.4 testing * add simple tests for transit and shamir * fix typo in test suite * debug wrapper type * test debug * test-debug * refactor core migration * Revert "refactor core migration" This reverts commit a776452. * begin refactor of adjustForSealMigration * fix bug in adjustForSealMigration * clean up tests * clean up core refactoring * fix bug in shamir->transit migration * stub out test that brings individual nodes up and down * refactor NewTestCluster * pass listeners into newCore() * simplify cluster address setup * simplify extra test core setup * refactor TestCluster for readability * refactor TestCluster for readability * refactor TestCluster for readability * add shutdown func to TestCore * add cleanup func to TestCore * create RestartCore * stub out TestSealMigration_ShamirToTransit_Post14 * refactor address handling in NewTestCluster * fix listener setup in newCore() * remove unnecessary lock from setSealsForMigration() * rename sealmigration test package * use ephemeral ports below 30000 * work on post-1.4 migration testing * clean up pre-1.4 test * TestSealMigration_ShamirToTransit_Post14 works for non-raft * work on raft TestSealMigration_ShamirToTransit_Post14 * clean up test code * refactor TestClusterCore * clean up TestClusterCore * stub out some temporary tests * use HardcodedServerAddressProvider in seal migration tests * work on raft for TestSealMigration_ShamirToTransit_Post14 * always use hardcoded raft address provider in seal migration tests * debug TestSealMigration_ShamirToTransit_Post14 * fix bug in RestartCore * remove debug code * TestSealMigration_ShamirToTransit_Post14 works now * clean up debug code * clean up tests * cleanup tests * refactor test code * stub out TestSealMigration_TransitToShamir_Post14 * set seals properly for transit->shamir migration * migrateFromTransitToShamir_Post14 works for inmem * migrateFromTransitToShamir_Post14 works for raft * use base ports per-test * fix seal verification test code * simplify seal migration test suite * simplify test suite * cleanup test suite * use explicit ports below 30000 * simplify use of numTestCores * Update vault/external_tests/sealmigration/seal_migration_test.go Co-authored-by: Calvin Leung Huang <[email protected]> * Update vault/external_tests/sealmigration/seal_migration_test.go Co-authored-by: Calvin Leung Huang <[email protected]> * clean up imports * rename to StartCore() * Update vault/testing.go Co-authored-by: Calvin Leung Huang <[email protected]> * simplify test suite * clean up tests Co-authored-by: Calvin Leung Huang <[email protected]>
hashicorp · Jul 17, 2020 · 2127461 · 2127461
1 parent c49c6a6
commit 2127461
Show file tree

Hide file tree

Showing 6 changed files with 955 additions and 485 deletions.
diff --git a/helper/testhelpers/testhelpers.go b/helper/testhelpers/testhelpers.go
@@ -412,16 +412,9 @@ func (p *TestRaftServerAddressProvider) ServerAddr(id raftlib.ServerID) (raftlib
 }
 
 func RaftClusterJoinNodes(t testing.T, cluster *vault.TestCluster) {
-	raftClusterJoinNodes(t, cluster, false)
-}
-
-func RaftClusterJoinNodesWithStoredKeys(t testing.T, cluster *vault.TestCluster) {
-	raftClusterJoinNodes(t, cluster, true)
-}
-
-func raftClusterJoinNodes(t testing.T, cluster *vault.TestCluster, useStoredKeys bool) {
 
 	addressProvider := &TestRaftServerAddressProvider{Cluster: cluster}
+
 	atomic.StoreUint32(&vault.UpdateClusterAddrForTests, 1)
 
 	leader := cluster.Cores[0]
@@ -430,11 +423,7 @@ func raftClusterJoinNodes(t testing.T, cluster *vault.TestCluster, useStoredKeys
 	{
 		EnsureCoreSealed(t, leader)
 		leader.UnderlyingRawStorage.(*raft.RaftBackend).SetServerAddressProvider(addressProvider)
-		if useStoredKeys {
-			cluster.UnsealCoreWithStoredKeys(t, leader)
-		} else {
-			cluster.UnsealCore(t, leader)
-		}
+		cluster.UnsealCore(t, leader)
 		vault.TestWaitActive(t, leader.Core)
 	}
 
@@ -454,37 +443,12 @@ func raftClusterJoinNodes(t testing.T, cluster *vault.TestCluster, useStoredKeys
 			t.Fatal(err)
 		}
 
-		if useStoredKeys {
-			// For autounseal, the raft backend is not initialized right away
-			// after the join.  We need to wait briefly before we can unseal.
-			awaitUnsealWithStoredKeys(t, core)
-		} else {
-			cluster.UnsealCore(t, core)
-		}
+		cluster.UnsealCore(t, core)
 	}
 
 	WaitForNCoresUnsealed(t, cluster, len(cluster.Cores))
 }
 
-func awaitUnsealWithStoredKeys(t testing.T, core *vault.TestClusterCore) {
-
-	timeout := time.Now().Add(30 * time.Second)
-	for {
-		if time.Now().After(timeout) {
-			t.Fatal("raft join: timeout waiting for core to unseal")
-		}
-		// Its actually ok for an error to happen here the first couple of
-		// times -- it means the raft join hasn't gotten around to initializing
-		// the backend yet.
-		err := core.UnsealWithStoredKeys(context.Background())
-		if err == nil {
-			return
-		}
-		core.Logger().Warn("raft join: failed to unseal core", "error", err)
-		time.Sleep(time.Second)
-	}
-}
-
 // HardcodedServerAddressProvider is a ServerAddressProvider that uses
 // a hardcoded map of raft node addresses.
 //
@@ -505,11 +469,11 @@ func (p *HardcodedServerAddressProvider) ServerAddr(id raftlib.ServerID) (raftli
 
 // NewHardcodedServerAddressProvider is a convenience function that makes a
 // ServerAddressProvider from a given cluster address base port.
-func NewHardcodedServerAddressProvider(cluster *vault.TestCluster, baseClusterPort int) raftlib.ServerAddressProvider {
+func NewHardcodedServerAddressProvider(numCores, baseClusterPort int) raftlib.ServerAddressProvider {
 
 	entries := make(map[raftlib.ServerID]raftlib.ServerAddress)
 
-	for i := 0; i < len(cluster.Cores); i++ {
+	for i := 0; i < numCores; i++ {
 		id := fmt.Sprintf("core-%d", i)
 		addr := fmt.Sprintf("127.0.0.1:%d", baseClusterPort+i)
 		entries[raftlib.ServerID(id)] = raftlib.ServerAddress(addr)
@@ -520,17 +484,6 @@ func NewHardcodedServerAddressProvider(cluster *vault.TestCluster, baseClusterPo
 	}
 }
 
-// SetRaftAddressProviders sets a ServerAddressProvider for all the nodes in a
-// cluster.
-func SetRaftAddressProviders(t testing.T, cluster *vault.TestCluster, provider raftlib.ServerAddressProvider) {
-
-	atomic.StoreUint32(&vault.UpdateClusterAddrForTests, 1)
-
-	for _, core := range cluster.Cores {
-		core.UnderlyingRawStorage.(*raft.RaftBackend).SetServerAddressProvider(provider)
-	}
-}
-
 // VerifyRaftConfiguration checks that we have a valid raft configuration, i.e.
 // the correct number of servers, having the correct NodeIDs, and exactly one
 // leader.
@@ -565,6 +518,35 @@ func VerifyRaftConfiguration(core *vault.TestClusterCore, numCores int) error {
 	return nil
 }
 
+// AwaitLeader waits for one of the cluster's nodes to become leader.
+func AwaitLeader(t testing.T, cluster *vault.TestCluster) (int, error) {
+
+	timeout := time.Now().Add(30 * time.Second)
+	for {
+		if time.Now().After(timeout) {
+			break
+		}
+
+		for i, core := range cluster.Cores {
+			if core.Core.Sealed() {
+				continue
+			}
+
+			isLeader, _, _, err := core.Leader()
+			if err != nil {
+				t.Fatal(err)
+			}
+			if isLeader {
+				return i, nil
+			}
+		}
+
+		time.Sleep(time.Second)
+	}
+
+	return 0, fmt.Errorf("timeout waiting leader")
+}
+
 func GenerateDebugLogs(t testing.T, client *api.Client) chan struct{} {
 	t.Helper()
 

diff --git a/helper/testhelpers/teststorage/teststorage_reusable.go b/helper/testhelpers/teststorage/teststorage_reusable.go
@@ -8,6 +8,7 @@ import (
 	"github.com/mitchellh/go-testing-interface"
 
 	hclog "github.com/hashicorp/go-hclog"
+	raftlib "github.com/hashicorp/raft"
 	"github.com/hashicorp/vault/physical/raft"
 	"github.com/hashicorp/vault/vault"
 )
@@ -73,7 +74,10 @@ func MakeReusableStorage(t testing.T, logger hclog.Logger, bundle *vault.Physica
 
 // MakeReusableRaftStorage makes a physical raft backend that can be re-used
 // across multiple test clusters in sequence.
-func MakeReusableRaftStorage(t testing.T, logger hclog.Logger, numCores int) (ReusableStorage, StorageCleanup) {
+func MakeReusableRaftStorage(
+	t testing.T, logger hclog.Logger, numCores int,
+	addressProvider raftlib.ServerAddressProvider,
+) (ReusableStorage, StorageCleanup) {
 
 	raftDirs := make([]string, numCores)
 	for i := 0; i < numCores; i++ {
@@ -87,17 +91,14 @@ func MakeReusableRaftStorage(t testing.T, logger hclog.Logger, numCores int) (Re
 			conf.DisablePerformanceStandby = true
 			opts.KeepStandbysSealed = true
 			opts.PhysicalFactory = func(t testing.T, coreIdx int, logger hclog.Logger) *vault.PhysicalBackendBundle {
-				return makeReusableRaftBackend(t, coreIdx, logger, raftDirs[coreIdx])
+				return makeReusableRaftBackend(t, coreIdx, logger, raftDirs[coreIdx], addressProvider)
 			}
 		},
 
 		// Close open files being used by raft.
 		Cleanup: func(t testing.T, cluster *vault.TestCluster) {
-			for _, core := range cluster.Cores {
-				raftStorage := core.UnderlyingRawStorage.(*raft.RaftBackend)
-				if err := raftStorage.Close(); err != nil {
-					t.Fatal(err)
-				}
+			for i := 0; i < len(cluster.Cores); i++ {
+				CloseRaftStorage(t, cluster, i)
 			}
 		},
 	}
@@ -111,6 +112,14 @@ func MakeReusableRaftStorage(t testing.T, logger hclog.Logger, numCores int) (Re
 	return storage, cleanup
 }
 
+// CloseRaftStorage closes open files being used by raft.
+func CloseRaftStorage(t testing.T, cluster *vault.TestCluster, idx int) {
+	raftStorage := cluster.Cores[idx].UnderlyingRawStorage.(*raft.RaftBackend)
+	if err := raftStorage.Close(); err != nil {
+		t.Fatal(err)
+	}
+}
+
 func makeRaftDir(t testing.T) string {
 	raftDir, err := ioutil.TempDir("", "vault-raft-")
 	if err != nil {
@@ -120,7 +129,10 @@ func makeRaftDir(t testing.T) string {
 	return raftDir
 }
 
-func makeReusableRaftBackend(t testing.T, coreIdx int, logger hclog.Logger, raftDir string) *vault.PhysicalBackendBundle {
+func makeReusableRaftBackend(
+	t testing.T, coreIdx int, logger hclog.Logger, raftDir string,
+	addressProvider raftlib.ServerAddressProvider,
+) *vault.PhysicalBackendBundle {
 
 	nodeID := fmt.Sprintf("core-%d", coreIdx)
 	conf := map[string]string{
@@ -134,6 +146,8 @@ func makeReusableRaftBackend(t testing.T, coreIdx int, logger hclog.Logger, raft
 		t.Fatal(err)
 	}
 
+	backend.(*raft.RaftBackend).SetServerAddressProvider(addressProvider)
+
 	return &vault.PhysicalBackendBundle{
 		Backend: backend,
 	}

diff --git a/vault/external_tests/sealmigration/seal_migration_pre14_test.go b/vault/external_tests/sealmigration/seal_migration_pre14_test.go
@@ -25,7 +25,7 @@ import (
 func TestSealMigration_TransitToShamir_Pre14(t *testing.T) {
 	// Note that we do not test integrated raft storage since this is
 	// a pre-1.4 test.
-	testVariousBackends(t, testSealMigrationTransitToShamir_Pre14, false)
+	testVariousBackends(t, testSealMigrationTransitToShamir_Pre14, basePort_TransitToShamir_Pre14, false)
 }
 
 func testSealMigrationTransitToShamir_Pre14(
@@ -42,7 +42,11 @@ func testSealMigrationTransitToShamir_Pre14(
 	tss.MakeKey(t, "transit-seal-key")
 
 	// Initialize the backend with transit.
-	rootToken, recoveryKeys, transitSeal := initializeTransit(t, logger, storage, basePort, tss)
+	cluster, _, transitSeal := initializeTransit(t, logger, storage, basePort, tss)
+	rootToken, recoveryKeys := cluster.RootToken, cluster.RecoveryKeys
+	cluster.EnsureCoresSealed(t)
+	storage.Cleanup(t, cluster)
+	cluster.Cleanup()
 
 	// Migrate the backend from transit to shamir
 	migrateFromTransitToShamir_Pre14(t, logger, storage, basePort, tss, transitSeal, rootToken, recoveryKeys)