Merge branch 'main' into ds-21-summary

.github/workflows/vitess_tester_vtgate.yml

@@ -112,7 +112,7 @@ jobs:
         go install github.com/vitessio/go-junit-report@HEAD
         
         # install vitess tester
-        go install github.com/vitessio/vitess-tester@89dd933a9ea0e15f69ca58b9c8ea09a358762cca
+        go install github.com/vitessio/vitess-tester/go/vt@374fd9f495c1afd3b6bea9d4ec7728119714055
 
     - name: Setup launchable dependencies
       if: steps.skip-workflow.outputs.is_draft == 'false' && steps.skip-workflow.outputs.skip-workflow == 'false' && steps.changes.outputs.end_to_end == 'true' && github.base_ref == 'main'
@@ -144,9 +144,9 @@ jobs:
           # We go over all the directories in the given path.
           # If there is a vschema file there, we use it, otherwise we let vitess-tester autogenerate it.
           if [ -f $dir/vschema.json ]; then
-            vitess-tester --xunit --vschema "$dir"vschema.json $dir/*.test
+            vt tester --xunit --vschema "$dir"vschema.json $dir/*.test
           else 
-            vitess-tester --sharded --xunit $dir/*.test
+            vt tester --sharded --xunit $dir/*.test
           fi
           # Number the reports by changing their file names.
           mv report.xml report"$i".xml

changelog/21.0/21.0.0/summary.md

@@ -18,6 +18,7 @@
     - **[Dynamic VReplication Configuration](#dynamic-vreplication-configuration)**
     - **[Reference Table Materialization](#reference-table-materialization)**
     - **[New VEXPLAIN Modes: TRACE and KEYS](#new-vexplain-modes)**
+    - **[Errant GTID Detection on VTTablets](#errant-gtid-vttablet)**
 
 ## <a id="major-changes"/>Major Changes
 
@@ -161,8 +162,8 @@ so please read the [documentation](https://vitess.io/docs/21.0/user-guides/opera
 
 ### <a id="dynamic-vreplication-configuration"/>Dynamic VReplication Configuration
 
-Previously, many of the configuration options for VReplication Workflows had to be provided using vttablet flags. This 
-meant that any change to VReplication configuration required restarting vttablets. We now allow these to be overridden 
+Previously, many of the configuration options for VReplication Workflows had to be provided using VTTablet flags. This 
+meant that any change to VReplication configuration required restarting VTTablets. We now allow these to be overridden 
 while creating a workflow or dynamically after the workflow is already in progress.
 
 ### <a id="reference-table-materialization"/>Reference Table Materialization
@@ -200,3 +201,11 @@ filter columns (potential candidates for indexes, primary keys, or sharding keys
 
 These new `VEXPLAIN` modes enhance Vitess's query analysis capabilities, allowing for more informed decisions about sharding 
 strategies and query optimization.
+
+### <a id="errant-gtid-vttablet"/>Errant GTID Detection on VTTablets
+
+VTTablets now run an errant GTID detection logic before they join the replication stream. So, if a replica has an errant GTID, it will
+not start replicating from the primary. This protects us from running into situations which are very difficult to recover from.
+
+For users running with the vitess-operator on Kubernetes, this change means that replica tablets with errant GTIDs will have broken 
+replication and will report as unready. Users will need to manually replace and clean up these errant replica tablets.

go/mysql/replication/mysql56_gtid_set.go

@@ -467,6 +467,33 @@ func (set Mysql56GTIDSet) SIDBlock() []byte {
 	return buf.Bytes()
 }
 
+// ErrantGTIDsOnReplica gets the errant GTIDs on the replica by comparing against the primary position and UUID.
+func ErrantGTIDsOnReplica(replicaPosition Position, primaryPosition Position) (string, error) {
+	replicaGTIDSet, replicaOk := replicaPosition.GTIDSet.(Mysql56GTIDSet)
+	primaryGTIDSet, primaryOk := primaryPosition.GTIDSet.(Mysql56GTIDSet)
+
+	// Currently we only support errant GTID detection for MySQL 56 flavour.
+	if !replicaOk || !primaryOk {
+		return "", nil
+	}
+
+	// Calculate the difference between the replica and primary GTID sets.
+	diffSet := replicaGTIDSet.Difference(primaryGTIDSet)
+	return diffSet.String(), nil
+}
+
+// RemoveUUID removes a specific UUID from the gtid set.
+func (set Mysql56GTIDSet) RemoveUUID(uuid SID) Mysql56GTIDSet {
+	newSet := make(Mysql56GTIDSet)
+	for sid, intervals := range set {
+		if sid == uuid {
+			continue
+		}
+		newSet[sid] = intervals
+	}
+	return newSet
+}
+
 // Difference will supply the difference between the receiver and supplied Mysql56GTIDSets, and supply the result
 // as a Mysql56GTIDSet.
 func (set Mysql56GTIDSet) Difference(other Mysql56GTIDSet) Mysql56GTIDSet {

go/mysql/replication/mysql56_gtid_set_test.go

@@ -704,3 +704,88 @@ func BenchmarkMySQL56GTIDParsing(b *testing.B) {
 		}
 	}
 }
+
+func TestErrantGTIDsOnReplica(t *testing.T) {
+	tests := []struct {
+		name             string
+		replicaPosition  string
+		primaryPosition  string
+		errantGtidWanted string
+		wantErr          string
+	}{
+		{
+			name:             "Empty replica position",
+			replicaPosition:  "MySQL56/",
+			primaryPosition:  "MySQL56/8bc65c84-3fe4-11ed-a912-257f0fcdd6c9:1-8",
+			errantGtidWanted: "",
+		}, {
+			name:             "Empty primary position",
+			replicaPosition:  "MySQL56/8bc65c84-3fe4-11ed-a912-257f0fcdd6c9:1-8",
+			primaryPosition:  "MySQL56/",
+			errantGtidWanted: "8bc65c84-3fe4-11ed-a912-257f0fcdd6c9:1-8",
+		}, {
+			name:             "Empty primary position - with multiple errant gtids",
+			replicaPosition:  "MySQL56/8bc65c84-3fe4-11ed-a912-257f0fcdd6c9:1-8,8bc65cca-3fe4-11ed-bbfb-091034d48b3e:1",
+			primaryPosition:  "MySQL56/",
+			errantGtidWanted: "8bc65c84-3fe4-11ed-a912-257f0fcdd6c9:1-8,8bc65cca-3fe4-11ed-bbfb-091034d48b3e:1",
+		}, {
+			name:             "Single errant GTID",
+			replicaPosition:  "MySQL56/8bc65c84-3fe4-11ed-a912-257f0fcdd6c9:1-8,8bc65cca-3fe4-11ed-bbfb-091034d48b3e:1,8bc65cca-3fe4-11ed-bbfb-091034d48bd3:34",
+			primaryPosition:  "MySQL56/8bc65c84-3fe4-11ed-a912-257f0fcdd6c9:1-50,8bc65cca-3fe4-11ed-bbfb-091034d48b3e:1-30",
+			errantGtidWanted: "8bc65cca-3fe4-11ed-bbfb-091034d48bd3:34",
+		}, {
+			name:             "Multiple errant GTID",
+			replicaPosition:  "MySQL56/8bc65c84-3fe4-11ed-a912-257f0fcdd6c9:1-8,8bc65cca-3fe4-11ed-bbfb-091034d48b3e:1-32,8bc65cca-3fe4-11ed-bbfb-091034d48bd3:3-35",
+			primaryPosition:  "MySQL56/8bc65c84-3fe4-11ed-a912-257f0fcdd6c9:1-50,8bc65cca-3fe4-11ed-bbfb-091034d48b3e:1-30,8bc65cca-3fe4-11ed-bbfb-091034d48bd3:34",
+			errantGtidWanted: "8bc65cca-3fe4-11ed-bbfb-091034d48b3e:31-32,8bc65cca-3fe4-11ed-bbfb-091034d48bd3:3-33:35",
+		},
+	}
+	for _, tt := range tests {
+		t.Run(tt.name, func(t *testing.T) {
+			replPos, err := DecodePosition(tt.replicaPosition)
+			require.NoError(t, err)
+			primaryPos, err := DecodePosition(tt.primaryPosition)
+			require.NoError(t, err)
+			errantGTIDs, err := ErrantGTIDsOnReplica(replPos, primaryPos)
+			if tt.wantErr != "" {
+				require.ErrorContains(t, err, tt.wantErr)
+			} else {
+				require.NoError(t, err)
+				require.EqualValues(t, tt.errantGtidWanted, errantGTIDs)
+			}
+
+		})
+	}
+}
+
+func TestMysql56GTIDSet_RemoveUUID(t *testing.T) {
+	tests := []struct {
+		name       string
+		initialSet string
+		uuid       string
+		wantSet    string
+	}{
+		{
+			name:       "Remove unknown UUID",
+			initialSet: "8bc65c84-3fe4-11ed-a912-257f0fcdd6c9:1-8,8bc65cca-3fe4-11ed-bbfb-091034d48b3e:1:4-24",
+			uuid:       "8bc65c84-3fe4-11ed-a912-257f0fcde6c9",
+			wantSet:    "8bc65c84-3fe4-11ed-a912-257f0fcdd6c9:1-8,8bc65cca-3fe4-11ed-bbfb-091034d48b3e:1:4-24",
+		},
+		{
+			name:       "Remove a single UUID",
+			initialSet: "8bc65c84-3fe4-11ed-a912-257f0fcdd6c9:1-8,8bc65cca-3fe4-11ed-bbfb-091034d48b3e:1:4-24",
+			uuid:       "8bc65c84-3fe4-11ed-a912-257f0fcdd6c9",
+			wantSet:    "8bc65cca-3fe4-11ed-bbfb-091034d48b3e:1:4-24",
+		},
+	}
+	for _, tt := range tests {
+		t.Run(tt.name, func(t *testing.T) {
+			gtidSet, err := ParseMysql56GTIDSet(tt.initialSet)
+			require.NoError(t, err)
+			sid, err := ParseSID(tt.uuid)
+			require.NoError(t, err)
+			gtidSet = gtidSet.RemoveUUID(sid)
+			require.EqualValues(t, tt.wantSet, gtidSet.String())
+		})
+	}
+}