Endtoend: stress tests for VTGate FOREIGN KEY support

.github/workflows/cluster_endtoend_vtgate_foreignkey_stress.yml

@@ -0,0 +1,148 @@
+# DO NOT MODIFY: THIS FILE IS GENERATED USING "make generate_ci_workflows"
+
+name: Cluster (vtgate_foreignkey_stress)
+on: [push, pull_request]
+concurrency:
+ group: format('{0}-{1}', ${{ github.ref }}, 'Cluster (vtgate_foreignkey_stress)')
+ cancel-in-progress: true
+
+permissions: read-all
+
+env:
+ LAUNCHABLE_ORGANIZATION: "vitess"
+ LAUNCHABLE_WORKSPACE: "vitess-app"
+ GITHUB_PR_HEAD_SHA: "${{ github.event.pull_request.head.sha }}"
+
+jobs:
+ build:
+ name: Run endtoend tests on Cluster (vtgate_foreignkey_stress)
+ runs-on: gh-hosted-runners-4cores-1
+
+ steps:
+ - name: Skip CI
+ run: |
+ if [[ "${{contains( github.event.pull_request.labels.*.name, 'Skip CI')}}" == "true" ]]; then
+ echo "skipping CI due to the 'Skip CI' label"
+ exit 1
+ fi
+
+ - name: Check if workflow needs to be skipped
+ id: skip-workflow
+ run: |
+ skip='false'
+ if [[ "${{github.event.pull_request}}" == "" ]] && [[ "${{github.ref}}" != "refs/heads/main" ]] && [[ ! "${{github.ref}}" =~ ^refs/heads/release-[0-9]+\.[0-9]$ ]] && [[ ! "${{github.ref}}" =~ "refs/tags/.*" ]]; then
+ skip='true'
+ fi
+ echo Skip ${skip}
+ echo "skip-workflow=${skip}" >> $GITHUB_OUTPUT
+
+ PR_DATA=$(curl \
+ -H "Authorization: token ${{ secrets.GITHUB_TOKEN }}" \
+ -H "Accept: application/vnd.github.v3+json" \
+ "https://api.github.com/repos/${{ github.repository }}/pulls/${{ github.event.pull_request.number }}")
+ draft=$(echo "$PR_DATA" | jq .draft -r)
+ echo "is_draft=${draft}" >> $GITHUB_OUTPUT
+
+ - name: Check out code
+ if: steps.skip-workflow.outputs.skip-workflow == 'false'
+ uses: actions/checkout@v3
+
+ - name: Check for changes in relevant files
+ if: steps.skip-workflow.outputs.skip-workflow == 'false'
+ uses: frouioui/paths-filter@main
+ id: changes
+ with:
+ token: ''
+ filters: |
+ end_to_end:
+ - 'go/**/*.go'
+ - 'test.go'
+ - 'Makefile'
+ - 'build.env'
+ - 'go.sum'
+ - 'go.mod'
+ - 'proto/*.proto'
+ - 'tools/**'
+ - 'config/**'
+ - 'bootstrap.sh'
+ - '.github/workflows/cluster_endtoend_vtgate_foreignkey_stress.yml'
+
+ - name: Set up Go
+ if: steps.skip-workflow.outputs.skip-workflow == 'false' && steps.changes.outputs.end_to_end == 'true'
+ uses: actions/setup-go@v4
+ with:
+ go-version: 1.21.0
+
+ - name: Set up python
+ if: steps.skip-workflow.outputs.skip-workflow == 'false' && steps.changes.outputs.end_to_end == 'true'
+ uses: actions/setup-python@v4
+
+ - name: Tune the OS
+ if: steps.skip-workflow.outputs.skip-workflow == 'false' && steps.changes.outputs.end_to_end == 'true'
+ run: |
+ # Limit local port range to not use ports that overlap with server side
+ # ports that we listen on.
+ sudo sysctl -w net.ipv4.ip_local_port_range="22768 65535"
+ # Increase the asynchronous non-blocking I/O. More information at https://dev.mysql.com/doc/refman/5.7/en/innodb-parameters.html#sysvar_innodb_use_native_aio
+ echo "fs.aio-max-nr = 1048576" | sudo tee -a /etc/sysctl.conf
+ sudo sysctl -p /etc/sysctl.conf
+
+ - name: Get dependencies
+ if: steps.skip-workflow.outputs.skip-workflow == 'false' && steps.changes.outputs.end_to_end == 'true'
+ run: |
+
+ # Get key to latest MySQL repo
+ sudo apt-key adv --keyserver keyserver.ubuntu.com --recv-keys 467B942D3A79BD29
+ # Setup MySQL 8.0
+ wget -c https://dev.mysql.com/get/mysql-apt-config_0.8.24-1_all.deb
+ echo mysql-apt-config mysql-apt-config/select-server select mysql-8.0 | sudo debconf-set-selections
+ sudo DEBIAN_FRONTEND="noninteractive" dpkg -i mysql-apt-config*
+ sudo apt-get update
+ # Install everything else we need, and configure
+ sudo apt-get install -y mysql-server mysql-client make unzip g++ etcd curl git wget eatmydata xz-utils libncurses5
+
+ sudo service mysql stop
+ sudo service etcd stop
+ sudo ln -s /etc/apparmor.d/usr.sbin.mysqld /etc/apparmor.d/disable/
+ sudo apparmor_parser -R /etc/apparmor.d/usr.sbin.mysqld
+ go mod download
+
+ # install JUnit report formatter
+ go install github.com/vitessio/go-junit-report@HEAD
+
+ - 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'
+ run: |
+ # Get Launchable CLI installed. If you can, make it a part of the builder image to speed things up
+ pip3 install --user launchable~=1.0 > /dev/null
+
+ # verify that launchable setup is all correct.
+ launchable verify || true
+
+ # Tell Launchable about the build you are producing and testing
+ launchable record build --name "$GITHUB_RUN_ID" --no-commit-collection --source .
+
+ - name: Run cluster endtoend test
+ if: steps.skip-workflow.outputs.skip-workflow == 'false' && steps.changes.outputs.end_to_end == 'true'
+ timeout-minutes: 45
+ run: |
+ # We set the VTDATAROOT to the /tmp folder to reduce the file path of mysql.sock file
+ # which musn't be more than 107 characters long.
+ export VTDATAROOT="/tmp/"
+ source build.env
+
+ set -exo pipefail
+
+ # run the tests however you normally do, then produce a JUnit XML file
+ eatmydata -- go run test.go -docker=false -follow -shard vtgate_foreignkey_stress | tee -a output.txt | go-junit-report -set-exit-code > report.xml
+
+ - name: Print test output and Record test result in launchable if PR is not a draft
+ if: steps.skip-workflow.outputs.skip-workflow == 'false' && steps.changes.outputs.end_to_end == 'true' && always()
+ run: |
+ if [[ "${{steps.skip-workflow.outputs.is_draft}}" == "false" ]]; then
+ # send recorded tests to launchable
+ launchable record tests --build "$GITHUB_RUN_ID" go-test . || true
+ fi
+
+ # print test output
+ cat output.txt

go.mod

@@ -107,6 +107,7 @@ require (
  github.com/spf13/jwalterweatherman v1.1.0
  github.com/xlab/treeprint v1.2.0
  go.uber.org/goleak v1.2.1
+ golang.org/x/exp v0.0.0-20230817173708-d852ddb80c63
  golang.org/x/sync v0.3.0
  modernc.org/sqlite v1.20.3
 )

go.sum

@@ -677,6 +677,8 @@ golang.org/x/exp v0.0.0-20191227195350-da58074b4299/go.mod h1:2RIsYlXP63K8oxa1u0
 golang.org/x/exp v0.0.0-20200119233911-0405dc783f0a/go.mod h1:2RIsYlXP63K8oxa1u096TMicItID8zy7Y6sNkU49FU4=
 golang.org/x/exp v0.0.0-20200207192155-f17229e696bd/go.mod h1:J/WKrq2StrnmMY6+EHIKF9dgMWnmCNThgcyBT1FY9mM=
 golang.org/x/exp v0.0.0-20200224162631-6cc2880d07d6/go.mod h1:3jZMyOhIsHpP37uCMkUooju7aAi5cS1Q23tOzKc+0MU=
+golang.org/x/exp v0.0.0-20230817173708-d852ddb80c63 h1:m64FZMko/V45gv0bNmrNYoDEq8U5YUhetc9cBWKS1TQ=
+golang.org/x/exp v0.0.0-20230817173708-d852ddb80c63/go.mod h1:0v4NqG35kSWCMzLaMeX+IQrlSnVE/bqGSyC2cz/9Le8=
 golang.org/x/image v0.0.0-20190227222117-0694c2d4d067/go.mod h1:kZ7UVZpmo3dzQBMxlp+ypCbDeSB+sBbTgSJuh5dn5js=
 golang.org/x/image v0.0.0-20190802002840-cff245a6509b/go.mod h1:FeLwcggjj3mMvU+oOTbSwawSJRM1uh48EjtB4UJZlP0=
 golang.org/x/lint v0.0.0-20181026193005-c67002cb31c3/go.mod h1:UVdnD1Gm6xHRNCYTkRU2/jEulfH38KcIWyp/GAMgvoE=

go/test/endtoend/cluster/cluster_util.go

@@ -223,26 +223,53 @@ func filterResultWhenRunsForCoverage(input string) string {
  return result
 }
 
+func ValidateReplicationIsHealthy(t *testing.T, tablet *Vttablet) bool {
+ query := "show replica status"
+ rs, err := tablet.VttabletProcess.QueryTablet(query, "", true)
+ assert.NoError(t, err)
+ row := rs.Named().Row()
+ require.NotNil(t, row)
+
+ ioRunning := row.AsString("Replica_IO_Running", "")
+ require.NotEmpty(t, ioRunning)
+ ioHealthy := assert.Equalf(t, "Yes", ioRunning, "Replication is broken. Replication status: %v", row)
+ sqlRunning := row.AsString("Replica_SQL_Running", "")
+ require.NotEmpty(t, sqlRunning)
+ sqlHealthy := assert.Equalf(t, "Yes", sqlRunning, "Replication is broken. Replication status: %v", row)
+
+ return ioHealthy && sqlHealthy
+}
+
 // WaitForReplicationPos will wait for replication position to catch-up
-func WaitForReplicationPos(t *testing.T, tabletA *Vttablet, tabletB *Vttablet, hostname string, timeout float64) {
+func WaitForReplicationPos(t *testing.T, tabletA *Vttablet, tabletB *Vttablet, validateReplication bool, timeout time.Duration) {
+ hostname := "localhost"
+ ctx, cancel := context.WithTimeout(context.Background(), timeout)
+ defer cancel()
+ ticker := time.NewTicker(10 * time.Millisecond)
+ defer ticker.Stop()
+
  replicationPosA, _ := GetPrimaryPosition(t, *tabletA, hostname)
  for {
+ if validateReplication {
+ if !ValidateReplicationIsHealthy(t, tabletB) {
+ assert.FailNowf(t, "Replication broken on tablet %v. Will not wait for position", tabletB.Alias)
+ }
+ if t.Failed() {
+ return
+ }
+ }
  replicationPosB, _ := GetPrimaryPosition(t, *tabletB, hostname)
  if positionAtLeast(t, tabletA, replicationPosB, replicationPosA) {
- break
+ return
  }
  msg := fmt.Sprintf("%s's replication position to catch up to %s's;currently at: %s, waiting to catch up to: %s", tabletB.Alias, tabletA.Alias, replicationPosB, replicationPosA)
- waitStep(t, msg, timeout, 0.01)
- }
-}
-
-func waitStep(t *testing.T, msg string, timeout float64, sleepTime float64) float64 {
- timeout = timeout - sleepTime
- if timeout < 0.0 {
- t.Errorf("timeout waiting for condition '%s'", msg)
+ select {
+ case <-ctx.Done():
+ assert.FailNowf(t, "Timeout waiting for condition '%s'", msg)
+ return
+ case <-ticker.C:
+ }
  }
- time.Sleep(time.Duration(sleepTime) * time.Second)
- return timeout
 }
 
 func positionAtLeast(t *testing.T, tablet *Vttablet, a string, b string) bool {

go/test/endtoend/onlineddl/vtgate_util.go

@@ -207,7 +207,7 @@ func CheckLaunchAllMigrations(t *testing.T, vtParams *mysql.ConnParams, expectCo
 }
 
 // CheckMigrationStatus verifies that the migration indicated by given UUID has the given expected status
-func CheckMigrationStatus(t *testing.T, vtParams *mysql.ConnParams, shards []cluster.Shard, uuid string, expectStatuses ...schema.OnlineDDLStatus) {
+func CheckMigrationStatus(t *testing.T, vtParams *mysql.ConnParams, shards []cluster.Shard, uuid string, expectStatuses ...schema.OnlineDDLStatus) bool {
  query, err := sqlparser.ParseAndBind("show vitess_migrations like %a",
  sqltypes.StringBindVariable(uuid),
  )
@@ -229,7 +229,7 @@ func CheckMigrationStatus(t *testing.T, vtParams *mysql.ConnParams, shards []clu
  }
  }
  }
- assert.Equal(t, len(shards), count)
+ return assert.Equal(t, len(shards), count)
 }
 
 // WaitForMigrationStatus waits for a migration to reach either provided statuses (returns immediately), or eventually time out

go/test/endtoend/tabletgateway/buffer/reparent/failover_buffer_test.go

@@ -51,7 +51,7 @@ func failoverExternalReparenting(t *testing.T, clusterInstance *cluster.LocalPro
  primary.VttabletProcess.QueryTablet(demoteQuery, keyspaceUnshardedName, true)
 
  // Wait for replica to catch up to primary.
- cluster.WaitForReplicationPos(t, primary, replica, "localhost", 60.0)
+ cluster.WaitForReplicationPos(t, primary, replica, false, time.Minute)
 
  duration := time.Since(start)
  minUnavailabilityInS := 1.0