func (this *Server) BindSocketFile() (err error) {
if this.migrationContext.ServeSocketFile == "" {
return nil
}
if this.migrationContext.DropServeSocket && base.FileExists(this.migrationContext.ServeSocketFile) {
os.Remove(this.migrationContext.ServeSocketFile)
}
this.unixListener, err = net.Listen("unix", this.migrationContext.ServeSocketFile)
if err != nil {
return err
}
log.Infof("Listening on unix socket file: %s", this.migrationContext.ServeSocketFile)
return nil
}
// printMigrationStatusHint prints a detailed configuration dump, that is useful
// to keep in mind; such as the name of migrated table, throttle params etc.
// This gets printed at beginning and end of migration, every 10 minutes throughout
// migration, and as reponse to the "status" interactive command.
func (this *Migrator) printMigrationStatusHint(writers ...io.Writer) {
w := io.MultiWriter(writers...)
fmt.Fprintln(w, fmt.Sprintf("# Migrating %s.%s; Ghost table is %s.%s",
sql.EscapeName(this.migrationContext.DatabaseName),
sql.EscapeName(this.migrationContext.OriginalTableName),
sql.EscapeName(this.migrationContext.DatabaseName),
sql.EscapeName(this.migrationContext.GetGhostTableName()),
))
fmt.Fprintln(w, fmt.Sprintf("# Migrating %+v; inspecting %+v; executing on %+v",
*this.applier.connectionConfig.ImpliedKey,
*this.inspector.connectionConfig.ImpliedKey,
this.hostname,
))
fmt.Fprintln(w, fmt.Sprintf("# Migration started at %+v",
this.migrationContext.StartTime.Format(time.RubyDate),
))
maxLoad := this.migrationContext.GetMaxLoad()
criticalLoad := this.migrationContext.GetCriticalLoad()
fmt.Fprintln(w, fmt.Sprintf("# chunk-size: %+v; max-lag-millis: %+vms; max-load: %s; critical-load: %s; nice-ratio: %f",
atomic.LoadInt64(&this.migrationContext.ChunkSize),
atomic.LoadInt64(&this.migrationContext.MaxLagMillisecondsThrottleThreshold),
maxLoad.String(),
criticalLoad.String(),
this.migrationContext.GetNiceRatio(),
))
if replicationLagQuery := this.migrationContext.GetReplicationLagQuery(); replicationLagQuery != "" {
fmt.Fprintln(w, fmt.Sprintf("# replication-lag-query: %+v",
replicationLagQuery,
))
}
if this.migrationContext.ThrottleFlagFile != "" {
setIndicator := ""
if base.FileExists(this.migrationContext.ThrottleFlagFile) {
setIndicator = "[set]"
}
fmt.Fprintln(w, fmt.Sprintf("# throttle-flag-file: %+v %+v",
this.migrationContext.ThrottleFlagFile, setIndicator,
))
}
if this.migrationContext.ThrottleAdditionalFlagFile != "" {
setIndicator := ""
if base.FileExists(this.migrationContext.ThrottleAdditionalFlagFile) {
setIndicator = "[set]"
}
fmt.Fprintln(w, fmt.Sprintf("# throttle-additional-flag-file: %+v %+v",
this.migrationContext.ThrottleAdditionalFlagFile, setIndicator,
))
}
if throttleQuery := this.migrationContext.GetThrottleQuery(); throttleQuery != "" {
fmt.Fprintln(w, fmt.Sprintf("# throttle-query: %+v",
throttleQuery,
))
}
if this.migrationContext.PostponeCutOverFlagFile != "" {
setIndicator := ""
if base.FileExists(this.migrationContext.PostponeCutOverFlagFile) {
setIndicator = "[set]"
}
fmt.Fprintln(w, fmt.Sprintf("# postpone-cut-over-flag-file: %+v %+v",
this.migrationContext.PostponeCutOverFlagFile, setIndicator,
))
}
if this.migrationContext.PanicFlagFile != "" {
fmt.Fprintln(w, fmt.Sprintf("# panic-flag-file: %+v",
this.migrationContext.PanicFlagFile,
))
}
fmt.Fprintln(w, fmt.Sprintf("# Serving on unix socket: %+v",
this.migrationContext.ServeSocketFile,
))
if this.migrationContext.ServeTCPPort != 0 {
fmt.Fprintln(w, fmt.Sprintf("# Serving on TCP port: %+v", this.migrationContext.ServeTCPPort))
}
}
// cutOver performs the final step of migration, based on migration
// type (on replica? bumpy? safe?)
func (this *Migrator) cutOver() (err error) {
if this.migrationContext.Noop {
log.Debugf("Noop operation; not really swapping tables")
return nil
}
this.migrationContext.MarkPointOfInterest()
this.throttle(func() {
log.Debugf("throttling before swapping tables")
})
this.migrationContext.MarkPointOfInterest()
this.sleepWhileTrue(
func() (bool, error) {
if this.migrationContext.PostponeCutOverFlagFile == "" {
return false, nil
}
if atomic.LoadInt64(&this.userCommandedUnpostponeFlag) > 0 {
return false, nil
}
if base.FileExists(this.migrationContext.PostponeCutOverFlagFile) {
// Throttle file defined and exists!
atomic.StoreInt64(&this.migrationContext.IsPostponingCutOver, 1)
//log.Debugf("Postponing final table swap as flag file exists: %+v", this.migrationContext.PostponeCutOverFlagFile)
return true, nil
}
return false, nil
},
)
atomic.StoreInt64(&this.migrationContext.IsPostponingCutOver, 0)
this.migrationContext.MarkPointOfInterest()
if this.migrationContext.TestOnReplica {
// With `--test-on-replica` we stop replication thread, and then proceed to use
// the same cut-over phase as the master would use. That means we take locks
// and swap the tables.
// The difference is that we will later swap the tables back.
log.Debugf("testing on replica. Stopping replication IO thread")
if err := this.retryOperation(this.applier.StopReplication); err != nil {
return err
}
// We're merly testing, we don't want to keep this state. Rollback the renames as possible
defer this.applier.RenameTablesRollback()
// We further proceed to do the cutover by normal means; the 'defer' above will rollback the swap
}
if this.migrationContext.CutOverType == base.CutOverAtomic {
// Atomic solution: we use low timeout and multiple attempts. But for
// each failed attempt, we throttle until replication lag is back to normal
err := this.retryOperation(
func() error {
return this.executeAndThrottleOnError(this.atomicCutOver)
},
)
return err
}
if this.migrationContext.CutOverType == base.CutOverTwoStep {
err := this.retryOperation(
func() error {
return this.executeAndThrottleOnError(this.cutOverTwoStep)
},
)
return err
}
return log.Fatalf("Unknown cut-over type: %d; should never get here!", this.migrationContext.CutOverType)
}
// shouldThrottle performs checks to see whether we should currently be throttling.
// It also checks for critical-load and panic aborts.
func (this *Migrator) shouldThrottle() (result bool, reason string) {
// Regardless of throttle, we take opportunity to check for panic-abort
if this.migrationContext.PanicFlagFile != "" {
if base.FileExists(this.migrationContext.PanicFlagFile) {
this.panicAbort <- fmt.Errorf("Found panic-file %s. Aborting without cleanup", this.migrationContext.PanicFlagFile)
}
}
criticalLoad := this.migrationContext.GetCriticalLoad()
for variableName, threshold := range criticalLoad {
value, err := this.applier.ShowStatusVariable(variableName)
if err != nil {
return true, fmt.Sprintf("%s %s", variableName, err)
}
if value >= threshold {
this.panicAbort <- fmt.Errorf("critical-load met: %s=%d, >=%d", variableName, value, threshold)
}
}
// Back to throttle considerations
// User-based throttle
if atomic.LoadInt64(&this.migrationContext.ThrottleCommandedByUser) > 0 {
return true, "commanded by user"
}
if this.migrationContext.ThrottleFlagFile != "" {
if base.FileExists(this.migrationContext.ThrottleFlagFile) {
// Throttle file defined and exists!
return true, "flag-file"
}
}
if this.migrationContext.ThrottleAdditionalFlagFile != "" {
if base.FileExists(this.migrationContext.ThrottleAdditionalFlagFile) {
// 2nd Throttle file defined and exists!
return true, "flag-file"
}
}
// Replication lag throttle
maxLagMillisecondsThrottleThreshold := atomic.LoadInt64(&this.migrationContext.MaxLagMillisecondsThrottleThreshold)
lag := atomic.LoadInt64(&this.migrationContext.CurrentLag)
if time.Duration(lag) > time.Duration(maxLagMillisecondsThrottleThreshold)*time.Millisecond {
return true, fmt.Sprintf("lag=%fs", time.Duration(lag).Seconds())
}
checkThrottleControlReplicas := true
if (this.migrationContext.TestOnReplica || this.migrationContext.MigrateOnReplica) && (atomic.LoadInt64(&this.allEventsUpToLockProcessedInjectedFlag) > 0) {
checkThrottleControlReplicas = false
}
if checkThrottleControlReplicas {
lagResult := mysql.GetMaxReplicationLag(this.migrationContext.InspectorConnectionConfig, this.migrationContext.GetThrottleControlReplicaKeys(), this.migrationContext.GetReplicationLagQuery())
if lagResult.Err != nil {
return true, fmt.Sprintf("%+v %+v", lagResult.Key, lagResult.Err)
}
if lagResult.Lag > time.Duration(maxLagMillisecondsThrottleThreshold)*time.Millisecond {
return true, fmt.Sprintf("%+v replica-lag=%fs", lagResult.Key, lagResult.Lag.Seconds())
}
}
maxLoad := this.migrationContext.GetMaxLoad()
for variableName, threshold := range maxLoad {
value, err := this.applier.ShowStatusVariable(variableName)
if err != nil {
return true, fmt.Sprintf("%s %s", variableName, err)
}
if value >= threshold {
return true, fmt.Sprintf("max-load %s=%d >= %d", variableName, value, threshold)
}
}
if this.migrationContext.GetThrottleQuery() != "" {
if res, _ := this.applier.ExecuteThrottleQuery(); res > 0 {
return true, "throttle-query"
}
}
return false, ""
}