Merge pull request #116 from github/nice-ratio-float

nice-ratio is now float64

go/base/context.go

@@ -63,7 +63,7 @@ type MigrationContext struct {
 
 	defaultNumRetries                   int64
 	ChunkSize                           int64
-	NiceRatio                           int64
+	niceRatio                           float64
 	MaxLagMillisecondsThrottleThreshold int64
 	replicationLagQuery                 string
 	throttleControlReplicaKeys          *mysql.InstanceKeyMap
@@ -382,6 +382,26 @@ func (this *MigrationContext) GetCriticalLoad() LoadMap {
 	return this.criticalLoad.Duplicate()
 }
 
+func (this *MigrationContext) GetNiceRatio() float64 {
+	this.throttleMutex.Lock()
+	defer this.throttleMutex.Unlock()
+
+	return this.niceRatio
+}
+
+func (this *MigrationContext) SetNiceRatio(newRatio float64) {
+	if newRatio < 0.0 {
+		newRatio = 0.0
+	}
+	if newRatio > 100.0 {
+		newRatio = 100.0
+	}
+
+	this.throttleMutex.Lock()
+	defer this.throttleMutex.Unlock()
+	this.niceRatio = newRatio
+}
+
 // ReadMaxLoad parses the `--max-load` flag, which is in multiple key-value format,
 // such as: 'Threads_running=100,Threads_connected=500'
 // It only applies changes in case there's no parsing error.

go/cmd/gh-ost/main.go

@@ -72,7 +72,7 @@ func main() {
 	chunkSize := flag.Int64("chunk-size", 1000, "amount of rows to handle in each iteration (allowed range: 100-100,000)")
 	defaultRetries := flag.Int64("default-retries", 60, "Default number of retries for various operations before panicking")
 	cutOverLockTimeoutSeconds := flag.Int64("cut-over-lock-timeout-seconds", 3, "Max number of seconds to hold locks on tables while attempting to cut-over (retry attempted when lock exceeds timeout)")
-	flag.Int64Var(&migrationContext.NiceRatio, "nice-ratio", 0, "force being 'nice', imply sleep time per chunk time. Example values: 0 is aggressive. 3: for every ms spend in a rowcopy chunk, spend 3ms sleeping immediately after")
+	niceRatio := flag.Float64("nice-ratio", 0, "force being 'nice', imply sleep time per chunk time; range: [0.0..100.0]. Example values: 0 is aggressive. 1.5: for every ms spend in a rowcopy chunk, spend 1.5ms sleeping immediately after")
 
 	maxLagMillis := flag.Int64("max-lag-millis", 1500, "replication lag at which to throttle operation")
 	replicationLagQuery := flag.String("replication-lag-query", "", "Query that detects replication lag in seconds. Result can be a floating point (by default gh-ost issues SHOW SLAVE STATUS and reads Seconds_behind_master). If you're using pt-heartbeat, query would be something like: SELECT ROUND(UNIX_TIMESTAMP() - MAX(UNIX_TIMESTAMP(ts))) AS delay FROM my_schema.heartbeat")
@@ -169,6 +169,7 @@ func main() {
 	if migrationContext.ServeSocketFile == "" {
 		migrationContext.ServeSocketFile = fmt.Sprintf("/tmp/gh-ost.%s.%s.sock", migrationContext.DatabaseName, migrationContext.OriginalTableName)
 	}
+	migrationContext.SetNiceRatio(*niceRatio)
 	migrationContext.SetChunkSize(*chunkSize)
 	migrationContext.SetMaxLagMillisecondsThrottleThreshold(*maxLagMillis)
 	migrationContext.SetReplicationLagQuery(*replicationLagQuery)

go/logic/migrator.go

@@ -705,11 +705,11 @@ help                                 # This message
 		}
 	case "nice-ratio":
 		{
-			if niceRatio, err := strconv.Atoi(arg); err != nil {
+			if niceRatio, err := strconv.ParseFloat(arg, 64); err != nil {
 				fmt.Fprintf(writer, "%s\n", err.Error())
 				return log.Errore(err)
 			} else {
-				atomic.StoreInt64(&this.migrationContext.NiceRatio, int64(niceRatio))
+				this.migrationContext.SetNiceRatio(niceRatio)
 				this.printStatus(ForcePrintStatusAndHint, writer)
 			}
 		}
@@ -866,12 +866,12 @@ func (this *Migrator) printMigrationStatusHint(writers ...io.Writer) {
 	))
 	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: %d",
+	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(),
-		atomic.LoadInt64(&this.migrationContext.NiceRatio),
+		this.migrationContext.GetNiceRatio(),
 	))
 	if replicationLagQuery := this.migrationContext.GetReplicationLagQuery(); replicationLagQuery != "" {
 		fmt.Fprintln(w, fmt.Sprintf("# Replication lag query: %+v",
@@ -1190,9 +1190,10 @@ func (this *Migrator) executeWriteFuncs() error {
 						if err := copyRowsFunc(); err != nil {
 							return log.Errore(err)
 						}
-						if niceRatio := atomic.LoadInt64(&this.migrationContext.NiceRatio); niceRatio > 0 {
+						if niceRatio := this.migrationContext.GetNiceRatio(); niceRatio > 0 {
 							copyRowsDuration := time.Now().Sub(copyRowsStartTime)
-							sleepTime := copyRowsDuration * time.Duration(niceRatio)
+							sleepTimeNanosecondFloat64 := niceRatio * float64(copyRowsDuration.Nanoseconds())
+							sleepTime := time.Duration(time.Duration(int64(sleepTimeNanosecondFloat64)) * time.Nanosecond)
 							time.Sleep(sleepTime)
 						}
 					}