Merge pull request #87 from github/nice

added nice-ratio

Author: Shlomi Noach

build.sh

@@ -1,7 +1,7 @@
 #!/bin/bash
 #
 #
-RELEASE_VERSION="0.9.8"
+RELEASE_VERSION="0.9.9"
 
 buildpath=/tmp/gh-ost
 target=gh-ost

doc/interactive-commands.md

@@ -21,6 +21,7 @@ replication lag on to determine throttling
 - `max-load=<max-load-thresholds>`: modify the `max-load` config; applies on next running copy-iteration
   The `max-load` format must be: `some_status=<numeric-threshold>[,some_status=<numeric-threshold>...]`. For example: `Threads_running=50,threads_connected=1000`, and you would then write/echo `max-load=Threads_running=50,threads_connected=1000` to the socket.
 - `critical-load=<load>`: change critical load setting (exceeding given thresholds causes panic and abort)
+- `nice-ratio=<ratio>`: change _nice_ ratio: 0 for aggressive, positive integer `n`: for any unit of time spent copying rows, spend `n` units of time sleeping.
 - `throttle-query`: change throttle query
 - `throttle-control-replicas`: change list of throttle-control replicas, these are replicas `gh-ost` will cehck
 - `throttle`: force migration suspend

go/base/context.go

@@ -58,6 +58,7 @@ type MigrationContext struct {
 
 	defaultNumRetries                   int64
 	ChunkSize                           int64
+	NiceRatio                           int64
 	MaxLagMillisecondsThrottleThreshold int64
 	ReplictionLagQuery                  string
 	ThrottleControlReplicaKeys          *mysql.InstanceKeyMap

go/cmd/gh-ost/main.go

@@ -71,6 +71,7 @@ func main() {
 	flag.BoolVar(&migrationContext.SwitchToRowBinlogFormat, "switch-to-rbr", false, "let this tool automatically switch binary log format to 'ROW' on the replica, if needed. The format will NOT be switched back. I'm too scared to do that, and wish to protect you if you happen to execute another migration while this one is running")
 	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")
+	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")
 
 	flag.Int64Var(&migrationContext.MaxLagMillisecondsThrottleThreshold, "max-lag-millis", 1500, "replication lag at which to throttle operation")
 	flag.StringVar(&migrationContext.ReplictionLagQuery, "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")

go/logic/migrator.go

@@ -790,6 +790,7 @@ func (this *Migrator) onServerCommand(command string, writer *bufio.Writer) (err
 			fmt.Fprintln(writer, `available commands:
 status                               # Print a status message
 chunk-size=<newsize>                 # Set a new chunk-size
+nice-ratio=<ratio>                   # Set a new nice-ratio, integer (0 is agrressive)
 critical-load=<load>                 # Set a new set of max-load thresholds
 max-load=<load>                      # Set a new set of max-load thresholds
 throttle-query=<query>               # Set a new throttle-query
@@ -813,6 +814,16 @@ help                                 # This message
 				this.printStatus(ForcePrintStatusAndHint, writer)
 			}
 		}
+	case "nice-ratio":
+		{
+			if niceRatio, err := strconv.Atoi(arg); err != nil {
+				fmt.Fprintf(writer, "%s\n", err.Error())
+				return log.Errore(err)
+			} else {
+				atomic.StoreInt64(&this.migrationContext.NiceRatio, int64(niceRatio))
+				this.printStatus(ForcePrintStatusAndHint, writer)
+			}
+		}
 	case "max-load":
 		{
 			if err := this.migrationContext.ReadMaxLoad(arg); err != nil {
@@ -963,11 +974,12 @@ 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: %+vms; max-load: %s; critical-load: %s",
+	fmt.Fprintln(w, fmt.Sprintf("# chunk-size: %+v; max lag: %+vms; max-load: %s; critical-load: %s; nice-ratio: %d",
 		atomic.LoadInt64(&this.migrationContext.ChunkSize),
 		atomic.LoadInt64(&this.migrationContext.MaxLagMillisecondsThrottleThreshold),
 		maxLoad.String(),
 		criticalLoad.String(),
+		atomic.LoadInt64(&this.migrationContext.NiceRatio),
 	))
 	if this.migrationContext.ThrottleFlagFile != "" {
 		fmt.Fprintln(w, fmt.Sprintf("# Throttle flag file: %+v",
@@ -1264,10 +1276,16 @@ func (this *Migrator) executeWriteFuncs() error {
 				select {
 				case copyRowsFunc := <-this.copyRowsQueue:
 					{
+						copyRowsStartTime := time.Now()
 						// Retries are handled within the copyRowsFunc
 						if err := copyRowsFunc(); err != nil {
 							return log.Errore(err)
 						}
+						if niceRatio := atomic.LoadInt64(&this.migrationContext.NiceRatio); niceRatio > 0 {
+							copyRowsDuration := time.Now().Sub(copyRowsStartTime)
+							sleepTime := copyRowsDuration * time.Duration(niceRatio)
+							time.Sleep(sleepTime)
+						}
 					}
 				default:
 					{