v1.1.4

RELEASE_VERSION

@@ -1 +1 @@
-1.1.2
+1.1.4

build.sh

@@ -18,7 +18,7 @@ function build {
   GOOS=$3
   GOARCH=$4
 
-  if ! go version | egrep -q 'go(1\.1[56])' ; then
+  if ! go version | egrep -q 'go1\.(1[5-9]|[2-9][0-9]{1})' ; then
     echo "go version must be 1.15 or above"
     exit 1
   fi
@@ -41,8 +41,9 @@ function build {
     builddir=$(setuptree)
     cp $buildpath/$target $builddir/gh-ost/usr/bin
     cd $buildpath
-    fpm -v "${RELEASE_VERSION}" --epoch 1 -f -s dir -n gh-ost -m 'shlomi-noach <shlomi-noach+gh-ost-deb@github.com>' --description "GitHub's Online Schema Migrations for MySQL " --url "https://github.com/github/gh-ost" --vendor "GitHub" --license "Apache 2.0" -C $builddir/gh-ost --prefix=/ -t rpm --rpm-rpmbuild-define "_build_id_links none" .
+    fpm -v "${RELEASE_VERSION}" --epoch 1 -f -s dir -n gh-ost -m 'GitHub' --description "GitHub's Online Schema Migrations for MySQL " --url "https://github.com/github/gh-ost" --vendor "GitHub" --license "Apache 2.0" -C $builddir/gh-ost --prefix=/ -t rpm --rpm-rpmbuild-define "_build_id_links none" .
-    fpm -v "${RELEASE_VERSION}" --epoch 1 -f -s dir -n gh-ost -m 'shlomi-noach <shlomi-noach+gh-ost-deb@github.com>' --description "GitHub's Online Schema Migrations for MySQL " --url "https://github.com/github/gh-ost" --vendor "GitHub" --license "Apache 2.0" -C $builddir/gh-ost --prefix=/ -t deb --deb-no-default-config-files .
+    fpm -v "${RELEASE_VERSION}" --epoch 1 -f -s dir -n gh-ost -m 'GitHub' --description "GitHub's Online Schema Migrations for MySQL " --url "https://github.com/github/gh-ost" --vendor "GitHub" --license "Apache 2.0" -C $builddir/gh-ost --prefix=/ -t deb --deb-no-default-config-files .
+    cd -
   fi
 }
 
@@ -63,10 +64,16 @@ main() {
   mkdir -p ${buildpath}
   rm -rf ${buildpath:?}/*
   build GNU/Linux linux linux amd64
-  # build macOS osx darwin amd64
+  build macOS osx darwin amd64
 
   echo "Binaries found in:"
   find $buildpath/gh-ost* -type f -maxdepth 1
+
+  echo "Checksums:"
+  (cd $buildpath && shasum -a256 gh-ost* 2>/dev/null)
 }
 
+. script/bootstrap
+cd .gopath/src/github.com/github/gh-ost
+
 main "$@"

doc/command-line-flags.md

@@ -22,7 +22,7 @@ If, for some reason, you do not wish `gh-ost` to connect to a replica, you may c
 
 ### approve-renamed-columns
 
-When your migration issues a column rename (`change column old_name new_name ...`) `gh-ost` analyzes the statement to try and associate the old column name with new column name. Otherwise the new structure may also look like some column was dropped and another was added.
+When your migration issues a column rename (`change column old_name new_name ...`) `gh-ost` analyzes the statement to try and associate the old column name with new column name. Otherwise, the new structure may also look like some column was dropped and another was added.
 
 `gh-ost` will print out what it thinks the _rename_ implied, but will not issue the migration unless you provide with `--approve-renamed-columns`.
 
@@ -32,7 +32,7 @@ If you think `gh-ost` is mistaken and that there's actually no _rename_ involved
 
 `gh-ost` infers the identity of the master server by crawling up the replication topology. You may explicitly tell `gh-ost` the identity of the master host via `--assume-master-host=the.master.com`. This is useful in:
 
-- _master-master_ topologies (together with [`--allow-master-master`](#allow-master-master)), where `gh-ost` can arbitrarily pick one of the co-masters and you prefer that it picks a specific one
+- _master-master_ topologies (together with [`--allow-master-master`](#allow-master-master)), where `gh-ost` can arbitrarily pick one of the co-masters, and you prefer that it picks a specific one
 - _tungsten replicator_ topologies (together with [`--tungsten`](#tungsten)), where `gh-ost` is unable to crawl and detect the master
 
 ### assume-rbr
@@ -61,7 +61,13 @@ Comma delimited status-name=threshold, same format as [`--max-load`](#max-load).
 
 `--critical-load` defines a threshold that, when met, `gh-ost` panics and bails out. The default behavior is to bail out immediately when meeting this threshold.
 
-This may sometimes lead to migrations bailing out on a very short spike, that, while in itself is impacting production and is worth investigating, isn't reason enough to kill a 10 hour migration.
+This may sometimes lead to migrations bailing out on a very short spike, that, while in itself is impacting production and is worth investigating, isn't reason enough to kill a 10-hour migration.
+
+### critical-load-hibernate-seconds
+
+When `--critical-load-hibernate-seconds` is non-zero (e.g. `--critical-load-hibernate-seconds=300`), `critical-load` does not panic and bail out; instead, `gh-ost` goes into hibernation for the specified duration. It will not read/write anything from/to any server during this time.  Execution then continues upon waking from hibernation.
+
+If `critical-load` is met again, `gh-ost` will repeat this cycle, and never panic and bail out.
 
 ### critical-load-interval-millis
 
@@ -98,7 +104,7 @@ Noteworthy is that setting `--dml-batch-size` to higher value _does not_ mean `g
 
 ### exact-rowcount
 
-A `gh-ost` execution need to copy whatever rows you have in your existing table onto the ghost table. This can, and often be, a large number. Exactly what that number is?
+A `gh-ost` execution need to copy whatever rows you have in your existing table onto the ghost table. This can and often will be, a large number. Exactly what that number is?
 `gh-ost` initially estimates the number of rows in your table by issuing an `explain select * from your_table`. This will use statistics on your table and return with a rough estimate. How rough? It might go as low as half or as high as double the actual number of rows in your table. This is the same method as used in [`pt-online-schema-change`](https://www.percona.com/doc/percona-toolkit/2.2/pt-online-schema-change.html).
 
 `gh-ost` also supports the `--exact-rowcount` flag. When this flag is given, two things happen:
@@ -135,6 +141,10 @@ Add this flag when executing on a 1st generation Google Cloud Platform (GCP).
 
 Default 100. See [`subsecond-lag`](subsecond-lag.md) for details.
 
+### hooks-status-interval
+
+Defaults to 60 seconds. Configures how often the `gh-ost-on-status` hook is called, see [`hooks`](hooks.md) for full details on how to use hooks.
+
 ### initially-drop-ghost-table
 
 `gh-ost` maintains two tables while migrating: the _ghost_ table (which is synced from your original table and finally replaces it) and a changelog table, which is used internally for bookkeeping. By default, it panics and aborts if it sees those tables upon startup. Provide `--initially-drop-ghost-table` and `--initially-drop-old-table` to let `gh-ost` know it's OK to drop them beforehand.
@@ -230,7 +240,7 @@ Provide a command delimited list of replicas; `gh-ost` will throttle when any of
 
 ### throttle-http
 
-Provide a HTTP endpoint; `gh-ost` will issue `HEAD` requests on given URL and throttle whenever response status code is not `200`. The URL can be queried and updated dynamically via [interactive commands](interactive-commands.md). Empty URL disables the HTTP check.
+Provide an HTTP endpoint; `gh-ost` will issue `HEAD` requests on given URL and throttle whenever response status code is not `200`. The URL can be queried and updated dynamically via [interactive commands](interactive-commands.md). Empty URL disables the HTTP check.
 
 ### timestamp-old-table
 

doc/hooks.md

@@ -68,6 +68,7 @@ The following variables are available on all hooks:
 - `GH_OST_INSPECTED_LAG` - lag in seconds (floating point) of inspected server
 - `GH_OST_HEARTBEAT_LAG` - lag in seconds (floating point) of heartbeat
 - `GH_OST_PROGRESS` - progress pct ([0..100], floating point) of migration
+- `GH_OST_ETA_SECONDS` - estimated duration until migration finishes in seconds
 - `GH_OST_MIGRATED_HOST`
 - `GH_OST_INSPECTED_HOST`
 - `GH_OST_EXECUTING_HOST`

doc/triggerless-design.md

@@ -112,7 +112,7 @@ It is also interesting to observe that `gh-ost` is the only application writing
 
 When `gh-ost` pauses (throttles), it issues no writes on the ghost table. Because there are no triggers, write workload is decoupled from the `gh-ost` write workload. And because we're using an asynchronous approach, the algorithm already handles a time difference between a master write time and the ghost apply time. A difference of a few microseconds is no different from a difference of minutes or hours.
 
-When `gh-ost` [throttles](throttle.md), either by replication lag, `max-load` setting or and explicit [interactive user command](interactive-commands.md), the master is back to normal. It sees no more writes on the ghost table.
+When `gh-ost` [throttles](throttle.md), either by replication lag, `max-load` setting or an explicit [interactive user command](interactive-commands.md), the master is back to normal. It sees no more writes on the ghost table.
 An exception is the ongoing heartbeat writes onto the changelog table, which we consider to be negligible.
 
 #### Testability

go/base/context.go

@@ -141,6 +141,7 @@ type MigrationContext struct {
 	HooksHintMessage                    string
 	HooksHintOwner                      string
 	HooksHintToken                      string
+	HooksStatusIntervalSec              int64
 
 	DropServeSocket bool
 	ServeSocketFile string
@@ -552,8 +553,8 @@ func (this *MigrationContext) SetMaxLagMillisecondsThrottleThreshold(maxLagMilli
 }
 
 func (this *MigrationContext) SetChunkSize(chunkSize int64) {
-	if chunkSize < 100 {
+	if chunkSize < 10 {
-		chunkSize = 100
+		chunkSize = 10
 	}
 	if chunkSize > 100000 {
 		chunkSize = 100000

go/cmd/gh-ost/main.go

@@ -8,6 +8,7 @@ package main
 import (
 	"flag"
 	"fmt"
+	"net/url"
 	"os"
 	"os/signal"
 	"syscall"
@@ -98,7 +99,7 @@ func main() {
 	flag.BoolVar(&migrationContext.AssumeRBR, "assume-rbr", false, "set to 'true' when you know for certain your server uses 'ROW' binlog_format. gh-ost is unable to tell, event after reading binlog_format, whether the replication process does indeed use 'ROW', and restarts replication to be certain RBR setting is applied. Such operation requires SUPER privileges which you might not have. Setting this flag avoids restarting replication and you can proceed to use gh-ost without SUPER privileges")
 	flag.BoolVar(&migrationContext.CutOverExponentialBackoff, "cut-over-exponential-backoff", false, "Wait exponentially longer intervals between failed cut-over attempts. Wait intervals obey a maximum configurable with 'exponential-backoff-max-interval').")
 	exponentialBackoffMaxInterval := flag.Int64("exponential-backoff-max-interval", 64, "Maximum number of seconds to wait between attempts when performing various operations with exponential backoff.")
-	chunkSize := flag.Int64("chunk-size", 1000, "amount of rows to handle in each iteration (allowed range: 100-100,000)")
+	chunkSize := flag.Int64("chunk-size", 1000, "amount of rows to handle in each iteration (allowed range: 10-100,000)")
 	dmlBatchSize := flag.Int64("dml-batch-size", 10, "batch size for DML events to apply in a single transaction (range 1-100)")
 	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)")
@@ -124,13 +125,14 @@ func main() {
 	flag.StringVar(&migrationContext.HooksHintMessage, "hooks-hint", "", "arbitrary message to be injected to hooks via GH_OST_HOOKS_HINT, for your convenience")
 	flag.StringVar(&migrationContext.HooksHintOwner, "hooks-hint-owner", "", "arbitrary name of owner to be injected to hooks via GH_OST_HOOKS_HINT_OWNER, for your convenience")
 	flag.StringVar(&migrationContext.HooksHintToken, "hooks-hint-token", "", "arbitrary token to be injected to hooks via GH_OST_HOOKS_HINT_TOKEN, for your convenience")
+	flag.Int64Var(&migrationContext.HooksStatusIntervalSec, "hooks-status-interval", 60, "how many seconds to wait between calling onStatus hook")
 
 	flag.UintVar(&migrationContext.ReplicaServerId, "replica-server-id", 99999, "server id used by gh-ost process. Default: 99999")
 
 	maxLoad := flag.String("max-load", "", "Comma delimited status-name=threshold. e.g: 'Threads_running=100,Threads_connected=500'. When status exceeds threshold, app throttles writes")
 	criticalLoad := flag.String("critical-load", "", "Comma delimited status-name=threshold, same format as --max-load. When status exceeds threshold, app panics and quits")
 	flag.Int64Var(&migrationContext.CriticalLoadIntervalMilliseconds, "critical-load-interval-millis", 0, "When 0, migration immediately bails out upon meeting critical-load. When non-zero, a second check is done after given interval, and migration only bails out if 2nd check still meets critical load")
-	flag.Int64Var(&migrationContext.CriticalLoadHibernateSeconds, "critical-load-hibernate-seconds", 0, "When nonzero, critical-load does not panic and bail out; instead, gh-ost goes into hibernate for the specified duration. It will not read/write anything to from/to any server")
+	flag.Int64Var(&migrationContext.CriticalLoadHibernateSeconds, "critical-load-hibernate-seconds", 0, "When non-zero, critical-load does not panic and bail out; instead, gh-ost goes into hibernation for the specified duration. It will not read/write anything from/to any server")
 	quiet := flag.Bool("quiet", false, "quiet")
 	verbose := flag.Bool("verbose", false, "verbose")
 	debug := flag.Bool("debug", false, "debug mode (very verbose)")
@@ -188,6 +190,11 @@ func main() {
 			log.Fatalf("--database must be provided and database name must not be empty, or --alter must specify database name")
 		}
 	}
+
+	if err := flag.Set("database", url.QueryEscape(migrationContext.DatabaseName)); err != nil {
+		migrationContext.Log.Fatale(err)
+	}
+
 	if migrationContext.OriginalTableName == "" {
 		if parser.HasExplicitTable() {
 			migrationContext.OriginalTableName = parser.GetExplicitTable()

go/logic/migrator.go

@@ -1016,7 +1016,7 @@ func (this *Migrator) printStatus(rule PrintStatusRule, writers ...io.Writer) {
 	w := io.MultiWriter(writers...)
 	fmt.Fprintln(w, status)
 
-	if elapsedSeconds%60 == 0 {
+	if elapsedSeconds%this.migrationContext.HooksStatusIntervalSec == 0 {
 		this.hooksExecutor.onStatus(status)
 	}
 }

script/bootstrap

@@ -10,7 +10,6 @@ set -e
 # Since we want to be able to build this outside of GOPATH, we set it
 # up so it points back to us and go is none the wiser
 
-set -x
 rm -rf .gopath
 mkdir -p .gopath/src/github.com/github
 ln -s "$PWD" .gopath/src/github.com/github/gh-ost

script/ensure-go-installed

@@ -1,7 +1,7 @@
 #!/bin/bash
 
 PREFERRED_GO_VERSION=go1.16.4
-SUPPORTED_GO_VERSIONS='go1.1[56]'
+SUPPORTED_GO_VERSIONS='go1.1[567]'
 
 GO_PKG_DARWIN=${PREFERRED_GO_VERSION}.darwin-amd64.pkg
 GO_PKG_DARWIN_SHA=0f215de06019a054a3da46a0722989986c956d719c7a0a8fc38a5f3c216d6f6b
@@ -35,7 +35,7 @@ if [ -z "$(which go)" ] || [ -z "$(go version | grep "$SUPPORTED_GO_VERSIONS")"
     curl -L -O https://dl.google.com/go/$GO_PKG_DARWIN
     shasum -a256 $GO_PKG_DARWIN | grep $GO_PKG_DARWIN_SHA
     xar -xf $GO_PKG_DARWIN
-    cpio -i < com.googlecode.go.pkg/Payload
+    cpio -i < org.golang.go.pkg/Payload
   else
     curl -L -O https://dl.google.com/go/$GO_PKG_LINUX
     shasum -a256 $GO_PKG_LINUX | grep $GO_PKG_LINUX_SHA

vendor/github.com/siddontang/go-mysql/client/resp.go

@@ -1,6 +1,5 @@
 package client
 
-import "C"
 import (
 	"encoding/binary"
 

vendor/github.com/siddontang/go-mysql/packet/conn.go

@@ -1,6 +1,5 @@
 package packet
 
-import "C"
 import (
 	"bytes"
 	"io"
@@ -127,7 +126,7 @@ func (c *Conn) WritePacket(data []byte) error {
 func (c *Conn) WriteClearAuthPacket(password string) error {
 	// Calculate the packet length and add a tailing 0
 	pktLen := len(password) + 1
-	data := make([]byte, 4 + pktLen)
+	data := make([]byte, 4+pktLen)
 
 	// Add the clear password [null terminated string]
 	copy(data[4:], password)
@@ -140,7 +139,7 @@ func (c *Conn) WriteClearAuthPacket(password string) error {
 // http://dev.mysql.com/doc/internals/en/connection-phase-packets.html#packet-Protocol::AuthSwitchResponse
 func (c *Conn) WritePublicKeyAuthPacket(password string, cipher []byte) error {
 	// request public key
-	data := make([]byte, 4 + 1)
+	data := make([]byte, 4+1)
 	data[4] = 2 // cachingSha2PasswordRequestPublicKey
 	c.WritePacket(data)
 
@@ -163,7 +162,7 @@ func (c *Conn) WritePublicKeyAuthPacket(password string, cipher []byte) error {
 	}
 	sha1v := sha1.New()
 	enc, _ := rsa.EncryptOAEP(sha1v, rand.Reader, pub.(*rsa.PublicKey), plain, nil)
-	data = make([]byte, 4 + len(enc))
+	data = make([]byte, 4+len(enc))
 	copy(data[4:], enc)
 	return c.WritePacket(data)
 }